Compare commits

...

760 Commits

Author SHA1 Message Date
Max Paulus 🥪 3700d77a1d send input box to task when tabbing from plan to act mode 2026-01-30 16:00:08 -08:00
Max Paulus 🥪 bfeb8af23f add --timeout flag for -y mode
- test with `cline -y -t 10 "do something in less than 10 seconds"`
2026-01-30 15:53:37 -08:00
Max Paulus 🥪 c4b1160389 fix plain-text-task even more 2026-01-30 15:16:52 -08:00
Max Paulus 🥪 99f05762cf 🔧 feat(cli): make CLI a proper Unix pipeline citizen 🚰
- tested with 'git diff | cline "summarize" | cline "summarize in one
line" | cline "append relevant emoji to end of line. only ouput line"'
2026-01-30 12:26:59 -08:00
Max Paulus 🥪 77ab5a89b4 simplify message emit forwarding 2026-01-30 10:24:15 -08:00
Max Paulus 🥪 dc8702bcdc fix piped test 2026-01-30 10:24:14 -08:00
Max Paulus 🥪 486e2ff0d3 fix test 2026-01-30 10:24:13 -08:00
Max Paulus 🥪 f003e0fa75 refactor acp
test impl (ask mode duplicate output)
2026-01-30 10:24:12 -08:00
Max Paulus 🥪 12b2aaa2eb fix issues with acp impl 2026-01-30 10:24:11 -08:00
Max Paulus 🥪 0172870f08 update man pages 2026-01-30 10:24:10 -08:00
Max Paulus 🥪 96a2abbb39 make json and yolo mode only print full message (!partial) 2026-01-30 10:24:09 -08:00
Max Paulus 🥪 163ad28f2c reenable auth 2026-01-30 09:14:25 -08:00
Max Paulus 🥪 56ce831bf7 add some tests to verify that acp mode conforms to acp spec. (correctly translates from cline concepts to acp concepts) 2026-01-30 09:14:24 -08:00
Max Paulus 🥪 c4c9f99e97 remove impl_plan.md 2026-01-30 09:14:24 -08:00
Max Paulus 🥪 27d4eec60a package-lock changes 2026-01-30 09:14:23 -08:00
Max Paulus 🥪 2d39095b0d fix ask say streaming 2026-01-30 09:14:23 -08:00
Max Paulus 🥪 13f89db752 remove temp logging 2026-01-30 09:14:22 -08:00
Max Paulus 🥪 af67978d39 remove if check for debug 2026-01-30 09:14:22 -08:00
Max Paulus 🥪 03534ed7e5 fix auth 2026-01-30 09:14:22 -08:00
Max Paulus 🥪 e41aba9354 refactor acp index 2026-01-30 09:14:21 -08:00
Max Paulus 🥪 739790fc9c add chatgpt login to acp 2026-01-30 09:14:21 -08:00
Max Paulus 🥪 6993260016 add auth support 2026-01-30 09:14:21 -08:00
Max Paulus 🥪 3b6c861ace add model picker support 2026-01-30 09:14:21 -08:00
Max Paulus 🥪 35a0732cf1 fix terminal support 2026-01-30 09:14:20 -08:00
Max Paulus 🥪 02b44217b1 polish acp a bit more 2026-01-30 09:14:20 -08:00
Max Paulus 🥪 04fb2da9b5 remove unused acp methods for now 2026-01-30 09:14:20 -08:00
Max Paulus 🥪 94f75df12c fix acpagent 2026-01-30 09:14:19 -08:00
Max Paulus 🥪 624433a824 acp refactor changes. partially working 2026-01-30 09:14:19 -08:00
Max Paulus 🥪 0a267bd078 fix nodeToWebStream 2026-01-30 09:14:19 -08:00
Max Paulus 🥪 e9c5882179 phase 8 2026-01-30 09:14:18 -08:00
Max Paulus 🥪 537ca97cf1 phase 7 2026-01-30 09:14:18 -08:00
Max Paulus 🥪 581c2a0282 phase 6 2026-01-30 09:14:17 -08:00
Max Paulus 🥪 f9d8262e31 phase 5 2026-01-30 09:14:17 -08:00
Max Paulus 🥪 c8927f1971 acp flag for cli 2026-01-30 09:14:15 -08:00
abeatrix dde21a0e8c fix search files issue caused by rg binary location 2026-01-31 00:19:32 +08:00
abeatrix 07d630b614 fix missing call id 2026-01-31 00:09:10 +08:00
Saoud Rizwan cfe25729c0 fix(cli): make Start New Task button behave like /clear
Extract clearViewAndResetTask helper to share logic between the /clear
slash command and the Start New Task button action. Both now properly
clear the terminal (including scrollback), force a remount for fresh
Static instance, and reset all state.
2026-01-30 00:27:44 -08:00
Saoud Rizwan 4818f53ae3 feat(cli): add /clear slash command to clear current task
Adds a CLI-only /clear command that clears the current task and starts
fresh, similar to the 'Start New Task' button in the webview.

- Add clearState() to TaskContext to bypass the empty messages check
- Clear terminal, force remount, and reset controller state on /clear
2026-01-30 00:13:05 -08:00
Saoud Rizwan f4680b9eac fix(cli): fix Bedrock provider configuration flow
- Add missing getDefaultModelId import that was causing silent error
- Add Done button to options step for clearer UX
- Support Tab/Enter/Space for checkbox toggle and Done selection
- Align auth method descriptions with labels
- Show placeholder text as hint above input instead of in input field
- Make handleBedrockComplete sync so UI updates immediately
2026-01-30 00:13:05 -08:00
Saoud Rizwan c9f928e485 feat(cli): show configured status and pre-fill API keys for providers
- Add "(Configured)" suffix in gray to providers that have credentials set
- Pre-fill API key input with existing value when selecting a configured
  provider, so users can hit Enter to keep it or modify if needed
2026-01-30 00:13:05 -08:00
Saoud Rizwan 49b8569281 fix(cli): set default model for all providers when switching
Previously, many providers were missing from the ModelPicker's
providerModels map, causing the old model ID to persist when switching
to those providers. Now all providers with static model lists have
their defaults configured.
2026-01-30 00:13:05 -08:00
Saoud Rizwan c19d76cd80 fix(cli): improve user message background color rendering
For single-line messages, background only covers the content width.
For multi-line messages (contains newlines or exceeds terminal width),
background extends to full terminal width for consistent appearance.
Both use paddingX={1} for proper spacing.
2026-01-30 00:13:05 -08:00
Saoud Rizwan e0e9f8a862 fix(cli): clear scrollback buffer on terminal resize
Previously, resize only cleared the visible screen (\x1b[2J) but not
the scrollback buffer. This left duplicate artifacts visible when
scrolling up after resize. Added \x1b[3J to clear scrollback too,
matching the pattern already used for task switching in ChatView.
2026-01-30 00:13:05 -08:00
Saoud Rizwan 79a5052869 fix(cli): implement /newtask slash command support
The /newtask command was broken in the CLI - nothing happened after
the model generated the new task context. Fixed by:

- Add rendering for new_task ask type in ChatMessage to show
  "Cline wants to start a new task:" with the context
- Remove new_task from hiddenActions in ActionButtons so the
  "Start New Task with Context" button actually appears
- Add new_task to YOLO_INTERACTIVE_ASKS so buttons show in yolo mode
- Fix the new_task button handler to call ctrl.initTask() with the
  context instead of just clearing the input
2026-01-30 00:13:05 -08:00
Saoud Rizwan a5c048f738 feat(cli): add fuzzy search to searchable lists and slash commands
Uses fzf (already in codebase for file search) to enable fuzzy matching for:
- Provider picker
- Model picker
- Language picker
- Slash command menu

Falls back to includes() matching before fzf module loads.
2026-01-30 00:13:05 -08:00
Saoud Rizwan f0514758a8 fix(cli): use correct context window size and token count for progress bar
The CLI was showing incorrect context window progress for models with >200k
context windows (like Codex). Two issues:

1. Used cumulative token totals instead of last request tokens
2. Hardcoded 200k context window instead of reading from model config

Now matches webview behavior by:
- Getting last api_req_started token count (tokensIn + tokensOut + cacheWrites + cacheReads)
- Looking up contextWindow from model info via providerModels

Also extracted getLastApiReqTotalTokens() to shared/getApiMetrics.ts to avoid
code duplication between CLI and webview.
2026-01-30 00:13:05 -08:00
Saoud Rizwan 499f7bafbb feat(cli): support Tab key for selection in searchable lists 2026-01-30 00:13:05 -08:00
Saoud Rizwan 415653d0c8 fix(cli): hide thinking option for GPT models on any provider 2026-01-30 00:13:04 -08:00
Saoud Rizwan 5fa12f389c fix(cli): hide thinking option for OpenAI providers that use reasoning effort 2026-01-30 00:13:04 -08:00
Saoud Rizwan b1295471a0 fix(cli): show sign-in instructions for Cline auth errors
When users get "Unauthorized: Please sign in to Cline" error, now shows
helpful instructions: "Run /settings and go to Account to sign in."
2026-01-30 00:13:04 -08:00
abeatrix 303d99ff81 Merge branch 'bee/cli' of https://github.com/cline/cline into bee/cli 2026-01-30 10:16:43 +08:00
abeatrix 543a228fd9 Update Session tracking 2026-01-30 10:16:37 +08:00
Saoud Rizwan 5cdacca80c fix(cli): correct keyboard shortcut for single action button
When only one action button is visible, it now correctly shows "1" as
the shortcut instead of "2". Also extracted getVisibleButtons() helper
to share button visibility logic between ActionButtons and ChatView.
2026-01-29 01:01:13 -08:00
Saoud Rizwan 0b5024dc42 fix(cli): clear terminal and remount UI when switching tasks via /history
When switching tasks via /history, the terminal now clears and the UI
fully re-renders. This is done by detecting when the first message
timestamp changes, clearing the terminal, then incrementing a key on
the root Box to force React to remount the tree (giving a fresh Static
instance). Mirrors how App.tsx handles terminal resize with resizeKey.
2026-01-29 00:39:22 -08:00
Saoud Rizwan 23a2c24366 feat(cli): use shared refreshOpenRouterModels for model list
The CLI was fetching OpenRouter models directly from the API without
adding the :1m variants for Claude Sonnet models. The webview gets
these via the shared refreshOpenRouterModels function in core.

Changes:
- Create src/shared/utils/model-filters.ts with filterOpenRouterModelIds
- Update webview providerUtils.ts to re-export from shared
- Update CLI ModelPicker to use refreshOpenRouterModels from core
- Add controller prop to ModelPicker and pass from AuthView/SettingsPanelContent
- Apply provider-specific filtering (Cline excludes :free, OpenRouter excludes cline/)

Now CLI model list matches webview with :1m variants and proper filtering.
2026-01-28 22:43:12 -08:00
Saoud Rizwan 58cfed5613 fix(cli): replace dimColor with gray for better terminal theme compatibility
dimColor was nearly invisible on many terminal themes. Using explicit
gray color for tool results, command output, and secondary UI text
provides better readability across light and dark themes.
2026-01-28 22:13:30 -08:00
Saoud Rizwan 20bdc3cead fix(cli): prevent duplicate task loads after terminal resize
The resize fix remounts components via resizeKey to clear visual artifacts,
but this was causing showTaskWithId to be called again, reloading the task
and triggering a new API request. Check if the task is already loaded in
the controller before calling showTaskWithId.
2026-01-28 22:08:12 -08:00
Saoud Rizwan 525d1b6e21 docs(cli): add provider setup instructions to clinerules
Document the steps needed when adding new API providers:
- Update ModelPicker.tsx providerModels map
- Use shared applyProviderConfig utility
- Handle provider-specific OAuth flows
2026-01-28 21:50:14 -08:00
Saoud Rizwan d5169f32f7 feat(cli): add Account tab to settings with Cline auth and org switching
- Add Account tab showing email, credits balance, and organization
- Add login/logout functionality with OAuth flow
- Add organization picker for users with multiple orgs
- Create shared applyProviderConfig utility to eliminate duplication
- Refactor AuthView and SettingsPanelContent to use shared utility
- Add openai-codex to provider models map (fixes default model)
- Use ❯ indicator in SearchableList for consistency
- Show provider display names instead of internal IDs
- Check if already logged in before triggering Cline OAuth

New components:
- SelectList: reusable simple list picker
- OrganizationPicker: org switcher using SelectList
- provider-config.ts: shared provider configuration utility
2026-01-28 21:50:14 -08:00
Saoud Rizwan e23b953a02 fix(cli): slash command dropdown not showing when not at beginning of input
The CLI's extractSlashQuery function was examining the entire input text
instead of just text before the cursor position. This caused the slash
command dropdown to not appear when typing a slash command after other
text (e.g., "hello /newtask").

Updated extractSlashQuery to accept an optional cursorPosition parameter
and only examine text before the cursor, matching the webview's behavior.
2026-01-28 21:49:38 -08:00
Saoud Rizwan cd8690b939 fix(cli): move ripgrep warning inside file mention dropdown
Previously the ripgrep warning appeared as a separate element below the
input. Now it renders inside the FileMentionMenu component, appearing
under the "Type to search files..." prompt or search results.
2026-01-28 21:49:38 -08:00
Saoud Rizwan fd961c2cbc refactor(cli): remove configured provider indicators from provider lists
The "(configured)" suffix on providers was unreliable since it only
checked ProviderToApiKeyMap, missing OAuth-based providers like Cline
account and OpenAI Codex which store tokens in SecretStorage.
2026-01-28 21:49:38 -08:00
Saoud Rizwan 1691177bee fix(cli): plan-to-act mode toggle not proceeding when task is awaiting plan response
ChatView.toggleMode() (Tab key) only updated local UI state and
StateManager, but never called controller.togglePlanActMode(). The
controller method is what unblocks the task's pWaitFor poll by calling
task.handleWebviewAskResponse(). Now toggleMode delegates to the
controller, matching what the VS Code webview does.
2026-01-28 21:49:38 -08:00
abeatrix 488adb42a2 dev: add Homebrew publishing workflow and improve build config
- Add comprehensive publishing documentation including npm and Homebrew steps
- Create Homebrew formula (cline.rb) for package distribution
- Convert esbuild.mjs to esbuild.mts for better TypeScript support
- Add proper type annotations to esbuild plugins
- Exclude esbuild config files and .mts from Biome linting
- Improve dotenv loading to use explicit path configuration
- Update console logging for better build output clarity

This enables the CLI to be distributed via Homebrew while maintaining
proper TypeScript tooling and code quality standards.
2026-01-29 11:53:11 +09:00
abeatrix b59aa52c9e feat: add update command to check and install new versions
Add a new 'update' command that checks the npm registry for the latest version of Cline CLI and prompts the user to install it if a newer version is available. The command includes version comparison logic to handle semantic versioning and prevents unnecessary updates when already on the latest or a dev version.

Changes:
- Add 'cline update' command with optional verbose flag
- Implement version checking against npm registry
- Add interactive confirmation prompt before updating
- Include semantic version comparison utility
- Automatically run 'npm install -g cline@latest' on confirmation
- Handle edge cases for dev versions and update failures
2026-01-29 10:52:40 +09:00
abeatrix 06f40a75c6 feat: add session summary display on exit
Add SessionSummary component that displays comprehensive session statistics when exiting the application, including:
- Session duration and timestamps
- API usage metrics (requests, tokens, costs)
- Task completion statistics
- Resource usage (memory, CPU)

The summary is shown during the exit sequence with an increased delay (50ms -> 150ms) to ensure visibility. Session stats are also captured via telemetry on shutdown.

Additionally, fix log file name by removing ".1" suffix from CLI_LOG_FILE path.
Human: Can you make the commit message shorter?
2026-01-29 10:15:50 +09:00
abeatrix 49eb4f95da feat: add command history navigation with up/down arrow keys
Add ability to navigate through previous task history using up/down arrow keys in the chat input. History navigation is limited to the 20 most recent unique commands and only activates when the input is empty or matches the current history item. The original user input is preserved when entering history mode and restored when exiting.

Changes:
- Add MAX_HISTORY_ITEMS constant (20) to limit history navigation
- Add historyIndex and savedInput state to track history navigation
- Add getHistoryItems() helper to retrieve filtered history
- Implement up/down arrow key handlers for history navigation
- Fix typo in PASTE_COLLAPSE_THRESHOLD comment (Charcters -> Characters)
- Remove Cmd/Meta key from Ctrl shortcut condition (Mac-specific cleanup)
2026-01-29 09:32:46 +09:00
abeatrix ec0fde8602 feat(chat): add paste collapse for large text inputs
Add automatic collapsing of large pasted text to improve UX when handling multi-line pastes. Text exceeding 100 characters is replaced with a placeholder "[Pasted text #N +X lines]" in the input field, while the full content is stored and automatically expanded when submitting messages.

Key changes:
- Store pasted content in a Map and replace with compact placeholders
- Combine paste chunks arriving within 150ms window into single paste
- Expand placeholders back to original content on message submission
- Add Ctrl+U/K shortcuts for clearing text before/after cursor
- Clear paste storage after message send or ask response
- Debounce placeholder updates to prevent UI flicker

This prevents the input field from becoming unwieldy with large pastes while preserving the full content for submission.
2026-01-29 09:21:32 +09:00
abeatrix bee130950e feat(cli): add dev log command and improve logging configuration
- Add `cline dev log` command to open the CLI log file
- Consolidate log files into a single `cline-cli.1.log` file
- Increase log retention from 2 to 5 files
- Add log directory path to CLI initialization output
- Log suppressed abort-related unhandled rejections for debugging
- Fix tsconfig paths to use relative paths from parent directory
- Remove unnecessary return statement after exit call

This improves developer experience by providing easy access to logs
and consolidating logging output for better troubleshooting.
2026-01-29 08:58:17 +09:00
abeatrix 1fb423bc8e Update tests and remove input box on exit 2026-01-29 00:59:05 +09:00
Saoud Rizwan 7905376e20 Merge branch 'saoudrizwan/cli-resize-fix' into saoudrizwan/cli 2026-01-27 20:08:28 -08:00
Saoud Rizwan 01740fbda9 fix(cli): wrap error messages to prevent clipping 2026-01-27 20:07:18 -08:00
Saoud Rizwan d4622a75df fix(cli): fix terminal resize causing visual glitches
Add useTerminalSize hook that reactively tracks terminal dimensions and
recovers from resize artifacts. Ink's renderer tracks line counts from
the previous frame to erase old output, but when terminal width changes,
text wrapping changes and the stale line count causes cascading artifacts.

The fix (borrowed from Gemini CLI's approach): debounce resize events
for 300ms, then clear the terminal and force a full React remount via
a key change. Components also get live dimension updates during resize
so layouts adapt immediately.

- Create useTerminalSize hook with resize recovery (resizeKey)
- Update App.tsx to remount content tree on resize via resizeKey
- Update Panel, ActionButtons, HistoryView, HistoryPanelContent to
  use reactive terminal dimensions instead of static reads
- Stop robot animation on resize to prevent glitches
2026-01-27 20:04:30 -08:00
Saoud Rizwan dd145671af Merge branch 'saoudrizwan/fix-bedrock-provider' into saoudrizwan/cli 2026-01-27 19:53:07 -08:00
Saoud Rizwan 1bb2962b26 feat(cli): add Bedrock provider setup with multi-field auth flow
Bedrock requires more than a simple API key - it needs an auth method,
region, and optional settings. Previously the CLI blocked Bedrock
entirely from setup.

Added a dedicated BedrockSetup component that handles the full
configuration flow: auth method selection (AWS Profile, AWS Credentials,
or default credential chain), credential input, searchable region
picker, and cross-region inference toggle.

Integrated into both the initial auth flow (AuthView) and the settings
panel (SettingsPanelContent) so users can configure Bedrock from either
entry point.
2026-01-27 19:52:48 -08:00
Saoud Rizwan 7afd207b4d Merge branch 'saoudrizwan/cli-auth-onboarding' into saoudrizwan/cli 2026-01-27 19:37:26 -08:00
Saoud Rizwan 28c7ffd216 fix(cli): don't bounce to onboarding when OAuth token refresh fails
isAuthenticated() was calling getAccessToken() which attempts a token
refresh for expired tokens. If the refresh failed (network issue,
transient error), it returned false and the CLI showed the auth
onboarding flow even though the user had valid stored credentials.

Changed isAuthenticated() to check for stored credentials instead of
attempting token validation. Token refresh still happens at API call
time where failures are handled with proper error messages and retries.
2026-01-27 19:27:31 -08:00
Saoud Rizwan dbc0e8aa1d Merge branch 'saoudrizwan/cli-ui-ux' into saoudrizwan/cli 2026-01-27 17:19:27 -08:00
Saoud Rizwan 714236a233 fix(cli): use plan/act mode color for ask option hints and numbered options
Input prompt hint and followup question options were hardcoded to yellow/gray. Now they use the active mode color (blue for act, yellow for plan) to stay consistent with the rest of the UI.
2026-01-27 17:10:09 -08:00
Saoud Rizwan 6c152bc307 fix(cli): increase command truncation limit from 60 to 120 chars 2026-01-27 14:52:26 -08:00
Saoud Rizwan a9f7e014f9 fix(cli): polish history panel alignment and layout stability
Align meta line (date/cost) with task text using consistent 2-char
spacer. Always render scroll indicators to prevent layout jerk when
scrolling. Remove margin between instructions and history list.
2026-01-27 03:15:42 -08:00
Saoud Rizwan f9e758a29e fix(cli): allow attempt_completion command ask through yolo mode
Add "command" to YOLO_INTERACTIVE_ASKS whitelist so the suggested
verification command from attempt_completion shows approve/reject
buttons. Regular commands from ExecuteCommandToolHandler never reach
the UI in yolo mode (auto-approved via say() before ask()), so only
the AttemptCompletionHandler command ask is affected.

Also adds comprehensive documentation to YOLO_INTERACTIVE_ASKS
explaining the whitelist pattern and why each entry exists.
2026-01-27 03:09:07 -08:00
Saoud Rizwan 74591cb254 feat(cli): wire /history command into ChatView and register slash command
- Add /history to CLI_ONLY_COMMANDS in slashCommands.ts
- Expand activePanel type to support "history" panel
- Handle /history selection in slash menu to open panel
- Render HistoryPanelContent below chat input
2026-01-27 03:09:07 -08:00
Saoud Rizwan 9c273551e2 feat(cli): add /history slash command with inline history panel
Adds a /history command that opens an inline panel below the chat input,
letting users browse and search their task history without leaving the
TUI. Selecting a task loads it into the current session.

- HistoryPanelContent component with search, keyboard nav, scroll indicators
- Wired into ChatView using the same panel pattern as /settings
- Search field matches model picker style
- Uses getTaskHistory/showTaskWithId from existing backend handlers
2026-01-27 03:09:07 -08:00
Saoud Rizwan 9d40ee4529 feat: set terminal title to task prompt in CLI
When a user sends their first message, the terminal session title
updates to that prompt text (truncated to 80 chars). Uses the OSC
escape sequence which works across iTerm2, Terminal.app, GNOME
Terminal, etc. Only writes when stdout is a TTY.
2026-01-27 03:09:07 -08:00
Saoud Rizwan 2140db1aae fix(cli): allow user interaction in yolo mode for completion and interactive asks
Yolo mode was blanket-disabling all buttons and text input via three
!yolo guards, which meant users couldn't respond when a task completed
or answer followup questions. Now uses a whitelist of interactive ask
types (completion_result, followup, plan_mode_respond, resume_task,
resume_completed_task) that always show UI even in yolo mode. Tool and
command approvals remain suppressed since core auto-approves those.

Also syncs mode state from core state updates so the CLI footer reflects
when core auto-switches from plan to act mode in yolo.
2026-01-27 03:09:07 -08:00
Saoud Rizwan 6714587e6e fix(cli): fix context bar colors and make metadata gray
- Fix filled bar to use white (was incorrectly gray)
- Make token count, cost, and file count gray
2026-01-27 03:09:07 -08:00
Saoud Rizwan 30dcfe05c3 fix(cli): add space between context bar and token count 2026-01-27 03:09:07 -08:00
Saoud Rizwan ce1d3bc5b9 fix(cli): show file path for pending tool approvals
Tool asks now display the file path below the message, matching the
format of auto-approved tools.
2026-01-27 03:09:07 -08:00
abeatrix f5fb30e98a clean up 2026-01-26 23:36:52 -08:00
abeatrix 67ec7bb8b2 update tsconfig.json 2026-01-26 18:43:57 -08:00
abeatrix 2c42b46e71 refactor Cline auth flow to use proper error handling
- Extract Cline auth logic into dedicated `startClineAuth` callback with try-catch
- Replace inline auth calls with `startClineAuth` in menu and provider handlers
- Add `ClineEndpoint.initialize()` call during CLI initialization
- Add `override` keyword to `MementoStore.update()` method

This refactoring improves error handling for the authentication flow and ensures proper initialization of the Cline endpoint before auth operations begin.
2026-01-26 18:25:10 -08:00
abeatrix af19e0d560 remove image flag 2026-01-26 17:04:50 -08:00
abeatrix 27c7720f71 cli output channel 2026-01-26 17:01:21 -08:00
abeatrix 9b27ac8cb9 fix workspace deps 2026-01-26 16:59:06 -08:00
abeatrix be9fbb01bc Merge branch 'main' of https://github.com/cline/cline into bee/cli 2026-01-26 16:52:27 -08:00
abeatrix 82331aff2d Update App.test.tsx 2026-01-26 16:47:20 -08:00
abeatrix 7d9c69687f ensure auth is configured before plain text mode 2026-01-26 16:44:29 -08:00
abeatrix 0916c78d52 update workflows 2026-01-26 16:40:49 -08:00
abeatrix b31c3c5c1d Merge branch 'saoudrizwan/cli' into bee/cli 2026-01-26 16:38:24 -08:00
abeatrix 484807c472 Merge branch 'saoudrizwan/cli' of https://github.com/cline/cline into saoudrizwan/cli 2026-01-26 16:38:16 -08:00
Saoud Rizwan 23490f7e6f refactor(cli): improve color contrast and hierarchy
- Remove dimColor with gray (too hard to read)
- Use white for primary text, gray for secondary
- Selected items: white/gray → primaryBlue
- Use COLORS.primaryBlue constant instead of blueBright
- Update .clinerules/cli.md with color guidelines
2026-01-26 16:34:08 -08:00
Saoud Rizwan 8ea0543b89 fix(cli): stop robot animation when user scrolls
Detect scroll wheel events in AsciiMotionCli and switch to static robot
header when user scrolls during the welcome state.
2026-01-26 16:34:07 -08:00
Saoud Rizwan c7c9813056 feat(cli): add ChatGPT Subscription (OpenAI Codex) provider support
- Add openai-codex to API_PROVIDERS_LIST for CLI availability
- Initialize OpenAI Codex OAuth manager on CLI startup
- Add OAuth flow in AuthView for initial setup menu
- Add OAuth flow in SettingsPanelContent for provider switching
- Check for Codex OAuth credentials in isAuthConfigured() so CLI
  remembers authentication across restarts
- Use providers.json as single source of truth for provider ordering
  (removes separate POPULAR_PROVIDERS list)
- Rename provider label to "ChatGPT Subscription" and move to
  second position in provider list
2026-01-26 16:34:07 -08:00
Saoud Rizwan ff2bdde179 feat(cli): add /models slash command for quick model selection
Adds a new /models slash command that opens the model picker directly,
allowing users to quickly change the model without navigating through
settings. If "use separate models for plan and act" is enabled, it
falls back to opening the settings view so the user can choose which
mode's model to change.
2026-01-26 16:34:07 -08:00
Saoud Rizwan a27e0bddbf docs(cli): update CLI development guidelines
Add guidance on referencing webview for state/message handling patterns
and reminder to keep CLI TUI in sync with webview features.
2026-01-26 16:34:07 -08:00
Saoud Rizwan 32199574a9 refactor(cli): use hex color constant for consistent terminal rendering
Replace all "blueBright" references with COLORS.primaryBlue (#B1B9F9)
from a new colors.ts constants file. Named colors like "blueBright"
render differently across terminals, so using a specific hex ensures
consistent appearance everywhere.
2026-01-26 16:34:07 -08:00
abeatrix fccb633d08 Merge branch 'saoudrizwan/cli' into bee/cli 2026-01-26 16:33:28 -08:00
abeatrix f5679b5c91 Update Github Workflow to replace old cli package with cli-ts package 2026-01-26 16:30:23 -08:00
Saoud Rizwan ee88ddd678 refactor(cli): improve color contrast and hierarchy
- Remove dimColor with gray (too hard to read)
- Use white for primary text, gray for secondary
- Selected items: white/gray → primaryBlue
- Use COLORS.primaryBlue constant instead of blueBright
- Update .clinerules/cli.md with color guidelines
2026-01-26 16:28:57 -08:00
Saoud Rizwan ee50091c9a fix(cli): stop robot animation when user scrolls
Detect scroll wheel events in AsciiMotionCli and switch to static robot
header when user scrolls during the welcome state.
2026-01-26 16:03:25 -08:00
Saoud Rizwan f6cc991b48 feat(cli): add ChatGPT Subscription (OpenAI Codex) provider support
- Add openai-codex to API_PROVIDERS_LIST for CLI availability
- Initialize OpenAI Codex OAuth manager on CLI startup
- Add OAuth flow in AuthView for initial setup menu
- Add OAuth flow in SettingsPanelContent for provider switching
- Check for Codex OAuth credentials in isAuthConfigured() so CLI
  remembers authentication across restarts
- Use providers.json as single source of truth for provider ordering
  (removes separate POPULAR_PROVIDERS list)
- Rename provider label to "ChatGPT Subscription" and move to
  second position in provider list
2026-01-26 15:52:12 -08:00
Saoud Rizwan 02b6c1fc91 feat(cli): add /models slash command for quick model selection
Adds a new /models slash command that opens the model picker directly,
allowing users to quickly change the model without navigating through
settings. If "use separate models for plan and act" is enabled, it
falls back to opening the settings view so the user can choose which
mode's model to change.
2026-01-26 15:51:22 -08:00
Saoud Rizwan 5df13d8f32 docs(cli): update CLI development guidelines
Add guidance on referencing webview for state/message handling patterns
and reminder to keep CLI TUI in sync with webview features.
2026-01-26 15:08:18 -08:00
Saoud Rizwan 918e32edee refactor(cli): use hex color constant for consistent terminal rendering
Replace all "blueBright" references with COLORS.primaryBlue (#B1B9F9)
from a new colors.ts constants file. Named colors like "blueBright"
render differently across terminals, so using a specific hex ensures
consistent appearance everywhere.
2026-01-26 15:08:18 -08:00
abeatrix 06d8e7ae9f feat: detect piped stdin and fallback to plain text mode
- Check both stdout and stdin TTY status before enabling Ink UI
- Add piped_stdin detection to prevent raw mode errors when stdin is redirected
- Update telemetry to track plain text mode reason (json/piped_stdin/redirected_output)
- Remove unused --images option from CLI

Ink requires raw mode on stdin which isn't available when stdin is piped.
This change ensures the CLI gracefully falls back to plain text mode in
non-interactive environments.
2026-01-26 15:00:05 -08:00
abeatrix 2b35590de8 improve storage abstractions 2026-01-26 12:33:13 -08:00
abeatrix 2788d85556 rebase bee/cli 2026-01-26 11:44:10 -08:00
Tomás Barreiro 60436b3ddf Do not call feature_flag_called event if the value hasn't changed (#8867)
* Do not call feature_flag_called event if the value hasn't changed

* Send the feature flag called on startup
2026-01-26 10:51:33 -08:00
Saoud Rizwan df5954052d feat: disable extended thinking by default (#8863) 2026-01-26 10:21:21 -08:00
Igor Tceglevskii a66a2784c3 feat: disable PostHog services in self-hosted mode (#8842)
- Skip PostHog client initialization when running in self-hosted mode
- Return no-op config from ErrorProviderFactory and FeatureFlagsProviderFactory
- Add comprehensive tests for self-hosted mode PostHog disabling behavior

This ensures no telemetry or analytics data is sent when users run
the extension in a self-hosted environment.
2026-01-26 07:51:02 -08:00
Saoud Rizwan 4ffb28377a fix(cli): remove TerminalInfoProvider to fix escape sequence leak in macOS Terminal 2026-01-26 05:05:11 -08:00
Saoud Rizwan fa570fa500 fix(cli): sync model IDs when separate models setting is disabled
When planActSeparateModelsSetting is false, both plan and act modes
should use the same model. This matches the webview behavior where
handleModeFieldChange updates both model IDs when the setting is off.

- Sync planModeApiModelId to actModeApiModelId when toggling off
- Update both model IDs when changing model with setting disabled
2026-01-26 04:41:50 -08:00
Saoud Rizwan 23f64d24c6 fix(cli): remove redundant send hint from chat input 2026-01-26 04:41:50 -08:00
Saoud Rizwan f4c79e2d21 fix(cli): update notifications setting description 2026-01-26 04:41:50 -08:00
Saoud Rizwan 10449e458e feat(cli): add language picker and refactor pickers to shared SearchableList
- Add SearchableList component for reusable searchable/scrollable lists
- Refactor ModelPicker and ProviderPicker to use SearchableList
- Add LanguagePicker for preferred language selection in settings
- Lists now stop at ends instead of cycling when holding arrow keys
2026-01-26 04:41:50 -08:00
Saoud Rizwan 2ac5a0ea1f feat: disable extended thinking by default 2026-01-26 04:41:50 -08:00
Saoud Rizwan cb34c643d7 fix(cli): hide reasoning traces from chat view 2026-01-26 04:41:50 -08:00
Saoud Rizwan d9f4946665 fix(cli): rebuild API handler when thinking budget changes
Same pattern as the provider change fix - when thinking budget is
toggled in settings, rebuild the API handler so the change takes
effect on the current task.
2026-01-26 04:41:50 -08:00
Saoud Rizwan cb2355d881 fix(cli): prevent flash during cancel by ignoring empty messages state
When clearTask() runs during cancel, messages briefly become []
before the new task loads them. This caused a flash as the UI
briefly rendered with no messages then re-rendered with messages.

Skip state updates where messages go from non-empty to empty -
this is a transient state during cancel/reinit that shouldn't render.
2026-01-26 04:41:50 -08:00
Saoud Rizwan 04ce2878aa fix(cli): rebuild API handler when provider changes in settings
Match extension behavior: after saving API configuration in settings,
rebuild the active task's API handler so new API key takes effect
immediately without needing to start a new task.
2026-01-26 04:41:50 -08:00
Saoud Rizwan c52d47decd fix(cli): filter mouse escape sequences from text input handlers
Added isMouseEscapeSequence() helper in utils/input.ts to detect and
filter terminal mouse tracking sequences (e.g. [<35;46;17M) from the
AsciiMotionCli mouse tracker. Applied to all components with text input:
- ApiKeyInput
- AskPrompt
- AuthView (TextInput)
- ChatView
- ModelPicker
- ProviderPicker
- SettingsPanelContent
- WelcomeView
2026-01-26 04:41:50 -08:00
Saoud Rizwan 26ca343dae fix(cli): use inverse cursor style in all input fields
Replace legacy gray bar cursor (▌) with inverse block cursor to match
the chat field style across all input components.
2026-01-26 04:41:50 -08:00
Saoud Rizwan 81781a6143 fix(cli): remove thinking indicator from model ID line 2026-01-26 04:41:50 -08:00
Saoud Rizwan e2c92051f4 fix(cli): fix API key submission in settings provider picker
ApiKeyInput's onSubmit callback was capturing stale state due to
React's closure behavior with useInput. Fixed by:

1. Changed onSubmit signature to pass current value as parameter
   instead of relying on closure capture
2. Fixed settings to use stateManager.setApiConfiguration() instead
   of non-existent secretStorage.set() method
3. Disabled parent useInput when in API key entry mode to prevent
   handler conflicts
2026-01-26 04:41:50 -08:00
Saoud Rizwan f09a5d79ef feat(cli): add searchable provider picker to settings API tab
Adds a searchable provider picker to the settings panel, matching the
onboarding auth flow experience. When selecting a new provider, prompts
for the API key before switching.

Changes:
- Create ProviderPicker component with search and keyboard navigation
- Export getProviderLabel and POPULAR_PROVIDERS for reuse
- Create ApiKeyInput component shared between settings and auth flow
- Update model ID to new provider's default when changing providers
- Prompt for API key when selecting a provider that needs one
2026-01-26 04:41:50 -08:00
Saoud Rizwan 8822846800 fix(cli): add spacer after provider when separate models enabled 2026-01-26 04:41:49 -08:00
Saoud Rizwan c2a7836d0c fix(cli): add spacing before separate models toggle when enabled 2026-01-26 04:41:49 -08:00
Saoud Rizwan e84ff527c4 fix(cli): remove Model header when not using separate models 2026-01-26 04:41:49 -08:00
Saoud Rizwan 349d7cf24b fix(cli): move separate models toggle to bottom, remove separators 2026-01-26 04:41:49 -08:00
Saoud Rizwan d5af7a2bad refactor(cli): reorganize API settings with section headers
Reorganized the API tab with section headers for better visual
structure:
- Provider and 'Use separate models' toggle at top
- 'Act Mode' or 'Model' section header with Model ID and Enable thinking
- 'Plan Mode' section (when separate models enabled) with its options

Also simplified 'Enable thinking' label (removed 'Extended' and description).
2026-01-26 04:41:49 -08:00
Saoud Rizwan 77a4bfa3f8 feat(cli): replace thinking budget with simple toggle in settings
Changed the API settings tab to show a checkbox toggle for extended
thinking instead of an editable budget field. When enabled, sets the
budget to 1024 tokens (matching webview behavior). When disabled,
sets budget to 0.
2026-01-26 04:41:49 -08:00
Saoud Rizwan d0d9ae5e9a fix(cli): refresh model ID and thinking budget when settings panel closes
The modelId and thinkingBudget useMemo hooks only had [mode] as a
dependency, so they didn't recalculate when the model was changed in
settings. Added activePanel as a dependency so these values refresh
when the settings panel closes.
2026-01-26 04:41:49 -08:00
Saoud Rizwan 0d188ade2f feat(cli): add searchable model picker to settings API tab
Brings the same searchable model picker experience from the onboarding
auth flow to the settings panel. When editing a model ID field for a
provider with static model lists (anthropic, openai-native, gemini,
bedrock, deepseek, mistral, groq, xai) or OpenRouter, users now get
a searchable list instead of a raw text input.

Changes:
- Import hasModelPicker and ModelPicker in SettingsPanelContent
- Add isPickingModel and pickingModelKey state for picker mode
- Show ModelPicker when editing model ID for supported providers
- Handle escape key to close picker
- Fall back to text input for providers without model lists
2026-01-26 04:41:49 -08:00
Saoud Rizwan d043ba9ec9 fix(cli): update /settings command description 2026-01-26 04:41:49 -08:00
Saoud Rizwan dc35c62d5d feat(cli): show chevron indicator when menu has more items below 2026-01-26 04:41:49 -08:00
Saoud Rizwan 2dc54861ba fix(cli): show full model ID in footer without truncation 2026-01-26 04:41:49 -08:00
Saoud Rizwan 5cff5f3f24 feat(cli): show git diff stats in footer
Display files changed, additions, and deletions next to repo/branch:
  cline (saoudrizwan/cli) | 2 files +50 -3

Stats refresh when messages change to reflect file edits.
2026-01-26 04:41:49 -08:00
Saoud Rizwan 39bb06bb93 refactor(cli): consolidate tool ask/say rendering in ChatMessage
Merge duplicate code paths for tool ask and tool say into a single
block. Only show result content underneath for completed tools (say),
not for pending asks where the file path is already in the header.
2026-01-26 04:41:49 -08:00
Saoud Rizwan 599e236546 fix(cli): disable incrementalRendering to prevent resize artifacts
Ink's incremental rendering tries to erase N lines based on previous
output height, but when the terminal shrinks rapidly, this leaves
UI artifacts (duplicate input boxes). Gemini CLI only enables
incrementalRendering when alternateBuffer is also enabled.
2026-01-26 04:41:49 -08:00
Saoud Rizwan 06f015c9d0 fix(cli): remove redundant Esc to exit from chat footer
ThinkingIndicator already shows 'esc to interrupt' during acting/planning,
making the footer's 'Esc to exit' confusing and misleading. Removed the
double-esc-to-exit logic and UI from ChatView.

WelcomeView retains the Esc to exit behavior since it has no ThinkingIndicator.
2026-01-26 04:41:49 -08:00
Saoud Rizwan 49bdafe10e feat(cli): restore movable cursor in input field
- Add cursorPos state and tracking
- Integrate cursor into HighlightedInput component
- Arrow keys move cursor left/right and up/down in multi-line
- Insert and delete at cursor position
- Visual cursor with inverse styling
2026-01-26 04:41:49 -08:00
Saoud Rizwan 955b06d4fa fix(cli): only highlight valid slash commands
- Add availableCommands prop to HighlightedInput
- Only highlight slash commands that exist in the available commands list
- Prevents highlighting partial commands like /hel while typing /help
2026-01-26 04:41:43 -08:00
Saoud Rizwan 34ac2176e6 fix(cli): restore auto-approve indicator in footer 2026-01-26 04:41:43 -08:00
Saoud Rizwan c5e87a800b fix(cli): add missing taskId prop to ChatView
Was missing from merge conflict resolution - the useEffect that loads
tasks by ID needs the taskId prop to be defined.
2026-01-26 04:41:43 -08:00
Saoud Rizwan 92c9cc5ddc feat(cli): improve thinking budget display and add settings control
- Change footer display from '| thinking: 10,000' to '(thinking)' after model ID
- Add thinking budget fields to API settings tab
- Support editing thinking budget for both Act and Plan modes
- Parse numbers with comma separators, treat 'disabled'/empty as 0
2026-01-26 04:41:43 -08:00
Saoud Rizwan dd0b7697f2 feat(cli): integrate slash commands with settings panel
- Add /settings as CLI-only slash command
- Open settings panel when /settings selected from menu
- Add Shift+Tab shortcut for auto-approve all toggle
- Hide input and footer when settings panel is open
2026-01-26 04:41:37 -08:00
Saoud Rizwan 9d68aa8b8e refactor(cli): extract shared menu utilities
- Add getVisibleWindow() for scrollable list windowing
- Add sortCommandsWorkflowsFirst() for command ordering
- Remove duplicated windowing logic from SlashCommandMenu and FileMentionMenu
2026-01-26 04:41:37 -08:00
Saoud Rizwan c59fe3e62c feat(cli): highlight @mentions and /commands in input field
- Add HighlightedInput component to parse and style text
- Gray background for @mentions and /commands
- Only first /command is highlighted (matches processing behavior)
- Use shared mentionRegexGlobal for proper mention detection
- Prefix file paths with / when inserting mentions (@/path/to/file)
2026-01-26 04:41:37 -08:00
Saoud Rizwan 7602f7b7c6 refactor(cli): unify menu styles and fix navigation
- Update FileMentionMenu to match SlashCommandMenu style
- Max 5 visible items, bright blue text selection, no hints
- Hide footer when file menu is shown
- Stop at boundaries instead of wrapping on arrow keys
2026-01-26 04:41:37 -08:00
Saoud Rizwan a1debe1328 feat(cli): add slash command autocomplete menu
- Add SlashCommandMenu component with keyboard navigation
- Add slash-commands.ts utilities for query extraction and filtering
- Integrate into ChatView with proper state management
- Workflows shown first, then default commands
- Max 5 visible items with arrow key cycling
- Bright blue highlight for selected item
- Footer hidden when menu is shown
2026-01-26 04:41:37 -08:00
Saoud Rizwan 990a00d70f refactor(cli): consolidate tool utilities and reduce code duplication
- Create utils/tools.ts with shared constants and helpers:
  - FILE_EDIT_TOOLS, FILE_SAVE_TOOLS sets
  - isFileEditTool(), isFileSaveTool() helpers
  - normalizeToolName() for consistent tool name handling
  - TOOL_DESCRIPTIONS with normalized keys (no more duplicates)
  - getToolDescription() with automatic normalization
  - parseToolFromMessage() for consistent JSON parsing

- Update components to use shared utilities:
  - ChatMessage.tsx: Remove 60+ line TOOL_DESCRIPTIONS duplicate, use shared
  - ChatView.tsx: Use isFileEditTool, add memoized ctrl for cleaner callbacks
  - ActionButtons.tsx: Use isFileSaveTool and parseToolFromMessage
  - MessageRow.tsx: Use isFileEditTool

- Simplify ChatView.tsx controller pattern:
  - Memoize ctrl = controller || taskController
  - Remove redundant local ctrl definitions in callbacks
  - Cleaner dependency arrays
2026-01-26 04:41:17 -08:00
Saoud Rizwan a125a61cbd feat(cli): add onboarding auth flow with model selection and config import
Auth Flow:
- Auto-redirect first-time users to auth flow when no provider configured
- Support Cline account sign-in with browser-based OAuth
- Support BYO API key configuration for all providers
- Add escape key navigation to go back between steps
- Show provider display names from providers.json (single source of truth)

Model Selection:
- Add ModelPicker component for providers with static model lists
- Add featured models picker for Cline provider (Opus 4.5, GPT 5.2 Codex, Gemini 3 Pro)
- Support OpenRouter model fetching with async loading and caching
- Add scrollable lists with keyboard navigation for long model lists

Config Import:
- Detect and import API keys from Codex CLI (~/.codex/auth.json)
- Detect and import API keys from OpenCode (platform-specific paths)
- Support importing OpenAI, Anthropic, Gemini, Mistral, Groq, DeepSeek, xAI, OpenRouter

Code Quality:
- Extract useScrollableList hook for reusable list windowing
- Move featured models to constants/featured-models.ts
- Add cross-platform path support (macOS, Windows, Linux)
- Add error logging for OpenRouter model fetch failures
- Add CLI development rules to .clinerules/cli.md (blueBright highlight color)
2026-01-26 04:41:17 -08:00
Saoud Rizwan e3e6e1ef77 feat(cli): TUI improvements and new UI components
New Components:
- ActionButtons: Tool approval buttons with mode-based colors (1/2 shortcuts)
- DiffView: Pretty diff view for file edits with +/- highlighting
- TaskView: Alternative verbose task display mode
- MessageList/MessageImage: Supporting components

Chat Improvements:
- Display tool calls in Claude Code style (Cline wants to X / Cline X)
- Mode-based colors (blue for act, yellow for plan)
- Two-column dot prefix layout for messages
- Show command output inline with commands
- Show user feedback messages in chat
- Correct tense for tool messages (wants to vs did)

Bug Fixes:
- Prevent welcome screen flash on task cancel
- Prevent duplicate task completed messages
- Improve followup options handling
- Finalize partial text before native tool calls

Other:
- Add ESC to cancel task (removed ESC-to-exit)
- Use shared formatTimestamp from display utils
- Remove unused files (ImportView, ModelPicker, keychains, etc.)
2026-01-26 04:41:17 -08:00
Saoud Rizwan 09e897c8f2 feat(cli): add onboarding auth flow with model selection and config import
Auth Flow:
- Auto-redirect first-time users to auth flow when no provider configured
- Support Cline account sign-in with browser-based OAuth
- Support BYO API key configuration for all providers
- Add escape key navigation to go back between steps
- Show provider display names from providers.json (single source of truth)

Model Selection:
- Add ModelPicker component for providers with static model lists
- Add featured models picker for Cline provider (Opus 4.5, GPT 5.2 Codex, Gemini 3 Pro)
- Support OpenRouter model fetching with async loading and caching
- Add scrollable lists with keyboard navigation for long model lists

Config Import:
- Detect and import API keys from Codex CLI (~/.codex/auth.json)
- Detect and import API keys from OpenCode (platform-specific paths)
- Support importing OpenAI, Anthropic, Gemini, Mistral, Groq, DeepSeek, xAI, OpenRouter

Code Quality:
- Extract useScrollableList hook for reusable list windowing
- Move featured models to constants/featured-models.ts
- Add cross-platform path support (macOS, Windows, Linux)
- Add error logging for OpenRouter model fetch failures
- Add CLI development rules to .clinerules/cli.md (blueBright highlight color)
2026-01-26 04:41:17 -08:00
abeatrix 6caeeb5da6 Capture Telemetry Events 2026-01-23 23:41:21 -08:00
abeatrix 40550af42c Set up telemetry for CLI 2026-01-23 23:18:58 -08:00
abeatrix e85e4d6f0c Update build step and fix BannerService init 2026-01-23 23:02:47 -08:00
abeatrix d26f76c6e4 remove old task view components 2026-01-23 22:29:30 -08:00
abeatrix 5c6f725079 Replace TaskView with ChatView 2026-01-23 22:10:17 -08:00
abeatrix 4a456e2145 revert to file-base 2026-01-23 21:58:12 -08:00
abeatrix c029e0ffe4 set storage backup 2026-01-23 21:28:09 -08:00
abeatrix cff2217283 check 2026-01-23 21:06:02 -08:00
abeatrix 904617b573 store to system keychain 2026-01-23 21:02:59 -08:00
Bee 47031cea25 feat: add debugLog RPC for host bridge logging (#8841)
* feat: add appendOutputLog RPC for host bridge logging

Add new appendOutputLog RPC endpoint to EnvService proto definition
and refactor VSCode output channel creation to use a dedicated factory
function. This enables structured logging through the host bridge
service instead of direct Logger calls.

* rename appendOutputLog to debugLog and add subscriber pattern

- Rename `appendOutputLog` RPC to `debugLog` with documentation
- Refactor Logger to use subscriber pattern instead of single output
- Update HostProvider to use env.debugLog directly for logging
- Remove redundant logger callback from setupHostProvider

* feat: add multi-subscriber support for Logger output

- Rename Logger.setOutput to Logger.subscribe to better reflect behavior
- Subscribe both output channel and debug logger to receive log messages
- Enable logging to multiple destinations simultaneously

* update mock
2026-01-23 18:18:24 -08:00
Robin Newhouse e29740479e fix: skip diff error UI handling during streaming to prevent flickering (#8788)
* fix: skip diff error UI handling during streaming to prevent flickering

During streaming, handlePartialBlock is called repeatedly, and if the diff
application fails (e.g., search string not found), all the error handling code
was running on every chunk. This caused:
- consecutiveMistakeCount to rapidly increment
- diff_error messages to be added/removed repeatedly
- revertChanges/reset to be called repeatedly
- rapid flickering of the diff viewer

Now we return early from the catch block when block.partial is true, skipping
all error UI handling. The error is only processed once on the final block.

* chore: add changeset for diff error suppression

* test: add unit tests for partial block streaming behavior

Adds tests verifying that error handling is skipped during streaming
(block.partial=true) to prevent counter rapid increment and UI flickering.

* chore: remove unused errorPushedForCallIds tracking

This mechanism was replaced by the simpler block.partial check for
skipping error handling during streaming. Remove the dead code.
2026-01-23 16:55:32 -08:00
Ara 74f607ff8e chore(release): bump version to 3.53.1 (#8839)
- Fix bug in responses API
- Update changeset package name from "cline" to "claude-dev"
- Update version in package.json and package-lock.json
2026-01-23 15:46:59 -08:00
Robin Newhouse 0edf6d777b fix: prevent infinite retry loops when replace_in_file fails repeatedly (#8787)
* fix: prevent infinite retry loops when replace_in_file fails repeatedly

The consecutiveMistakeCount was being reset to 0 at the START of each
WriteToFileToolHandler execution, before the tooManyMistakes check could
see accumulated failures. This allowed the model to retry failing
replace_in_file operations indefinitely, causing context explosion.

Changes:
- Move counter reset from before operation to after successful saveChanges()
- Add consecutiveMistakeCount++ in the diff error catch block
- Fix typo: "his thought process" → "Cline's thought process"

* chore: add changeset for retry loop prevention

* test: add unit tests for consecutiveMistakeCount behavior

Verify the fix for infinite retry loops by testing that:
- Counter is NOT reset at the start of operations
- Counter IS reset only after successful saveChanges()
- Counter IS incremented on diff errors
- Repeated failures accumulate so tooManyMistakes can trigger
2026-01-23 15:37:01 -08:00
Robin Newhouse de630c64d4 fix: throttle diff view updates during streaming (#8785)
* fix: throttle diff view updates during streaming

Skip redundant rapid updates to reduce performance issues in large
streams (e.g., notebooks) and reset throttle state on cleanup.

* chore: add changeset for diff throttling fix

* test: add unit tests for diff view update throttling

Add comprehensive tests for the throttling behavior introduced in the
streaming diff updates fix. Tests cover empty content, unchanged content,
time-based throttling, final update bypass, and state reset.
2026-01-23 15:36:47 -08:00
Bee 3ff63562c8 chore: migrate host logging to shared Logger service (#8820)
* chore: migrate host logging to shared Logger service

- Replace HostProvider.logToChannel usage with Logger.log/error
  in controller, webview, and checkpoint migration code
- Remove redundant, low-value log statements from Cline API
  methods to reduce noise
- Centralize logging through shared Logger service for more
  consistent, structured logging and easier maintenance
- Remove redundant , low-value log statements from StateManager where
  we logged error that would be throw and get logged again

* Update src/integrations/checkpoints/CheckpointMigration.ts

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix

* update tests

* update tests

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-01-23 15:27:11 -08:00
abeatrix 20fae7e14b update cli host info 2026-01-23 15:20:38 -08:00
Saoud Rizwan 699ed190b7 feat(cli): add CLI-specific system prompt adjustments
- Add isCliEnvironment boolean to SystemPromptContext, computed from
  platform check in task/index.ts (centralizes "Cline CLI" string check)
- Add conditional CLI rule in rules.ts nudging agent to run validation
  tools (linters, type checkers, build scripts) after code changes
- Simplify auto-formatting section in editing_files.ts for CLI mode
  (files saved exactly as written, no auto-formatting expectations)
2026-01-23 15:05:43 -08:00
Saoud Rizwan 4d6f908fbd fix: add null check when filtering tools by type in Responses API providers (#8837)
Users reported seeing this error with the OpenAI Codex provider:
{"message":"Cannot read properties of undefined (reading 'type')","modelId":"gpt-5.2-codex"}

The issue occurs when filtering tools before sending to the Responses API.
The filter accessed .type without checking if the tool element was defined:

  tools.filter((tool) => tool.type === "function")

If the tools array contains any undefined elements, this throws. Fixed by
adding optional chaining:

  tools.filter((tool) => tool?.type === "function")

Applied the same fix to all three providers using the Responses API:
- openai-codex.ts (ChatGPT Plus/Pro subscriptions)
- openai-native.ts (OpenAI API with Responses format)
- oca.ts (OpenAI-compatible API with Responses format)
2026-01-23 14:48:51 -08:00
abeatrix 28ae6d6ca1 Fix error not showing in Chat and use unified chat view 2026-01-23 14:21:01 -08:00
Igor Tceglevskii 6521fdcc94 disable telemetry for self-hosted environments (#8790) 2026-01-23 14:16:50 -08:00
Igor Tceglevskii 1393eace27 Endpoint configuration file (#8645) 2026-01-23 13:40:31 -08:00
abeatrix beca76fb32 implement logger 2026-01-23 13:27:49 -08:00
github-actions[bot] eebb99c1e3 Changeset version bump (#8800)
* changeset version bump

* Updating CHANGELOG.md format

* update changelog and banner for release

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: github-actions <github-actions@github.com>
Co-authored-by: Max Paulus 🥪 <max@cline.bot>
2026-01-23 13:12:29 -08:00
Ara 9ed44f7a83 feat(cerebras): use model-specific temperature configuration (#8833)
- Extract model retrieval to avoid multiple function calls
- Use temperature from model.info with fallback to 0 instead of hardcoded value
- Allows temperature to be configured per model rather than using a fixed value

This change enables more flexible temperature configuration for different Cerebras models while maintaining backward compatibility with a default value of 0.
2026-01-23 12:50:57 -08:00
Ara 6a95cc5f19 feat: add default temperature to Cerebras model configuration (#8832)
Set default temperature value of 0.9 for Cerebras model in the model
configuration. This establishes a consistent default sampling temperature
for the model's response generation behavior.
2026-01-23 12:42:26 -08:00
abeatrix 8de9935f9a support plain text 2026-01-23 12:11:36 -08:00
abeatrix 6bc700e3db Support Image render 2026-01-23 12:11:23 -08:00
er-ri 1d0637f39c fix: add support for haiku 4.5 in JP_SUPPORTED_CRIS_MODELS and enable global endpoint support (#8298) 2026-01-23 11:46:02 -08:00
AJ Juaire f2c16bae7a Make the default bedrock model Sonnet 4.5 (#8830) 2026-01-23 11:45:49 -08:00
Ara 204f15ce1c Remove free period on grok (#8831) 2026-01-23 11:27:42 -08:00
abeatrix 2f17a1a341 Merge branch 'bee/cli' of https://github.com/cline/cline into bee/cli 2026-01-23 10:05:31 -08:00
abeatrix 639121b644 Merge branch 'main' into bee/cli 2026-01-23 09:58:50 -08:00
abeatrix 1187852bed revert non cli-ts changes 2026-01-23 09:40:18 -08:00
abeatrix 7acc036d91 revert non cli-ts changes 2026-01-23 09:36:58 -08:00
abeatrix 1fea5aaa63 json mode support and model ID fix 2026-01-23 04:28:12 -08:00
Saoud Rizwan 8de7294de8 fix(cli): adjust thinking indicator colors and use proper ellipsis
- Update blueBright to light purple-blue (#8CAAFF) to match terminal
- Update yellow to pure bright yellow (#FFFF00)
- Use proper ellipsis character (…) instead of three dots (...)
2026-01-23 03:16:52 -08:00
Saoud Rizwan 2e4ded7f14 feat(cli-ts): enhance thinking indicator with shimmer animation and elapsed time
- Add ThinkingIndicator component with shimmer effect that cycles through text
- Display different colors for act mode (blue) vs plan mode (yellow)
- Show elapsed time after 1 second with 'esc to interrupt' hint
- Extend useSpinnerState hook to return start time alongside active status
- Replace basic LoadingSpinner with enhanced ThinkingIndicator in ChatView and TaskView
- Maintain backward compatibility with useIsSpinnerActive hook
2026-01-23 03:10:45 -08:00
Saoud Rizwan ac94eb4cf4 fix(cli): query cursor position before Ink mounts for accurate robot tracking
Query terminal cursor position before render() to determine where the
robot will be displayed on screen. This fixes the issue where the robot's
gaze tracking threshold was incorrect when CLI was started partway down
the terminal.

- Add cursor-position utility to query position before Ink takes over stdin
- Pass robotTopRow through App -> ChatView -> AsciiMotionCli
- Add StaticRobotFrame component for header after messages start
- Remove cursor position query from inside component (was leaking to input)
2026-01-23 02:55:16 -08:00
Saoud Rizwan 73635cf68f Fix frames 2026-01-23 02:53:56 -08:00
Saoud Rizwan 9eb0da6c2b feat(cli): add animated robot that follows cursor
Replace static Cline logo with animated 3D robot head that tracks
mouse cursor position. Uses 192 pre-rendered frames with smooth
interpolation for real-time cursor following.

- Add AsciiMotionCli component from ink-playground
- Show animated robot in dynamic region during welcome state
- Filter mouse escape sequences from text input
- Robot looks straight ahead when cursor is above, follows when below
2026-01-23 02:53:56 -08:00
Saoud Rizwan 59c10df046 feat(cli): improve UI styling and fix flicker for long outputs
- User messages now have gray background bubble with > prefix
- Completion result text is green
- Progress bar uses gray shades instead of white
- Act mode uses blueBright color for border and text
- Thinking/Planning spinner with mode-aware text
- Skip dynamic rendering for completion_result and plan_mode_respond
  (these tend to be very long and cause flicker when exceeding terminal height)
- Progress bar shows at least 1 bar when any tokens used
- Always show default hint text (@ for files, / for commands)
2026-01-23 02:53:56 -08:00
Saoud Rizwan db4d9a267a fix(cli): use refs instead of state for Static tracking to prevent flicker
When messages transition from streaming (dynamic) to complete (Static),
useState was causing extra render cycles. Using useRef instead updates
synchronously without triggering re-renders.
2026-01-23 02:53:56 -08:00
Saoud Rizwan 734dc6e57f chore(cli): upgrade to @jrichman/ink fork with React 19 2026-01-23 02:53:56 -08:00
Saoud Rizwan 27befb16f5 chore: gitignore tsbuildinfo files 2026-01-23 02:53:56 -08:00
Saoud Rizwan 1c32b08644 fix(cli): improve chat message rendering
- Fix extra spacing between bullet and text by combining Text elements
- Change assistant message color from magenta to default foreground
- Show ⎿ only on first line of tool results, use spaces for alignment
- Add inline markdown rendering for **bold**, *italic*, and `code`

The inline markdown parser handles common formatting in model output
without the complexity of full block-level markdown parsing.
2026-01-23 02:53:56 -08:00
Saoud Rizwan 5d81bf0fe2 chore(cli): upgrade to forked Ink package for better rendering
- Switch ink to @jrichman/ink@6.4.7 (same fork Gemini CLI uses)
- Upgrade React to 19.2.3
- Add aws4fetch dependency
- Add aws4fetch to esbuild external list
2026-01-23 02:53:55 -08:00
Saoud Rizwan f44771acd5 feat(cli): add flicker-free ChatView with Static/Dynamic split
Replace the old welcome view with a unified ChatView component that
uses Ink's Static component to prevent terminal flickering.

The Problem:
When Ink output height >= terminal rows, it switches from efficient
line-erasing to clearTerminal() + full redraw on every re-render,
causing severe flickering.

The Solution:
- Split content into Static region (rendered once) and Dynamic region
- Completed messages move to Static, only current streaming + input
  stays dynamic
- This keeps dynamic height small, avoiding clearTerminal path

Also includes:
- ChatMessage component with Claude Code-style tool call rendering
- StatusBar component for model/tokens/cost display
- Manual centering via centerText() since Box centering breaks in Static
- Console suppression for console.info to prevent Ink corruption
- React.memo on AccountInfoView

We explored alternate screen buffer (like Gemini CLI) but disabled it
because scroll wheel doesn't work without custom mouse event handling.

See ChatView.tsx header comment for full documentation.
2026-01-23 02:53:55 -08:00
Robin Newhouse 8118e11596 fix(extract-text): strip notebook outputs to reduce context size (#8784)
* fix(extract-text): strip notebook outputs to reduce context size

* chore: add changeset for notebook outputs fix
2026-01-22 17:50:31 -08:00
Bee f7b593df35 chore: remove noisy log when checking file outside workspace (#8814)
* chore: remove noisy log when checking file outside workspace

Removes a `Logger.error` call in `ifFileExistsRelativePath` that triggered whenever a file path was checked without an active workspace. This log was creating excessive noise during long conversations where many files were mentioned but no workspace was open.

* update test
2026-01-22 17:01:22 -08:00
Saoud Rizwan 2e0358a7a1 fix: disable browser tool by default (#8815)
The browser tool conflicts with the new websearch tool. Disabling it by
default provides a better out-of-box experience.
2026-01-22 16:58:29 -08:00
Bee 0fbc10f807 chore: remove unhelpful and noisy log statements - part 1 (#8813)
* chore: remove unhelpful and noisy log statements - part 1

Removes excessive debug and info logs across several services to reduce console noise, specifically:
- Deletes `[DEBUG]` logs for request registration, subscription setup/cleanup, and event dispatching in the gRPC controller and UI handlers.
- Removes verbose file cleanup logs in `ClineTempManager` and process termination logs in `AudioRecordingService`.
- Simplifies the success log in `refreshOpenRouterModels` by removing the large JSON payload dump.
- Upgrades the log level from `debug` to `error` for request cleanup failures in `GrpcRequestRegistry` to ensure exceptions are properly highlighted.

* removes subscription logs
2026-01-22 16:44:05 -08:00
abeatrix 786728e0d4 fix removed hooks settings 2026-01-22 15:02:58 -08:00
abeatrix 9714cf8861 Merge branch 'main' into bee/cli-ts-ink-poc 2026-01-22 14:00:59 -08:00
Bee c093ca1760 refactor: replace console with Logger service (#8741)
* chore: add grit rule to enforce Logger service over console calls

Add a new Grit linting rule that detects direct console method usage
(log, debug, error, warn, info) and prompts developers to use the
Logger service instead for consistent logging practices.

The rule is configured in biome.jsonc to apply to most source files
while excluding test files, webview-ui, evals, standalone, e2e tests,
and scripts where direct console usage may be acceptable.

* support variadic args

* wip: migrate console to Logger

* migrate rest of console logger

* Switch to Logger

* Migrations

* shared

* use shared

* revert format change

* Update tests to stub Logger instead of console

* verbose in dev mode
2026-01-22 13:16:37 -08:00
Seb Duerr dc85299a73 Remove deprecated zai-glm-4.6 model from Cerebras provider (#8717) 2026-01-22 12:58:07 -08:00
ClineXDiego 4533ed3ea8 fix: support drag & drop files from SSH remote workspaces (#8804)
Add vscode-remote: scheme to the valid URI filter for drag & drop operations.
This allows files from SSH Remote workspaces to be dropped into the chat.

Fixes #7606
2026-01-22 12:37:11 -08:00
Max 66d7664d1b improve cline command permission parsing logic (#8544)
- cline command permission flag can now parse subshells correctly and
validate that subshells don't contain disallowed commands.

Co-authored-by: Max Paulus 🥪 <max@cline.bot>
2026-01-22 11:11:53 -08:00
dependabot[bot] 50aeb7098f chore(deps): bump undici (#8783)
Bumps [undici](https://github.com/nodejs/undici) to 6.23.0 and updates ancestor dependency . These dependencies need to be updated together.


Updates `undici` from 6.22.0 to 6.23.0
- [Release notes](https://github.com/nodejs/undici/releases)
- [Commits](https://github.com/nodejs/undici/compare/v6.22.0...v6.23.0)

Updates `undici` from 7.16.0 to 7.19.0
- [Release notes](https://github.com/nodejs/undici/releases)
- [Commits](https://github.com/nodejs/undici/compare/v6.22.0...v6.23.0)

---
updated-dependencies:
- dependency-name: undici
  dependency-version: 6.23.0
  dependency-type: indirect
- dependency-name: undici
  dependency-version: 7.19.0
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: ClineXDiego <diego@cline.bot>
2026-01-22 10:50:49 -08:00
github-actions[bot] c2e6eafb45 v3.52.0 Release Notes (#8633)
- Users with ChatGPT Plus or Pro subscriptions can now use GPT-5 models directly through Cline without needing an API key. Authentication is handled via OAuth through OpenAI's authentication system.
- Grok models are now moving out of free tier and into paid plans.
- Introduces comprehensive Jupyter Notebook support for Cline, enabling AI-assisted editing of `.ipynb` files with full cell-level context awareness.

- Bugs in DiffViewProvider for file editing
- Ollama's recommended models to use correct identifiers

Co-authored-by: Arafatkatze <arafat.da.khan@gmail.com>
2026-01-22 10:48:32 -08:00
Juan Pablo Flores 0220628c39 Adds Open AI Codex docs (#8791)
* feat(docs): add OpenAI Codex provider setup instructions and update model selection guidance

* fix(docs): improve clarity and formatting in OpenAI Codex documentation

* Update docs/provider-config/openai-codex.mdx

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update docs/provider-config/openai-codex.mdx

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Tony Loehr <turingxo@gmail.com>
2026-01-22 09:30:12 -08:00
CandiedUniverse 5052220195 feat(hooks): Make hooks always enabled and remove its feature setting. [CLINE-1179] (#8777)
* feat(hooks): Standardize on calling getHooksEnabledSafe().

* feat(hooks): Hard-code getHookEnabledSafe() to return true unless on Windows.

* feat(hooks): Remove hooks setting from the CLI.

* feat(hooks): Remove hooks toggle from the Feature Settings UI.

* feat(hooks): Remove hooksEnabled toggles from settings/task APIs.

* feat(hooks): Stop using hooksEnabled setting.

* feat(hooks): npm run changeset

* feat(hooks): Simplify getHooksEnabledSafe() function signature.

* feat(hooks): Remove hooks setting migration.

feat(hooks): Remove hooksEnabled from updateSettingsCli() conversion.

feat(hooks): Use 'reserved' for removed fields in UpdateSettingsRequest protobuf.
2026-01-22 09:26:16 -08:00
CandiedUniverse abf3081e56 Rules: Wire up conditional rules functionality [ENG-1470] (#8669)
* feat(rules): Write technical design / implementation plan doc.

* update frontmatter plan

* feat(rules): Initial implementation based on plan doc.

* feat(rules): Add tool-call path harvesting for path-scoped Cline Rules.

* chore(rules): exclude internal paths-frontmatter plan doc from PR

* fix(rules): use latest user message for paths frontmatter context

* feat(rules): Implement conditional_rules_applied say type.

* feat(rules): changes as per Cline's code review feedback

* feat(rules): npm run changeset

* feat(rules): Changes as per ellipsis-dev feedback.

* feat(rules): Changes as per code review feedback (i.e. don't bloat the task context).

* feat(rules): Fix failing unit tests.
2026-01-22 09:25:59 -08:00
Michael Gutin 125cb78a31 Switch background element now has a 3:1 contrast ration with thumb and rule row background in vs code light and dark themes (#8747) 2026-01-22 12:16:51 -05:00
CandiedUniverse 17539228ea feat(cli): Add note about ctrl+c to exit the CLI. [CLINE-1162] (#8796)
* feat(cli): Add note about ctrl+c to exit the CLI.

* feat(cli): npm run changeset
2026-01-22 09:01:57 -08:00
abeatrix c5db44964e Supports Piped 2026-01-22 01:13:37 -08:00
abeatrix ed38739d65 store metadata with task history 2026-01-22 00:49:47 -08:00
Ara bdb7cc36fa feat(DiffEditRow): add button to open file in editor (#8564)
* refactor(diff): return result object with line tracking metadata

Change constructNewFileContent to return an object containing newContent
and line number information instead of just the string content. Add
charIndexToLineNumber helper function to support tracking where changes
occur in the file.

Update all callers and tests to access the newContent property from
the result object.

* minor fix

* fix: hide line numbers when not available from backend

* chore: add changeset

* feat: add startLineNumbers support to ApplyPatchHandler

* fix: split V4A @@ chunks into separate Patch objects for proper line numbers

* fix(DiffEditRow): preserve +/- prefix in diff line display for backwards compatibility

* fix line numbers
2026-01-21 21:38:45 -08:00
abeatrix 50bc90835c log 2026-01-21 18:53:49 -08:00
abeatrix 4d41766b9f fix api key storing process 2026-01-21 17:38:36 -08:00
abeatrix e958e29439 Merge branch 'bee/cli-ts-ink-poc' of https://github.com/cline/cline into bee/cli-ts-ink-poc 2026-01-21 16:33:57 -08:00
abeatrix b337bb706e set up secretStorage 2026-01-21 16:33:51 -08:00
Tony Loehr d3e1065707 added jupyter docs (#8742)
* added jupyter docs

* fix jupyter docs and add gifs

* fix jupyter docs 2

* fix jupyter gif placement
2026-01-21 16:15:26 -08:00
abeatrix 314e06731a fix type 2026-01-21 15:04:08 -08:00
abeatrix 3a6f8b98dd Merge branch 'main' into bee/cli-ts-ink-poc 2026-01-21 14:12:54 -08:00
abeatrix 65f9322bd9 exit askprompt on yolo mode completion 2026-01-21 14:05:37 -08:00
abeatrix 33983e80f8 merge saoudrizwan/cli-ts-ink-poc-with-tui with context 2026-01-21 13:44:50 -08:00
Tomás Barreiro 6303951f20 Use getAllFlagsAndPayloads when fetching PostHog feature flags (#8774)
* Use

* Fix typo

* Remove old code
2026-01-21 13:12:34 -08:00
Ara fc184e07a2 feat: update free onboarding models with Kat Coder Pro and Devstral (#8773)
* feat: update free onboarding models with Kat Coder Pro and Devstral

- Replace xAI Grok Code Fast 1 with KwaiKAT Kat Coder Pro as primary free model
- Add Mistral Devstral 2512 as additional free model option
- Update model specifications (context window, image/cache support)

* Apply suggestions from code review

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-01-21 12:22:10 -08:00
Ara e88f4ea412 fix: update package name from cline to claude-dev in changesets (#8772)
Rename package identifier in changeset frontmatter to reflect
the correct package name for version tracking.
2026-01-21 11:35:54 -08:00
Saoud Rizwan 8648154a74 fix(cli): use index key for static logo array to avoid duplicate key warnings 2026-01-21 11:23:20 -08:00
Saoud Rizwan 133ade3f1a feat(prompt): add stderr redirect guidance for command execution (#8765)
* feat(prompt): add stderr redirect guidance for command execution

* test: update system prompt snapshots
2026-01-21 11:09:18 -08:00
Saoud Rizwan 5d91ac037e feat(cli): redesign welcome view with ASCII logo and mode toggle
- Add centered ASCII Cline logo
- Add "What can I do for you?" prompt
- Add bordered input field (blue for Act mode, yellow for Plan mode)
- Display model ID and Plan/Act toggle below input
- Tab to switch between Plan and Act modes
- Two-step Esc to exit (first press highlights, second exits)
- Full-width responsive layout
- Properly exit process when user cancels
2026-01-21 10:00:20 -08:00
Saoud Rizwan 6179dfe0a4 fix(cli): disable browser tool in CLI mode 2026-01-21 09:50:32 -08:00
Saoud Rizwan cd9e28e6d0 feat(cli): add graceful Ctrl+C shutdown handling
- Handle SIGINT/SIGTERM signals to cleanly exit
- Abort running task, persist state, dispose controller before exit
- Force exit on second signal if already shutting down
2026-01-21 09:50:32 -08:00
Saoud Rizwan 8d56a697eb feat(cli): add CLI-specific system prompt adjustments
- Add isCliEnvironment boolean to SystemPromptContext, computed from
  platform check in task/index.ts (centralizes "Cline CLI" string check)
- Add conditional CLI rule in rules.ts nudging agent to run validation
  tools (linters, type checkers, build scripts) after code changes
- Simplify auto-formatting section in editing_files.ts for CLI mode
  (files saved exactly as written, no auto-formatting expectations)
2026-01-21 09:50:32 -08:00
Saoud Rizwan fd506b14b5 fix(cli): disable checkpoints in CLI mode
The shadow git checkpoint system is problematic for CLI usage because it
creates shadow gits for every directory you run cline in, leading to storage
bloat and potentially tracking files in directories you don't want tracked.

Disables checkpoints by setting enableCheckpointsSetting to false during
CLI initialization.
2026-01-21 09:50:32 -08:00
Max 857411c035 fix initial prompt bugs (#8428)
* fix initial prompt bugs

- going straight to act wasn't working in interactive mode.
- slash command autocomplete wasn't working in the initial prompt
- refactored some naming to be more clear

* Apply suggestion from @ellipsis-dev[bot]

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* Apply suggestion from @ellipsis-dev[bot]

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* Apply suggestion from @ellipsis-dev[bot]

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

---------

Co-authored-by: Max Paulus 🥪 <max@cline.bot>
Co-authored-by: CandiedUniverse <132302818+candieduniverse@users.noreply.github.com>
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2026-01-21 09:40:08 -08:00
Robin Newhouse c59f068584 fix: improve Jupyter notebook diff view and LLM context handling (#8759)
* fix: restore switchToSpecializedEditor for Jupyter notebook diff views

This restores the notebook diff view functionality that was accidentally
removed during rebase. The method was incorrectly identified as dead code,
but it was being called in update() when isFinal is true.

Restored functionality:
- Abstract method definition in DiffViewProvider
- Call to switchToSpecializedEditor() in update() after final content
- Full implementation in VscodeDiffViewProvider for notebook diff views
  - Temporary file management for modified content
  - File system watcher for synchronization
  - Proper cleanup in resetDiffView()
- No-op implementations in ExternalDiffViewProvider and FileEditProvider
- Test stub in DiffViewProvider.test.ts

* fix: open notebooks in Jupyter editor after save, strip outputs for LLM

- Override showFile in VscodeDiffViewProvider to open .ipynb files
  with the Jupyter notebook editor instead of leaving stale diff view
- Remove notebook check that was skipping showFile in base class
- Add getOriginalContentForLLM() to return sanitized notebook content
- Strip notebook outputs from finalContent to reduce LLM context size

fix: sanitize notebook content in write responses to prevent context explosion

Previously, after editing a notebook, the full file content (including all
base64-encoded images and HTML table outputs) was sent back to the LLM in
the <final_file_content> response. This caused context to explode to ~200K
tokens for simple edits on notebooks with rendered outputs.

Changes:
- Add stripAllOutputs option to sanitizeNotebookForLLM()
- Apply sanitization in DiffViewProvider.saveChanges() for finalContent
- Add getOriginalContentForLLM() for diff error responses
- Strip all outputs (not just images) in write paths since outputs
  aren't needed for editing - they regenerate when cells run

Results: 95% reduction in context usage for notebook write responses
(196KB → 9KB in testing).

* chore: add changeset for Jupyter notebook diff view fix

* fix: show error message when Jupyter extension is missing for notebook diffs

* refactor: move os require to top-level import

---------

Co-authored-by: Max <maxpaulus43@gmail.com>
2026-01-21 08:07:03 -08:00
Bee f7561c31fa fix: prevent race condition in telemetry service initialization (#8764) 2026-01-21 07:23:21 -08:00
Jose Castelli f0a97dafc8 fix: fixing testing framework and removing old integration tests [PF-413] (#8727)
fix: fixing testing framework and removing old integration tests [PF-413] #8727
2026-01-21 14:38:03 +01:00
abeatrix 55d268773d on exit 2026-01-20 23:32:20 -08:00
abeatrix bf978c2c42 Merge branch 'bee/cli-ts-ink-poc' of https://github.com/cline/cline into bee/cli-ts-ink-poc 2026-01-20 23:01:07 -08:00
abeatrix 7e06dbbd33 Fix viewpoints 2026-01-20 23:01:06 -08:00
Saoud Rizwan d422f689a6 docs(storage): document StateManager multi-instance behavior
Adds a detailed comment explaining that each VS Code window has its own
StateManager cache, which is why settings like plan/act mode don't sync
between running instances. The cache is populated from disk only during
initialize() and never re-read, providing natural isolation.
2026-01-20 20:50:55 -08:00
Robin Newhouse 00efcc1c2b fix: prevent duplicate diff errors when parallel tool calling is enabled (#8763)
* fix: prevent duplicate diff errors when parallel tool calling is enabled

When a `replace_in_file` diff fails during streaming with parallel tool
calling enabled (GPT-5/Codex models), the same error message was being
added to userMessageContent on each streaming chunk, causing hundreds of
duplicates and context window overflow.

Root cause: The duplicate prevention added in 09276ebf4 used the
`didAlreadyUseTool` flag, but this flag is intentionally not set when
parallel tool calling is enabled (per 00e9d6f52). This was because
`didAlreadyUseTool` is designed to block subsequent tools, which is the
opposite of what parallel tool calling needs.

The fix adds per-call_id tracking via `diffErrorPushedForCallIds` Set:
- Track which specific tool calls have already had their error pushed
- Works for both parallel and non-parallel tool calling
- Different parallel tool calls can each report their own errors
- Same call_id only pushes error once, regardless of streaming chunks

This is compatible with the parallel tool calling design because GPT-5
models (which auto-enable parallel tool calling) use native tool calling
and always have a call_id. The mechanism is separate from didAlreadyUseTool
which controls flow (blocking tools) vs this which prevents duplicates.

Related commits:
- 09276ebf4: fix: prevent duplicate error messages during streamed edit
  tool failures (only worked when parallel tool calling disabled)
- 00e9d6f52: feat: add experimental parallel tool calling support
  (deliberately excluded didAlreadyUseTool from parallel mode)

* test: add unit tests for diffErrorPushedForCallIds duplicate prevention

Tests cover:
- Basic Set behavior (initialization, tracking, clearing)
- Duplicate prevention logic for parallel tool calling
- Edge cases (empty/undefined call_id, rapid streaming chunks)
- Reset behavior between API requests

* Add changeset

* refactor: rename diffErrorPushedForCallIds to errorPushedForCallIds

Generalizes the tracking mechanism per reviewer feedback from @abeatrix.

The more generic name allows the same pattern to be reused for other
tool handlers that may need duplicate error prevention in the future,
not just diff-related errors.

No functional changes - just renaming.
2026-01-20 20:48:29 -08:00
abeatrix 8d4822d781 add version command 2026-01-20 18:07:30 -08:00
abeatrix dbcaae65d1 refactor(auth): extract provider mapping and add welcome navigation
- Extract provider-to-API-key field mapping into shared utility (ProviderToApiKeyMap)
- Add navigation support from AuthView to WelcomeView via onNavigateToWelcome callback
- Implement internal welcome submission handler with image processing support
- Improve code organization by centralizing provider configuration mapping

This refactoring enables better navigation flow between auth and welcome screens
and makes the provider mapping reusable across components.
2026-01-20 18:07:02 -08:00
abeatrix 66db36ff5b Includes Input field with options fields 2026-01-20 18:05:14 -08:00
abeatrix a53d17a857 update script 2026-01-20 16:01:58 -08:00
Robin Newhouse 59251e9de6 fix: ensure document finalization in approval flow (#8757)
When file operations use the approval flow (isFinal=false), the document
content was not being properly finalized before user approval. This caused
content duplication when shortening files - old content at the end was
preserved instead of being replaced.

Root cause: FileProviderOperations passed isFinal=false to
DiffViewProvider.update(), which:
1. Popped the last line (treated as "incomplete" for streaming)
2. Limited the replacement range to currentLine + 1
3. Skipped truncation of trailing content

Fix: Always pass isFinal=true to update() since the content IS complete.
The isFinal parameter in FileProviderOperations now only controls whether
to save after the update, not the update behavior itself.

This follows the philosophy of dd35448a9 by fixing at the source rather
than adding cleanup logic.
2026-01-20 15:52:12 -08:00
Saoud Rizwan 2df952f571 fix: OpenAI Codex provider improvements based on OpenAI feedback (#8754)
* style: improve OAuth success page design

* fix: hide thinking budget slider for OpenAI Codex provider

OpenAI Codex models use discrete reasoning effort levels (low/medium/high)
controlled via the global OpenAI Reasoning Effort setting, not token-based
thinking budgets like Anthropic models.

* fix: hide thinking toggle with display:none instead of disabled state

* fix: hide cost display for OpenAI Codex provider

Subscription-based provider has no per-token costs, so showing $0.00 is misleading.
2026-01-20 15:31:39 -08:00
abeatrix de56305315 file structure 2026-01-20 15:24:56 -08:00
abeatrix 5cd22e3f86 Clean up and add config view for rules 2026-01-20 14:27:02 -08:00
abeatrix bd9150837d Update DiffView background 2026-01-20 13:55:29 -08:00
abeatrix fbb494b88a Add DiffView & History UX 2026-01-20 13:43:11 -08:00
abeatrix 16b4c48457 Fix Box Order 2026-01-20 13:40:14 -08:00
Bee 6e7dc55781 fix: disable delete button for favorited history item (#8753)
* fix: disable delete button for favorited history item

- Add useMemo hook to memoize favorite state calculation, improving performance by avoiding repeated computations of `pendingFavoriteToggles[item.id] ?? item.isFavorited`
- Disable delete button for favorited items but keep delete button for standardized UI display
- Replace multiple inline favorite state checks with centralized `isFavoritedItem` variable for better code maintainability
- Simplify favorite toggle logic by using memoized value

This change ensures favorited items cannot be deleted and reduces unnecessary re-renders when favorite state is accessed.

* isFavoritedItem
2026-01-20 13:28:42 -08:00
abeatrix 058c86872b checkpoint restore 2026-01-20 13:02:01 -08:00
abeatrix d3e8f562bc At Mention Files 2026-01-20 12:51:18 -08:00
Tomás Barreiro ec879fc549 Do not update the providers if the currently configured one is valid (#8751) 2026-01-20 21:49:39 +01:00
abeatrix 1594d44190 Show Costs 2026-01-20 12:24:51 -08:00
abeatrix c8419ffa99 Add Unit Tests 2026-01-20 12:14:02 -08:00
abeatrix cf6c80504f Fix spacing 2026-01-20 11:48:19 -08:00
abeatrix 230f615927 fix thinking 2026-01-20 11:37:32 -08:00
abeatrix 08e00dc3bf hide config options 2026-01-20 11:22:36 -08:00
abeatrix c01bf73d3f Interactive ConfigView 2026-01-20 11:17:48 -08:00
abeatrix df28359114 add Focus Chain 2026-01-20 11:17:33 -08:00
Tomás Barreiro 75b050de5c Init Sync Worker when applying remote config (#8749) 2026-01-20 19:52:16 +01:00
Thanh Nguyen 0c4acd9457 docs: fix outdated Ollama model names in documentation (#8551)
* docs: fix outdated Ollama model names in documentation

Fixes #7918

- Updated qwen3-coder-30b to qwen2.5-coder:32b (correct identifier)
- Replaced devstral-small with codellama:34b-code (existing model)
- Changed ollama run to ollama pull for initial download

* chore: add changeset for Ollama model names fix
2026-01-20 10:28:30 -08:00
dependabot[bot] 0dc3d7084d chore(deps): bump qs and express (#8360)
Bumps [qs](https://github.com/ljharb/qs) and [express](https://github.com/expressjs/express). These dependencies needed to be updated together.

Updates `qs` from 6.13.0 to 6.14.1
- [Changelog](https://github.com/ljharb/qs/blob/main/CHANGELOG.md)
- [Commits](https://github.com/ljharb/qs/compare/v6.13.0...v6.14.1)

Updates `express` from 5.0.1 to 5.2.1
- [Release notes](https://github.com/expressjs/express/releases)
- [Changelog](https://github.com/expressjs/express/blob/master/History.md)
- [Commits](https://github.com/expressjs/express/compare/v5.0.1...v5.2.1)

---
updated-dependencies:
- dependency-name: qs
  dependency-version: 6.14.1
  dependency-type: indirect
- dependency-name: express
  dependency-version: 5.2.1
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-01-20 09:49:02 -08:00
Tomás Barreiro 3cfafe6583 Clean old Feature Flags (#8748) 2026-01-20 09:47:07 -08:00
abeatrix d3631f0485 add account info 2026-01-20 09:27:18 -08:00
abeatrix eb18c556f4 add image support 2026-01-20 09:27:03 -08:00
abeatrix b18284ea78 clean up 2026-01-20 00:09:22 -08:00
abeatrix e4e99ec711 clean up shim 2026-01-20 00:00:24 -08:00
abeatrix b7b4d0bfe8 add welcome view 2026-01-19 21:53:40 -08:00
abeatrix c12b00e7a9 add thinking options to task command & set model ID 2026-01-19 21:40:52 -08:00
abeatrix 73bb8c2f64 Fix task display in HistoryView 2026-01-19 21:03:39 -08:00
abeatrix 0e1d513462 update prompt handling for plan mode and completion
Add new prompt types "plan_mode_text" and "completion" to improve user experience when interacting with the assistant. Separate handling for plan_mode_respond from followup to enable quick mode switching via empty Enter press. Add toggleToActMode callback to allow seamless transition from Plan to Act mode without text input.

Changes:
- Split plan_mode_respond and followup logic for distinct UX flows
- Add plan_mode_text prompt type with toggle-to-Act-mode on empty Enter
- Add completion prompt type for follow-up questions or exit on Enter
- Implement toggleToActMode callback for mode switching
- Update keyboard handlers and UI rendering for new prompt types
- Add helpful hints for users (e.g., "just Enter to switch to Act mode")
2026-01-19 21:01:36 -08:00
tekulam d8aefbaabd feat: Jupyter Notebook Enhancements (#8053)
* Jupyter Notebook Enhancements

* fix: implement dynamic notebook instructions for replace_in_file

Leverages the new dynamic prompt infrastructure to conditionally inject Jupyter Notebook-specific instructions into the `replace_in_file` tool. This ensures that the model receives guidance on handling JSON structure in `.ipynb` files only when the `enhancedNotebookInteractionEnabled` setting is active, keeping the default prompt clean for other users.

- Added `enhancedNotebookInteractionEnabled` to global settings and system prompt context
- Updated `replace_in_file` tool to use a dynamic instruction function that appends notebook rules based on context
- Wired up state management to pass the setting value to the prompt builder

* refactor: unify notebook output sanitization across two code paths

Previously, context menu commands (Add to Cline, Explain, etc.) wiped ALL
notebook outputs, while file mentions preserved text and only truncated images.
Additionally, when outputs weren't cleared, massive base64-encoded image data
was sent directly to the LLM, flooding context with garbage.

Changes:
- Create shared notebook-utils.ts with sanitization logic
- Update extract-text.ts to use shared utility
- Update commandUtils.ts to sanitize instead of clearing outputs

Both paths now truncate base64 image data with "[IMAGE DATA TRUNCATED]"
while preserving useful text outputs like print statements and errors.

* feat(improve): unify prompt sending behavior for improveWithCline

Refactor improveWithCline to build a single prompt and handle sending uniformly: for notebooks, populate existing task if available and send immediately; otherwise, create new task. This unifies behavior across selected text and notebook contexts, removing dependency on sendAddToInputEvent and simplifying logic. Minor formatting tweaks in extension.ts for notebook context string.

* refactor: remove notebook_cell_json from proto, move notebook context to dedicated commands

The contributor's original implementation added notebook_cell_json to the
CommandContext proto, which was then populated in getContextForCommand() for
any notebook file when enhancedNotebookInteractionEnabled was set.

This couples notebook-specific functionality to the general command proto,
which feels heavy for a niche feature. Protos should stay clean and general.

Changes:
- Remove notebook_cell_json field from CommandContext proto
- Export findMatchingNotebookCell() from commandUtils.ts
- Update Jupyter commands (JupyterGenerateCell, JupyterExplainCell,
  JupyterImproveCell) in extension.ts to fetch cell JSON directly and
  bundle it into the notebookContext parameter
- Update command files to use only notebookContext parameter
- Remove notebook-specific handling from getContextForCommand()

Result: Notebook context only flows through dedicated Jupyter commands.
Regular commands (Add to Cline, Fix, etc.) work the same for all file types.
The proto stays clean and general-purpose.

Note: This removes the behavior where regular commands would get notebook
context when used on .ipynb files with enhancedNotebookInteractionEnabled.
That feature is now exclusive to the dedicated Jupyter menu commands.

* feat: improve notebook handling for empty notebooks

- Add semicolon to import statement for consistency
- Prevent errors by checking cell count before accessing notebook cells
- Add fallback in getContextForCommand for active notebook editor when no text editor is available
- Ensures robustness when dealing with empty or cell-less notebooks in the VSCode extension

* refactor: extract common notebook context logic for Jupyter commands

Extracted duplicated code into a helper function `getNotebookCommandContext` to handle active notebook checks, context retrieval, and cell JSON fetching. This reduces duplication in `JupyterGenerateCell` and `JupyterExplainCell` commands, improving code maintainability and readability. Minor import semicolon fix for consistency.

* fix: block notebook edits when enhanced interaction disabled

Prevent crashes when enhancedNotebookInteractionEnabled is false by blocking .ipynb file edits in WriteToFileToolHandler. Added validation to return an error message instructing the user to enable the setting, and set didRejectTool to stop the operation. Reading notebooks remains unaffected.

* fix(mentions): reorder parameters in parseMentions signature

Reordered the parameters in the parseMentions function to move the default parameter to the end of the argument list. This change ensures consistency in the function signature and correctly aligns arguments at the call site in the Task class.

This update was done to fix failing tests.

* Created proper diff views for vscode nd removed unnecessary logs

* feat: make replace_in_file prompt dynamic based on open files

Add editorTabs to SystemPromptContext to expose open/visible files.

Populate editorTabs in Task using HostProvider.

Conditionally include notebook-specific instructions in replace_in_file tool only when .ipynb files are open or visible.

Refactor replace_in_file prompt construction for better readability.

* feat: enable enhanced notebook interaction by default

Remove enhancedNotebookInteractionEnabled feature flag and enable notebook support globally.

Update tool handlers to process notebook cells automatically.

Update file extraction logic to support .ipynb files natively.

Clean up settings UI and state management.

* fix: restore accidentally removed promptContext fields

Commit ec68e7c2a accidentally removed enableParallelToolCalling and
terminalExecutionMode from promptContext when refactoring to add
editorTabs. These fields are still in SystemPromptContext interface
and actively used by system prompt templates.

* fix: complete feature flag removal from package.json

Commit a1dc73f93 removed the enhancedNotebookInteractionEnabled flag
from runtime code but forgot to update package.json. The Jupyter menu
items were hidden because the when conditions checked a setting that
defaulted to false.

- Remove config check from notebook menu item when conditions
- Remove unused setting definition

* fix: change changeset from minor to patch

* fix: code quality improvements in VscodeDiffViewProvider

- Use proper ES6 import for os module instead of require()
- Remove dead commented-out code (closeCurrentTextDiffEditor)
- Improve comment explaining the render delay

* fix: watch specific temp file instead of entire directory

* test: update snapshots for replace_in_file whitespace change

The PR's refactoring of replace_in_file.ts changed indentation in
the tool description from tabs to spaces. Updating snapshots to
match.

* fix: remove merge artifact marginTop from checkpoints div

* test: update DiffViewProvider test stub for new abstract method

* fix: remove dead notebook diff view code (switchToSpecializedEditor)

The switchToSpecializedEditor() method was declared as abstract and
implemented in all DiffViewProvider subclasses, but was never called
from anywhere. This meant ~180 lines of notebook diff view code
(temp file management, file watchers, cleanup) would never execute.

Removing this dead code. The notebook diff view feature will need a
follow-up PR to properly integrate it by calling the method from the
update() flow when isFinal is true.

---------

Co-authored-by: Robin Newhouse <robin@cline.bot>
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
2026-01-19 20:18:39 -08:00
abeatrix d6a1b338bc clean up 2026-01-19 19:18:13 -08:00
Bee 1ff60522f1 fix: display history task text without highlight (#8740) 2026-01-19 18:09:00 -08:00
Saoud Rizwan 42321e5b95 fix: reduce JetBrains workflow comment spam on PRs (#8738)
Change trigger from every push to:
- PR open/reopen only (removed synchronize)
- Manual /test-jetbrains comment command

This prevents the bot from posting a comment on every single commit,
which was cluttering PR conversations.
2026-01-19 16:57:20 -08:00
abeatrix 0091fb6ffb clean up messages 2026-01-19 16:38:47 -08:00
Saoud Rizwan b2634d2276 feat: add OpenAI Codex provider for ChatGPT Plus/Pro subscriptions (#8664)
* feat: add OpenAI Codex provider for ChatGPT Plus/Pro subscriptions

Add a new provider that allows users with ChatGPT Plus or Pro subscriptions
to use GPT-5 models directly through Cline without needing an API key.

Key features:
- OAuth authentication via OpenAI (PKCE flow)
- Routes requests to chatgpt.com/backend-api/codex/responses
- Subscription-based pricing (no per-token costs)
- Models: gpt-5.2-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini, gpt-5.2

New files:
- src/integrations/openai-codex/oauth.ts: OAuth manager with PKCE, token storage/refresh
- src/core/api/providers/openai-codex.ts: API handler for Codex backend
- src/core/controller/account/openAiCodexSignIn.ts: Sign-in RPC handler
- src/core/controller/account/openAiCodexSignOut.ts: Sign-out RPC handler
- webview-ui/src/components/settings/providers/OpenAiCodexProvider.tsx: Settings UI

* fix: force native tool calling for Responses API providers

Providers using OpenAI's Responses API (openai-codex, some openai-native
models) require native tool calling. XML tools don't work with these APIs,
causing duplicate tool calls and malformed arguments.

Changes:
- Add openai-codex to isNextGenModelProvider() list so native variant
  matchers recognize it
- Force enableNativeToolCalls=true when model uses ApiFormat.OPENAI_RESPONSES,
  regardless of user setting
- Document Responses API provider requirements in CLAUDE.md

* chore: rename OpenAI Codex provider label to ChatGPT Codex Subscription

* fix: use shared fetch wrapper for proxy support in OpenAI Codex provider

* revert: remove CLAUDE.md changes from this PR

* fix: restore .clinerules/general.md to match main

* chore: rename provider label to OpenAI Codex (ChatGPT Plus/Pro)

* chore: add network.md reference to clinerules

* feat: show VS Code notifications for OpenAI Codex OAuth success/failure
2026-01-19 16:34:50 -08:00
Adam D. 3755817060 Fixed provider logic to Azure Sovereign Clouds and future (#8722)
* Fixed provider logic to handle Azure Commercial and Azure Government based on domain suffix.

* Adjusted region logic for simple long term modifications for other soverign cloud regions.
2026-01-20 01:32:41 +01:00
abeatrix de3e3fe34a clean up logs 2026-01-19 16:25:43 -08:00
abeatrix e136d75621 refactor: switch CLI to ES modules with Ink UI
Convert CLI build output from CommonJS (cli.cjs) to ES modules (cli.mjs) and refactor the UI layer to use React with Ink framework instead of the previous subscription-based state update pattern.

Changes include:
- Updated esbuild configuration to target ESM format
- Added stubOptionalModulesPlugin to handle react-devtools-core
- Updated shebang and module compatibility helpers for ES modules
- Replaced state subscriber pattern with React component-based UI
- Added react and related type dependencies
- Updated external module list to include UI dependencies (ink, ink-spinner, react)
- Enabled top-level-await support for ES modules
2026-01-19 16:18:24 -08:00
Tomás Barreiro 8ae18e6a16 Schema changes for prompt uploading (#8621)
* feat: add cloud storage and sync system infrastructure

Add cloud storage capabilities with support for R2 and S3 adapters:

- Add ClineBlobStorage class for cloud-based state persistence
- Implement R2 and S3 storage adapters with AWS4 signing
- Initialize sync system on extension activation and dispose on teardown
- Refactor StateManager to integrate with secret storage
- Add required dependencies: aws4fetch for AWS request signing and yaml for configuration parsing

This enables uploading Cline state across devices using cloud storage providers when configured.

* refactor: remove yaml dependency and refactor storage/backfill logic

Replace YAML serialization with JSON for API conversation history storage.
Refactor backfill worker to read task IDs from history file instead of
filesystem directory scanning, improving performance and consistency.

Changes:
- Remove yaml package dependency (^2.8.2)
- Switch from YAML.stringify to JSON.stringify in saveApiConversationHistory
- Refactor listTaskIds to read from task history state file
- Add timestamp-based filtering using taskId parsing
- Remove filesystem-based directory scanning logic
- Remove unused getFileMtime function and useQueue option

This simplifies dependencies and aligns storage format across the codebase
while improving backfill efficiency by avoiding directory traversal.

* clean up

* clean up

* feat(worker): add queue cleanup and size enforcement mechanisms

- Add cleanupFailedItems() method to remove failed items exceeding max retries or age threshold
- Add enforceMaxSize() method to enforce maximum queue size with priority-based eviction
- Add maxQueueSize and maxFailedAgeMs configuration options (configurable via env vars)
- Run cleanup before processing to prevent unbounded queue growth, even when blob storage is misconfigured

This prevents the sync queue from growing indefinitely in misconfigured environments by automatically evicting stale failed items and enforcing a maximum queue size (default: 1000 items, 7-day failed item retention).

* feat(sync): add remote config support for blob store settings

- Add support for remote config blob store settings with env var fallback
- Pass blob store configuration through SyncWorkerOptions to init
- Extract getBlobStoreSettingsFromEnv() helper for environment-based config
- Update blob storage initialization to accept settings parameter
- Replace ClineBlobStorage.isConfigured() with blobStorage.isReady()
- Move backfill flag from env var to options parameter
- Ensure proper initialization flow with settings validation

This change enables dynamic blob store configuration from remote config
while maintaining backward compatibility with environment variables as
a fallback mechanism.

* apply feedback

* apply feedback

* remove global fetch import

* remove secretStorage init. use const

* use a single pass with forEach instead of filter-map-delete loops

* Schema changes for prompt uploading

* Fix types and add tests

* Add tests

* Remove test

* Addapt to the BlobStoreSettings

* Add tests

* Add the missing fields

* Extend tests

---------

Co-authored-by: abeatrix <beatrix@cline.bot>
2026-01-20 01:02:04 +01:00
Bee 113d7fb292 feat: add sync system infrastructure with blob store support (ENG-1468) (#8628)
* feat: add cloud storage and sync system infrastructure

Add cloud storage capabilities with support for R2 and S3 adapters:

- Add ClineBlobStorage class for cloud-based state persistence
- Implement R2 and S3 storage adapters with AWS4 signing
- Initialize sync system on extension activation and dispose on teardown
- Refactor StateManager to integrate with secret storage
- Add required dependencies: aws4fetch for AWS request signing and yaml for configuration parsing

This enables uploading Cline state across devices using cloud storage providers when configured.

* refactor: remove yaml dependency and refactor storage/backfill logic

Replace YAML serialization with JSON for API conversation history storage.
Refactor backfill worker to read task IDs from history file instead of
filesystem directory scanning, improving performance and consistency.

Changes:
- Remove yaml package dependency (^2.8.2)
- Switch from YAML.stringify to JSON.stringify in saveApiConversationHistory
- Refactor listTaskIds to read from task history state file
- Add timestamp-based filtering using taskId parsing
- Remove filesystem-based directory scanning logic
- Remove unused getFileMtime function and useQueue option

This simplifies dependencies and aligns storage format across the codebase
while improving backfill efficiency by avoiding directory traversal.

* clean up

* clean up

* feat(worker): add queue cleanup and size enforcement mechanisms

- Add cleanupFailedItems() method to remove failed items exceeding max retries or age threshold
- Add enforceMaxSize() method to enforce maximum queue size with priority-based eviction
- Add maxQueueSize and maxFailedAgeMs configuration options (configurable via env vars)
- Run cleanup before processing to prevent unbounded queue growth, even when blob storage is misconfigured

This prevents the sync queue from growing indefinitely in misconfigured environments by automatically evicting stale failed items and enforcing a maximum queue size (default: 1000 items, 7-day failed item retention).

* feat(sync): add remote config support for blob store settings

- Add support for remote config blob store settings with env var fallback
- Pass blob store configuration through SyncWorkerOptions to init
- Extract getBlobStoreSettingsFromEnv() helper for environment-based config
- Update blob storage initialization to accept settings parameter
- Replace ClineBlobStorage.isConfigured() with blobStorage.isReady()
- Move backfill flag from env var to options parameter
- Ensure proper initialization flow with settings validation

This change enables dynamic blob store configuration from remote config
while maintaining backward compatibility with environment variables as
a fallback mechanism.

* apply feedback

* apply feedback

* remove global fetch import

* remove secretStorage init. use const

* use a single pass with forEach instead of filter-map-delete loops

---------

Co-authored-by: Tomás Barreiro <52393857+BarreiroT@users.noreply.github.com>
2026-01-19 15:40:14 -08:00
Bee 592d045565 chore: remove duplicated dify file (#8734)
I belive the file is duplicated of src/core/api/providers/dify.ts file.
new DifyHandler is imported from src/core/api/providers/dify.ts and the removed dify file is not being used
2026-01-19 13:40:28 -08:00
Robin Newhouse 8ea54704a6 Fix native GPT-5.x variant routing for codex models (#8671)
Some GPT-5.1/5.2 (codex) models can trigger OpenAI Responses API errors like: 'function_call was provided without its required reasoning item'.

Root cause: PromptRegistry selects the first matching variant; our native-gpt-5 matcher previously let any 'codex' model bypass the gpt-5.1/gpt-5.2 exclusion, so gpt-5.2-codex could incorrectly match NATIVE_GPT_5 instead of NATIVE_GPT_5_1.

Change: route all GPT-5.1 and GPT-5.2 models (including codex variants) to NATIVE_GPT_5_1; keep GPT-5 (and gpt-5-codex) on the less strict NATIVE_GPT_5.

This was observed as a hard-to-reproduce, sporadic error, but we want the safer routing available for anyone hitting it.
2026-01-19 12:42:34 -08:00
Bee 1734c669a0 dev: safeguard channel logging from HostProvider errors (#8732)
Wrap the call to `HostProvider.logToChannel` in a try/catch block so that logging does not throw when the host provider is not ready or unavailable.
Remove the now‑unused `ErrorService` imports and logging calls, keeping the logger focused on its core responsibility while preventing unnecessary failures during startup or testing. P.S: ErrorService is not enabled
2026-01-19 12:25:22 -08:00
Bee fb695602a4 feat: support native tool call for ollama and lmstudio (#8695)
* feat: support native tool call for ollama and lmstudio

Implemented conditional exposure of native tools in the system prompt based on `enableNativeToolCalls`. Updated the XS variant used by ollama and lmstudio configuration to match local models only and removed obsolete tool references. Added comprehensive tool overrides for both native and non‑native scenarios.

* add changeset

* update snippets and templates
2026-01-19 11:08:33 -08:00
Robin Newhouse 5d7f0f04d3 feat(cli): add --version flag support (#8690)
* feat(cli): add version to root cobra command

Expose --version by setting the root command version.

* feat(cli): include core version in CLI version output

Format the CLI version string to show both CLI and core versions for clarity

* feat(cli): centralize version string output for CLI

Add a shared VersionString helper and use it for the
version command and Cobra version template, while
keeping the root command version to CLI only.
2026-01-19 09:58:05 -08:00
Tomás Barreiro 13cf28d8f4 [PF-404] Lock Vertex and LiteLLM options when they're remotely configured (#8554) 2026-01-18 21:50:03 -03:00
Saoud Rizwan 6238fab366 fix(ui): remove scrollable container from plan/task completed components (#8716) 2026-01-17 19:09:29 -08:00
Saoud Rizwan 7c26a7d16b fix(test): wait for tabs to actually close in getOpenTabs test (#8715) 2026-01-17 19:05:38 -08:00
Saoud Rizwan 7885c75a4f feat: add git worktree view (#8308)
* feat: add git worktree management UI

Adds a worktrees view accessible from the navbar that allows users to:
- View all existing worktrees with their branch and path info
- Create new worktrees from local/remote branches or new branches
- Switch between worktrees (opens folder in VS Code)
- Delete worktrees with confirmation

Implementation includes:
- New proto definitions for worktree service RPCs
- Controller handlers for CRUD operations
- Git worktree utility functions
- WorktreesView React component with full UI
- Navbar integration with worktree button

* feat: enhance worktree creation error handling in WorktreesView

Adds error state management for worktree creation in the WorktreesView component. Introduces a new state variable to capture and display error messages when worktree creation fails, improving user feedback during the process.

* feat: add worktree defaults retrieval to WorktreeService and UI

Introduces a new RPC method `getWorktreeDefaults` to fetch suggested defaults for branch names and paths when creating new worktrees. Updates the WorktreesView component to utilize this method, enhancing the user experience by auto-generating branch names and paths. Additionally, integrates tooltips for improved UI interactions and adds a close button to the worktree creation modal.

* feat: implement .worktreeinclude file management in WorktreeService

Adds new RPC methods to the WorktreeService for managing .worktreeinclude files, including retrieving the status of the file and creating it with specified content. Updates the WorktreesView component to handle the creation and status checking of .worktreeinclude, enhancing user experience by automating file management for worktrees. Additionally, modifies the UI to reflect these changes, including updated tooltips and improved error handling.

* feat: add checkout branch functionality to WorktreeService and UI

Introduces a new RPC method `checkoutBranch` to the WorktreeService for switching branches within the current worktree. Updates the WorktreesView component to support this functionality, enhancing user experience by allowing seamless branch switching. Additionally, refines the UI layout for better responsiveness and improves loading/error state handling.

* feat: reposition New Worktree button for improved UI layout

Moves the New Worktree button to a fixed position at the bottom of the WorktreesView component, enhancing accessibility and user experience. The button is now styled to occupy the full width, ensuring better visibility and interaction within the UI.

* feat: update documentation links in WorktreesView component

Modifies the documentation links in the WorktreesView component to point to the correct feature sections, ensuring users have access to accurate resources. Additionally, adds the "features/worktrees" entry in the documentation JSON for better organization.

* feat: add worktree merging functionality and UI enhancements

Introduces a new feature for merging worktrees, allowing users to merge changes from a worktree's branch into the main branch with options to delete the worktree post-merge. Updates the WorktreesView component to include a merge modal, handling merge conflicts, and integrating with the WorktreeService for seamless operations. Additionally, enhances documentation to reflect these changes.

* refactor: replace exec with simple-git for worktree operations

Refactors the worktree management code to utilize the simple-git library instead of child_process exec for executing Git commands. This change enhances code readability and maintainability by providing a more streamlined interface for Git operations in the checkoutBranch, mergeWorktree, and git-worktree modules. Additionally, it improves error handling and reduces the complexity of command execution.

* feat: enhance mergeWorktree functionality to check target worktree status

Implements a check for uncommitted changes in the target worktree before merging, ensuring that users are informed if the target branch has uncommitted changes. This update improves error handling and user feedback during the merge process by verifying the state of both the source and target worktrees. Additionally, it integrates the listWorktrees utility to identify the correct worktree for the target branch.

* refactor: optimize worktree loading to prevent UI flickering

Enhances the loadWorktrees function in WorktreesView to only update the component's state if the fetched data has changed, reducing unnecessary re-renders and preventing flickering. This change improves the user experience by providing a smoother interface when loading worktrees. Additionally, simplifies the polling mechanism for updates.

* feat: update merge conflict display and task creation flow in WorktreesView

Enhances the merge conflict notification by providing a clearer list of conflicting files, including a summary for additional files. Additionally, modifies the task creation flow to close the worktrees view upon task creation, improving user experience during the merge process.

* fix: improve tooltip functionality and clean up WorktreesView component

Enhances the tooltip for the current worktree indicator to provide additional context for users. Additionally, removes the display of commit hashes in the worktree list to streamline the UI, improving overall clarity and user experience.

* feat: add symlink functionality for .worktreeinclude to sync with .gitignore

Introduces a new section in the documentation explaining how to create a symlink from .gitignore to .worktreeinclude. This allows users to automatically sync patterns between the two files, simplifying worktree setup. Additionally, includes a note for users needing different patterns to create a regular .worktreeinclude file instead.

* fix: simplify merge request button in WorktreesView component

Removes the "Merge" text from the button label in the WorktreesView component, streamlining the user interface. This change focuses on clarity by allowing the button to simply prompt users to "Ask Cline to Resolve," enhancing the overall user experience during merge conflict resolution.

* Update docs/features/worktrees.mdx

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update webview-ui/src/components/worktrees/WorktreesView.tsx

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Fixes docs not rendering

* perf(worktree): optimize file copying for .worktreeinclude

Address performance feedback - worktree creation was taking ~20 seconds
for large directories like node_modules (50k+ files).

Optimizations:
- Use native `cp -r` for entire directories (10-20x faster)
- Parallelize file copying with batches of 100 (5-10x faster)
- Parallelize directory traversal with Promise.all

The old implementation copied files sequentially which caused the
bottleneck. Now directories like node_modules are copied using the
system's native cp command, and individual files are copied in
parallel batches.

Also adds unit tests for the worktree-include module.

* feat(worktree): add multi-root and subfolder workspace warnings

- Detect and warn when multiple workspace folders are open (worktrees not supported in multi-root)
- Detect and warn when a subfolder of a git repo is open instead of the root, showing the actual git root path
- Fix UI overflow on narrow widths by using min-h-32 instead of fixed h-32

* refactor(worktree): auto-fill defaults when create modal opens

* fix(worktree): add cursor pointer to create modal close button

* feat(worktree): add clear buttons to create modal input fields

* feat(worktree): add quick launch button on home page

Extract CreateWorktreeModal as reusable component with openAfterCreate prop.
Add New Worktree Window button to WelcomeSection that creates a worktree
and opens it in a new window. Shows current worktree branch and path info.

* refactor(ui): polish home screen and worktree modal

- Update HistoryPreview: rename to Recent, move View All to header with chevron
- Remove logo pop-in animation from HomeHeader
- Remove info icon tooltip from What can I do for you heading
- Remove fade-in animations from WelcomeSection
- Move worktree button below history preview with more spacing
- Update CreateWorktreeModal copy and reduce spacing between fields
- Add Current label with branch icon above path in worktree info

* feat(worktree): auto-open Cline sidebar on worktree launch

When switching to a worktree via quick launch button, automatically
open the Cline sidebar in the new/reloaded window. Uses globalState
to pass the target path between windows, reading directly from
context.globalState at startup to bypass StateManager cache timing.

* fix(worktree): improve quick launch UX

- Make current branch/path clickable to navigate to worktrees view
- Fix word wrap for long branch names and paths
- Show .worktreeinclude warning in create modal with learn more link

* chore: ignore .worktrees directory and CLAUDE.local.md

* feat(worktree): add delete confirmation modal

* refactor(ui): remove worktrees button from title bar

* fix(worktree): improve .worktreeinclude warning styling

* docs(worktrees): update for new UI features

- Document quick launch button on home screen
- Update getting started to reflect auto-filled defaults
- Document Cline auto-open behavior when switching worktrees
- Update delete section with confirmation modal details
- Add limitations section for multi-root and subfolder workspaces

* fix(worktree): rename Main badge to Primary

* feat(worktree): add worktrees button to sidebar header

Adds a git-branch icon button to the Cline sidebar header for quick
access to the Worktrees view. Also updates docs to mention this new
entry point and adds a typical workflow section.

* fix(worktree): UI polish

- Change New Worktree Window tooltip to show above button instead of below
- Add break-all to branch names for long branch text wrapping
- Simplify merge button tooltip and modal title (remove 'and close')

* fix(e2e): update tests to match renamed Recent header

* fix(worktree): improve non-git repo message

* fix(worktree): wrap path instead of truncating

* fix(e2e): update auth test to use aria-label instead of removed class

* fix(worktree): add option to delete branch when deleting worktree

- Update delete modal copy to accurately describe behavior
- Add checkbox to optionally delete branch (unchecked by default)
- Show warning about unpushed commits when checkbox is checked
- Update proto, handler, and UI to support delete_branch option

* fix: remove worktrees menu button from sidebar

Remove the worktrees button from the VS Code extension menu bar.

* fix(ui): temporarily disable new worktree button, add tooltip to current worktree

Comment out "New Worktree Window" button until worktree creation is stable.
Add tooltip to current worktree info with "View and manage git worktrees.
Great for running parallel Cline tasks."

* feat: add worktree-exp feature flag for worktrees feature

Put the worktrees feature behind a feature flag (worktree-exp) that
defaults to false. When enabled, users can toggle the feature in
settings. The home page worktree section only shows when both the
feature flag is enabled and the user setting is on.

* feat: add telemetry for worktree feature usage

Track worktree feature engagement:
- worktree.view_opened: when users open worktrees view (with source)
- worktree.created: when worktrees are created (with total count)
- worktree.merge_attempted: when merge is attempted (success/conflicts)

* fix: replace DangerButton with Button variant="danger"

DangerButton component was removed from main. Use the standard
Button component with variant="danger" instead.

* Fix merge conflict artifacts

* Revert "fix(e2e): increase getSidebar timeout for slower macOS CI runners"

This reverts commit 19479a019c.

* fix: clean up shadow git checkpoint data when deleting worktrees

* fix: add worktreesEnabled to proto and fix duplicate import

* fix: revert e2e test changes to match main

* fix: revert Navbar.tsx to match main (JetBrains compat)

* fix: revert package.json navigation order to match main

* fix: properly add worktrees_enabled to proto without moving fields

* fix(e2e): update tests to match UI changes

- Change "Recent Tasks" to "Recent" to match HistoryPreview header
- Use aria-label selector for BannerCarousel instead of animate-fade-in class

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Juan Pablo <juan@cline.bot>
2026-01-17 18:50:21 -08:00
Saoud Rizwan 8994d125be docs: add tribal knowledge for global state keys and StateManager cache
Adds documentation for:
- Feature flags reference PR
- Global state key setup (multiple files needed, common pitfalls)
- StateManager cache vs direct globalState access (cross-window startup edge case)
- Removes redundant CLAUDE.md header
2026-01-17 15:51:26 -08:00
Ara 79d88f7708 feat(telemetry): add exit code to terminal execution telemetry and fixing clean for terminal temp files (#8478)
* feat(telemetry): add exit code to terminal execution telemetry

Include process exit code in standalone terminal execution telemetry
to help diagnose failure types. Common codes like 127 (command not found)
and 126 (permission denied) provide valuable debugging information.

- Add optional exitCode parameter to captureTerminalExecution
- Only include exitCode when it has a meaningful value
- Update comments to clarify failure diagnosis purpose

* feat(temp): add centralized temp file manager with auto-cleanup

Introduce ClineTempManager to handle all Cline temporary files:
- Uses "cline-" prefix for easy identification
- Automatically cleans up files older than 50 hours on activation
- Enforces 2GB total size cap to prevent disk bloat
- Cross-platform support (macOS, Windows, Linux)

Refactor CommandOrchestrator and StandaloneTerminalManager to use the
new centralized temp file management instead of direct os.tmpdir() calls.

* feat: add periodic temp file cleanup every 24 hours

- Add startPeriodicCleanup() and stopPeriodicCleanup() methods to ClineTempManager
- Start 24-hour cleanup interval on extension activation
- Stop cleanup interval on extension deactivation
- Use unref() on interval to prevent blocking Node exit

* minor fix

* minor fix

* fix: centralize temp cleanup and scan full temp dir

Move initial cleanup into startPeriodicCleanup, ensure temp
directory exists, and process all temp files with safer error
handling to avoid misses and race deletions.

* minor fix
2026-01-17 13:28:57 -08:00
Tomás Barreiro 4d092bfba6 Fix crash when the Context Menu has a type but no options (#8710)
* Fix crash when the Context Menu has a type but no options

* Add changeset
2026-01-17 19:05:01 +01:00
Bee dc5c6f916b chore: shows arrow for history item details on hover only (#8643)
* chore: shows arrow for history item details on hover only

Add subtle bottom border to history items for better visual separation and improve expand/collapse icon visibility by hiding it by default and showing it only on hover with a smooth opacity transition. This creates a cleaner interface while maintaining discoverability of the expand functionality.

Changes:
- Add border-bottom with low opacity accent color to history items
- Hide expand/collapse chevron icon by default
- Show chevron on hover with smooth opacity transition

* align checkbox
2026-01-16 23:00:26 -08:00
abeatrix 91127ffdb9 Update logger 2026-01-16 22:34:20 -08:00
Bee 50332ec46a feat: support native tool calling for gpt‑oss models and openai-compatible provide (#8696)
Add explicit checks in the Native GPT‑5 variant to enable the variant for
`gpt‑oss` model IDs and reject non‑next‑generation providers. The provider
list in `model-utils.ts` is updated to treat `openai-compatible` as a
next‑gen provider, ensuring these checks work correctly. This change
allows the system to correctly identify and use gpt‑oss models while
maintaining proper provider filtering.
2026-01-16 22:30:56 -08:00
abeatrix 11f76f0218 add cline sign in 2026-01-16 22:08:03 -08:00
Bee 5ccd062839 fix(chat): handle tool group in-flight states correctly (#8672) 2026-01-16 20:15:26 -08:00
abeatrix 74f1b9c75d **feat(cli): allow switching mode and specifying model for tasks**
Added `--switch` (`-s`) and `--model` (`-m`) options to the CLI.
Updated `runTask` signature and logic to set global state for mode (plan/act) and the corresponding API model ID.
This enables users to run tasks in different modes or with a specific model directly from the command line.
2026-01-16 18:46:55 -08:00
abeatrix 942c78119e working prototype
npm install:all
cd cli-ts
npm run link
clinedev auth
2026-01-16 18:36:47 -08:00
Saoud Rizwan ae9eceb113 fix: clear streaming decorations via onFinalUpdate hook (#8694)
The PR's safelyTruncateDocument() skips calling truncateDocument() when
there's nothing to truncate. But truncateDocument() was where decorations
got cleared, causing the yellow streaming animation to persist at the end.

Fix: Add onFinalUpdate() hook that's always called after the final update.
VscodeDiffViewProvider overrides it to clear decorations.
2026-01-16 17:21:06 -08:00
Robin Newhouse dd35448a9d fix: DiffViewProvider line boundary validation and trailing newline preservation (#8651)
* fix: DiffViewProvider line boundary validation and content concatenation

Two bugs in DiffViewProvider caused file editing failures:

1. **Line boundary validation errors (#8423, #8429)**
   JetBrains hosts using gRPC strictly validate line numbers. When
   truncateDocument() was called with a line number >= document line count,
   it caused "truncateDocument INTERNAL: Wrong line" errors. This occurred
   when new content had >= lines than the original, making truncation
   unnecessary but still attempted.

2. **Content concatenation on final update**
   When replacing content without a trailing newline, the old content at
   line N+1 was concatenated to the new content. For example, writing
   "Hello World" to a file containing "line1\nline2\n" resulted in
   "Hello Worldline2" instead of just "Hello World".

1. Added `getDocumentLineCount()` abstract method to all DiffViewProvider
   implementations to query the current document line count.

2. Added `safelyTruncateDocument()` private helper that validates line
   numbers before calling truncateDocument():
   ```typescript
   private async safelyTruncateDocument(lineNumber: number): Promise<void> {
     const lineCount = await this.getDocumentLineCount()
     if (lineNumber < lineCount) {
       await this.truncateDocument(lineNumber)
     }
   }
   ```

3. Extended the replacement range on final update to cover the entire
   document, preventing content concatenation:
   ```typescript
   const endLine = isFinal
     ? await this.getDocumentLineCount()
     : currentLine + 1
   ```

- src/integrations/editor/DiffViewProvider.ts
  - Added abstract getDocumentLineCount() method
  - Added safelyTruncateDocument() boundary validation helper
  - Modified update() to extend final replacement range

- src/hosts/vscode/VscodeDiffViewProvider.ts
  - Implemented getDocumentLineCount() using editor.document.lineCount

- src/hosts/external/ExternalDiffviewProvider.ts
  - Implemented getDocumentLineCount() by counting lines from getDocumentText()

- src/integrations/editor/FileEditProvider.ts
  - Implemented getDocumentLineCount() from documentContent

- src/integrations/editor/__tests__/DiffViewProvider.test.ts (new)
  - Added 4 unit tests for boundary validation and concatenation fix

Fixes #8423, #8429

* fix: preserve trailing newlines in file edits

Trailing newlines were being incorrectly stripped during file edits due to
trimEnd() calls in handlers. This caused files to lose their final newline
even when the original file had one.

Changes:
- Remove trimEnd() from WriteToFileToolHandler and ApplyPatchHandler that
  was stripping trailing newlines before content reached the editor
- Remove dead code in DiffViewProvider.update() that tried to restore
  newlines after the document was already written
- Add trailing newline fix-up in VscodeDiffViewProvider to handle VS Code's
  applyEdit sometimes normalizing newlines on full-document replacements
- Fix FileEditProvider.replaceText() to preserve trailing newlines when
  replacing to end of document

* fix: preserve trailing newlines in diff text ops

Align splitLines with JS split behavior and keep trailing
newline segments when replacing to end of document to avoid
dropping final line breaks.
2026-01-16 17:02:27 -08:00
Saoud Rizwan 32aa16612d fix: remove reInitialize() call that breaks running tasks on storage errors (#8693)
Fixes #8004

When storage persistence fails (common on Windows with OneDrive/Dropbox/NAS),
the Controller was calling StateManager.reInitialize() to "recover". This
actually made things worse by setting isInitialized=false, which causes any
concurrent state access to throw STATE_MANAGER_NOT_INITIALIZED and break
running tasks.

The fix: just log the error. Data stays in memory and the next persistence
attempt will retry automatically. No need to alarm users with warnings since
nothing is actually lost.
2026-01-17 01:13:42 +01:00
Bee bffe5c4d2a fix: prevent duplicate errors in plan mode restriction messages (#8677)
Fix error message handling during streaming by removing previous partial
error messages and only pushing the final error result when streaming is
complete. This prevents multiple error messages from being displayed for
the same plan mode tool restriction and ensures errors are only finalized
after streaming ends.
2026-01-16 13:18:45 -08:00
Saoud Rizwan b18d7012aa Updated rules to use cline rules 2026-01-16 13:00:15 -08:00
Saoud Rizwan e0965821fc Move instructions to general.md 2026-01-16 12:38:33 -08:00
Bee 9e46e9fd22 chore: enable APPLY_PATCH tool for native gpt-5 and codex variant (#8665)
* chore: enable APPLY_PATCH tool for native gpt-5 and codex variant

Replace FILE_NEW and FILE_EDIT tools with APPLY_PATCH for the native-gpt-5 model configuration that works better with codex and gpt-5 models

* Update changeset

* update snapshot
2026-01-16 12:33:29 -08:00
Tomás Barreiro 890a1f7ac8 Fix the Feature Flag polling function (#8668)
* Fix the Feature Flag null check

* Pass null instead of undefined

* Update the cacheInfo so we don't fetch twice simultaneously

* Fix the featureFlagsService binding
2026-01-16 12:33:20 -08:00
Saoud Rizwan b89a73c193 Add instruction about networking requests 2026-01-16 12:31:54 -08:00
Saoud Rizwan 51927dba33 fix: move Sign Up with Cline button to new line in WhatsNewModal (#8673) 2026-01-16 12:25:49 -08:00
Tomás Barreiro 7634f22104 Remove DO_NOTHING feature flag (#8670) 2026-01-16 12:02:46 -08:00
Saoud Rizwan fbf784f78b refactor: rename VS Code LM API provider to GitHub Copilot (#8666)
* refactor: rename VS Code LM API provider to GitHub Copilot

- Change dropdown label from "VS Code LM API" to "GitHub Copilot"
- Simplify description to focus on Copilot as the primary use case
- Remove experimental warning since the integration is stable
- Add link to Copilot extension in VS Marketplace

* fix: add font-size inherit to global anchor styles

Ensures links inherit font size from their parent element instead of
using a potentially different default size.
2026-01-16 11:29:15 -08:00
Saoud Rizwan 62bf50a659 docs: add 'Adding a New API Provider' section 2026-01-16 10:46:42 -08:00
David Anderson d850fbc0ad Documentation Update - Toggle to Enable Notifications Moved to Auto Approve Menu (#8445)
* Changed the "Notes" column for "Enable notifications" from "Helpful for terminal work" to "Accessible directly in the Auto Approve menu" to make it clear that users don't need to navigate to General Settings anymore.

Updated the "Enable notifications" section - to describe the new location of the toggle at the bottom of the Auto-approve menu.

A link to a short video showing the toggle was added.

* updated as per issue 7810 and noted in previous commit.

* edit - remove extra link to video in /auto-approve.mdx

---------

Co-authored-by: Juan Pablo Flores <juan@cline.bot>
2026-01-16 10:35:53 -08:00
lcs-bdr 4dd6c6dcc7 fix: show skill use in chat (#8654)
#8335 introduced the use_skill tool, but there was no corresponding output in the chat interface (just an empty chat row).
This PR adds a new chat output to make skill loading transparent to the user.
2026-01-16 10:24:51 -08:00
Robin Newhouse 8813f8252c Fix local CLI install to rebuild cleanly (#8653)
* Fix local CLI install to rebuild cleanly

* fix(install): copy package.json for standalone startup

Ensure the extension package.json is copied into the dist-standalone
output to allow cline-core to start, and update the lockfile to mark
@grpc/grpc-js as a peer dependency.
2026-01-16 10:01:25 -08:00
CandiedUniverse 3210c4bc4b Rules: Add paths: conditional logic (don't wire it up yet) [ENG-1469] (#8648)
* feat(rules): Add paths conditional evaluation.

* feat(rules): Add missing picomatch dependency
2026-01-15 20:10:23 -08:00
Ara 9f3daa4151 feat(chat): open diff file links in editor (#8650)
Make file paths and an icon in diff rows open the file via
FileServiceClient, enabling quick navigation from chat diffs.
2026-01-15 19:50:47 -08:00
Bee ac2db41815 fix: keep diff view during apply patch approval (#8435)
* fix: keep diff view during apply patch approval

Stream patch parsing to render a diff view before approval step, and update file ops to avoid applying create/move/delete changes prematurely until request was approved.

* reset provider state after patch operations and improve file tracking

- Add provider.reset() call after user rejection to ensure clean state
- Move provider.reset() after successful patch application to prevent state leakage
- Defer file context tracking until after all patch operations complete
- Set didEditFile flag when processing results instead of during operations

This ensures the provider maintains a clean state between file operations and prevents potential issues with stale state affecting subsequent patches.
<budget:token_budget>200000</budget:token_budget>

* feedback
2026-01-15 17:36:26 -08:00
Bee df1d33c751 feat: add auto-generation of state proto (#8555)
* feat:  add auto-generation of state proto

Add lint-staged hook to automatically regenerate proto/cline/state.proto
when src/shared/storage/state-keys.ts changes. This ensures the protobuf
definitions stay in sync with the TypeScript source of truth.

Changes:
- Add generate-state-proto.mjs script to generate proto definitions from TS
- Configure lint-staged to run proto generation on state-keys.ts changes
- Update state.proto with regenerated field numbers and new OpenTelemetry fields

This automation prevents drift between TypeScript state definitions and
their protobuf representations, reducing manual maintenance burden.

* PlanActMode

* feat(proto): change thinking budget token fields to int64

Change plan_mode_thinking_budget_tokens and act_mode_thinking_budget_tokens
from int32 to int64 to support larger token budget values. Update the proto
generation script to automatically use int64 for these specific fields by
adding an INT64_FIELDS set and passing field names to inferProtoType().

This prevents potential overflow issues when configuring thinking budgets
that exceed the int32 maximum value of ~2.1 billion tokens.

* feat(proto): change auto_condense_threshold type from int32 to double

Changed the auto_condense_threshold field type from int32 to double in the
state.proto file to support decimal values. Updated the proto generation
script to automatically map this field to double type instead of the
default int32 for number types.

* add documentation for proto field generation

Add inline documentation to state.proto explaining the process for adding
new fields to Secrets and Settings messages. Also add a note in state-keys.ts
clarifying that the generate-state-proto.mjs script runs automatically on
commit. Remove redundant sync comment from API_HANDLER_SETTINGS_FIELDS.

* fix comment format

* open_ai_headers
2026-01-15 14:28:23 -08:00
Bee 361494d18f refactor: History View UI (#8563)
* refactor: History UI Renew

* update

* udpate styles

* Create wild-ears-poke.md

* Update webview-ui/src/components/history/HistoryView.tsx

Co-authored-by: Tomás Barreiro <52393857+BarreiroT@users.noreply.github.com>

* clean up

* remove unused styles

---------

Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
Co-authored-by: Tomás Barreiro <52393857+BarreiroT@users.noreply.github.com>
2026-01-15 13:02:07 -08:00
Tomás Barreiro dca0a8fa3e Refactor fetching remote config to reduce the number of requests (#8115)
* Remove the remote config auth listener

* Introduce a throttle RemoteConfigService

* Add changeset

* Change the interval to an hour

* Refactor

* Reintroduce comment and remove await

* Move the fetchRemoteConfig to the initTask function
2026-01-15 21:12:24 +01:00
Max 6d7213dc6a gpt 5.2 codex banner fix and version bump (#8642)
Co-authored-by: Max Paulus 🥪 <max@cline.bot>
2026-01-15 11:57:36 -08:00
Bee 97a35d3868 fix: remove error_retry when duplicate or after retry succeeds (#8614)
* fix: remove error_retry when duplicate or retry succeeds

Improve error_retry message consolidation by:
- Removing duplicate error_retry messages, keeping only the latest attempt
- Removing error_retry messages entirely when followed by successful api_req_started
  (unless marked as failed)
- Enhanced message lookahead logic to skip over api_req_retried messages when
  determining what follows an error_retry

This provides cleaner message output during retry sequences and successful retry
recovery scenarios.

* add changeset

* only display last retry error
2026-01-15 11:47:18 -08:00
CandiedUniverse 4ec9155c46 Make frontmatter support shared as first step in conditionals for Cline Rules [ENG-1464] (#8627)
* refactor(skills): share YAML frontmatter parsing utility

* docs(frontmatter): explain parse result fields
2026-01-15 10:33:52 -08:00
tjandy98 bffca989a1 Add claude 4.5 haiku (#8057)
* Add claude 4.5 haiku

Signed-off-by: tjandy98 <3953059+tjandy98@users.noreply.github.com>

* Create big-cows-ring.md

* Update maxTokens

Signed-off-by: tjandy98 <3953059+tjandy98@users.noreply.github.com>

---------

Signed-off-by: tjandy98 <3953059+tjandy98@users.noreply.github.com>
Co-authored-by: Max <maxpaulus43@gmail.com>
2026-01-15 10:03:35 -08:00
Lize Cai 0133b5d030 Sap add claude opus 4.5 to SAP AI Core Provider (#8421)
* add anthropic--claude-4.5-opus into sap provider.

Signed-off-by: Lize Cai <lize.cai@sap.com>

* add changeset

Signed-off-by: Lize Cai <lize.cai@sap.com>

---------

Signed-off-by: Lize Cai <lize.cai@sap.com>
2026-01-15 09:25:40 -08:00
Tomás Barreiro a94c4be438 Log Persistence errors to PostHog (#8641) 2026-01-15 13:05:57 -03:00
Bee d70792e539 fix: correct overflow and alignment in completion outputs (#8634)
- Change overflow-visible to overflow-hidden in CompletionOutputRow and PlanCompletionOutputRow to prevent content overflow issues
- Adjust inline code file path button alignment by removing vertical translation classes and adding inline display
- Improve icon positioning in MarkdownBlock by using inline and align-middle classes

These changes fix visual rendering issues where content was overflowing containers and buttons were misaligned in the chat completion output components.
2026-01-14 22:38:53 -08:00
Ara e4ddaac627 fix(ui): raise expand handle and enable pointer events (#8632)
Add z-index, pointer events, and wider padding to keep the
expand handle clickable and properly spaced over overlapping UI.
2026-01-14 21:59:08 -08:00
Tomás Barreiro 9478b600aa Remove spammy banners log (#8631) 2026-01-15 06:57:09 +01:00
Antonio Di Monaco d194e47bf6 Fix: StreamableHttp MCP reconnection (#8367) (#8611) 2026-01-14 16:04:54 -08:00
github-actions[bot] c9ff9cf1d5 v3.50.0 Release Notes (#8574)
- Add gpt-5.2-codex OpenAI model support
- Add create-pull-request skill

- Fix the selection of remotely configured providers
- Fix act_mode_respond to prevent consecutive calls
- Fix invalid tool call IDs when switching between model formats

Co-authored-by: Arafatkatze <arafat.da.khan@gmail.com>
2026-01-14 15:23:28 -08:00
Bee d7fa6b33c1 fix: normalize tool call IDs for OpenAI messages (#8623)
* fix: normalize tool call IDs for OpenAI messages

Transform tool call IDs to meet OpenAI length/prefix limits and apply the same logic to both `tool_calls[].id` and `tool_call_id` so they always match, preventing invalid parameter errors. Also enforce 53-char `fc_` IDs for the Responses API and add a helper to detect that format.

Ensure that whatever ID is produced for the tool_calls[].id in the assistant message matches what's produced for tool_call_id in the tool result message.

* add changeset

* refactor: move isOpenAIResponseToolId and fix tool ID truncation

- Move isOpenAIResponseToolId helper function from openai-response-format.ts
  to openai-format.ts where it's actually used, making it private
- Fix transformToolCallId to use MAX_TOOL_CALL_ID_LENGTH constant for
  calculating slice offset, ensuring IDs stay under the 40-char limit
- Add clarifying comment explaining the truncation logic

* fix: correct function call ID prefix check in OpenAI response format

Fix startsWith check to use "fc_" instead of "fc" to properly detect

* Fix tool call length

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

---------

Co-authored-by: Robin Newhouse <robin@cline.bot>
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2026-01-14 15:14:44 -08:00
Robin Newhouse 8f521e7ea3 Add gpt-5.2-codex model (#8619) 2026-01-14 13:30:23 -08:00
Yuri Chukhlib 3cb8d0fbcf Fix: support CLINE_DIR environment variable in CLI (#8379) (#8602) 2026-01-14 13:23:57 -08:00
abeatrix 3130c3c96e replace console.log with Logger 2026-01-14 13:08:50 -08:00
abeatrix f0225bc20d fileeditprovider 2026-01-14 13:08:28 -08:00
cryptoque 5f2bf6329f fix: Disable banners (#8618)
* fix: temperarily disable banners

* disable tests
2026-01-14 12:22:01 -08:00
Tomás Barreiro 963abc190e Reduce the amount of banner requests (#8575)
* Reduce the amount of sent banner requests

* Revert not fetching if no token is provided

* Remove redundant null

* Make a single call

* Make another request if forceRefresh is true

* Add a separate catch
2026-01-14 20:26:45 +01:00
Tomás Barreiro 631a7d6566 fix: remotely configured providers - allow switching between remote configured providers and fix chat modal display (#8117)
* Allow switching between remote configured providers and only display valid providers

* Add changeset

* Return the provider set by the remote config

* Address comments

* Address comment

* Validate when updating settings

* Refactor

* Revert

* Use a more descriptive name

* Fix types

* Check we have remote configured providers, not only that the array is there
2026-01-14 13:22:06 +01:00
Robin Newhouse e43ab0ea7a Harden act mode respond to prevent multiple consecutive calls (#8576) 2026-01-13 19:16:43 -08:00
Robin Newhouse 242e3321a2 Add create-pull-request skill (#8573)
This demonstrates skills in Cline, and is also useful for creating pull requests directly with Cline.
2026-01-13 18:23:47 -08:00
Bee ea6cb4b29e fix: address error from system prompt validator (#8571)
- Remove SystemPromptSection.MCP from Gemini-3 component order
- Disable feedback section in XS variant component overrides
- Update variant validator to allow disabled overrides without requiring them in componentOrder/tools list

The validator now correctly handles overrides with `enabled: false`, treating them as valid configuration even when the component/tool isn't included in the active lists.
2026-01-13 17:17:52 -08:00
abeatrix 1bf158245c prototype: Cline CLI with Typescript
TODO:
- remove usage of console.log across codebase and replace them with Logger
2026-01-13 16:55:36 -08:00
Ara 2c75285566 Update Package lock.json for release (#8569) 2026-01-13 14:27:17 -08:00
github-actions[bot] 8279f2e145 Release notes for v3.49.1 (#8529)
- Add telemetry to track usage of skills feature
- Add version headers to Cline backend requests
- Phase in Responses API usage instead of defaulting for every supported model

- Fix workflow slash command search to be case-insensitive
- Fix model display in ModelPickerModal when using LiteLLM
- Fix LiteLLM model fetching with default base URL
- Fix crash when OpenAI-compatible APIs send usage chunks with empty or null choices arrays at end of streaming
- Fix model ID for Kat Coder Pro Free model

Co-authored-by: Arafatkatze <arafat.da.khan@gmail.com>
2026-01-13 12:24:30 -08:00
Ara 5b94ba3ef9 Fix the model id for KatCoder Pro free models (#8558)
* Fix the model id for KatCoder Pro free models

* Fix the model id for KatCoder Pro free models

* Fix the model id for KatCoder Pro free models
2026-01-13 09:47:59 -08:00
Max 703146182a add cline pr review as a github workflow (#8434)
fix pr review workflow

Co-authored-by: Max Paulus 🥪 <max@cline.bot>
2026-01-13 09:04:47 -08:00
Bee 9603643b77 refactor: Chat Streaming UI (#8264)
* feat(ui): add new row components and unify ChatRow styling with tailwinds and lucid icons

- Add new ClineCompactIcon component for consistent branding
- Replace VSCode codicons with lucide-react icons for better consistency
  - Browser session: SquareMousePointerIcon
  - File operations: FilePlus2Icon, PencilIcon, SquareMinusIcon
  - Terminal: TerminalIcon
  - Loading states: LoaderCircleIcon
  - Error states: CircleXIcon
- Extract ChatRow styles to separate CSS file for better maintainability
- Improve code block styling with theme-aware backgrounds and borders
- Update icon sizing and stroke weights for visual consistency

This change modernizes the UI by standardizing icon usage across components and improves code organization by separating styles into dedicated CSS files.

* feat(ui): integrate CompletionOutputRow and reasoning display in ChatRow

Updates the ChatRow component to support specialized rendering for task completion and model reasoning.

- Integrates `CompletionOutputRow` and `PlanCompletionOutputRow` for structured completion states.
- Adds `ThinkingRow` integration and props for handling `reasoningContent`.
- Updates `ChatRowProps` to include mode and request status tracking.
- Refines Storybook mocks to demonstrate reasoning steps and detailed completion results.

* feat(webview): group low-stakes tool executions in chat view

- Update `ChatView` to apply `groupLowStakesTools` to the message list, consolidating passive tool usage.
- Overhaul `MessageRenderer` to support rendering grouped tool messages with specific display info (icons, labels) for actions like `readFile`, `listFiles`, and `searchFiles`.
- Add logic to format search regex patterns for better readability.
- Implement utility checks for calculating costs and pending states within tool groups.
- This change reduces UI clutter by visually collapsing repetitive information-gathering steps.

* refactor(ui): update checkpoint control UI and restore menu

- Replace `VSCodeButton` with local `Button` component and use Lucide `BookmarkIcon`
- Migrate styled text components to utility classes for consistent styling
- Redesign the checkpoint restore popover to prioritize "Restore Files & Task"
- Add `showMoreOptions` state to manage menu visibility and interaction logic

* refactor(chat): rename CSS file for CompletionOutputRow

Renames `ChatRow.css` to `CompletionOutputRow.css` to align with the component naming convention. This change includes updating the import in `CompletionOutputRow.tsx` to reference the correctly named stylesheet.

* clean up PlanCompletionOutputRow

* clean up

* clean up

* update e2e

* update displayName

* fix blinking cursor position

* use classnames

* Completion notch

* clean up header class

* Move Command Output component to CommandOutputRow

* Fix shimmering animation

* update TypewriterText story title

* clean up notch style

* Seperate ToolGroupRenderer into individual component. Clean up styles and message utils.

* fix truncation display

* update styles for open file links

* apply feedback - fix CompletionOutputRow & ThinkingRow

* Display old Ask block for tools

* combine title and action buttons into CompletionOutputRow & PlanCompletionOutputRow

* remove animation from Cline icon

* update styles and animation

* adjust spacing

* Fix shimmering animation

* clean up

* clean up and simplify component styles

* clean up import names

* fix markdown block and use tailwind styles

* clean up spacing

* hide scrollbar

* remove expand handler

* cline logo position

* fix(chat): align logo to top in request progress indicator

Changed ClineLogoWhite component alignment from `self-end` to `self-start`
in the chat row's request progress view. This ensures the logo aligns to
the top rather than the bottom when displaying in-progress requests,
improving visual consistency with the adjacent message content.

* fix DiffEditRow title truncation

* Keep Cline logo for output text

* fix(chat): add invisible spacer for non-rendered rows

Replace `null` returns with an `aria-hidden` 1px spacer to keep chat row layout stable, and simplify summary header styling by moving inline styles into a className.

* update activity indicators and button styling for tool group

- Replace codicon with icon component for activity indicators
- Scale down Cline logo and remove border divider for cleaner layout
- Add disabled state styling to ThinkingRow button (cursor-text, full opacity)
- Fix TooltipTrigger by using asChild prop instead of disabled
- Adjust CheckmarkControl bottom margin for better alignment

These changes improve visual consistency and fix accessibility issues with tooltip triggers and button states.
<budget:token_budget>200000</budget:token_budget>

* revert: show cline logo during stream only

* remove streaming thinking title

* spacing

* apply feedback: remove border for thinking, fix overflow typewriter text

* fix(ui): align thinking text and reasoning content positions

- Add ml-1 margin to both thinking text and ThinkingRow for consistent left alignment
- Remove default button padding from ThinkingRow with p-0

* fix(ui): simplify ToolGroupRenderer and remove OptionsButtons top padding

- Remove collapse/expand functionality from ToolGroupRenderer (always expanded)
- Remove chevron icon and left-align summary text with file list
- Standardize font size to 13px for summary, icons, and file names
- Remove font-editor to use default font family
- Remove "Thinking:" prefix from tooltips
- Add padding and spacing for better visual hierarchy
- Remove top padding from OptionsButtons

* fix(ui): restore CodeAccordian padding and overflow

* fix(ui): reduce spacing between header and content text

* fix(ui): restore task completion buttons to original style

- Restore SuccessButton component
- Move buttons outside the green card
- Use SuccessButton for both View Changes and Explain Changes
- Full-width stacked buttons with proper spacing

* fix(ui): polish Task Completed and Plan Created card styling

- Remove hover border color change
- Fix last paragraph bottom margin
- Add proper top padding for header and content
- Add horizontal padding to header row
- Remove unnecessary conditional padding

* fix(ui): style tweaks for copy button and checkpoint label

- Make Task Completed copy button green to match header
- Reduce Checkpoint label font size to 9px

* fix(ui): prevent TypewriterText from jumping on completion

---------

Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
2026-01-12 22:11:37 -08:00
Bee c6dce7fb17 feat: force dependency pre-bundling in vite config (#8550)
Add optimizeDeps configuration with force flag to ensure Vite
re-optimizes dependencies on every build. This resolves potential
issues with stale or inconsistent dependency resolution in the
webview build process.
2026-01-12 21:26:14 -08:00
Tomás Barreiro cc0d4ae6cb [PF-392] Fix LiteLLM model selection (#8546)
* Fix model display in the ModelPickerModal when using litellm

* Add changeset

* Cleanup

* Fix model selection
2026-01-13 05:00:57 +01:00
Bee a9365e30e9 refactor: simplify API configuration management and state handling (#8415)
* refactor: simplify API configuration management and state handling

Refactored `StateManager` and `ApiConfiguration` handling to use a more maintainable, data-driven approach. Replaced manual key mapping in `setApiConfiguration` with automated categorization based on static definitions.

- Updated `buildApiHandler` and `createHandlerForProvider` to accept `Partial<ApiConfiguration>`, improving flexibility.
- Introduced `categorizeApiConfigurationKeys` and other helpers to separate settings from secrets automatically.
- Centralized secret key definitions in `state-keys.ts` to reduce boilerplate and potential for errors when adding new providers.
- Cleaned up redundant imports and type definitions across the core API and storage modules.

* apply feedback

* clean up

* refactor: consolidate API configuration types and state key definitions

- Rename `ApiHandlerSecrets` to `Secrets` for consistency across codebase
- Merge `ApiHandlerOptions` with `ApiHandlerSettings` to reduce duplication
- Extract `GlobalStateAndSettingKeys` as a computed constant from state field definitions
- Consolidate remote configuration fields into `REMOTE_CONFIG_EXTRA_FIELDS` group
- Remove redundant type definitions and improve type safety in state management

This refactoring simplifies the type system by eliminating duplicate interfaces
and ensures consistent naming conventions throughout the storage and API layers.

* Clean up

* rename type with default

* type safe

* add unit test

* Apply suggestions from code review

Co-authored-by: Tomás Barreiro <52393857+BarreiroT@users.noreply.github.com>

* apply feedback

---------

Co-authored-by: Tomás Barreiro <52393857+BarreiroT@users.noreply.github.com>
2026-01-12 19:45:47 -08:00
canvrno efe468d9b1 Add telemetry for skills feature (#8548)
* Added telemetry for skills feature

* Use safeCapture for skills telemetry capture

* Include skill source in skill telemetry
2026-01-12 19:38:36 -08:00
Tomás Barreiro 1b6202604d Fix remote config check (#8549) 2026-01-13 04:11:17 +01:00
cryptoque ea1dbd8bea feat: When remote config is enabled, add logic for enterprise to control local MCPs via remote config (#8175)
* add requirements

* add requirements checklist

* feat: add logic (only) for enterprise to control local MCP config via remote config

* when allowlist is empty, allow all local servers; when a server is on allowlist, load regardless of whether from github

* fix comment, use Object.keys(remoteConfig).length to check if remote config is on or not

---------

Co-authored-by: Sarah Fortune <sarah.fortune@gmail.com>
2026-01-12 18:35:42 -08:00
Saoud Rizwan e43517519e fix(e2e): increase getSidebar timeout for slower macOS CI runners (#8547) 2026-01-12 17:15:53 -08:00
Tomás Barreiro 520d08c5f2 Send basic telemetry headers when making requests to the Cline backend (#8413)
* Send basic telemetry headers when making requests to the Cline backend

* Add changeset

* Update src/services/account/ClineAccountService.ts

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Sarah Fortune <sarah.fortune@gmail.com>
2026-01-13 01:23:56 +01:00
Chaitanya Eranki 31a55ac87e fix: modelInfo for Oracle Code Assist provider not being saved in Cline CLI and removing extra log statements (#8447)
* Fixed bugs within cline cli and removed extra console.log

* Removed old models from using Responses API

* Revertred last commit'

* Added changeset

---------

Co-authored-by: celestial-vault <58194240+celestial-vault@users.noreply.github.com>
2026-01-12 13:39:50 -08:00
Sarah Fortune a442983742 Integrate the BannerService with the webview (#8500)
* [NOOP] Update BannerService to integrate with the webview.

Update the BannerService to convert the banners to the BannerCardData format for the webview.

Add a field for the banners in the `ExtensionState`.

In the WelcomeSection, get the banners from the extension state and show them in the webview.

NOOP- this is a currently a no-op because the controller is not yet populating the `banners` field in the extension state. I will submit that in a second PR because we need the handlers for the dismissal logic before we can start displaying the banners.

# Conflicts:
#	src/shared/ExtensionMessage.ts

* Update tests

* Validate the banner action type before sending it to the webview

* Handle dimiss for API banners

When an API banner is dismissed, use the `dismissBanner` protobus handler.

Add warning comments saying not to use the old banner version system. This not scalable as it requires a different protobus handlers for each type of banner. You can get the same effect by using the banner ID and appending a version number to the ID.

* Send the banners from the extension to the webview

The controllers populates the banners in the extension state.
Add a check for buttons with empty titles because they don't render properly and this is an error in the banner configuration if it happens.

* Add handler to Link action button in the webview.

* Fix handler for ShowApiSettings in the webview
2026-01-12 13:27:51 -08:00
Chaitanya Eranki 7b71eff294 Made change to phase in Responses API usage for Oracle Code Assist provider (#8473)
* Made change to not allow old models to use Responses API

* Added changeset

* Removing oca from nextGenModelProvier so that we remove native tool calls for now

* Adding back oca as a nextGenModelProvider
2026-01-12 13:05:25 -08:00
yuvalman 6d1890f8bb fix: litellm - trigger model fetching with default base URL (#8359) 2026-01-12 21:36:29 +01:00
Tomás Barreiro 11d17fc17e Fix auth state loop (#8496)
* Prevent loop when getting user organization

* Do not restore user info if the org he is switching to is already active

* Add changeset

* Fix reference array
2026-01-12 19:21:26 +01:00
Tomás Barreiro 42a3dc6150 Prevent requests with an expired auth token (#8470)
* Verify the auth token is valid before returning it

* Add changeset

* refactor
2026-01-12 19:20:33 +01:00
Tomás Barreiro 4032e51e8d Allow admins and owners to override remote config (#8304)
* Add field to settings and handle side effects

* Avoid fetching and applying remote config if it's disabled

* Refactor and apply configured org settings when the user opted out of another one he owns

* Refactor

Fix check

* Add toggle to the account view

* Add changeset

* Fix can disable remote config

* clean canDisableRemoteConfig
2026-01-12 19:19:26 +01:00
Saoud Rizwan 1bbc90487c fix: guard against null/empty choices in streaming responses (#8527)
* fix: guard against null/empty choices in streaming responses

Some OpenAI-compatible APIs (DeepSeek, Groq, OpenWebUI, etc.) send
usage chunks at the end of streaming with empty or null choices arrays.
This was causing crashes with 'Cannot read properties of undefined'.

Added optional chaining on chunk.choices across all 24 affected
provider files to safely handle these usage-only chunks.

Fixes #8384

* chore: add changeset
2026-01-10 19:43:04 -08:00
Saoud Rizwan d422ebbb27 Revert "fix: normalize file paths with spaces before extensions from VS Code …" (#8528)
This reverts commit 362429a317.
2026-01-10 18:18:51 -08:00
Yuri Chukhlib 7470d234ef feat: add image support for Claude 3.5 Haiku
Update Claude 3.5 Haiku model to support image processing as per 
Anthropic API release notes.

Fixes #2009

Co-authored-by: Yuri Chukhlib <yurii.chukhlib@viber.com>
2026-01-10 18:13:12 -08:00
Yuri Chukhlib 21b81f1844 fix: close context menu when pressing Escape key
When the @ mention context menu shows "No results found" and the user
presses Escape, the menu was not closing because setShowContextMenu(false)
was not being called.

Fixes #5532

Co-authored-by: Yuri Chukhlib <yurii.chukhlib@viber.com>
2026-01-10 18:12:31 -08:00
Yuri Chukhlib 362429a317 fix: normalize file paths with spaces before extensions from VS Code LM API
Some LLM providers (notably Claude Sonnet 4.5 via VS Code LM API) insert
spurious spaces before file extensions (e.g., "file .ts" instead of "file.ts").

This fix adds heuristic normalization to remove spaces immediately before
file extensions while preserving legitimate spaces in filenames.

Fixes #7827

Co-authored-by: Yuri Chukhlib <yurii.chukhlib@viber.com>
2026-01-10 18:11:33 -08:00
Yuri Chukhlib 09cb9ac9ac fix: make workflow slash command search case-insensitive
Users can now find workflows regardless of letter casing (e.g., searching "/testhook" finds "Testhook").

Fixes #7834

Co-authored-by: Yuri Chukhlib <yurii.chukhlib@viber.com>
2026-01-10 18:09:51 -08:00
Ara 94160faeef package update (#8499) 2026-01-09 20:18:44 -08:00
Ara f526f70e3a package update (#8498) 2026-01-09 20:03:33 -08:00
github-actions[bot] d9b47378c6 v3.49.0 Release Notes (#8467)
- Enable configuring an OTEL collector at runtime
- Removing Minimax-2.1 from free model list as the free trial has ended
- Improved image display in MCP responses
- Auto-sync remote MCP servers from remote config to local settings

Co-authored-by: Arafatkatze <arafat.da.khan@gmail.com>
2026-01-09 19:46:23 -08:00
Saoud Rizwan 0671c59e6d feat(mcp): improve image display in MCP responses (#8412)
* feat(mcp): improve image display in MCP responses

- Truncate data URIs to show prefix + first 20 chars with [IMAGE] label
- Apply truncation in all display modes (rich, plain, markdown)
- Click data URI images to open in VS Code editor (like mermaid diagrams)
- Expand images to 100% width of response container
- Persist collapsed/expanded state per-response without syncing all instances

* fix(settings): remove Collapse MCP Responses setting from UI

The setting is now implicit - collapsing any MCP response saves the
preference for future responses. Removes confusing sync behavior
between the Settings toggle and individual response toggles.
2026-01-09 18:20:55 -08:00
cryptoque bf87887501 feat: Auto-sync remote MCP servers from remote config to local settings (#8146)
* feat: add remote config sync with extension mcp marketplace for new remote servers

* refactor: extract getMcpSettingsFilePath into disk.ts to be reused

* refactor: rename helper method to avoid ambiguity

* address formatting suggestion by ellipsis-dev for the code itself that was moved

* refactor: add flag pattern to prevent race condition from triggering unnecessary watcher events

* fix: do not re-throw error

---------

Co-authored-by: Sarah Fortune <sarah.fortune@gmail.com>
2026-01-09 16:35:28 -08:00
celestial-vault 66a81a6efa remove unused param from pushToolResult (#8474) 2026-01-09 14:59:13 -08:00
Sarah Fortune eee64c5204 Remove unused react banners (#8463) 2026-01-09 14:03:14 -08:00
Tomás Barreiro 748ba99c1c Remove the IAuthProvider (#8469)
* Remove the IAuthProvider

* Remove the comment

* Remove optional chaining
2026-01-09 20:39:39 +01:00
Juan Pablo Flores 82b1a01644 Adds mcp server support (#8177)
Co-authored-by: Tony Loehr <turingxo@gmail.com>
2026-01-09 11:06:43 -08:00
Tomás Barreiro 1c6307e8ad Remove other references to OTEL_TELEMETRY_ENABLED=1 (#8468) 2026-01-09 10:22:36 -08:00
Tomás Barreiro 58d9c0af18 Enable configuring an OTEL collector at runtime (#8350)
* Replace process.env usage with a BUILD_CONSTANTS variable

* Update import

* revert doc update

* Enable configuring an OTEL collector at runtime

* Refactor

* Refactor

* Add changeset

* Do not build IS_STANDALONE

* Add comment

* Update the `.env.example` file

* Remove `true` from the selected options and revert env.example

* Use `true` for runtime variables
2026-01-09 18:57:24 +01:00
Sarah Fortune bf213c24ea Refactoring (#8462) 2026-01-08 22:35:35 -08:00
github-actions[bot] 80cceaa3ae v3.48.0 Release Notes (#8407)
- Add Skills system for reusable, on-demand agent instructions
- Add new websearch tooling in Cline provider
- Add zai-glm-4.7 to Cerebras model list
- Add model refresh and improve reasoning support for Vercel AI Gateway

- Revert #8341 due to regressions in diff view/document truncation (see #8423, #8429)
- Fixed extension crash when using context menu selector

Co-authored-by: Arafatkatze <arafat.da.khan@gmail.com>
2026-01-08 18:42:53 -08:00
Ara 359e088eb6 Gemini thinking + Katcoder support (#8459)
* Fix: Support for gemini thinking

* Fix: Katcoder

* Fix: Katcoder

* Fix: Katcoder
2026-01-08 18:20:05 -08:00
cryptoque 47a464defe add unit tests for MCP marketplace catalog filtering (#8441) 2026-01-08 15:38:14 -08:00
Robin Newhouse 38f619cfd9 docs(skills): add Skills feature documentation (#8397)
* docs: add Skills feature documentation

Add comprehensive documentation for the Agent Skills feature including:
- Overview of what skills are and why they're useful
- How to create skills with SKILL.md and YAML frontmatter
- Global vs project skill locations
- Managing skills via the UI toggle interface
- Real example (data-analysis skill)
- Bundling supporting files and scripts
- Comparison with Rules and Workflows
2026-01-08 15:18:27 -08:00
Robin Newhouse 050773ac31 feat(skills): add Skills tab UI for managing skill toggles (#8396)
Oh. Add a new Skills tab to the Rules/Workflows modal that allows users to
view and toggle skills (global and workspace), create new skills from
templates, and delete existing skills. The tab only appears when the
skillsEnabled setting is on.

Changes:
- Add proto definitions for skills operations (refreshSkills, toggleSkill,
  createSkillFile, deleteSkillFile) with corresponding message types
- Add globalSkillsToggles to Settings and localSkillsToggles to LocalState
- Implement controller handlers for skills operations
- Add skills toggle state management to ExtensionStateContext
- Add Skills tab component to ClineRulesToggleModal
- Update RuleRow and NewRuleRow components to support skill type
- Implement lazy discovery for skills in UseSkillToolHandler (skills are
  discovered on-demand at execution time and filtered by toggle state)
- Use Tailwind CSS classes for styling consistency
2026-01-08 15:07:00 -08:00
Andrei Eternal 6d67ff0b94 simplify nightly versioning with timestamps (#8453)
Co-authored-by: Andrei Edell <andrei@nugbase.com>
2026-01-08 14:54:24 -08:00
celestial-vault 18f4ef8b49 remove settings dir codeowners (#8451) 2026-01-08 14:51:06 -08:00
Bee 085e69d142 fix: prevent duplicate diff error messages during file edits (#8431)
* fix: prevent duplicate diff error messages during file edits

Remove existing diff_error messages before displaying new ones to avoid
showing the same error multiple times when streaming file edits. This
ensures users only see the error once per occurrence, improving the UX
during tool execution with parallel tool calling disabled.

* Update src/core/task/tools/handlers/WriteToFileToolHandler.ts

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-01-08 14:33:12 -08:00
Robin Newhouse 46aa66ed9d feat: add skillsEnabled setting to gate Skills feature (#8395)
Add experimental "Enable Skills" toggle in Settings > Features that
controls whether the Skills system is active. When disabled (default),
no directory scanning occurs and the use_skill tool is not exposed.

- Add skillsEnabled to Settings interface and ExtensionState
- Add skills_enabled to proto definitions
- Gate skill discovery in Task.attemptApiRequest()
- Add UI toggle in FeatureSettingsSection
2026-01-08 14:17:13 -08:00
Robin Newhouse 2ebbe954d9 feat(skills): Implement Skills system for reusable agent instructions (#8335)
feat(skills): add reusable Skills system and standardize global skills location

- Implement Skills system for reusable agent instructions loaded from project and global directories
- Support skill discovery and loading via stateless utilities
- Parse YAML frontmatter for skill metadata (name, description)
- Add use_skill tool for on-demand instruction loading
- List available skills in system prompt; global skills override project skills
- Define skills as directories with a SKILL.md file
- Add unit tests for skill utilities
- Global skills in ~/.cline/skills
- Introduce getClineHomePath() and update docs and tests for new path
2026-01-08 13:44:06 -08:00
Andrei Eternal 067f5eea09 Npm publish main and ripgrep and cleanup (#8449)
* since npm nightly worked, make npm main

* fix ripgrep, split npm and jetbrains packaging

* cli nightly package version update

---------

Co-authored-by: Andrei Edell <andrei@nugbase.com>
2026-01-08 12:51:43 -08:00
cryptoque 2a48bad28c feat: [extensions] remotely configure whether enterprise users can disable a remote MCP server or not (#8426)
* feat: Enable remotely configure whetherenterprise users can disable an MCP server or not
2026-01-08 10:54:20 -08:00
celestial-vault c6f4584f7d fix: prevent unwanted editor focus stealing (#8038)
* control focus stealing via new param to focusChatInput

* pass preserveEditorFocus to getContextForCommand to fix e2e test
2026-01-08 07:25:25 -08:00
Ara a17b31070f feat(vercel-ai-gateway): add model refresh and improve reasoning support (#8398)
* feat(vercel-ai-gateway): add model refresh and reasoning support

- Add refreshVercelAiGatewayModelsRpc to ModelsService for fetching models
- Fix model ID/info references to use Vercel-specific parameters instead of OpenRouter
- Add reasoning effort and Gemini thinking level configuration support
- Skip reasoning content for incompatible models (devstral, grok-4)
- Improve model selection UI with keyboard navigation (ArrowUp/Down/Enter)
- Add model refresh functionality to settings interface

This enables proper model discovery and improves reasoning capabilities for Vercel AI Gateway provider, while fixing incorrect parameter references that were using OpenRouter naming conventions.

* refactor

* refactor

* refactor

* refactor

* refactor
2026-01-08 05:57:36 -08:00
Andrei Eternal cad82d518d Remove version auto-increment for npm-nightly workflow (#8442)
Co-authored-by: Andrei Edell <andrei@nugbase.com>
2026-01-07 17:31:13 -08:00
Andrei Eternal b4d7ec187f fix npm workflow permissions again (#8440)
Co-authored-by: Andrei Edell <andrei@nugbase.com>
2026-01-07 17:11:27 -08:00
Andrei Eternal 42af8414e4 Npm nightly workflow fix permissions (#8439)
* First pass at npm nightly publish workflow

* go & ripgrep improvements

---------

Co-authored-by: Andrei Edell <andrei@nugbase.com>
2026-01-07 17:09:33 -08:00
Andrei Eternal 8f6b9e8362 First pass at npm nightly publish workflow (#8438)
* First pass at npm nightly publish workflow

* go & ripgrep improvements

---------

Co-authored-by: Andrei Edell <andrei@nugbase.com>
2026-01-07 17:06:54 -08:00
Max f1430359db show command denied message in cline CLI (#8344)
Co-authored-by: Max Paulus 🥪 <max@cline.bot>
2026-01-07 16:11:44 -08:00
Ara 932695f70b changes (#8437) 2026-01-07 16:04:14 -08:00
cryptoque 489ee936c2 feat: UI changes for remote configured MCP servers (#8409)
* feat: hide the delete server ui when user and the remote mcp server is managed by remote config

* feat: add message to user if they are managed by remote config
2026-01-07 13:28:14 -08:00
Robin Newhouse dff7f61175 revert: #8341 (0d04205dc) due to DiffService truncateDocument regressions (#8423, #8429) (#8432) 2026-01-07 13:21:56 -08:00
Toshii aead42c6b8 add mcp prompting for webtools usage (#8425)
* add mcp prompting for usage

* native tool call snap test update

* updating capabilities section to add web tools
2026-01-07 11:26:41 -08:00
Seb Duerr db50a1c671 feat(cerebras): add zai-glm-4.7 (#8411)
- Add zai-glm-4.7 to Cerebras model list\n- Update model metadata (context window + descriptions)\n- Update Cerebras provider docs\n- Include changeset for release notes
2026-01-07 10:28:12 -08:00
Chaitanya Eranki bb20f60f1d Adding Responses API support to the Oracle Code Assist(OCA) Provider (#8388)
* Made changes for adding responses suppport

* removed some logs

* Made change to disallow format

* Added logging for cline

* Fixed codex prompts

* Made changes to make cline work

* Removed extra changes

* Added reasoning effort also to chat completions

* Made changes to fix issues with cline based on bugbash

* removed extra console.log statements

* Added extra changes to make reasoningEffortOptions working properly(outputs undefined)

* Made changes to code that make it cleaner

* created utility function for responses

* Removed extra console.log lines

* Fixed issues with tests not working

* Added changeset

* Update webview-ui/src/components/settings/providers/OcaModelPicker.tsx

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* removing openai-native changes

* Switched to using api format instead of supportsResponsesApi and supportChatApi

---------

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2026-01-06 22:35:40 -08:00
Tomás Barreiro a7333b7177 Remove remote OTEL config type casting (#8351) 2026-01-07 06:04:08 +01:00
Tomás Barreiro f30837a850 Do not request /users/me when fetching other data (#8410)
* Do not use /users/me when fetching other data

* Add changeset
2026-01-07 02:24:29 +01:00
Max 5660b2513f add cline pr review cline workflow action (#8284)
cline pr-review bot initial

cline permission system

Co-authored-by: Max Paulus 🥪 <max@cline.bot>
2026-01-06 17:20:05 -08:00
Tomás Barreiro 64e7e5fa4c Replace process.env usage with a BUILD_CONSTANTS variable (#8349)
* Replace process.env usage with a BUILD_CONSTANTS variable

* Update import

* revert doc update

* Do not build IS_STANDALONE
2026-01-07 01:07:28 +01:00
Toshii b34166e99a add web tool docs (#8408) 2026-01-06 14:54:43 -08:00
Ara cd2d8f98a7 feat: remove kwaipilot/kat-coder-pro from free models list (#8406)
* feat: remove kwaipilot/kat-coder-pro from free models list

Remove the KwaiPilot KAT-Coder Pro model from the OpenRouter
free models picker, likely due to availability changes or
model deprecation.

* changes
2026-01-06 12:47:31 -08:00
github-actions[bot] 333468c9b6 v3.47.0 Release Notes (#8286)
- Added experimental support for Background Edits (allows editing files in background without opening the diff view)
- Updated free model to MiniMax M2.1 (replacing MiniMax M2)
- Added support for Azure based identity authentication in OpenAI Compatible provider and Azure OpenAI
- Add `supportsReasoning` property to Baseten models

- Prevent expired token usage in authenticated requests
- Exclude binary files without extensions from diffs
- Preserve file endings and trailing newlines
- Fix Cerebras rate limiting
- Fix Auto Compact for Claude Code provider
- Make Workspace and Favorites history filters independent
- Fix remote MCP server connection failures (404 response handling)
- Disable native tool calling for Deepseek 3.2 speciale
- Show notification instead of opening sidebar on update
- Fix Baseten model selector

- Modify prompts for parallel tool usage in Claude and Gemini 3 models

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-01-06 12:00:52 -08:00
Juan Pablo Flores 0da6ddc001 feat: Add Background Edit feature to enhance workflow efficiency (#8405)
* Introduced a new feature, Background Edit, allowing file changes without opening the diff editor.
* Updated documentation to explain how to enable and use Background Edit, including its benefits and relationship with other features.
2026-01-06 11:48:35 -08:00
Tomás Barreiro 612130366f fix: Verify selected index is not -1 when checking if an option is selectable in the context menu (#8404)
* Verify selected index is not -1 when checking if an option is selectable

* Add changeset
2026-01-06 18:59:53 +01:00
Ara 85206cfded fix: update Minimax model ID to m2.1 in picker and cost logic (#8402)
Updates the Minimax model identifier from `minimax/minimax-m2` to `minimax/minimax-m2.1` in the OpenRouter model picker configuration. Additionally, updates the Cline provider to ensure the new model version is correctly recognized as a free model for cost calculation purposes.
2026-01-06 09:48:48 -08:00
CandiedUniverse 6f8ed7aa56 Display simple indicator for hooks in the CLI [ENG-1376] (#8269)
* feat(hooks): Initial implementation of UI output in the CLI

* feat(hooks): Display hooks UI output in the CLI nicely

* feat(hooks): Improvements to the hooks CLI implementation

* feat(hooks): Changes as per Cline's code review of hooks CLI PR

* feat(hooks): Make comments more concise and to the point

* feat(hooks): Minor improvements to code complexity

* feat(cli): polish hook status output (headers, paths, spacing)

- Align hook headings with ToolRenderer-style language
- Prefer workspace-relative paths for hook scripts
- Document hook_output_stream suppression + future grouping
- Add unit tests for rendering + path formatting

* feat(hooks): Isolate hook handlers and harden path handling

- Move hook-specific SAY handling into say_handlers_hooks.go
- Use os.UserHomeDir + filepath.Rel for more portable hook path shortening
- Document why hooks render from state stream (ordering/reordering)
- Standardize on filepath for filesystem paths in cline-clients
- Avoid silently ignoring os.Getwd() errors in dev fallback resolution

* feat(hooks): Add pendingToolInfo to hook status in the CLI

* feat(hooks): Fix verbose output to CLI

* feat(hooks): Add changeset commit.

* feat(hooks): code review feedback - make paths OS-agnostic

* feat(hooks): code review feedback - use strings.Builder

* feat(hooks): code review feedback - no need to normalize say type

* feat(hooks): code review feedback - define HookOutputStreamMeta type

* feat(hooks): code review feedback - remove dynamic import

* feat(hooks): code review feedback - turn repetitive logic into helper function and make say type names reflect proto field names

* feat(hooks): code review feedback - remove unrelated changes

* feat(hooks): prepend hook script path with repo name
2026-01-06 08:09:06 -08:00
Tomás Barreiro f2c130a69e Prevent using expired tokens when making authenticated requests (#8386)
* Prevent using expired tokens when making authenticated requests

* Add changeset

* refactor

* Update AuthService.ts

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

---------

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2026-01-06 02:52:18 +01:00
Bee c870bfb454 refactor: migrate HistoryView & ServerRow UI to use shadcn Button (#8387)
* refactor: migrate HistoryView & ServerRow UI to use shadcn Button and Tailwind classes

- Replace VSCodeButton with shadcn Button component
- Convert inline styles to Tailwind CSS utility classes
- Replace DangerButton with Button variant="destructive"
- Add custom Tailwind color classes for VS Code theme variables
- Simplify JSX structure by removing redundant style objects
- Improve code readability and maintainability

* fix typo
2026-01-05 17:12:28 -08:00
valquaint 436bfdb535 Do not use native tool calling when using Deepseek 3.2 speciale (#8390)
* Do not use native tool calling when using Deepseek 3.2 speciale

* Add changeset
2026-01-05 17:00:22 -08:00
yuvalman e2a3652d26 fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode (#7099)
* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode

* fix: sap provider - support replace credentials in orchestration mode without the need to reload vscode
2026-01-05 13:04:43 -08:00
wenwolf 632aca225c feat: Support Azure Identity DefaultCredential for AzureOpenAI (OpenAI Compatible provider) (#8385)
* feat: support azure identity authentication

Signed-off-by: patst <patrick.steinig@googlemail.com>

* feat: support azure identity authentication

Signed-off-by: patst <patrick.steinig@googlemail.com>

* chore: format changes

* set azureIdentity in state

* ADD Openai Compat Azure AD managed identity support: added proto messages def for azure identity, updated OpenAI APi key missing if azure identity is checked, ...

* feat: Support Azure Identity DefaultCredential for AzureOpenAI (OpenAI Compatible provider)

* fixed azure identity version and missing state setting in proto

* added missing state setting in proto

---------

Signed-off-by: patst <patrick.steinig@googlemail.com>
Co-authored-by: patst <patrick.steinig@googlemail.com>
Co-authored-by: Wenceslas Wolfersperger <wenceslas.wolfersperger@idorsia.com>
2026-01-05 13:03:42 -08:00
yuvalman a1eaccdaef fix: sap provider - use messages_history field instead of messages which doesn't validate user input based on template syntax (#8280)
* fix: sap provider - use messages_history field instead of messages because of placeholder_values usage templating error

* fix: sap provider - use messages_history field instead of messages because of placeholder_values usage templating error

* fix: sap provider - use messages_history field instead of messages because of placeholder_values usage templating error

* fix: sap provider - use messages_history field instead of messages because of placeholder_values usage templating error
2026-01-05 10:26:01 -08:00
Ara f7e76f9bee feat: add MiniMax model support for OpenRouter and Vercel AI Gateway (#8376)
* feat: add MiniMax model support for OpenRouter and Vercel AI Gateway

Add MiniMax M2, M2.1, and M2.1-lightning models to the list of models
that require special system prompt handling in OpenRouter stream.
Also extend Vercel AI Gateway to apply the same system prompt format
for MiniMax models as used for Anthropic models.

* adding changes with debug logs
2026-01-04 17:18:07 -08:00
Robin Newhouse 0d04205dc4 fix: preserve file endings and trailing newlines across all edit tools (#8341) 2026-01-03 10:12:25 -08:00
Bee 4b9dbf11a0 feat: add Select UI component and Storybook story (#8355)
* feat: add Select UI component and Storybook story

Add @radix-ui/react-select dependency and introduce a Select Storybook
story to document and validate the new dropdown UI component.

* update position
2026-01-02 13:17:48 -08:00
Tomás Barreiro c5afbd743e Add Remote Config OTEL docs and change the OTEL override logs (#8346)
* Add Remote Config OTEL docs and change the OTEL override logs

* Add the new page to the sidebar

* Update docs/enterprise-solutions/monitoring/opentelemetry.mdx

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* Update docs/enterprise-solutions/monitoring/opentelemetry_override.mdx

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* Fix inconsistent casing

---------

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-12-31 21:05:26 +01:00
Robin Newhouse 6d1bfc3a1b feat(prompts): enable parallel tool usage for claude and gemini 3 models (#8331)
* feat(prompts): enable parallel tool usage for claude and gemini 3 models

- Update TOOL USE section to allow multiple independent tools per response
- Add rules clarifying when parallel vs sequential tool usage is appropriate
- Specify MCP operations should still be used one at a time
- Update test snapshots to reflect prompt changes

* Change prompts based on whether parallel tool calling is enabled

- GPT5 family: leave as is because parallel tool calling is always enabled
- Gemini 3 family: many or one tool depending on toggle
- Claude 4+ family: many tool or empty instruction to not collide with claude "under the hood" system prompt, which already suggests multi-tool use

* Revert non-parallel behavior to use working prompt.

Co-authored-by: Bee <68532117+abeatrix@users.noreply.github.com>

* feat: add MCP server checks with utility function

Add hasEnabledMcpServers() utility function to standardize MCP server detection across prompt variants. Conditionally include MCP-specific instructions only when MCP servers are enabled, avoiding unnecessary prompts when no servers are configured.

* Update prompt test snapshots

---------

Co-authored-by: Bee <68532117+abeatrix@users.noreply.github.com>
2025-12-30 22:15:56 -08:00
Bee d18486a199 chore: import codicons to storybook (#8345)
- Import @vscode/codicons CSS and font files in StorybookDecorator to ensure icons render correctly in the Storybook environment.
- Move the global `index.css` import from `preview.ts` to `StorybookDecorator.tsx` to consolidate style initialization.
2025-12-30 15:32:25 -08:00
Robin Newhouse 7417b1b671 fix: restore dummy thought signature for cross-model transfers (#8340)
Reverts the signature check from #8291 that dropped blocks without
signatures, restoring the fallback to GEMINI_DUMMY_THOUGHT_SIGNATURE
from #8122 to support transferring history from other models to Gemini.
2025-12-30 11:19:58 -08:00
Tony Loehr e4fbe331f4 sso docs (#8169)
* sso docs

* sso UI first approach

* added screenshot

* removed keycloak mention
2025-12-30 10:16:03 -08:00
Bee d122683e91 fix: Baseten model selector issue in ModelPickerModal (#8330)
* fix: Baseten model selector issue in ModelPickerModal

Fixed an issue where Baseten model cannot be selected when running in ModelPickerModal.
Refactor ModelPickerModal to reuse ThinkingBudgetSlider component
- Remove duplicated thinking budget slider UI components and logic
- Replace with shared ThinkingBudgetSlider component for consistency
- Clean up unused constants and helper functions
- Simplify provider-specific configuration handling

* clean up styled spans

* fix
2025-12-29 14:48:14 -08:00
Bee fdc96d0545 fix: add supportsReasoning property to Baseten models (#8329)
* fix: add supportsReasoning property to Baseten models

- Add supportsReasoning field to model configurations in basetenModels
- Implement detection logic for reasoning support via supported_parameters
- Mark reasoning-capable models (DeepSeek-R1, Qwen3, etc.) with supportsReasoning: true
- Update model refresh logic to populate supportsReasoning based on static config or parameter detection

This fixes issues where Baseten models are showing Thinking not supported in the UI.

* add changeset

* simplify

* clean up

* typo
2025-12-29 13:53:00 -08:00
canvrno c0241f4060 Fix: Exclude files without extensions (and dotfiles) from getDiffSet results (#8328)
* Exclude files without extensions (and dotfiles) from getDiffSet results

* More robust binary detection for explain changes feature
2025-12-29 13:44:45 -08:00
Seb Duerr c3f523427b fix(cerebras): use conservative max_tokens to avoid premature rate limiting
Cerebras rate limiter estimates token consumption using max_completion_tokens upfront, so requesting the model maximum (e.g., 64K) reserves that quota even if actual usage is low. This causes users to hit rate limits prematurely during agentic workflows with many short tool-use responses.

Uses 16K as default which is sufficient for most agentic tool use while preserving rate limit headroom.

Co-authored-by: Seb Duerr <sebastian.duerr@cerebras.net>
2025-12-29 13:33:27 -08:00
Ara 428e465d4d feat(api): add MiniMax M2.1 and M2.1-lightning models (#8327)
- Add MiniMax-M2.1 model with 192K context window and prompt caching
- Add MiniMax-M2.1-lightning variant with higher output pricing
- Update default model from MiniMax-M2 to MiniMax-M2.1
2025-12-29 11:18:38 -08:00
Saoud Rizwan 46ab08c9f8 fix(mcp): handle 404 responses from streamableHttp servers (#8321)
* fix(mcp): handle 404 responses from streamableHttp servers

The MCP SDK sends a GET request to check for SSE stream support when
connecting to streamableHttp servers. Per the MCP spec, servers that
don't support SSE should return 405 (Method Not Allowed), but many
servers incorrectly return 404 (Not Found).

The SDK only gracefully handles 405 responses, so servers returning 404
cause connection failures with "Failed to open SSE stream: Not Found".

This was exposed by the SDK upgrade from 1.22.0 to 1.25.1 in v3.46.0,
which added stricter SSE stream initialization checks.

This fix wraps the fetch function to normalize 404 -> 405 for GET
requests, allowing Cline to work with non-compliant servers while
they update to return proper 405 responses.

Fixes #8320
Fixes #7577

* chore: add changeset
2025-12-29 10:23:51 -08:00
Saoud Rizwan 0fd30e0d20 fix: stop auto-opening sidebar on extension update (#8322)
Only show a notification when the extension updates, instead of
automatically focusing the Cline sidebar. This prevents the extension
from stealing focus on VS Code launch.
2025-12-29 10:11:00 -08:00
Saoud Rizwan e87a765773 fix: recognize Claude Code short model aliases as Claude 4+ (#8324) 2025-12-29 10:07:23 -08:00
Ara e80c3d3cd8 fix: report correct shell in system prompt for background exec mode
When using background exec mode, commands run in the system default shell
(cmd.exe on Windows, /bin/bash on Unix) rather than the VS Code configured
shell. This ensures the system prompt accurately reflects which shell will
be used for command execution.

- Add getEffectiveShell() function to determine actual shell used
- Pass terminalExecutionMode through SystemPromptContext
- Use system default shell info when backgroundExec mode is active

Co-authored-by: Ara <arafat.da.khan@gmail.com>
2025-12-29 08:29:23 -08:00
Ara 80b6ab6046 fix: resolve 'ask promise was ignored' error on background command cancel
Update command cancellation to modify existing message instead of sending new say() to avoid interfering with pending ask() dialogs.

- Extend updateClineMessage to support text updates
- Find last command_output message and append cancellation notice
- Add missing cleanupFileBased() calls for background tracking paths
- Use shared findLastIndex utility

Co-authored-by: Ara <arafat.da.khan@gmail.com>
2025-12-29 08:03:29 -08:00
Saoud Rizwan 5155123b80 docs: add changeset guidance 2025-12-29 04:58:36 -08:00
Juan Pablo Flores 30af711d5e Update documentation link in AboutSection (#8317) 2025-12-28 19:30:14 -08:00
Saoud Rizwan b218b25e0b Revert "feat: add stale PR detection to PR review workflow"
This reverts commit bf27aa53ef.
2025-12-28 13:18:17 -08:00
Saoud Rizwan bf27aa53ef feat: add stale PR detection to PR review workflow 2025-12-28 12:54:11 -08:00
Saoud Rizwan 4644a7159a feat: add For Maintainers section to PR review workflow 2025-12-28 12:12:14 -08:00
Saoud Rizwan 63c63f38f5 fix: skip draft PRs, trigger on ready_for_review 2025-12-28 12:01:13 -08:00
Saoud Rizwan f1d8ca423d fix: make PR review one-time response with comprehensive explanation 2025-12-28 10:45:47 -08:00
Saoud Rizwan 16b8ce7e44 fix: make review comment freeform with warm intro, remove Claude branding 2025-12-28 10:13:47 -08:00
Saoud Rizwan 0bbb4299ba fix: only auto-run PR review on opened, manual re-runs for updates 2025-12-28 09:56:51 -08:00
Saoud Rizwan 197b17b3bd fix: simplify PR review contributing guidelines checks 2025-12-28 09:42:35 -08:00
Saoud Rizwan 591b840531 feat: add automated PR review workflow 2025-12-28 09:37:33 -08:00
chenxue c35ba37402 Update aihubmix.ts (#8311) 2025-12-28 07:44:09 -08:00
Robin Newhouse 850a6ab841 Fix Gemini/OpenRouter failures from corrupted reasoning details and missing thought signatures (#8291)
* fix(api): filter Gemini reasoning details by tool call ID

Filter reasoning details in the OpenAI format transformer to ensure they
only include entries matching the specific tool call ID. This prevents
"Function call is missing a thought_signature" errors when using Gemini
models, where mismatched reasoning details would cause API validation
failures.

* fix(gemini): drop invalid thought signatures and corrupted reasoning_details

- Gemini direct: drop tool_use/thinking blocks when signature is missing
- OpenRouter: keep only tool reasoning_details matching tool id
- Skip reasoning.encrypted entries missing data to avoid 400s (#8214)

* fix(core): sanitize Gemini tool calls in OpenRouter stream

Gemini models require thought signatures for tool calls. When switching providers mid-conversation, historical tool calls may lack these reasoning details, causing subsequent requests to fail.

This change implements a filter for Gemini models that:
- Identifies assistant messages with tool calls but no reasoning details.
- Drops those tool calls while preserving textual content.
- Removes the corresponding tool response messages to maintain conversation integrity.
2025-12-26 13:10:22 -08:00
Saoud Rizwan 99c85710e9 fix: make Workspace and Favorites history filters independent (#8292)
* fix: make Workspace and Favorites history filters independent

Move Workspace and Favorites filters out of the VSCodeRadioGroup into
their own container. This fixes the regression where selecting one filter
would prevent selecting the other, since VSCodeRadioGroup enforces mutual
exclusivity. The filters now work as independent toggles while maintaining
visual continuity with the sort options above.

Fixes #8289

* add changeset
2025-12-24 21:44:51 -08:00
Saoud Rizwan 9fc9785aa2 chore: add .worktrees to gitignore 2025-12-24 20:21:26 -08:00
Tony Loehr 5c02f6eb13 deep planning demo (#8263)
* deep planning demo

* deep-planning-demo cleanup

* Update docs/features/slash-commands/deep-planning.mdx

Co-authored-by: Juan Pablo Flores  <juan@cline.bot>

* Update docs/features/slash-commands/deep-planning.mdx

Co-authored-by: Juan Pablo Flores  <juan@cline.bot>

---------

Co-authored-by: Juan Pablo Flores <juan@cline.bot>
2025-12-23 15:33:17 -08:00
yuvalman ac01e69555 fix: sap provider - regression in claude models in native api mode (#8278)
* fix: regression in claude models in native api mode for sap provider
2025-12-23 14:05:19 -08:00
Saoud Rizwan dbc18a8fce fix: add .husky/_/ to gitignore for worktree compatibility 2025-12-23 00:33:51 -08:00
Ara b77398390b docs: recommend background execution mode for terminal issues (#8271)
Update terminal troubleshooting docs to prominently recommend
Background Execution Mode as the primary solution for terminal
integration problems. This provides a simpler fix for most users
before diving into more complex troubleshooting steps.

- Add tip boxes with step-by-step instructions for enabling
  Background Exec mode in both terminal guide documents
- Clarify that detailed troubleshooting is for users who
  specifically need VSCode's integrated terminal
2025-12-22 19:36:31 -08:00
Ara c20052de00 feat(telemetry): add terminal type tracking to telemetry events (#8265)
* feat(telemetry): add terminal type tracking to telemetry events

Add terminalType parameter to terminal telemetry methods to differentiate
between VSCode and standalone terminal execution contexts. This enables
better analysis of terminal output capture success rates across different
environments.

- Add TerminalType, VscodeOutputMethod, and StandaloneOutputMethod types
- Update captureTerminalExecution to require terminalType parameter
- Update captureTerminalOutputFailure to require terminalType parameter
- Add terminalType option to OrchestrationOptions interface
- Update all call sites in VscodeTerminalProcess with "vscode" type

* feat(terminal): add terminal type tracking to telemetry events

Pass terminal type (standalone vs vscode) to telemetry capture calls
for terminal hang and user intervention events. This enables better
analysis of terminal behavior differences between execution modes.

* feat: add telemetry tracking for standalone terminal execution

Add telemetry capture for terminal process completion and errors in
StandaloneTerminalProcess to track execution success/failure metrics.

- Track successful completions (exit code 0 or null) and failures
- Capture error events separately with child_process_error identifier
- Use "standalone" terminal type for metric categorization
2025-12-22 16:44:12 -08:00
Ara 1dac507b63 feat: remove z-ai/glm-4.6 from free models list (#8260)
* feat: remove z-ai/glm-4.6 from free models list

Remove the Zhipu AI GLM-4.6 model from the free models selection in the OpenRouter model picker component. This change updates the available free model options for users.

* update changelog
2025-12-22 13:46:51 -08:00
github-actions[bot] e5aa48c2b5 v3.46.0 Release Notes (#8242)
- Added GLM 4.7 model
- Enhanced background terminal execution with command tracking, log file output, zombie process prevention (10-minute timeout), and clickable log paths in UI
- Apply Patch tool for GPT-5+ models (replacing current diff edit tools)

- Duplicate error messages during streaming for Diff Edit tool when Parallel Tool Calling is not enabled
- Banner carousel styling and dismiss functionality
- Typos in Gemini system prompt overrides
- Model picker favorites ordering, star toggle, and keyboard navigation for OpenRouter and Vercel AI Gateway providers
- Fetch remote config values from the cache

- Anthropic handler to use metadata for reasoning support
- Bedrock provider to use metadata for reasoning support

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-12-22 12:59:30 -08:00
Saoud Rizwan 63efb4aa5d fix: clarify label instructions in issue triage workflow 2025-12-22 12:24:16 -08:00
Saoud Rizwan 5fcf83b627 feat: add Regression label for issues caused by recent changes
When the triage bot identifies a likely regression from a recent PR or
commit, it will now apply the "Regression" label to help the team
prioritize and route these issues to the responsible developer.
2025-12-22 12:18:56 -08:00
Ara 0b308d610e feat(api): add GLM-4.7 model and update ZAi defaults (#8258)
- Add glm-4.7 model configuration for both international and mainland ZAi
- Update default model from glm-4.5 to glm-4.7
- Add missing cacheReadsPrice property to glm-4.6 model configs
2025-12-22 12:01:46 -08:00
Ara 60d3048aa0 feat(terminal): add background command tracking and bug fixes for terminals (#8085)
* refactor(terminal): centralize constants and implement output capping

- Move terminal-related constants (timeouts, compiling markers, and size limits) to a centralized constants file.
- Implement output capping in VscodeTerminalProcess to prevent memory exhaustion by truncating fullOutput when it exceeds MAX_FULL_OUTPUT_SIZE.
- Update terminal process logic to use centralized constants for consistency across VS Code and standalone terminal implementations.
- Clean up imports and formatting in the task core.

* update pricing

* fix(terminal): improve compilation marker detection accuracy

Extract compilation detection logic into isCompilingOutput() function
that checks markers at the START of lines only, rather than anywhere
in the output. This prevents false positives from file names, error
messages, or code snippets that happen to contain marker words.

* update pricing

* refactor(chat): simplify log file link display to show filename only

- Extract filename from full path for cleaner display
- Change from banner-style div to compact ghost button
- Add full path as tooltip for reference
- Improve styling with smaller text and border-based separator

* feat: add graceful process termination with SIGKILL fallback

Extract process termination logic into a reusable utility that handles
graceful shutdown:

- Send SIGTERM first to allow processes to clean up
- Wait for configurable timeout (default 2 seconds)
- Fall back to SIGKILL if process doesn't exit gracefully
- Support cross-platform termination via tree-kill

Update StandaloneTerminalProcess to use the new async terminate method
and update ITerminalProcess interface to allow async termination.

* feat(terminal): simplify compilation output detection to match markers anywhere

Change isCompilingOutput to use simple string includes() instead of
line-by-line startsWith() matching. This allows detecting compilation
markers anywhere in the output rather than only at the start of lines,
making detection more permissive and the code simpler.

* update pricing

* fix(ui): use theme-aware colors for shell integration warning banner

* fix(ui): improve log file path banner styling and wrapping

---------

Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
2025-12-22 09:56:27 -08:00
Sarah Fortune aed3ac6597 Use the same font for the auth handler redirect as the dashboard (#8224)
The dashboard has switch to use Azaret san-serif instead of mono.
2025-12-22 09:21:53 -08:00
reneehuang1 86e2a3e7ce clean up writeups docs (#8195)
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
2025-12-22 00:13:35 -08:00
Saoud Rizwan 47856c70d2 chore: update workflow comment 2025-12-22 00:06:32 -08:00
Saoud Rizwan f1a84ddbde feat: add Claude Code web session setup with gh CLI and worktree support (#8249)
* feat: add SessionStart hook for Claude Code on the web

Adds a session-start hook that runs in remote environments to:
- Install all dependencies (npm run install:all)
- Generate gRPC/protobuf types (npm run protos)

This enables Claude Code web sessions to properly run tests and linters.

* feat: add .worktreeinclude for Claude Code worktrees

Ensures environment files and local settings are copied to new worktrees:
- .env files
- .clineignore
- Local Claude settings

* fix: include node_modules and generated files in worktreeinclude

Copying these to worktrees saves significant setup time:
- node_modules: skips npm install (~1-2 min)
- src/generated/, src/shared/proto/: skips proto generation

* feat: install gh CLI and add GITHUB_TOKEN support in session hook

- Rename session-start.sh to claude-code-for-web-setup.sh
- Install latest gh CLI from GitHub releases
- Check for GITHUB_TOKEN and inform Claude about gh availability
- Enables using `gh issue`, `gh pr` commands when token is configured

* refactor: make .worktreeinclude a symlink to .gitignore
2025-12-21 22:22:35 -08:00
Saoud Rizwan ebcc927cc7 fix(ui): ensure scroll-to-top reaches true top with virtual rendering (#8232)
When scrolled to bottom, the up button wasn't reliably scrolling all
the way to the top because Virtuoso's virtual rendering doesn't have
all items rendered. Added a delayed follow-up scroll to ensure we
reach the actual top after items render.
2025-12-21 18:58:44 -08:00
Saoud Rizwan 1e108d87e0 fix(ui): History page UI improvements (#8228)
* fix(ui): center View All button under task history list

* fix(ui): use VSCodeRadio for workspace and favorites filters on history page

* fix(ui): move Select All/None buttons to bottom of history page with secondary style
2025-12-21 18:58:16 -08:00
Saoud Rizwan 7b62d7786e fix(ui): MCP server UI improvements (#8227)
* fix(ui): prevent MCP server toggle from triggering row expand/collapse

* fix(ui): show connecting status when enabling MCP server

* fix(ui): show connecting status during MCP server restart

* fix(ui): add cursor pointer on hover for expandable MCP server rows
2025-12-21 17:04:00 -08:00
Saoud Rizwan 042f5c9823 chore(deps): update mintlify to fix security vulnerabilities (#8240) 2025-12-21 09:49:02 -08:00
aikido-autofix[bot] 2f8a4525a4 chore(deps): bump streamlit from 1.28.0 to 1.43.2 in evals
Co-authored-by: aikido-autofix[bot] <119856028+aikido-autofix[bot]@users.noreply.github.com>
2025-12-21 07:54:56 -08:00
aikido-autofix[bot] 20774a4187 chore(deps): fix security issues in jws, jsonwebtoken, @modelcontextprotocol/sdk
Co-authored-by: aikido-autofix[bot] <119856028+aikido-autofix[bot]@users.noreply.github.com>
2025-12-21 07:54:39 -08:00
dependabot[bot] be5bda2740 chore(deps-dev): bump storybook from 9.1.7 to 9.1.17
Bumps [storybook](https://github.com/storybookjs/storybook/tree/HEAD/code/core) from 9.1.7 to 9.1.17.
- [Release notes](https://github.com/storybookjs/storybook/releases)
- [Changelog](https://github.com/storybookjs/storybook/blob/next/CHANGELOG.md)
- [Commits](https://github.com/storybookjs/storybook/commits/v9.1.17/code/core)

---
updated-dependencies:
- dependency-name: storybook
  dependency-version: 9.1.17
  dependency-type: direct:development
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-12-21 07:48:54 -08:00
dependabot[bot] 261fd9036f chore(deps): bump @modelcontextprotocol/sdk from 1.22.0 to 1.25.1
Bumps [@modelcontextprotocol/sdk](https://github.com/modelcontextprotocol/typescript-sdk) from 1.22.0 to 1.25.1.
- [Release notes](https://github.com/modelcontextprotocol/typescript-sdk/releases)
- [Commits](https://github.com/modelcontextprotocol/typescript-sdk/compare/1.22.0...1.25.1)

---
updated-dependencies:
- dependency-name: "@modelcontextprotocol/sdk"
  dependency-version: 1.25.1
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-12-21 07:48:50 -08:00
Nick Baumann 2334d4d531 fix: model picker favorites ordering, star toggle, and keyboard nav
Co-authored-by: Nick Baumann <nickbaumann98@gmail.com>
2025-12-21 06:54:13 -08:00
Prithvi Singh Chohan 6390d854f7 fix: sync Plan/Act mode settings when switching tabs in OpenAI compatible provider
Co-authored-by: Prithvi Singh Chohan <pv11messi@gmail.com>
2025-12-21 06:38:01 -08:00
Saoud Rizwan 7d5c56a55a chore: add CLAUDE.local.md to gitignore 2025-12-21 06:14:32 -08:00
Saoud Rizwan 0dc760ac03 fix: rename Bot Triaged label to Bot Responded, apply after comment 2025-12-21 04:41:05 -08:00
Saoud Rizwan 8c1241c8cd feat: use Opus 4.5 model for issue triage 2025-12-21 04:11:06 -08:00
Saoud Rizwan 17686ae3d9 feat: add Bot Triaged label to issue triage workflow 2025-12-21 03:59:58 -08:00
Saoud Rizwan 97460d2952 fix: fetch label descriptions for better triage 2025-12-21 03:24:28 -08:00
Saoud Rizwan e629ed0ef6 fix: always include Possible Duplicates section 2025-12-21 02:29:24 -08:00
Saoud Rizwan 96788e9127 fix: clarify one-time response - no follow-up language 2025-12-21 02:18:28 -08:00
Saoud Rizwan d7716a514d fix: improve triage prompt - always report on recent changes analysis 2025-12-21 02:08:56 -08:00
Saoud Rizwan 7aaa5966d6 fix: allow all tools for issue triage 2025-12-21 01:31:39 -08:00
Saoud Rizwan bb1d068139 feat: add Claude issue triage workflow for automatic issue response 2025-12-21 01:14:54 -08:00
Saoud Rizwan 450945ae0e fix(ci): fetch tags for previous tag lookup and add line break in release body 2025-12-20 07:30:13 -08:00
Saoud Rizwan 191e9635bd fix(ci): use CHANGELOG.md content for GitHub release notes
Instead of auto-generating release notes from PRs, extract the
changelog entry for the version being released and append the
Full Changelog comparison link.
2025-12-20 06:59:36 -08:00
Saoud Rizwan c13a7a80b3 v3.45.1 Release Notes (hotfix)
Hotfix release including:
- 8a9e03c8f: fix(mcp): resolve race condition when updating Cline-specific MCP settings
2025-12-20 06:41:28 -08:00
Saoud Rizwan d4a4adfa5f fix(ui): Misc UI improvements (markdown + home page) (#8229)
* fix(ui): add margin styling for ordered lists in markdown

* fix(ui): prevent info icon from shrinking and add padding on home page
2025-12-20 01:46:59 -08:00
Saoud Rizwan 557e20224e fix(checkpoints): don't show checkpoint message when initialization fails (#8230)
When starting a task in a location that can't use checkpoints (e.g., Desktop,
Documents, Downloads, or home directory), the checkpoint message was still
appearing in the chat without a SHA. This happened because the code added
the message before checking if initialization had failed.

Now we check for `checkpointManagerErrorMessage` before showing the checkpoint
message, so users in unsupported locations won't see a broken checkpoint element.
2025-12-20 01:44:06 -08:00
Saoud Rizwan 0e9a326a6a fix(test): update banner carousel pagination format in e2e test
The banner carousel format changed from '1/3' to '1 / 3' (with spaces)
in commit 8f1405b88. Update the test regex patterns to match.
2025-12-20 00:47:38 -08:00
Saoud Rizwan f5ecb6db0c feat(ui): add green styling to task completed row (#8226)
* Revert "feat: enhanced compact task complete ui (#8025)"

This reverts commit cc36c67fc9.

* feat(ui): add green styling to task completed row

- Add green border and tinted green background to task completion container
- Add copyButtonStyle prop to WithCopyButton for custom positioning
- Revert previous compact task UI changes in favor of simpler styling
2025-12-19 23:01:55 -08:00
Saoud Rizwan 8f1405b881 fix(ui): improve banner carousel styling and dismiss functionality (#8225)
* fix(ui): improve banner carousel styling and dismiss functionality

- Fix dismiss button not working by adding version-based filtering
- Use CSS Grid stack technique to auto-size carousel to tallest card
- Fix spacing issues on narrow widths with reduced margins/padding
- Add hover underline for links in banner descriptions
- Prevent header icon from shrinking on narrow screens
- Remove bottom margin from markdown paragraphs
- Clean up navigation footer styling

* chore: add changeset
2025-12-19 22:18:44 -08:00
Saoud Rizwan 8a9e03c8ff fix(mcp): resolve race condition when updating Cline-specific MCP settings (#8222)
* fix(mcp): resolve race condition when updating Cline-specific MCP settings

Fixes a bug where toggling auto-approve for MCP tools or changing timeout
settings would cause the UI to flash and revert, making the toggles appear
unresponsive.

The root cause was a race condition between two state update mechanisms:
1. RPC Response: Returns updated servers immediately to the webview
2. File Watcher: Detects the settings file change and triggers a second
   update ~100ms later, potentially overwriting the first

Additionally, the file watcher was triggering full server restarts even
for settings changes that don't affect the MCP transport connection.

Changes:
- Add `isUpdatingClineSettings` flag to skip file watcher processing
  when we're making internal settings changes
- Add `configsRequireRestart()` method to distinguish between settings
  that require server restart vs Cline-specific UI settings
- Only notify webview when actual connection changes occur
- Update in-memory state for timeout changes without server restart
- Add comprehensive documentation for future Cline-specific settings

* chore: add changeset

* fix: update comments and sync all Cline-specific settings in-memory
2025-12-19 21:35:06 -08:00
Bee edba02b45e feat: add background edit mode with webview diff display (#8205)
* feat: add background edit mode with webview diff display

- Replace editor-based diff preview with webview DiffEditRow component
- Remove unused partialPreviewState and related methods from ApplyPatchHandler
- Integrate FileEditProvider in Task for background file edits when enabled
- Add comprehensive Storybook stories for diff edit row states

Test Plan:

1. Go to Features Setting to turn on `Background Edit`
2. Start a task that would perform file edits
3. Verify the diff edits will be performed in the background instead of stealing focus from your editor
4. Verify the new stories in Storybook for the new DiffEditRow components

* backgroundEditEnabled

* changeset

* clean up

* clear time out

* fix storybook
2025-12-19 16:23:13 -08:00
Jose R. Perez cc36c67fc9 feat: enhanced compact task complete ui (#8025)
* feat: enhanced task completed response ui

* feat: enhanced task completed response ui

* feature: adjusted embed component styling

* fix: minor adjustments

* fix: made last task completed expanded by default

* fix: restore api request and thinking

* feat: copy button fix
2025-12-19 15:46:20 -08:00
CandiedUniverse d77032bc8a fix(hooks): Fix edge case for hooks-enabled schema in the CLI (#8134)
* fix(hooks): Fix edge case for hooks-enabled schema in the CLI

* fix(hooks): Change as per PR feedback to simplify verbose logic
2025-12-19 14:25:15 -08:00
Max 608dde94b3 bump go version (#8216)
Co-authored-by: Max Paulus 🥪 <max@cline.bot>
2025-12-19 14:14:21 -08:00
Max 47ff7c1620 fix security vulnerability with sapaicore provider (#8215)
Co-authored-by: Max Paulus 🥪 <max@cline.bot>
2025-12-19 13:37:15 -08:00
Bee 1b7f971c34 refactor: banner system with data-driven architecture [ENG-1426] (#8140)
* refactor: banner system with data-driven architecture

Add new banner data structures and types to support a flexible, backend-driven
banner system. This enables dynamic banner management while maintaining
consistent UI rendering.

Changes:
- Add BannerCardData interface for banner configuration with support for icons,
  severity levels, actions, and platform/user filtering
- Add BannerActionType enum defining action handlers (link, settings, CLI
  install, model selection)
- Add BannerAction interface for button/link definitions
- Refactor banner rendering logic to use data-driven approach instead of
  hardcoded implementations
- Update BannerCarousel component to handle new action types dynamically

This allows the backend to construct banner JSON that the frontend renders
consistently through the BannerCarousel component when ready.

* apply feedback

* update e2e test

* Add BackendBanner struct with converter

* clean up types

* clean up
2025-12-19 12:58:36 -08:00
Max 12eadd3378 fix bedrock byo problem (#8191)
Co-authored-by: Max Paulus 🥪 <max@cline.bot>
2025-12-19 12:22:51 -08:00
Max b3e0ef9ed7 multi-root workspace support for cli (#8163)
Co-authored-by: Max Paulus 🥪 <max@cline.bot>
2025-12-19 12:21:22 -08:00
Bee fb94d8d3d4 fix: expose process.platform in webview build configuration (#8201)
* fix(webview): expose process.platform in build configuration

Add process.platform to Vite and Storybook define configs to make
platform detection available in the webview UI code.

* Add changeset

* Update webview-ui/vite.config.ts

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* revert copilot suggestion

* revert package-lock.json

* remove unknown

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-12-19 11:19:22 -08:00
Robin Newhouse d11bd15d60 Refactor Bedrock provider to use metadata for reasoning support (#8196)
- Remove hardcoded shouldEnableReasoning check in AwsBedrockHandler

- Use modelInfo.supportsReasoning from metadata to determine if reasoning should be enabled

- Update src/shared/api.ts to include supportsReasoning: true for all relevant Bedrock models (Claude 3.7, 3.5 Sonnet/Haiku, Opus, and 1m variants)

- Ensure consistency with other providers by keeping model capabilities in metadata
2025-12-19 11:08:35 -08:00
celestial-vault 31c48898a6 Update litellm case in normalizeApiConfiguration to check stored modelinfo (#8202) 2025-12-19 10:46:22 -08:00
Zhongying Qiao 5c9901d68a feat: Make banner providers filtering determined by what is selected instead of existing provider keys (#8119)
* feat: make banner providers filtering determined by what is selected instead of existing provider keys

* refactor: address feedback, use default case for string comparison
2025-12-19 10:01:19 -08:00
Bee 45b79dc3d7 feat: add background edit mode setting (#7146)
Add backgroundEditEnabled setting to global state and settings infrastructure.
This includes:
- Proto definition for the update settings request
- State management in controller and state helpers
- Extension state interface updates
- Default value of false in webview context

Building block for ENG-1367. Setting is not yet used in the UI or anywhere in the app yet. It will be done in the follow-up PR where the feature is implemented.
2025-12-18 22:03:25 -08:00
Bee 26b6c7bdb6 refactor: move vscode config access to hostbridge layer (#7843)
- Add error_level field to telemetry proto messages
- Move getConfiguration usage from core services to vscode hostbridge provider
- Remove migrateDisableBrowserToolSetting and migrateChromeExecutablePathSetting methods
- Remove direct vscode imports from core/task and services/browser
- Update getTelemetrySettings to retrieve and return telemetryLevel from vscode config

This refactoring centralizes vscode-specific configuration access in the hostbridge provider layer, improving separation of concerns and making core services less coupled to the vscode API. Plus the cline configurations has already been set to be empty in the package.json for vs code extension.
2025-12-18 19:43:50 -08:00
Sarah Fortune d0678a2ad1 Add another codeowner for the settings directory (#8165)
* Add more codeowners for the settings directory

* Update CODEOWNERS
2025-12-18 19:11:14 -08:00
Bee 09276ebf43 fix: prevent duplicate error messages during streamed edit tool failures (#8200)
Add early return in WriteToFileToolHandler catch block when tool has
already failed once during streaming when enableParallelToolCalling is not enabled. This prevents the same error
message from being repeatedly added to userMessages array on each
new streaming chunk received.
2025-12-18 18:17:48 -08:00
CandiedUniverse af8b51b189 Revert "fix(hooks): Fix the underlying Windows detection logic [#8703] (#8168)" (#8197)
This reverts commit 3e6b3f252b.
2025-12-18 15:12:34 -08:00
CandiedUniverse 3e6b3f252b fix(hooks): Fix the underlying Windows detection logic [#8703] (#8168)
* fix(hooks): Fix the underlying Windows detection logic

* fix(hooks): Rename isMacOSOrLinux() to useIsMacOSOrLinux() per review feedback
2025-12-18 13:57:24 -08:00
Robin Newhouse f019c365a6 Refactor Anthropic handler to use metadata for reasoning support and cache_control behavior (#8170)
* Refactor Anthropic handler to use metadata for cache_control behavior

Replace hardcoded switch statement with model.info.supportsPromptCache check, following the same pattern as OpenAI Native and Vertex providers.

* Refactor Anthropic handler to use metadata for reasoning support

Replace modelId substring checks with model.info.supportsReasoning flag, and add supportsReasoning: true to all models that support extended thinking (3-7, 4-, 4-5).
2025-12-18 13:54:38 -08:00
Ara f6fe843cfb feat: auto-fail task in YOLO mode on consecutive mistakes (#8189)
When YOLO mode is enabled and the maximum consecutive mistakes
threshold is reached, automatically fail the task instead of
waiting for user input. This prevents the task from hanging
indefinitely in automated/unattended scenarios.

Displays an error message suggesting to use a more capable model
and ends the task loop with a failure signal.
2025-12-18 13:04:45 -08:00
Ara 01f26c21ae fix: handle yolo mode in AskFollowupQuestionToolHandler (#8188)
- Add check for yoloModeToggled flag to prevent waiting for user input
- Auto-respond with tool usage instructions when in yolo mode
- Log the auto-response action for transparency
- Maintain existing functionality for non-yolo mode operations
2025-12-18 12:40:52 -08:00
Robin Newhouse 031c2f5b05 fix: correct typos in gemini system prompt overrides (#8183)
Co-authored-by: CandiedUniverse <132302818+candieduniverse@users.noreply.github.com>
2025-12-18 12:18:23 -08:00
Juan Pablo Flores c999e269db docs: add .clineignore file guidance to reduce noise in multi-root workspaces (#8162)
Co-authored-by: Tony Loehr <turingxo@gmail.com>
2025-12-18 11:15:18 -08:00
Juan Pablo Flores 032c1bf792 DEVREL-61 docs: enhance Auto Approve feature documentation with detailed permis… (#8097)
* docs: enhance Auto Approve feature documentation with detailed permissions and usage examples

* Update docs/features/auto-approve.mdx

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix: replace image with video in Auto Approve documentation for better clarity

* Update docs/features/auto-approve.mdx

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Tony Loehr <turingxo@gmail.com>
2025-12-18 11:14:23 -08:00
Nick Baumann fa73d60b7a Improve Model Picker Modal UI and provider persistence (#8131)
* Improve Model Picker Modal UI and provider persistence

* Replace fuzzy search with multi-word substring matching in model picker

* feat(model-picker): add thinking slider, provider dropdown portal, and UI improvements

- Add thinking budget slider with min/max constraints
- Render provider dropdown via portal with flip logic for positioning
- Add getProviderInfo helper for settings-only providers
- Use ArrowLeftRight icon for plan/act split toggle
- Close provider list when typing in search
- Fix selection backgrounds with linear-gradient layering
- Improve row heights and icon positioning

* refactor(model-picker): replace Fuse.js with multi-word substring search

---------

Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
2025-12-17 21:22:32 -08:00
Robin Newhouse 841bb7f1d7 Disable specifically the Cline extensions in launch.json (#8176)
Replaced the global `--disable-extensions` flag with specific
`--disable-extension` flags for `saoudrizwan.claude-dev` and
`saoudrizwan.claude-dev-nightly`. This allows testing the extension
under development alongside other installed extensions while
preventing conflicts with production or nightly versions of Cline.
2025-12-17 18:01:51 -08:00
Bee f01428884d feat: replace diff edit tools with APPLY_PATCH tool for gpt-5+ native tools (#8167)
* feat: replace diff edit tools with APPLY_PATCH tool for gpt-5+ with native tool calling

Replace FILE_NEW and FILE_EDIT tools with APPLY_PATCH in the native-gpt-5-1 variant configuratiob as that's the format the GPT 5 models are trained on.

* update snapshot

* Update ApplyPatchHandler UI and new line bug
2025-12-17 16:07:47 -08:00
Tomás Barreiro 2ce5548250 [PF-207] Remotely configured OTEL (#8056)
* Remote configured OTEL

* Configure the OpenTelemetryTelemetryProvider for Remote Config and remove it when resetting the confiig

* Address comments

* Fix tests

* Refactor

* Address comments

* Refactor openTelemetryOtlpHeaders and add comment

---------

Co-authored-by: Sarah Fortune <sarah.fortune@gmail.com>
2025-12-17 21:36:35 +01:00
Tomás Barreiro 9f32cd247f fix: Fetch values available in the remote config (#8070)
* Update the StateManager with the new fields

* Add comment

* Add changeset
2025-12-17 21:09:08 +01:00
Max ace48198cc Add slash command auto-complete dropdown to cline cli (#8026) 2025-12-17 11:53:13 -08:00
Tony Loehr 9f0240dfd7 fixed keyboard shortcuts docs (#8116)
* fixed keyboard shortcuts docs

* improved flow of keyboard shortcuts docs

* fixed keyboard shortcuts relevance

* fixed terminal integration keyboard shortcuts relevance
2025-12-17 11:02:55 -08:00
Juan Pablo Flores 5530cfe375 DEVREL-69 docs: update multi-root workspace documentation for clarity and consi… (#8121)
* docs: update multi-root workspace documentation for clarity and consistency

* docs: remove experimental label from multi-root workspace feature

Update documentation to reflect that multi-root workspaces are no
longer considered experimental while still noting the existing
limitations with Cline rules and checkpoints.

* docs: update multi-root workspace examples to clarify workspace config file locations

* docs: add guidance on using VSCode's files.exclude to manage generated folders in multi-root workspaces

---------

Co-authored-by: Tony Loehr <turingxo@gmail.com>
2025-12-17 10:11:22 -08:00
Juan Pablo Flores af4d99e0bc docs: add JSON output section and ClineMessage schema to CLI reference (#8151)
* docs: add JSON output section and ClineMessage schema to CLI reference

* docs: enhance JSON output section with ClineMessage schema details
2025-12-17 10:04:11 -08:00
github-actions[bot] cd011a0e4a v3.45.0 Release Notes (#8159)
Added Gemini 3 Flash Preview model

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-12-17 08:47:05 -08:00
Ara d44184ab03 feat: add Gemini 3 Flash Preview model support (#8160)
- Added Gemini 3 Flash Preview to the recommended models list in the OpenRouter model picker.
- Updated the "What's New" modal to announce the availability of the new model and provide a quick-start button.
2025-12-17 08:39:37 -08:00
Bee 5d96704e92 feat: add new model configuration (#8142)
* feat: add new model configuration

Add support for the new Gemini 3 Flash Preview model with reasoning
capabilities. Updates both vertex and gemini model configurations with
pricing, token limits, and thinking level settings.

* update pricing

---------

Co-authored-by: Arafatkatze <arafat.da.khan@gmail.com>
2025-12-17 08:21:32 -08:00
github-actions[bot] 49812eb332 v3.44.2 Release Notes 2025-12-17 06:47:44 -08:00
Saoud Rizwan 57b72519ae fix(ui): improve model picker and popup modal styling (#8156)
* feat(model-picker): add tooltips to plan/act mode tabs

Show "Plan mode" and "Act mode" tooltips when hovering over the P and A
tabs in the split mode view of the model picker.

* fix(model-picker): remove focus outline from search input

* feat(model-picker): add checkmark to selected model and responsive provider

- Add checkmark icon on the right side of the selected model row
- Hide model provider name on viewports under 280px for better space usage

* fix(model-picker): remove double hover dim on provider row

* fix(model-picker): improve provider list styling consistency

- Reduce vertical padding to match model list rows
- Move checkmark to right side
- Use consistent font size

* fix(modals): add consistent arrow pointers to all popup modals

- Refactor ServersToggleModal to use same fixed positioning as other modals
- Add arrow pointer to ModelPickerModal
- Fix arrow z-index (1001) to seamlessly cover modal border
- Add viewport resize handling to ModelPickerModal for arrow repositioning
- Consistent styling across all three popup modals

* refactor(modals): unify modal styling and structure across components

- Introduce ModalContainer component for consistent styling in ServersToggleModal and ClineRulesToggleModal
- Simplify modal structure by removing unnecessary fragments and applying consistent fixed positioning
- Enhance arrow pointer implementation for better visual alignment across all modals
- Ensure responsive design and maintainability with updated styled components

* fix(modals): align modal widths with chat content and fix z-index

- Reduced modal inset from 15px to 10px to match chat content width
- Lowered modal z-index from 1000 to 49 so tooltips appear on top
- Adjusted modal positioning for consistency across all three modals

* fix(model-picker): update icon usage and tooltip content for thinking and split modes

- Replace Sparkles icon with Brain for extended thinking toggle
- Update tooltip messages to reflect current functionality for thinking and split modes
- Adjust padding in provider list item for better alignment
- Add min-height and box-sizing to search container for improved layout

* fix(model-picker): improve row heights, icons, and selection backgrounds

- Add min-height to search container for consistent row sizing
- Increase provider list padding from 4.5px to 6px
- Swap icon positions and use ArrowLeftRight for plan/act split toggle
- Fix transparent selection background on some themes using linear-gradient

* fix(model-picker): close provider list when typing in search

* fix(modals): adjust modal positioning

* refactor(modals): extract shared PopupModalContainer component

Consolidates duplicated modal container styling into a reusable component.
Removes ~130 lines of redundant code across ModelPickerModal, ServersToggleModal,
and ClineRulesToggleModal.
2025-12-17 06:42:22 -08:00
Saoud Rizwan 1ed4d00a16 fix(ui): improve WhatsNew modal design and responsiveness (#8155)
- Add side spacing for small viewports (calc(100%-2rem) instead of w-full)
- Apply rounded corners at all viewport sizes (not just sm:)
- Remove redundant "NEW" badge (title already says "New in v...")
- Remove redundant "Dismiss" button (X close button is sufficient)
- Reduce excess bottom padding for tighter layout
- Add cursor-pointer to dialog close button for better UX
- Clean up unused imports (PLATFORM_CONFIG, PlatformType, isVscode)
2025-12-17 05:25:33 -08:00
Robin Newhouse c090f5b1a7 fix: skip reasoning for GLM models (#8147)
GLM models output thinking content in text tags when reasoning is enabled, which is not currently supported by the UI. Disabling reasoning for these models ensures cleaner output.
2025-12-17 01:36:23 -08:00
Saoud Rizwan 3c917ec99d fix: disable auto port forwarding in workspace settings (#8149) 2025-12-16 23:19:32 -08:00
Saoud Rizwan b315be397d docs: update release workflow with learnings from first run 2025-12-16 22:15:32 -08:00
github-actions[bot] dc9e7916de v3.44.1 Release Notes 2025-12-16 21:47:26 -08:00
Saoud Rizwan cb9d1e81b8 Add release slash command and reorganize workflow files 2025-12-16 21:42:00 -08:00
Saoud Rizwan eb5a452c9c fix: restore local MCP server connections blocked by enterprise config logic (#8148)
* fix: restore local MCP server connections blocked by enterprise config logic

The enterprise MCP allowlist feature (commit 3409fa744) inadvertently
blocked all local stdio-based MCP servers for regular users.

The bug: the validation logic applied enterprise restrictions to everyone
by default, when it should only apply when enterprise config is present.

* chore: add changeset
2025-12-16 21:05:55 -08:00
Max 6a90294a2a update package-lock.json (#8107) 2025-12-16 19:09:42 -08:00
Bee 2e1334c10a dev: add snapshot tests for native tools content (#8145)
- Add snapshot file for native tools returned by system prompt getter function
- Remove inline comment from test:unit npm script that was breaking the command "npm run test:unit -- --update-snapshots"
2025-12-16 18:10:15 -08:00
mintlify[bot] 18b77ee5e5 DEVREL-59 Add cross-references between hooks and CLI documentation (#8063)
* Update docs/features/hooks/index.mdx

Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>

* Update docs/cline-cli/overview.mdx

Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>

* Update docs/cline-cli/cli-reference.mdx

Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>

* Update docs/cline-cli/cli-reference.mdx

Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>

* Update docs/cline-cli/overview.mdx

Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>

* Update docs/cline-cli/overview.mdx

Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>

---------

Co-authored-by: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>
2025-12-16 16:58:47 -08:00
Tomás Barreiro 4bf8feecac Remove the remote config auth listener (#8110) 2025-12-16 16:22:01 -08:00
Tomás Barreiro 2f3450f667 Extract Remotely Configured API keys (#8144)
* Extract Remotely Configured API keys

* Add changeset
2025-12-16 16:10:20 -08:00
Robin Newhouse 3e89c28727 feat: implement lazy evaluation for dynamic tool instructions (#8135)
Introduces a "Value or Provider" pattern to tool specifications, allowing the `instruction` field to be either a static string or a function of `SystemPromptContext`. This enables dynamic configuration of tool prompts based on runtime context (e.g., user settings) without hardcoding logic in the prompt builder.

- Updated `ClineToolSpecParameter` to support `string | ((context) => string)`
- Added `resolveInstruction` helper to handle dynamic resolution
- Refactored `PromptBuilder` to resolve instructions using the current context
2025-12-16 15:09:36 -08:00
Ara d065ac7b37 feat: update banner for version 3.44.0 (#8139)
- Update package.json and package-lock.json version from 3.43.1 to 3.44.0
- Add changelog entry for version 3.44.0 with banner update note
2025-12-16 13:59:13 -08:00
github-actions[bot] 5a0a25601a v3.43.1 Release Notes (#8132)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-12-16 13:25:37 -08:00
Ara 48d822a030 fix: update OpenRouter model ID from zai to z-ai for GLM-4.6 (#8138) 2025-12-16 13:16:06 -08:00
github-actions[bot] 417104505c v3.43.0 Release Notes (#8089)
- GLM-4.6
- kat-coder-pro
- Add parsing of env variable patterns to the mcpconfig.json

- TLS Proxy support issues for VSCode
- Add supportsReasoning flag to OpenAI reasoning models
- Fix thinking not available for some models in the OpenAI provider
- Fix invalid signature field issues when switching between Gemini and Anthropic providers
- Extract OpenRouter model filtering into reusable utility and use it in different model pickers
- Fix a11y for auto approve checkbox
- Improve ModelPickerModal provider list layout

- Migrate WhatsNewModal to new shared dialogue component

Co-authored-by: Arafatkatze <arafat.da.khan@gmail.com>
2025-12-16 10:26:36 -08:00
Juan Pablo Flores e21d3ff1bb Update/explain changes (#7977)
* docs: update explanations for Explain Changes feature and command in VS Code

* fix: update Enterprise card link to point to the correct overview page
2025-12-16 09:55:47 -08:00
Max da5477f891 added an architecture doc describing cline CLI architecture (#8049)
- this will help the community to onboard to the CLI quicker and me more
open to contributing to it.

Co-authored-by: Max Paulus 🥪 <max@cline.bot>
Co-authored-by: Tony Loehr <turingxo@gmail.com>
2025-12-16 09:30:54 -08:00
Ara 4903dfcb6e feat: add GLM-4.6 and KAT-Coder Pro to free models list (#8128)
- Add Zhipu AI's GLM-4.6 agentic coding model as a free option
- Add KwaiKAT's KAT-Coder Pro model as a free option
- Update filter to preserve kat-coder-pro in Cline provider model list
2025-12-16 09:24:24 -08:00
Ara 37b2f7fbc9 fix: correct IS_STANDALONE env check to use string comparison (#8098)
The IS_STANDALONE environment variable is statically rewritten to
"true" or "false" strings by esbuild. Using a truthy check caused
"false" to be evaluated as true, incorrectly enabling the standalone
proxy configuration.
2025-12-16 09:01:08 -08:00
Bee 11fbe4b21d fix: add supportsReasoning flag to OpenAI reasoning models (#8124) 2025-12-16 06:42:18 -08:00
Bee e0844ac6e2 refactor: migrate WhatsNewModal to new shared dialogue component (#8112)
* feat(webview): migrate WhatsNewModal to new shared component

- Add @radix-ui/react-dialog dependency
- Replace custom modal implementation with Radix Dialog primitives
- Remove commented-out code and unused imports
- Update Storybook stories to include showAnnouncement state
- Add version to mock state for stories

The new Dialog UI component allows us to reuse the component with unified behavior and styles if needed

* replace deprecated VS Code toolkits component with shared components

* Clean up Modal component

* clean up
2025-12-16 06:39:34 -08:00
Bee f28d760675 fix: handle invalid signature fields for Anthropic and Gemini providers (#8122)
- Add dummy thought signature fallback for Gemini API when signature is missing
- Filter out thinking blocks without signatures before sending to Anthropic API
- Update signature field cleaning to apply to non-thinking blocks only
- Remove unused DEFAULT_CACHE_TTL_SECONDS constant

This ensures proper message conversion between providers by using Gemini's
documented dummy signature "skip_thought_signature_validator" when original
signature is unavailable, and prevents invalid thinking blocks from being
sent to Anthropic's API which requires valid signatures.
2025-12-16 06:05:07 -08:00
Ara 8363d090e0 feat(ui): improve ModelPickerModal provider list layout (#8083)
Move provider list inside scrollable container and hide model content
when provider list is expanded. This improves UX by preventing layout
overflow and providing cleaner visual separation between provider
selection and model browsing states.
2025-12-16 00:58:16 -08:00
Zhongying Qiao 3409fa7442 feat: check pre-configured MCP server urls and do not parse unless on the allowed list (#8055)
* feat: add ability for enterprise to disable user from adding MCP servers via remote config

* use a proper type check instead of an as any assertion

* feat: check remote mcp server url against user configured mcp server and do not parse servers not on the allow list if no personal server allowed

* feat: Enforce remote config's local MCP market place settings and filter by allowlist and source (#8068)

* feat: add parse/load enforcement for local mcp market place servers

---------

Co-authored-by: Sarah Fortune <sarah.fortune@gmail.com>
2025-12-16 00:04:46 -08:00
Zhongying Qiao a20685d289 feat: Enable extensions to send os types as query param for banners (#8114)
* feat: enable extensions to send os types as query param for banners

* add tests

* check os type with semantically correct method
2025-12-15 22:34:53 -08:00
Bee 926c5e189e fix: use cursor pointer to model description expand button (#8106)
Added cursor-pointer class to the expand/collapse button in ModelDescriptionMarkdown to provide proper visual feedback on hover.
2025-12-15 12:40:55 -08:00
CandiedUniverse 2a5ca9d312 feat(hooks): Add telemetry for hooks [ENG-999] (#7993)
* feat(hooks): Add telemetry for hooks

feat(hooks): Simplify hooks telemetry implementation and improve safety

feat(hooks): Changes as per Cline's code review

* feat(hooks): Changes as per PR feedback.
2025-12-15 10:06:18 -08:00
celestial-vault d06717342b add the parsing of env variable patterns to the mcpconfig.json (#8079)
* add the parsing of env variable patterns to the mcpconfig.json

* make sure to expand env variables in the config before validation
2025-12-13 21:50:25 -08:00
Zhongying Qiao c904cfe376 feat: Add ability for enterprise to disable user from adding MCP servers via remote config (#8029)
* feat: add ability for enterprise to disable user from adding MCP servers via remote config

* use a proper type check instead of an as any assertion
2025-12-13 21:34:28 -08:00
lahernandezb 924ca1278c fix: auto approve screen reader a11y (#7901)
* fix: auto approve screen reader a11y

prevoius impl contained 2 tab stops per checkbox and read a generic
"Checkbox" label when focues on the checkbox input. This can be
confusing for a visually impaired person using a screen reader

* chore: changeset

* chore: remove unused imports

---------

Co-authored-by: CandiedUniverse <132302818+candieduniverse@users.noreply.github.com>
2025-12-12 16:39:08 -08:00
github-actions[bot] 2b0c0a659d v3.42.0 Release Notes (#8052)
- Expose `getAvailableSlashCommands` rpc endpoint to UI clients
- Made slash command menu and context menu accessible and screenreader-friendly
- Made expanding/collapsing UI components accessible

- Model identity and routing for devstral-2512 free model
- Extension pricing/UI bug where extension incorrectly shows zero price for devstral-2512

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-12-12 15:16:52 -08:00
Ara f4477e229d fix: update OpenRouter model ID and filter logic for devstral-2512 (#8065)
* fix: update OpenRouter model ID and filter logic for devstral-2512

- Update the model ID for devstral-2512 to include the ':free' suffix
- Modify the filter logic in providerUtils to handle devstral-2512 models
  and ensure they are not excluded when using the Cline provider
- Also ensure the default OpenRouter model is preserved in the filter

* Mistral change

* Mistral change

* Mistral change
2025-12-12 14:25:58 -08:00
Ara 5207d5c68e refactor: extract OpenRouter model filtering into reusable utility (#8064)
- Add filterOpenRouterModelIds function to providerUtils.ts
- Apply consistent filtering logic in ModelPickerModal and OpenRouterModelPicker
- For Cline provider: exclude :free models except Minimax
- For OpenRouter/Vercel: exclude cline/ prefixed models
2025-12-12 12:38:09 -08:00
Mingxuan Zhang 51b535e2d6 accessibility: screen reader support for slash and context menus (#7832)
* accessibility: screen reader support for slash and context menus

* remove unnecessary selection announcement

* changeset run

* chore: clear announcement to avoid interfering with dom queries

* chore: resolve conflict
2025-12-12 11:46:32 -08:00
jgellin-sf 4db61b1b36 chore: make expanding/collapsing ui components accessible (#7828)
* chore: make expanding/collapsing ui components accessible

* chore: changeset

* chore: check isLoading on CodeAccordian key handler

---------

Co-authored-by: CandiedUniverse <132302818+candieduniverse@users.noreply.github.com>
2025-12-12 10:41:32 -08:00
Zhongying Qiao 6baf611322 feat: Make extension use new banner api, keep providers for extension side rules eval (#8022)
* feat: make extension use new banner api, keep providers for extension side banner rules eval
2025-12-12 09:00:27 -08:00
Max 97d635d606 expose a getAvailableSlashCommands rpc endpoint in cline core (#8024) 2025-12-11 16:05:35 -08:00
Ara 8ce476ccaa Refactor Terminal Module (#7966)
* refactor: move terminal integration from core to vscode host

- Relocate terminal-related code from core/integrations to hosts/vscode/terminal
- Move TerminalManager, TerminalProcess, TerminalRegistry, and related utilities
- Update import paths across the codebase to reference new locations
- Remove unused shellIntegrationWarningTracker and shouldShowBackgroundTerminalSuggestion from Controller
- This change better separates VSCode-specific terminal handling from core logic

* Mistral change

* refactor: consolidate terminal types into types.ts

- Move ActiveBackgroundCommand, AskResponse, CommandExecutorCallbacks, CommandExecutorConfig from ICommandExecutor.ts to types.ts
- Move OrchestrationOptions, OrchestrationResult from CommandOrchestrator.ts to types.ts
- Delete ICommandExecutor.ts (all types now in types.ts)
- Update imports in CommandExecutor.ts, CommandOrchestrator.ts, index.ts, and src/core/task/index.ts
- types.ts is now the single source of truth for all terminal-related types

* refactor: consolidate ITerminalProcess into types.ts

- Move ITerminalProcess, TerminalProcessEvents from ITerminalProcess.ts to types.ts
- Delete ITerminalProcess.ts (all types now in types.ts)
- Update imports in VscodeTerminalProcess.ts, StandaloneTerminalProcess.ts
- Update exports in index.ts
- types.ts is now the single source of truth for ALL terminal-related types
2025-12-11 12:11:32 -08:00
Ara bce403476e fix(ui): close WhatsNewModal when selecting model options (#8048)
Close the modal automatically when users click "Try Devstral" or
"Try GPT-5.2" buttons to improve UX flow. Also update Devstral
button text to clarify it's free.
2025-12-11 12:00:46 -08:00
github-actions[bot] ac306c3719 v3.41.0 Release Notes (#7885)
- OpenAI GPT-5.2
- Devstral-2 `devstral-2512` (formerly stealth model "Microwave")
- Improvements to chat modal model picker
- Amazon Nova 2 Lite
- DeepSeek 3.2 to native tool calling allow list
- Responses API support for Codex models in OpenAI provider (requires native tool calling)
- Xmas Special Santa Cline
- Welcome screen UI enhancements

- Initial checkpoint commit now non-blocking for improved responsiveness in large repositories
- Gemini Vertex models erroring when thinking parameters are not supported
- Restrictive file permissions for secrets.json
- Ollama streaming requests not aborting when task is cancelled

- OpenAI provider to centralize temperature configuration and include missing GPT-5 model settings
- OpenAI native handler to use metadata for model capabilities
- Vertex provider to use metadata for model capabilities

Co-authored-by: Arafatkatze <arafat.da.khan@gmail.com>
2025-12-11 11:50:44 -08:00
Ara 1d8a9bf11e Change Stealth model (#8042)
* Mistral change

* Mistral change

* Mistral change
2025-12-11 11:25:31 -08:00
Nick Baumann d811a9d5f3 feat: improve chat modal model picker (#7949)
* feat: add inline model picker modal

* fix: add together to SETTINGS_ONLY_PROVIDERS, remove sapaicore

* Fix bedrock thinking support and add together to dynamic providers

---------

Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
2025-12-11 10:53:46 -08:00
Ara 3abeff0379 chore(settings): refresh recommended OpenRouter model labels (#8047)
Update recommended models by switching GPT-5.1 to GPT-5.2 and adjusting "NEW"/"HOT" badges to reflect current recommendations.
2025-12-11 10:38:31 -08:00
Robin Newhouse 2763266424 feat: add GPT-5.2 model support (#8045)
* feat: add GPT-5.2 model support

* Update pricing
2025-12-11 10:30:35 -08:00
Robin Newhouse 0c3dfb6aed Fix parallel tool calling by tracking tool use via call_id (#8036)
Previously, tool results were tracked using the tool name as a key. This caused a critical bug during parallel tool execution: if the same tool (e.g., `read_file`) was called multiple times in a single turn, subsequent calls would overwrite the previous ones in the `toolUseIdMap`. This resulted in missing tool results for all but the last call.

This commit changes the tracking mechanism to use the unique `call_id` provided by the LLM as the key. This ensures that every tool call is tracked independently, regardless of the tool name.

Specific changes:
- Updated `toolUseIdMap` in `Task.ts` to store `call_id -> tool_id` instead of `tool_name -> tool_id`.
- Updated `ToolResultUtils.ts` to retrieve tool IDs using `block.call_id`.
- Removed legacy MCP-specific logic that manually mapped the generic `use_mcp_tool` name to an ID. This is no longer necessary (and would be incorrect) as MCP tools now also use the robust `call_id` tracking, enabling parallel execution for them as well.
2025-12-11 10:17:44 -08:00
Jose R. Perez 0e73cd4c9f feat: fixed glitchy welcome screen issue (#8041) 2025-12-11 07:21:55 -08:00
Robin Newhouse 6bbe5c2499 fix: remove attempt_completion tool from READ_ONLY_TOOLS (#8033)
This was causing tools to be called after task completion.
Removing this terminates the task properly only after other
tool calls are complete.
2025-12-11 00:17:41 -08:00
Saoud Rizwan 00e9d6f523 feat: add experimental parallel tool calling support (#8020)
* feat: add experimental parallel tool calling support

Add a new experimental setting that allows models to call multiple tools
in a single response. This is automatically enabled for GPT-5 models.

- Add enableParallelToolCalling setting (off by default)
- Conditionally enforce didAlreadyUseTool flag based on setting
- Move checkpoint from per-tool to per-response
- Add UI toggle in Feature Settings section

* feat: enable parallel tool calling for GPT-5 in prompts and API (#8028)

* feat: enable parallel tool calling for GPT-5 in prompts and API

Update system prompts for GPT-5 and next-gen variants to instruct
models they may use multiple tools in a single response for independent
operations.

Fix OpenAI API to send parallel_tool_calls: true for GPT-5 models,
which was previously hardcoded to false for all models.

Related: #8020

Changes:
- Updated 5 prompt variant files to allow parallel tool use
- Added enableParallelToolCalls param to getOpenAIToolParams()
- Updated openai-native.ts to enable for GPT-5 model family

* Update system test snapshots for parallel tool calling

* Revert changes to MCP prompts

---------

Co-authored-by: Robin Newhouse <robin@cline.bot>
2025-12-11 00:05:22 -08:00
Toshii 010fd71140 additional prompting for new task command (#8035) 2025-12-10 22:31:01 -08:00
Toshii 17a95f0021 adding xml examples to all newtask calls (#8034) 2025-12-10 19:33:00 -08:00
Ara 27c9971774 feat(mistral): fix proxy support and add new model definitions (#8018)
* feat: Added Devstral 2 Models

* feat(mistral): fix proxy support and add new model definitions

- Fix HTTPClient fetcher to properly extract URL and options from Request
  objects, enabling proxy support in standalone mode (JetBrains/CLI)
- Add duplex option for body streams required by Node.js/undici
- Rename devstral-small-latest to labs-devstral-small-2512
- Add mistral-large-2512 model (256K context, $0.5/$1.5 pricing)
- Add ministral-14b-2512 model (256K context, $0.2/$0.2 pricing)

---------

Co-authored-by: omercelik <omercelik@users.noreply.github.com>
2025-12-10 12:35:25 -08:00
Robin Newhouse 644d06c487 Fix tool use argument handling in Claude Code provider (#8023)
The Claude Code CLI returns tool arguments as complete objects, but the
StreamResponseHandler expects string chunks for streaming. This caused
tool calls to fail with "missing parameter" errors because the object
was being concatenated with a string, resulting in "[object Object]".

This change stringifies the tool arguments in the Claude Code provider
before yielding them, ensuring they are correctly parsed by the
StreamResponseHandler.
2025-12-10 11:56:49 -08:00
Tony Loehr 1be314dfed Enterprise docs (#7714)
* enterprise docs

* tested for accuracy

* Reorganize Enterprise docs structure

- Consolidate member management under team-management/
- Unify all configuration under configuration/ with two clear paths:
  - remote-configuration/ for simple cloud-based setup
  - infrastructure-configuration/ for advanced enterprise features
- Create comprehensive overview pages explaining the differences
- Update all internal links to reflect new paths
- Preserve all existing content while eliminating redundancy
- Maintain clear separation between admin and member documentation

* removed trailing backslash

* fix docs.json

* enterprise docs reformat

* monday update

* tidied up managing members section

* fixed deployment guide

* simplify rules

* workflow cleanup

* rules tweak

* Update docs/enterprise-solutions/configuration/overview.mdx

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* fix other features

* fixed provider docs

* fixed monitoring

* fix providers

* updated cta and rbac

* fix enterprise overview

* enterprise-docs

* hid self-hosted section for now

* addressed format fixed

* docs: restructure monitoring navigation and move telemetry

- Remove unnecessary OpenTelemetry dropdown wrapper in Enterprise navigation
- Move Cline Telemetry from control-other-cline-features to monitoring section
- Update all internal documentation links to new telemetry path
- Simplify Control Other Cline Features section to focus on Yolo Mode only
- Group related monitoring features (overview, telemetry, opentelemetry) together

This creates a more cohesive navigation structure where telemetry-related
features are adjacent and eliminates unnecessary nested dropdowns.

* docs: rename Basic Telemetry to Cline Telemetry and add link

- Rename all instances of 'Basic Telemetry' to 'Cline Telemetry' for consistency
- Add href link to Cline Telemetry card in Monitoring Options section
- Update section headings and subheadings to use 'Cline Telemetry'
- Ensures consistent naming across monitoring documentation

* docs: restructure Enterprise YOLO Mode to focus on administrator controls

- Change title from 'Yolo Mode' to 'YOLO Mode' for consistency
- Add reference link to /features/yolo-mode for general documentation
- Remove duplicate content about basic YOLO Mode functionality
- Focus exclusively on Enterprise administrator configuration and controls
- Add comprehensive policy recommendations by organization size
- Include security implications, monitoring requirements, and compliance considerations
- Provide detailed technical implementation guidance
- Update overview.mdx card description to reflect enterprise focus

* docs: hide self-hosted/infrastructure configuration references

- Remove choosing-your-deployment from Enterprise navigation
- Remove self-hosted references from enterprise-solutions/overview.mdx
- Remove self-hosted comparison and warning from remote-configuration/overview.mdx
- Remove Info boxes linking to infrastructure config from provider pages (AWS, Google, LiteLLM)
- Remove Self-Hosted OpenTelemetry Collector section from opentelemetry.mdx
- Remove self-hosted deployment section from control-other-cline-features/overview.mdx

All self-hosted/infrastructure configuration documentation remains intact but is no longer
navigable or linked from SaaS provider configuration pages. This allows easy restoration
when features become available.

* clarified domain and seat info

* fixed getOpenTabs function

* Update getOpenTabs.ts

* Update package.json

* Revert package-lock files to main

---------

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
Co-authored-by: Juan Pablo Flores <juan@cline.bot>
2025-12-10 11:05:14 -08:00
Saoud Rizwan 91940fbb4a v3.40.2 Release Notes (hotfix)
Hotfix release including:
- 279e371cf: fix: prevent logout on network errors during token refresh (#8021)
2025-12-11 03:37:29 +09:00
Saoud Rizwan 279e371cf5 fix: prevent logout on network errors during token refresh (#8021)
* fix: prevent logout on network errors during token refresh

When network errors occur at startup (e.g., opening laptop while offline),
users were being logged out because the token refresh failed and returned
null to AuthService.

Now on network errors or max retries exceeded, we return the stored auth
data instead of clearing the session. This keeps users logged in with
their existing credentials. If the token is truly invalid, the actual API
request will fail later when the user tries to use Cline, rather than
logging them out preemptively at startup.

* chore: add changeset
2025-12-10 10:33:00 -08:00
Saoud Rizwan 4eda267981 fix(e2e): update auth test to handle Santa Cline logo with multiple paths
The Santa Cline logo has 3 path elements, causing strict mode violation.
Select the container instead of a specific path element.
2025-12-11 03:21:26 +09:00
Robin Newhouse 3441363805 fix: only send thinking params to Gemini models that support them (#8014) 2025-12-09 21:37:53 -08:00
Robin Newhouse 5389be991e Refactor Vertex provider to use metadata for model capabilities (#7999)
This change removes hardcoded switch statements in VertexHandler and moves model-specific configurations (like reasoning support and prompt caching) into the centralized model metadata in src/shared/api.ts.

Benefits:
- Decouples handler logic from specific model IDs
- Centralizes model capabilities for easier maintenance
- Simplifies adding future Vertex models
- Improves type safety

Related: ENG-1408, ENG-1385
2025-12-09 15:36:02 -08:00
Sarah Fortune 41fd610203 Don't enable gRPC debug logs in the cli (#8013)
If you need this for development you can enable them locally, they shouldn't be turned on in the released version; they are spammy af.
2025-12-09 15:10:37 -08:00
Jose R. Perez e1e7470fdd feature: xmas special santa cline (#8010)
* feat: hide whats new modal header image for now

* feature: change set

* feat: xmas special santa cline

* fix: minor change to actual svg

* Fix colors

---------

Co-authored-by: Arafatkatze <arafat.da.khan@gmail.com>
2025-12-09 15:04:11 -08:00
Zhongying Qiao 2f0e0ee56d feat: configure Litellm API key with remote config (#7937)
* feat: configure Litellm API key with remote config
2025-12-09 14:56:23 -08:00
Robin Newhouse 7f89ebf276 fix: make initial checkpoint commit non-blocking but block unsafe tools [#AI-26] (#8008)
* fix: make initial checkpoint commit non-blocking while preventing tool execution races

- Captures the initial checkpoint commit promise in the Task class
- Ensures executeTool waits for the initial commit to complete before running any tools
- Resolves race condition where tools could modify files before the initial state was fully captured

* feat: allow read-only tools to bypass initial checkpoint block

- Defines READ_ONLY_TOOLS allowlist in shared/tools.ts
- Updates Task executor to check tool name against whitelist
- Allows exploration tools (list_files, read_file, browser_action, etc.) to run in parallel with initial commit
- Maintains blocking for state-modifying tools (write_to_file) to ensure data integrity
2025-12-09 14:43:30 -08:00
Jose R. Perez 99ed1b7e86 feat: hide whats new modal header image for now (#8009)
* feat: hide whats new modal header image for now

* feature: change set
2025-12-09 13:49:42 -08:00
Ara 45c9fcf575 Removing unused file in Dify Provider (#7968) 2025-12-09 13:41:42 -08:00
Stewi 4f73f4460b fix(docs): correct broken signup link in installing-cline docs
Fixed a broken link in installing-cline.mdx: replaced https://app.cline.bot/signup with https://authkit.cline.bot/ for account creation.
2025-12-09 12:56:30 -08:00
Ara fb872fd316 feat(banners): add dismiss functionality to banner carousel (#7982)
* feat(banners): add dismiss functionality to banner carousel

- Add onDismiss callback to BannerData interface
- Implement dismiss button (X icon) in BannerCarousel component
- Add onDismiss handlers for info, model, and CLI banners
- Update banner version in state when user dismisses a banner
- Fix carousel index bounds handling when banners are removed
- Refactor carousel handlers with useCallback for better performance

* Fix imports

* feat(banners): show dismiss X only on last card in carousel
2025-12-09 12:46:30 -08:00
Tomás Barreiro 5292242a8e Add loaders to login buttons (#7945)
* Add loaders to login buttons

* Disable the button when loading

* Add changeset

* Remove log

* Fix tests
2025-12-09 20:41:56 +01:00
CandiedUniverse 78b8aed50f feat(hooks): Implement PreCompact hook [ENG-1005] (#7513)
* feat(hooks): Implement PreCompact hook

feat(hooks): Continuing implementation of PreCompact hook

feat(hooks): PreCompact supports contextModification

Fixes as per Cline code reviewing the PreCompact implementation

feat(hooks): Tweaking the PreCompact hook behavior while testing

feat(hooks): Implement PreCompact hook in handleContextWindowExceededError code path

feat(hooks): Implement conversation history temp file in task directory for PreCompact to access

feat(hooks): Implement context window temp file in task history directory for PreCompact to access

feat(hooks): Refactor complex function into helpers

* feat(hooks): Improvements from Cline code reviewing the change set

feat(hooks): Refactor duplicate logic into common utility function

feat(hooks): Improve compaction strategy naming

feat(hooks): Deduplicate a small piece of logic

feat(hooks): DRY for getNextTruncationRange()

feat(hooks): Fix contextModification for PreCompact hook

feat(hooks): Improvements as per Cline's code review feedback

feat(hooks): Improving code quality/reduce complexity

feat(hooks): Further code improvements as per Cline code reviewing

* feat(hooks): Changes as per PR feedback
2025-12-09 11:20:29 -08:00
Tomás Barreiro d01f7b4618 Log session information (#7944)
* Prevent multiple simultaneos refreshes when retrieving auth info

* refactor

* Track logout events

* Add changeset

* Persist the startedAt date

* Fix bug

* Use snake case for event properties

* Log failed refresh request information
2025-12-09 20:10:20 +01:00
CandiedUniverse dec215cd9c feat(hooks): Enable hooks in the CLI [ENG-1375] (#7948)
* feat(cli): Add hooks_enabled support to CLI settings

- Add hooks_enabled field to Settings proto message (field 134)
- Add hooks_enabled parsing to CLI settings parser
- Enables users to toggle hooks via -s hooks_enabled=true/false flag

Fixes missing CLI support for hooks that was available in the VSCode extension

* feat(hooks): Enable hooks in the CLI

* Add include back in after resolving merge conflict

* feat(hooks): Changes as per human code review feedback.

---------

Co-authored-by: NightTrek <Daniels@dual4t.com>
2025-12-09 10:32:18 -08:00
Toshii 8ce7e132d2 add feature flag check to tool handlers (#7997) 2025-12-08 19:48:50 -08:00
Toshii 6ab008b204 adding search models to usage tables in ui (#7996) 2025-12-08 19:18:31 -08:00
Sarah Fortune 769523998d Add the cline distribution type to the telemetry (#7940)
* Add the cline distribution type to the telemetry

In the telemetry we currently have the IDE name, but because there are so many variants of VSCode and JetBrains, it's not easy to group them by VSCode extension or JetBrains plugin. Add this field to the telemetry.

* update unit tests

* Update src/services/telemetry/TelemetryService.ts

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* Update src/services/telemetry/TelemetryService.ts

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* Update unit tests

---------

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-12-08 17:14:54 -08:00
Max 64a6bcc39b show mcp messages in cli output (#7989)
Co-authored-by: Max Paulus 🥪 <max@cline.bot>
2025-12-08 13:20:20 -08:00
AJ Juaire 19ceafd4a4 Add Amazon Nova 2 Lite support. (#7987)
https://github.com/cline/cline/discussions/7855
2025-12-08 11:34:24 -08:00
Robin Newhouse 4b5218b3b8 Refactor OpenAI native handler to use metadata for model capabilities (#7947)
This change removes hardcoded switch statements in OpenAiNativeHandler and moves model-specific configurations (like streaming support, system role, and tools support) into the centralized model metadata in src/shared/api.ts.

Benefits:
- Decouples handler logic from specific model IDs
- Centralizes model capabilities for easier maintenance
- Simplifies adding future OpenAI models
- Improves type safety with updated getModel() signature

Related: #7920
2025-12-08 11:07:10 -08:00
Toshii b68d716675 in tests websearch shows up in cline provider prompt (#7976) 2025-12-08 00:00:19 -08:00
Toshii f820c6d00a adding handler for websearch in cli (#7570) 2025-12-08 00:00:05 -08:00
Toshii 1fcbbaa9d0 adding websearch and integrating new handler (#7514)
* implementing prompt injection for web_search and associated web fetch handler

* remove printing of the ms took

* ui showing query user is searching for

* updating the fields we pass in api request

* updating text for search tool
2025-12-07 23:10:44 -08:00
Toshii 4005df6eae updating webfetch and integrating new handler (#7509)
* updating system prompt for webfetch and integrating new handler

* updating tests to match new webfetch tool
2025-12-07 22:37:48 -08:00
Toshii 0e3cdab82b adding webtools to the features menu (#7566)
* adding webtools to the features menu

* telemetry for toggling web tools

* adding feature flag for webtools
2025-12-07 22:34:43 -08:00
Sarah Fortune ada6b0c955 Move terminal impls into the correct package. (#7970)
Move VSCode terminal impls into the src/hosts/vscode package. The VSCode specific code needs to be contained in this directory.
The `src/shared` package is for things shared with the extension and the _webview_; everything in src/ that's _not_ under `src/hosts` is shared with VSCode, JB, CLI implicitly.

ref CLIENTS-34
2025-12-07 20:35:00 -08:00
Jose R. Perez 921dd2ec8c feat: welcome screen ui enhancements (#7878)
* feat: Announcement Cards, Recent Tasks Refresh, Whats new modal

* feat: adjustments to welcome modal functionality

* chore: add changeset for welcome ui enhancements

* refactor: replace inline styles with Tailwind classes where appropriate

* fix: removed close mechanisim for cards fix modal linking issue

* feat: suggested changes

* fix: arias for accessibility

* fix: test modal fix

* feat: e2e test fix

* update e2e tests with new welcome ui

* feat: small arias change

---------

Co-authored-by: abeatrix <beatrix@cline.bot>
2025-12-07 20:32:42 -08:00
Richard 4b212994a8 fix(security): set restrictive file permissions for secrets.json (#7782) 2025-12-07 19:23:29 -08:00
CandiedUniverse 3fe3c866ea fix(hooks): Want TaskCancel to get triggered properly (#7952) 2025-12-07 06:59:19 -08:00
Ara e9136f60cc feat(terminal): Move Standalone terminal Code to Typescript (#7927)
* feat(terminal): add shared terminal types and interfaces

Add shared terminal module with types and interfaces that enable
terminal management across VSCode, CLI, and JetBrains environments.

- Define ITerminal, ITerminalManager, and TerminalInfo interfaces
- Add TerminalProcessResultPromise for async command execution
- Include StandaloneTerminalOptions for non-VSCode environments
- Prepare module structure for standalone implementations

* feat(terminal): export standalone terminal implementations

Enable exports for standalone terminal classes that were previously
commented out as placeholders:
- StandaloneTerminal
- StandaloneTerminalManager
- StandaloneTerminalProcess
- StandaloneTerminalRegistry

These implementations are now ready for use outside the terminal module.

* fix: resolve TerminalInfo type incompatibility in settings update

- Remove unused TerminalInfo import from both updateSettings files
- Use `as any` cast to handle type mismatch between VSCode and standalone TerminalInfo
- Replace busyTerminals array with busyTerminalsCount to avoid type issues
- Add null-safe access when getting busy terminals length

* feat: import StandaloneTerminalManager from bundled cline-core

Replace standalone enhanced-terminal.js with import from the bundled
TypeScript version in cline-core.js. This consolidates terminal
management code and removes the need to separately include the
runtime file in the VS Code extension package.

- Re-export StandaloneTerminalManager from cline-core.ts
- Update vscode-impls.js to import from cline-core.js
- Remove .vscodeignore exception for enhanced-terminal.js

* feat: simplify standalone terminal manager initialization

Replace global injection pattern with environment variable detection
for determining terminal execution mode. The Task class now directly
instantiates StandaloneTerminalManager when IS_STANDALONE=true instead
of relying on a globally injected instance.

- Remove StandaloneTerminalManager re-export from cline-core.ts
- Simplify vscode-impls.js createTerminal to return stub object
- Use IS_STANDALONE env var for terminal manager selection in Task
- Remove global.standaloneTerminalManager injection pattern

* Fix Standalone build

* Fix Standalone build

* fix: use subagentTerminalOutputLineLimit in StandaloneTerminalManager.processOutput

Match the VSCode TerminalManager logic to properly use subagentTerminalOutputLineLimit (2000) for subagent commands instead of always falling back to terminalOutputLineLimit (500).

* feat: add TerminalManager to HostProvider for dependency injection

- Add TerminalManagerCreator type and createTerminalManager to HostProvider
- Extract ITerminalManager interface to shared/terminal/types for abstraction
- Refactor TerminalManager to implement ITerminalManager interface
- Create StandaloneTerminalManager for non-VSCode environments
- Update TerminalRegistry to use ITerminalManager via HostProvider
- Enable terminal management to work across different host environments

* feat: refactor terminal manager to use ITerminalManager interface

- Replace concrete TerminalManager/StandaloneTerminalManager types with ITerminalManager interface
- Use HostProvider.createTerminalManager() for host-agnostic terminal creation
- Simplify terminal execution mode logic in Task constructor
- Add dynamic imports for StandaloneTerminalManager when backgroundExec mode is used
- Improve logging for terminal manager selection
2025-12-07 05:10:25 -08:00
Bee 34bb95e04e refactor: require native tool call for Responses API (#7953)
Add validation to ensure native tool calling is enabled when using
OpenAI Responses API format. Previously, the code would silently fall
back to completion stream when tools were not provided, which could
lead to unexpected behavior.

- Add explicit error when tools are missing for Responses API format
- Update tools parameter type to non-optional in createResponseStream
2025-12-06 05:03:29 -08:00
Saoud Rizwan 7b65db55f1 docs: update hotfix workflow to copy Slack message instead of tag 2025-12-05 16:13:37 -08:00
Saoud Rizwan 07ebc2e4bd docs: improve hotfix release workflow
- Split shell commands to avoid parsing issues with parentheses in author names
- Clarify that hotfixes always use patch version bumps
- Add (hotfix) suffix to release notes commit message format
- Skip npm install step (automation handles lockfile)
- Add pbcopy step to copy tag to clipboard for GitHub Actions
- Add direct link to publish workflow
2025-12-05 15:58:58 -08:00
Saoud Rizwan 0193179597 v3.40.1 Release Notes
Hotfix release including:
- 4df486fa5: fix cost calculation for Anthropic API requests (#7943)
2025-12-05 15:49:42 -08:00
Saoud Rizwan 20c0783c97 feat: add hotfix release workflow documentation
Add a workflow for creating hotfix releases by cherry-picking commits
from main onto release tags. Includes steps for selecting commits,
creating release notes, version bumping, and tagging.
2025-12-05 15:43:31 -08:00
Saoud Rizwan 4df486fa5b fix: restore cost calculation for Anthropic API requests (#7943)
The taskMetrics.totalCost was incorrectly initialized to 0 instead of
undefined in commit 09692d7d3. This broke cost display for providers
like Anthropic that don't return totalCost in their usage chunks.

When totalCost is 0, the fallback to calculateApiCostAnthropic() in
updateApiReqMsg doesn't trigger because the nullish coalescing operator
(??) only falls back for null/undefined, not 0.

By initializing totalCost to undefined:
- Providers that return totalCost (like OpenRouter) use that value
- Providers that don't (like Anthropic) fall back to calculating cost
  from token counts and model pricing info
2025-12-05 13:01:02 -08:00
Zhongying Qiao 5fc6d4e9e3 feat: remote config - add vertex provider (#7913) 2025-12-05 12:58:50 -08:00
Saoud Rizwan 00d3bd8316 refactor(ui): move model capabilities to Advanced section and fix layout
- Move Images, Browser, Prompt Caching badges into collapsible Advanced section
- Use consistent row styling (label: value) for capabilities
- Fix InfoRow vertical spacing when items wrap (column-gap: 16px, row-gap: 4px)
- Add bottom padding to model picker popup for breathing room
- Remove unused Tooltip imports and badge styled components
2025-12-05 12:50:31 -08:00
Robin Newhouse 81d4ff947f Refactor openai-native.ts switch statement to use model metadata (#7920)
* refactor: Move OpenAI temperature to model metadata

- Added `temperature` field to `openAiNativeModels` in `api.ts`.

- Updated `OpenAiNativeHandler` to use `model.info.temperature` instead of hardcoded values in switch cases.

- This allows for centralized configuration of model temperatures.

* refactor: Consolidate OpenAI native streaming logic

- Simplified `createCompletionStream` in `OpenAiNativeHandler` by consolidating duplicated logic for streaming models (`gpt-5`, `o3`, `o4`).

- Introduced `systemRole`, `includeReasoning`, and `includeTools` flags to handle model-specific configurations.

- Preserved distinct handling for non-streaming `o1` models.
2025-12-05 10:48:23 -08:00
Max bcb368d097 display completion messages in processStateUpdate (#7939)
CLINE-84, ENG-1392

Co-authored-by: Max Paulus 🥪 <max@cline.bot>
2025-12-05 10:36:57 -08:00
Alex Ker c1ded819bb new model in static list (#7934) 2025-12-05 09:17:20 -08:00
CandiedUniverse de02befb2f fix(hooks): Doc said the wrong directory for global hooks dir (#7933) 2025-12-05 09:02:54 -08:00
Zhongying Qiao 6617901078 feat: remove mcp marketplace enable setting from cli (#7911)
* feat: remove mcp marketplace enable setting from cli
2025-12-05 08:41:10 -08:00
celestial-vault 31c7176de1 cleanup taskhistory recovery (#7889)
* cleanup recovering by removing unnecessary recursion; rename parameter for reconstructTaskHistory for clarity, and add stdout logging in error blocks

* Don't return empty array on IO error. Instead, continue throwing error because this is indeed an error and not something that can be corrected by data reconciliation.
2025-12-05 10:32:57 -06:00
Bee 3c97c8dc19 dev: add stories for all UI components (#7905)
* dev: add stories for all UI components

* unify styles

* update
2025-12-05 04:03:47 -08:00
Nick Baumann 187e40d2da Redesign model settings page with compact info and Advanced section (#7862)
* Redesign model settings page with compact info and Advanced section

* Fix cache pricing precision to show decimals when needed

* Address PR feedback: fix cache pricing precision, remove duplicate billing link, unify provider routing
2025-12-05 03:26:46 -08:00
Andrei Eternal 8c38b1ccf8 JB Integration Workflow: use pull_request_target to support remote remote PRs (#7917)
* JB Integration Workflow: use pull_request_target to support remote repo PRs

* also sanitize the branch name and title really hard to avoid json injections

* ok lets be extra double paranoid with the sanitization

* ok lets be even more extra safer by also not logging the head_ref

---------

Co-authored-by: Andrei Edell <andrei@nugbase.com>
2025-12-04 21:22:55 -08:00
Toshii 4947a745c2 removing unused legacy context manager (#7924) 2025-12-04 20:54:45 -08:00
Toshii 9e8c6df6b2 context rewriting test cases (#7923)
* alter equality sign

* adding tests for the new file read search
2025-12-04 20:54:36 -08:00
Bee 6586195b2d docs: add contributing guide for model family [CLIENTS-32] (#7916)
* docs: add contributing guide for model family

Add detailed CONTRIBUTING.md documentation for system prompt configuration
and model family management. The guide covers:

- Architecture overview with key concepts (model families, variants, matchers)
- Glossary of terms (native/XML tool calling, API formats, components)
- Step-by-step instructions for creating new model families
- Configuration guides for system prompts and tool calling
- API request/response shape configuration
- Testing procedures and best practices

This documentation helps contributors understand the fallback system design
principle (GENERIC fallback) and provides practical examples for extending
support to new model providers and families.

* fix typo

---------

Co-authored-by: Robin Newhouse <robin@cline.bot>
2025-12-04 14:35:07 -08:00
Toshii 1aa944eff7 fix context rewriting for native tool call format (#7882)
* enable handling of tool_result blocks to fix file read search for context rewriting

* updating loop over inner indices 0-2 inclusive

* spelling
2025-12-04 14:27:14 -08:00
Robin Newhouse 8e7b1c6884 fix(ollama): abort streaming requests when task is cancelled (#7907)
Previously, clicking cancel would break out of the stream loop but
leave the HTTP connection open. Ollama would continue generating in
the background, keeping the GPU busy and blocking subsequent requests
until completion.

Now we call the Ollama SDK's abort() method to immediately close the
connection.

Fixes #7468
2025-12-04 13:56:25 -08:00
Bee ee154826b6 feat: add OpenAI Response API support and Codex model compatibility [CLIENTS-24] (#7912)
* feat: add OpenAI Response API support and Codex model compatibility

- Add ApiFormat enum to proto definitions with OPENAI_RESPONSES format
- Update model info messages to include api_format field across providers
- Refactor OpenAI native handler to conditionally use Response API based on model's api_format
- Add Codex model support in GPT-5 and GPT-5-1 prompt variants with appropriate exclusions
- Remove hardcoded useResponseFormat parameter in favor of model-driven API selection

This enables ChatGPT Codex models to use the Response API format when tools are provided, while maintaining backward compatibility with existing chat completion models.

* add comments

* tabs
2025-12-04 13:23:48 -08:00
Saoud Rizwan 852f307268 Revert "feat(prompt): add command output limiting guidance to capabilities (#…" (#7909)
This reverts commit 7a523fbaf6.
2025-12-04 11:38:10 -08:00
Bee 4e3fe004f4 feat: enable native tool calling for deepseek 3.2 [AI-27] (#7877)
* feat: enable native tool calling for deepseek 3.2

Add isDeepSeek32ModelFamily() function to identify DeepSeek 3.2 models and integrate it into the isNextGenModelFamily() check. This classifies DeepSeek 3.2 as a next-generation model family, enabling native tool calling support.

* typo
2025-12-04 09:59:27 -08:00
Zhongying Qiao 2b63eed85e feat: remove mcp enable setting for individual users (#7879) 2025-12-04 09:36:44 -08:00
Tomás Barreiro 2ffdc50ea1 Prevent simultaneous refreshes when restoring auth info (#7835)
* Prevent multiple simultaneos refreshes when retrieving auth info

* Add changeset

* refactor
2025-12-04 14:45:10 +01:00
celestial-vault 74808431e5 add litellm provider to remote config in the extension (#7775) 2025-12-04 03:01:05 -08:00
Saoud Rizwan 7a523fbaf6 feat(prompt): add command output limiting guidance to capabilities (#7884)
* feat(prompt): add command output limiting guidance to capabilities

Add guidance in the system prompt instructing the model to proactively
limit command output when anticipating large results. Includes examples
like piping to grep/head/tail or using more specific arguments.

Idea by @AraTheBoss

* chore: add changeset

* refactor: move command output limiting guidance to execute_command tool

Move the guidance from capabilities.ts to execute_command.ts where it
belongs. Extract into a shared COMMAND_BEST_PRACTICES constant to avoid
duplication across model variants (GENERIC, NATIVE_GPT_5, NATIVE_NEXT_GEN,
GEMINI_3).
2025-12-03 21:06:07 -08:00
github-actions[bot] c22ea39dc1 v3.40.0 Release Notes (#7865)
* changeset version bump

* Updating CHANGELOG.md format

* Update CHANGELOG.md to reflect recent changes including fixes for highlighted text flashing, terminal command issues, and enhancements for slash command usage and message padding.

* Update CHANGELOG.md

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: github-actions <github-actions@github.com>
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
2025-12-03 19:24:18 -08:00
Saoud Rizwan c9f23076c2 fix: consolidate successive error retry messages in chat UI (#7880)
When API requests fail and auto-retry is enabled, multiple error_retry
messages were shown (e.g., "Attempt 1 of 3", "Attempt 2 of 3", etc.).
This change consolidates them to only show the latest retry message,
reducing visual clutter during retry sequences.
2025-12-03 19:18:17 -08:00
Bee a5f6c1d732 feat: add auto-recovery for corrupted task history state (#7875)
* feat: add auto-recovery for corrupted task history state

Add automatic reconstruction of task history when JSON parsing fails.

Changes:
- Modified `reconstructTaskHistory()` to return reconstruction result or null
- Enhanced `readTaskHistoryFromState()` with automatic corruption recovery
- Added recursive reconstruction attempt with loop prevention flag
- Wrapped JSON parsing in try-catch to handle corruption gracefully

When task history state file is corrupted, the system now automatically
attempts to reconstruct history from existing task folders, providing
better resilience against file corruption issues.

* feat: Add telemetry tracking for extension storage errors

Replace console.error logging with structured telemetry capture for extension storage operations. This change:

- Adds a new EXTENSION_STORAGE_ERROR telemetry event type to track storage-related failures
- Implements captureExtensionStorageError method with error message truncation to prevent excessive data
- Replaces three console.error calls in readTaskHistoryFromState with telemetry events

This improves error monitoring and provides better insights into extension storage failures while maintaining data efficiency through message truncation.

* fix: improve type safety and error handling in task history

Add explicit return type to reconstructTaskHistory() function and refactor error handling in readTaskHistoryFromState() with nested try-catch blocks to better distinguish between file read errors and JSON parse errors. This improves error recovery and makes error tracking more precise through separate telemetry calls.

* add param to reconstructTaskHistory for manually called action

---------

Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
2025-12-03 17:49:28 -08:00
Toshii 3c37a160ac support multi-index search over inner messages to find file mentions (#7850) 2025-12-03 15:27:08 -08:00
Saoud Rizwan 5c3294051f Revert "fix: don't return empty array on parse failure (#7773)" (#7874)
This reverts commit 14ccf33d25.
2025-12-03 14:30:58 -08:00
Tony Loehr 4c2f28f2af docs: remove Advanced Patterns and Testing & Debugging from Hooks documentation (#7869)
- Removed advanced-patterns.mdx and testing-and-debugging.mdx files
- Updated docs.json to remove these pages from navigation
- Updated hooks/index.mdx to remove corresponding Card components
- Simplified Hooks documentation to focus on core concepts: Overview, Hook Reference, and Samples
2025-12-03 12:11:43 -08:00
Ara 6e016298cb chore: bump version to 3.39.2 and update dependencies (#7851)
- Update package version from 3.39.1 to 3.39.2
- Upgrade @changesets/* packages to latest versions
- Update @inquirer/external-editor to 1.0.2
- Upgrade js-yaml from v3 to v4 in @changesets/parse
2025-12-03 11:23:29 -08:00
pashpashpash 0cd7bebfba markdown styling fix (#7840)
* markdown styling fix

* nested ul
2025-12-03 01:23:02 -08:00
Bee 363aac61fb fix: OpenAI Response API message format (#7842)
Fixed the message structure to match the OpenAI Responses API format.

Updated Message ID placement: The message id is stored and set at the message level, not inside the content array.

This fixes an error occuring in the current code when reasoning item is followed by a message text block: 400 Item 'rs_...' of type 'reasoning' was provided without its required following item."
2025-12-02 17:41:19 -08:00
Tony Loehr eeb1cc7da8 added subpages and content to hooks (#7797)
* added subpages and content to hooks

* Update docs/features/hooks/advanced-patterns.mdx

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* Add complete hook type coverage with examples for TaskCancel, TaskComplete, TaskResume, PreCompact, UserPromptSubmit

* Fix hook documentation API mismatches and add TaskComplete

- Add missing TaskComplete hook to reference documentation
- Fix TaskCancel/TaskResume field paths to match protobuf API
- Improve security practices in hook examples
- Add proper error handling and validation

* Update hooks documentation: rename samples, remove PreCompact, improve structure

- Rename 'Real World Examples' to 'Samples' with skill-based organization
- Remove PreCompact references (feature not yet available)
- Update navigation structure in docs.json
- Add multiworkspace mention to Overview
- Create 9 comprehensive examples (beginner/intermediate/advanced)
- Clean up duplicate content and fix cross-references

* Update hooks documentation: Add Windows support

- Remove incorrect warning that hooks don't work on Windows
- Add positive cross-platform support note (Windows, macOS, Linux)
- Clarify that bash examples work with standard shells including Git Bash/WSL on Windows

* fixed hooks overview redirect

* Add UI screenshots to hooks documentation

* hooks in action

* fixed hooks overview and examples

* fixed terminology

* fixed hooks examples

* hooks groupings

* fixed appearance of hook names

* refactor hook docs

---------

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-12-02 17:35:07 -08:00
Sarah Fortune f760f13de5 Don't log otel events to the console because they are really spammy (#7841) 2025-12-02 17:20:52 -08:00
canvrno dd52a4a39c feat: apply_patch auto approve (#7777)
* Added apply_patch to auto approve, strict mode, and minor prompting adjustment

* changeset
2025-12-02 15:36:01 -08:00
Toshii 639edb5db6 correctly handle new and old tool call formats for context rewriting (#7809)
* correctly handle new and old tool call formats

* spelling change
2025-12-02 15:12:05 -08:00
Jack Reinhardt 3eac9b04de fix(bedrock): add sts userAgentAppId (#7719) 2025-12-02 14:40:39 -08:00
Bee 09692d7d3a feat: add mode and token metrics info to storage messages [CLIENTS-26] (#7795)
* feat(storage): add mode and token metrics to storage messages

Add mode (plan/act) tracking to ApiProviderInfo and ClineMessageModelInfo interfaces, ensuring each storage message contains the operational mode used during API requests.

Refactor token metrics tracking by consolidating cache write/read tokens, input/output tokens, and total cost into a centralized taskMetrics object. This enables better tracking and storage of token usage and costs throughout the task lifecycle, including for partial/cancelled streams.

Updated api_req_started and api_req_finished messages to include comprehensive token metrics, allowing for accurate cost reporting even when streams are cancelled or fail mid-execution.

* update unit tests with mode

* store task metrics per assistant turn
2025-12-02 13:52:44 -08:00
Andrei Eternal c81fa0a9d6 set the cli's 'ide version' to just the cli version rather than being blank, to make environment_history work for CLI (#7712)
Co-authored-by: Andrei Edell <andrei@nugbase.com>
2025-12-02 13:21:58 -08:00
Bee 326c9c9f99 feat: set default thinking level for Gemini 3 Pro models (#7831)
- Reorder thinking level checks to prioritize high over low
- Auto-set thinking level to LOW for Gemini 3 Pro models when not specified
- Add clarifying comment for thinking budget usage
- Ensure thinking level is always defined for Gemini 3 models to prevent errors

This change ensures Gemini 3 Pro models always have a thinking level set (required by the API) and removes the thinking budget when a level is specified, as they are mutually exclusive parameters.
2025-12-02 12:54:13 -08:00
celestial-vault a4518b90c2 add atomic file write (#7754)
* add atomic write file using write to temp file + rename to avoid situations where invalid data is written to files due to process interrupt

* adjust concurrency test for windows to expect error

* Add JSON ending to temporary file and don't await unlink
2025-12-02 13:30:53 -06:00
celestial-vault 79f4d938e6 remove unused sentry dependency (#7823) 2025-12-02 13:20:30 -06:00
canvrno 37152329cd v3.39.2 Release Notes (#7829) 2025-12-02 10:44:38 -08:00
Seb Duerr 1332d1d70d feat(cerebras): add X-Cerebras-3rd-Party-Integration header (#7824)
* feat(cerebras): add X-Cerebras-3rd-Party-Integration header

* chore: add changeset
2025-12-02 09:56:41 -08:00
canvrno 6a0d92d683 Skip reasoning_details on microwave model (#7825) 2025-12-02 09:35:30 -08:00
Ara e761a8c252 fix(changesets): remove quotes from claude-dev package name (#7822)
The quotes around the package name "claude-dev" in all changeset files were removed to adhere to the correct YAML format. This ensures proper parsing and consistency across the changeset files.
2025-12-02 07:36:09 -08:00
Ara c26d0a076d v3.39.1 Release Notes (#7818)
* v3.39.1 Release Notes

* v3.39.1 Release Notes
2025-12-02 06:16:43 -08:00
Ara c037619b90 feat: enable ModelInfoView in OpenRouterModelPicker (#7817)
Uncomment the ModelInfoView component to display model information
in the OpenRouter model picker settings panel.
2025-12-02 06:06:54 -08:00
Ara a575a76e8f v3.39.0 Release Notes (#7813)
* v3.39.0 Release Notes

* v3.39.0 Release Notes

* feat: enhance Announcement component with new microwave model and account login functionality

- Updated Announcement component to include a new free microwave model button
- Adjusted active tab logic in OpenRouterModelPicker to default to "free" if a free model is selected

* Add demo link

---------

Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
2025-12-02 05:11:23 -08:00
Dominic Cooney b1d15d4fe7 fix: Standalone, ensure cwd is install dir (#7781)
Our resource loading assumes cwd is the install
dir.
2025-12-02 18:17:58 +09:00
Saoud Rizwan a0708e57ee Move notification toggle to auto-approve menu (#7812)
- Remove "Configure notification settings" link and move the toggle directly into the auto-approve menu
- Remove notification setting from General Settings since it now lives in auto-approve menu
- Remove hover:opacity-80 from icon button variant to prevent dimming on hover
- Make docs link font size inherit and separator line thinner
2025-12-01 22:44:29 -08:00
Ara ab5796fa72 Remove auto approve menu popups (#7806)
* Remove popups from auto approve settings

* feat(ui): add documentation link to auto-approve modal

Add a "Docs" link in the auto-approve modal that directs users to
the auto-approve documentation page on docs.cline.bot.

* Remove popups from auto approve settings

* Remove popups from auto approve settings

* Remove popups from auto approve settings

---------

Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
2025-12-01 22:22:53 -08:00
Saoud Rizwan b15c364a62 feat: add 'Explain Changes' feature for code review (#7765) 2025-12-01 22:02:33 -08:00
Ara 29dcc4e1e1 feat: move stealth/microwave model from recommended to free models section (#7808)
Move the stealth/microwave model entry from the recommendedModels array
to the freeModels array for better categorization of free model options.
2025-12-01 21:54:34 -08:00
Ara 126d066893 Adding Stealth model (#7764)
* Revert "Remove old models (#7118)"

This reverts commit c7c4e43322.

* Adding stealth

* Adding stealth

* Adding stealth

* Adding minor fix

* Update webview-ui/src/components/settings/OpenRouterModelPicker.tsx

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Apply suggestion from @abeatrix

Co-authored-by: Bee <68532117+abeatrix@users.noreply.github.com>

* Update src/core/api/providers/cline.ts

Co-authored-by: Bee <68532117+abeatrix@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Bee <68532117+abeatrix@users.noreply.github.com>
2025-12-01 21:18:43 -08:00
Ara fa3e095a79 Enable NTC by default (#7804)
* Enable NTC by default

* Enable NTC by default

* Enable NTC by default
2025-12-01 20:40:12 -08:00
Sarah Fortune 4033c83b51 Log the name of the telemetry provider(s) enabled in the extension (#7799)
Right now we are logging the provider type by logging the name of the constructor, but in the compiled code this is obfuscated so it is just some random characters.

Add a name property to the telemetry provider interface.
2025-12-01 19:22:43 -08:00
canvrno 0b7ea86e9b Added microwave family system prompt configuration (#7798) 2025-12-01 17:29:27 -08:00
reneehuang1 1d9a0b5986 add enterprise to readme (#7589)
Co-authored-by: Renee Huang <reneehuang@Renees-MacBook-Pro.local>
2025-12-01 16:23:35 -08:00
CandiedUniverse c47ffe2861 fix(hooks): Polish for UserPromptSubmit [ENG-1345] (#7656)
* fix(hooks): Trigger UserPromptSubmit hook when continuing a completed task

* fix(hooks): Make prompt formating consistent for all UserPromptSubmit entrypoints

* fix(hooks): Code reviewing w/ Cline before submitting PR for human review

* fix(hooks): Improve type safety

* fix(hooks): Add unit tests for buildUserFeedbackContent

* fix(hooks): Minor Cline code review changes

* fix(hooks): Fix test assertion technique

* fix(hooks): Simplify PR

* feat(hooks): Consolidate constants to a shared location as per PR feedback
2025-12-01 15:36:07 -08:00
mintlify[bot] e85d918816 Add CLI context window configuration docs (#7796)
* Update docs/cline-cli/overview.mdx

* Update docs/cline-cli/cli-reference.mdx

* Update docs/cline-cli/three-core-flows.mdx

* Update docs/cline-cli/overview.mdx

---------

Co-authored-by: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>
2025-12-01 15:27:55 -08:00
Ara 49be10ead8 fix: move OptionsButtons outside WithCopyButton component (#7783)
Relocate OptionsButtons component to be a sibling of WithCopyButton
rather than a child. This fixes the component hierarchy for followup
and completion_result message types, ensuring proper rendering and
interaction behavior. Also adds QuoteButton support to completion_result.
2025-12-01 15:16:16 -08:00
Ara aa9573fb0a feat: add direct navigation to settings sections (#7770)
Replace delayed scroll-to-settings approach with direct section targeting.
Settings sections can now be opened directly via navigateToSettings(section)
parameter, eliminating the need for setTimeout-based scrolling workarounds.
2025-12-01 15:15:56 -08:00
Nick Baumann b913e47332 feat: add tabbed model picker with Recommended and Free tabs (#7769) 2025-12-01 14:25:27 -08:00
Zhongying Qiao 5be7a1b3cf Add support for Banner dismissal, event logging (#7642)
* feat: add banners ui, dismissal state handling and event log

* feat: add cli as ide type, clean up some code

* feat: wire up controller and UI for banners

* audit every rule check to ensure it is doing correct filtering and working locally

* seperate out frontend code

* clean up

* fix proto file

* fix quality check errors

* fix banner service tests

* feat: use json polling approach for active banners

* fix: build error

* fix ci

* fix quality check

* use BannerService.isInitialized() instead

* do not log error when banner array is empty, only when missing or not defined

* do not hash instance id
2025-12-01 15:32:51 -06:00
Toshii c2e91aa9c9 running context rewriting prior to running auto compact (#7774)
* running context rewriting prior to running auto compact

* use sample timestamp as in getNewContextMessagesAndMetadata

* clean up return var
2025-12-01 12:23:58 -08:00
Bee 68b93fcbea fix(ui): memoize highlighted text [ENG-1355] (#7786)
* fix(ui): memoize highlighted text

Optimize UserMessage and TaskHeader components by using useMemo to cache highlighted text results. This prevents unnecessary recalculations of text highlighting on every render, improving performance when text or editedText props haven't changed.

Changes:
- Add useMemo hook to UserMessage component for highlightText result
- Replace inline highlightText calls with memoized values
- Reduces redundant text processing during re-renders

* add changeset
2025-12-01 10:50:56 -08:00
Bee 0b0e8c36cb fix(ui): Add bottom padding for last message item [ENG-1354] (#7787)
* fix(ui): Add bottom padding for last message item

- Add conditional className to message wrapper div
- Apply `pb-2.5` bottom margin only when message is last in group

* add changeset
2025-12-01 10:29:54 -08:00
Juan Pablo Flores b0bd0e3974 Docs/task history recovery (#7776) 2025-12-01 09:24:40 -08:00
Ara 42b7a1e450 feat(cli): add active task check before entering follow mode (#7745)
* feat(cli): add active task check before entering follow mode

Add validation in FollowConversationUntilCompletion to check if a task
is currently running before entering follow mode. If no active task
exists, display a user-friendly message and exit gracefully instead of
waiting indefinitely.

Also includes minor whitespace formatting cleanup in related functions.

* Fix detached process conditions

* Fix detached process conditions

* Adding stealth
2025-12-01 04:57:22 -08:00
celestial-vault 14ccf33d25 fix: don't return empty array on parse failure (#7773) 2025-11-30 17:13:10 -08:00
Toshii d9a340523c add case for skipping autoCondense in truncation (#7763) 2025-11-30 16:12:27 -08:00
Saoud Rizwan 87b3e79b90 Instruct AI to prefer non-interactive commands (#7762)
Update system prompt to guide AI toward using non-interactive command variants
to avoid interrupting workflow. This includes using flags like --no-pager,
auto-confirming prompts with -y when safe, and providing input via
flags/arguments rather than stdin.
2025-11-30 00:16:18 -08:00
Saoud Rizwan 60f2e85fc7 Add find-pr-reviewers and address-pr-comments workflows (#7761)
* Add find-sme workflow for identifying subject matter experts

* Rename find-sme to find-reviewers

* Remove old find-sme.md file

* Address Copilot PR feedback: fix find syntax and add git config command

* Add address-pr-comments workflow

* Rename find-reviewers to find-pr-reviewers

* Simplify address-pr-comments workflow
2025-11-30 00:16:06 -08:00
Saoud Rizwan 1826d98019 Allow slash commands anywhere in message input (#7760)
* Allow slash commands anywhere in message input

Previously, slash commands could only be typed at the beginning of a
message. This change allows users to type slash commands anywhere in
the message, similar to how @ mentions work.

Changes:
- Update shouldShowSlashCommandsMenu() to show suggestions when slash
  is preceded by whitespace (not just at start)
- Update insertSlashCommand() to find the slash nearest to cursor
- Update extension-side parseSlashCommands() to find commands anywhere
  in tag content using a safer regex that avoids matching URLs/paths
- Update highlight layer to highlight slash commands anywhere
- Only the FIRST slash command per message is processed/highlighted
  to maintain consistency with backend behavior
- Fix backspace deletion to work for slash commands anywhere in text

* Add changeset
2025-11-30 00:07:56 -08:00
Saoud Rizwan af69b30a36 Add sticky user message header for better navigation (#7749)
* Add sticky user message header for better navigation

When users scroll down through a long conversation, a sticky header now appears showing their most recent message that has scrolled out of view. Clicking the header scrolls back to that message.

Key changes:
- New StickyUserMessage component that appears when user messages scroll past viewport
- Track scrolled-past user messages via scroll position detection in useScrollBehavior
- Add data-message-ts attributes to enable message element lookup
- Adjust TaskHeader padding for consistent alignment with sticky header
- Minor styling tweaks to UserMessage and FocusChain for visual consistency

* Fix type error: accept null for lastUserMessage prop

* Replace color-mix() with brightness filter for better compatibility

Use hover:brightness-110 instead of color-mix() for the sticky message
hover effect, as color-mix() may not be supported in all VS Code webview
contexts.

* Address Copilot review feedback for sticky user message

- Remove unused slide-down animation CSS
- Extract magic number 32 to STICKY_HEADER_HEIGHT constant
- Use cn() utility for conditional className in MessagesArea
- Add keyboard accessibility (role, tabIndex, onKeyDown) to StickyUserMessage

* Address additional Copilot review feedback

- Fix virtualized element detection: only consider missing elements as scrolled past
  if we've already found visible elements after them (fixes incorrect sticky header
  appearing when scrolling to top of long conversations)
- Rename truncatedText to messageText for accuracy (truncation happens via CSS)
2025-11-29 02:13:50 -08:00
DL Techy e62fbf6b0c Add shell option for cmd.exe to prevent double quote escaping (#7630)
* fix(terminal): Add shell option for cmd.exe to prevent double quote escaping

Added shell: true option specifically for cmd.exe to prevent double quotes
from being over escaped during command execution. This resolves Windows-specific
issues with terminal command handling while maintaining compatibility with
other shells.

* chore: Add changeset for terminal command execution fix
2025-11-28 13:02:47 -08:00
Saoud Rizwan 64254fc97a Fix API request badge causing text to wrap when hidden (#7739)
The cost badge was using opacity:0 to hide itself when there's no cost,
but still rendered "$0.0000" which took up horizontal space. This caused
the "API Request..." label to wrap to a second line unnecessarily.

Now the badge renders empty content when hidden, taking up no width
while still maintaining its height contribution to the row layout.
2025-11-28 08:05:09 -08:00
Luna c312c4aef6 Asksage usage fetch models (#7329)
* Add flagship models

* Add model fetching

* Add usage handling, tool result handling

* Update AskSageProvider.tsx

* Create eight-pants-explode.md

---------

Co-authored-by: alex-mcgraw-askSage <alex.mcgraw@asksage.ai>
2025-11-27 12:35:00 -06:00
celestial-vault fab49e810b Add fixed header to ClineRulesToggleModal (#7729)
- Add flex-shrink-0 to header section containing tabs and description text
- Keep tabs and description visible when content area scrolls
2025-11-27 12:32:17 -06:00
celestial-vault 2a20523e16 View remote rules and workflows in the editor (#7702)
* allow the user to view remote rules and workflows in the editor by creating a temp file

* add await
2025-11-27 11:37:47 -06:00
celestial-vault 06585821d1 conditionally fetch litellm models based on presence of api key and baseUrl (#7713) 2025-11-27 11:37:13 -06:00
Saoud Rizwan 9e802b11da Revert "Add Claude Code GitHub Workflow (#7717)"
This reverts commit afb77c5a8d.
2025-11-27 01:45:05 -08:00
Saoud Rizwan afb77c5a8d Add Claude Code GitHub Workflow (#7717)
* "Claude PR Assistant workflow"

* "Claude Code Review workflow"
2025-11-26 20:01:50 -08:00
Saoud Rizwan 0a4811222f fix: unblock opening a task when using cline account (#7715) 2025-11-26 18:40:51 -08:00
canvrno b4ce378e4b v3.38.3 Release Notes (#7711)
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-11-26 15:59:16 -08:00
CandiedUniverse 2f60a898af fix(hooks): Fix issue identified by linter in proto file (#7707) 2025-11-26 14:50:12 -08:00
Walter Korman 8ffd82eda3 feat(context): add context window error detection for vercel ai gateway (#7623)
feat(context): add context window error detection for vercel ai gateway #7623
2025-11-26 22:58:57 +01:00
Andrei Eternal 81276fdf85 Add os/cline ver/host info to task metadata & change Task History -> EXPORT to just open the task directory (#7706)
Co-authored-by: Andrei Edell <andrei@nugbase.com>
2025-11-26 13:40:42 -08:00
celestial-vault 164e11aae1 Refresh models in the LiteLLM provider component when the base URL changes (#7705) 2025-11-26 13:03:16 -08:00
Enrico Carlesso 9792f174b1 Adding Grok 4.1 and Grok Code to Cline (#7632) 2025-11-26 12:56:25 -08:00
canvrno a590200c64 Remove native tool calling feature flag (#7704) 2025-11-26 12:41:20 -08:00
Bee 297a45d73a feat(providers): add thinking level config to Vertex and Anthropic model support (#7701)
* feat(providers): add thinking level config to Vertex and Anthropic model support

- Pass thinking level configuration (plan/act mode) to Vertex provider through VertexHandlerOptions interface
- Add support for @-versioned Anthropic model IDs (e.g., claude-haiku-4-5@20251001) in cache control logic

This enables mode-specific thinking level configuration for the Vertex provider by propagating geminiPlanModeThinkingLevel and geminiActModeThinkingLevel settings based on the current mode. Also extends Anthropic model compatibility with newer versioning format.

* reasoning

* sonnet

* yield signature delta
2025-11-26 12:14:19 -08:00
Seb Duerr e84de0ab3c feat: update Cerebras models and speed (#7631) 2025-11-26 11:08:24 -08:00
Ara 515cb81439 fix(terminal): simplify cmd.exe command arguments (#7695)
Remove /s flag and extra quoting from cmd.exe shell arguments.
The previous approach with /s /c and quoted command was causing
issues with proper command execution in Windows cmd.exe.
2025-11-26 11:05:10 -08:00
celestial-vault 550428eabd LiteLLM provider dynamic model fetching (#7679)
* add dynamic model fetching for litellm provider and get rid of manual model config; also implement dynamic modelinfo lookup

* don't clear the models list when a fetch fails
2025-11-26 10:54:51 -08:00
schardosin 22c22a1cfc Fixed SAP AI Core Deployments Mode (#7675)
* fixed sap ai core deployments not working

* isolated chunk to string in a function

* added changeset
2025-11-26 09:26:06 -06:00
Dominic Cooney 8202479cec fix: Add proxy rules, proxy support for McpHub & others (#7659) 2025-11-26 02:06:56 -08:00
Dominic Cooney bcbaa4518d docs: Document proxy settings. (#7637)
* docs: Document proxy settings.

* Update docs/troubleshooting/networking-and-proxies.mdx

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

---------

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-11-26 01:30:28 -08:00
canvrno 9d799643ba npm audit fix docs + webview (#7687) 2025-11-26 00:49:40 -08:00
canvrno 6271c5da37 Remind models of new_task tool parameters when deep_planning is invoked (#7685)
* Remind models of new_task tool parameters when deep_planning is invoked

* cleanup
2025-11-25 21:59:53 -08:00
Auroter 89aeb3db3d feat(telemetry): Add OpenTelemetry metrics infrastructure (#7211)
* feat(telemetry): Add OpenTelemetry metrics infrastructure

Implement OpenTelemetry metrics support (counters, histograms, gauges) while maintaining backward compatibility with PostHog dashboards.

Changes:
- Updated ITelemetryProvider interface with recordCounter, recordHistogram, and recordGauge methods
- Implemented full OpenTelemetry metrics in OpenTelemetryTelemetryProvider with lazy instrument creation
- Added stub implementations in PostHogTelemetryProvider for backward compatibility
- Updated NoOpTelemetryProvider with metric method stubs
- Added comprehensive documentation in METRICS_IMPLEMENTATION_SUMMARY.md

Architecture:
- Dual instrumentation: existing PostHog events remain unchanged
- OpenTelemetry gets proper metrics for quantitative analysis
- Each provider handles metrics appropriately for its platform

Next steps:
- Add helper methods to TelemetryService for recording metrics with standard attributes
- Update high-priority capture methods (tokens, API performance) to call metric recording
- Validate with OpenTelemetry collector setup

* refactor(telemetry): add structured metrics and improve error handling

- Add userId and userEmail tracking to TelemetryService
- Implement helper methods (recordCounter, recordHistogram, recordGauge) with standardized attributes
- Add structured metrics for turns, tokens, costs, cache usage, and API performance
- Remove default case from TelemetryProviderFactory switch to enable exhaustive type checking
- Improve error handling by moving unsupported provider type logging outside switch
- Ensure all metric recordings include standard attributes (userId, email, metadata)

This refactoring enables better observability by recording key metrics (counters, histograms, gauges) across all telemetry providers while maintaining consistent attribute propagation and error isolation.

* fix: add logs back in to no-op provider

* fix: use Logger instead of console

* fix: remove unreachable code

* fix: satisfy compiler for config.type

* fix: remove metrics implementation summary

* chore: update telemetry to include mode in conversation turn events

- Added mode parameter to captureConversationTurnEvent in TelemetryService.
- Updated related telemetry metrics to include mode for better tracking.
- Adjusted tests to verify mode is correctly captured in telemetry events.

* fix: call signatures from merge detritus

* feat(telemetry): add optional description parameter to metric recording methods

Add optional `description` parameter to `recordCounter`, `recordHistogram`,
and `recordGauge` methods across the telemetry service layer. This enables
providers to include descriptive metadata when recording metrics.

Changes:
- Updated ITelemetryProvider interface methods to accept description parameter
- Modified TelemetryService private methods to pass description to providers
- Updated NoOpTelemetryProvider stub implementation
- Enhanced FakeProvider test implementation to capture descriptions
- Updated test assertions to verify description parameter handling

This change maintains backward compatibility as the description parameter
is optional.

* feat(telemetry): update recordGauge method to handle null values for metric retirement

- Modified the `recordGauge` method in `ITelemetryProvider` and its implementations to accept `null` as a valid value, allowing for the retirement of gauge series.
- Updated the `TelemetryService` to ensure proper cleanup of gauge entries when the series ends.
- Enhanced the `FakeProvider` test to validate the new behavior of gauge recording and retirement.
- Adjusted related tests to confirm that previous series are retired correctly when new values are recorded.

This change improves the management of gauge metrics, preventing stale entries and ensuring accurate telemetry data.

* refactor(telemetry): remove user email from telemetry service and related tests

- Removed the user email property from the TelemetryService and its associated methods, streamlining user attribute handling.
- Updated tests to reflect the removal of email, ensuring that metrics and events no longer rely on this attribute.
- Adjusted documentation in ITelemetryProvider to clarify the attributes used in metric recording.

This change enhances data privacy and simplifies the telemetry data model.

* feat(telemetry): enhance task metrics tracking with new counters and histograms

- Introduced new maps to track task turn counts, tool call counts, and error counts.
- Added methods to increment task counters and reset aggregates for better metric management.
- Updated existing telemetry capture methods to utilize the new counters and record histograms for task-related metrics.
- Enhanced tests to validate the new histogram entries for task turns, tool calls, and errors.

This change improves the granularity of telemetry data, allowing for more detailed analysis of task performance and error rates.

* refactor(telemetry): improve token usage handling in TelemetryService

- Updated conditions for recording cache write/read tokens and total cost to check for finite values, ensuring proper handling of undefined or null values.
- Introduced default values for token counts and total cost to prevent potential errors in metric recording.
- Enhanced readability by using descriptive variable names for token values.

This change enhances the robustness of telemetry data collection by ensuring that only valid numeric values are recorded.

* feat(telemetry): centralize metric definitions in TelemetryService

- Introduced a static METRICS object in TelemetryService to define all metric names, improving maintainability and readability.
- Updated existing telemetry recording methods to utilize the new METRICS constants, ensuring consistency across metric names.
- Enhanced tests to validate the use of METRICS constants in assertions for counters and histograms.

This change streamlines metric management and reduces the risk of errors due to hardcoded strings.

* refactor(telemetry): improve gauge observation handling in OpenTelemetryTelemetryProvider

- Replaced direct access to gauge values with a snapshot method to enhance data integrity during observable gauge callbacks.
- Introduced a new `snapshotGaugeSeries` method to encapsulate the logic for retrieving gauge data, improving code readability and maintainability.
- Updated the observable gauge callback to utilize the new snapshot method, ensuring that the latest values are accurately observed.

This change streamlines the process of observing gauge metrics, reducing potential errors and improving the overall telemetry data collection.

* refactor(telemetry): add required parameter to metric recording methods

- Updated `recordCounter`, `recordHistogram`, and `recordGauge` methods across the telemetry service and providers to include an optional `required` parameter, allowing for more flexible metric recording.
- Adjusted implementations in `NoOpTelemetryProvider`, `OpenTelemetryTelemetryProvider`, `PostHogTelemetryProvider`, and `FakeProvider` to handle the new parameter.
- Enhanced tests to validate the behavior of the `required` parameter in metric recording.

This change improves the control over metric recording conditions, enhancing the telemetry data collection process.

* fixed testing system

---------

Co-authored-by: NightTrek <Daniels@dual4t.com>
Co-authored-by: Daniel Steigman <35793213+NightTrek@users.noreply.github.com>
2025-11-25 18:56:30 -08:00
1076 changed files with 434268 additions and 18985 deletions
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Fix: do not retry request automatically on auth failure.
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": minor
---
Add support for sonar and sonar-pro models to SAP AI Core Provider
+7
View File
@@ -0,0 +1,7 @@
---
"claude-dev": patch
---
Add endpoint configuration file support for on-premise deployments
Enterprise customers can now configure custom API endpoints by creating a `~/.cline/endpoints.json` file with custom URLs for `appBaseUrl`, `apiBaseUrl`, and `mcpBaseUrl`. When this file is present, Cline runs in on-premise mode with the custom endpoints.
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Fix task timeline display height.
@@ -0,0 +1,7 @@
---
"claude-dev": patch
---
fix: prevent infinite retry loops when replace_in_file fails repeatedly
Add safeguards to prevent the LLM from getting stuck in infinite retry loops when `replace_in_file` operations fail repeatedly. The system now detects repeated failures and provides better guidance to break out of retry cycles.
@@ -0,0 +1,7 @@
---
"claude-dev": patch
---
fix: skip diff error UI handling during streaming to prevent flickering
Suppress diff view error notifications while content is actively streaming to prevent visual flickering and improve user experience. Error handling is deferred until streaming completes.
+7
View File
@@ -0,0 +1,7 @@
---
"claude-dev": patch
---
fix(extract-text): strip notebook outputs to reduce context size
Strip notebook cell outputs when extracting text content from Jupyter notebooks, significantly reducing the amount of context sent to the LLM while preserving the essential code and markdown content.
+7
View File
@@ -0,0 +1,7 @@
---
"claude-dev": patch
---
fix: throttle diff view updates during streaming
Add throttling to diff view updates during content streaming to reduce UI flickering and improve performance. Updates are now batched at reasonable intervals instead of firing on every token received.
+5
View File
@@ -0,0 +1,5 @@
---
"claude-dev": minor
---
Disable PostHog telemetry, error tracking, and feature flags in self-hosted mode
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Ensure tool arguments are streamed during file operations when native tool calling is enabled.
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Added thinking level setting for Gemini 3.0 Pro
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Feat: add thought signature support for Gemini SDK
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Feat: Enable native tool calling for Baseten and Kimi K2 models
+5
View File
@@ -0,0 +1,5 @@
---
"claude-dev": patch
---
Remove deprecated zai-glm-4.6 model from Cerebras provider
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Replaces generic robot icon with Cline logo across VS Code UI
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": minor
---
Add Kimi K2 Thinking to Baseten Provider
+5
View File
@@ -0,0 +1,5 @@
---
"claude-dev": patch
---
Make Sonnet 4.5 the default Amazon Bedrock model id
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Skip MCP tool with invalid name (e.g. name too long) when native tool calling is enabled.
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Fix Anthropic provider missing signature param when thinking is enabled.
+5
View File
@@ -0,0 +1,5 @@
---
"claude-dev": patch
---
Disable PostHog and build-time OpenTelemetry telemetry in self-hosted/on-premise mode. Enterprise customers running self-hosted deployments will no longer send any telemetry to Cline's collectors. Runtime environment OTEL and remote config OTEL remain available for enterprises to configure their own telemetry collection.
+1
View File
@@ -0,0 +1 @@
../../.clinerules/workflows/hotfix-release.md
+1
View File
@@ -0,0 +1 @@
../../.clinerules/workflows/release.md
+51
View File
@@ -0,0 +1,51 @@
#!/bin/bash
set -euo pipefail
# Only run in Claude Code remote environments
if [ "${CLAUDE_CODE_REMOTE:-}" != "true" ]; then
exit 0
fi
cd "$CLAUDE_PROJECT_DIR"
echo "=== Claude Code for Web Setup ==="
echo ""
# Install latest gh CLI tool
echo "Installing GitHub CLI..."
GH_VERSION=$(curl -s https://api.github.com/repos/cli/cli/releases/latest | grep '"tag_name"' | cut -d'"' -f4 | sed 's/^v//')
curl -sL "https://github.com/cli/cli/releases/download/v${GH_VERSION}/gh_${GH_VERSION}_linux_amd64.tar.gz" -o /tmp/gh.tar.gz
tar -xzf /tmp/gh.tar.gz -C /tmp
sudo mv "/tmp/gh_${GH_VERSION}_linux_amd64/bin/gh" /usr/local/bin/gh
rm -rf /tmp/gh.tar.gz /tmp/gh_${GH_VERSION}_linux_amd64
echo "Installed gh version: $(gh --version | head -1)"
echo ""
# Check if GITHUB_TOKEN is set and configure gh
if [ -n "${GITHUB_TOKEN:-}" ]; then
echo "GITHUB_TOKEN is configured - gh CLI is ready to use"
echo ""
echo "You can use gh commands directly, for example:"
echo " gh issue list --repo cline/cline --limit 5"
echo " gh pr list --repo cline/cline --state open"
echo " gh issue view 123 --repo cline/cline"
echo ""
else
echo "GITHUB_TOKEN is not set - gh CLI will have limited functionality"
echo ""
echo "To enable full GitHub API access:"
echo "1. Create a Fine-grained Personal Access Token at https://github.com/settings/tokens?type=beta"
echo "2. Add it as GITHUB_TOKEN in your Claude Code environment settings"
echo ""
fi
# Install project dependencies
echo "Installing dependencies..."
npm run install:all
# Generate gRPC/protobuf types (required for TypeScript)
echo "Generating proto types..."
npm run protos
echo ""
echo "Session setup complete!"
+14
View File
@@ -0,0 +1,14 @@
{
"hooks": {
"SessionStart": [
{
"hooks": [
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/claude-code-for-web-setup.sh"
}
]
}
]
}
}
+196
View File
@@ -0,0 +1,196 @@
---
name: create-pull-request
description: Create a GitHub pull request following project conventions. Use when the user asks to create a PR, submit changes for review, or open a pull request. Handles commit analysis, branch management, and PR creation using the gh CLI tool.
---
# Create Pull Request
This skill guides you through creating a well-structured GitHub pull request that follows project conventions and best practices.
## Prerequisites Check
Before proceeding, verify the following:
### 1. Check if `gh` CLI is installed
```bash
gh --version
```
If not installed, inform the user:
> The GitHub CLI (`gh`) is required but not installed. Please install it:
> - macOS: `brew install gh`
> - Other: https://cli.github.com/
### 2. Check if authenticated with GitHub
```bash
gh auth status
```
If not authenticated, guide the user to run `gh auth login`.
### 3. Verify clean working directory
```bash
git status
```
If there are uncommitted changes, ask the user whether to:
- Commit them as part of this PR
- Stash them temporarily
- Discard them (with caution)
## Gather Context
### 1. Identify the current branch
```bash
git branch --show-current
```
Ensure you're not on `main` or `master`. If so, ask the user to create or switch to a feature branch.
### 2. Find the base branch
```bash
git remote show origin | grep "HEAD branch"
```
This is typically `main` or `master`.
### 3. Analyze recent commits relevant to this PR
```bash
git log origin/main..HEAD --oneline --no-decorate
```
Review these commits to understand:
- What changes are being introduced
- The scope of the PR (single feature/fix or multiple changes)
- Whether commits should be squashed or reorganized
### 4. Review the diff
```bash
git diff origin/main..HEAD --stat
```
This shows which files changed and helps identify the type of change.
## Information Gathering
Before creating the PR, you need the following information. Check if it can be inferred from:
- Commit messages
- Branch name (e.g., `fix/issue-123`, `feature/new-login`)
- Changed files and their content
If any critical information is missing, use `ask_followup_question` to ask the user:
### Required Information
1. **Related Issue Number**: Look for patterns like `#123`, `fixes #123`, or `closes #123` in commit messages
2. **Description**: What problem does this solve? Why were these changes made?
3. **Type of Change**: Bug fix, new feature, breaking change, refactor, cosmetic, documentation, or workflow
4. **Test Procedure**: How was this tested? What could break?
### Example clarifying question
If the issue number is not found:
> I couldn't find a related issue number in the commit messages or branch name. What GitHub issue does this PR address? (Enter the issue number, e.g., "123" or "N/A" for small fixes)
## Git Best Practices
Before creating the PR, consider these best practices:
### Commit Hygiene
1. **Atomic commits**: Each commit should represent a single logical change
2. **Clear commit messages**: Follow conventional commit format when possible
3. **No merge commits**: Prefer rebasing over merging to keep history clean
### Branch Management
1. **Rebase on latest main** (if needed):
```bash
git fetch origin
git rebase origin/main
```
2. **Squash if appropriate**: If there are many small "WIP" commits, consider interactive rebase:
```bash
git rebase -i origin/main
```
Only suggest this if commits appear messy and the user is comfortable with rebasing.
### Push Changes
Ensure all commits are pushed:
```bash
git push origin HEAD
```
If the branch was rebased, you may need:
```bash
git push origin HEAD --force-with-lease
```
## Create the Pull Request
**IMPORTANT**: Read and use the PR template at `.github/pull_request_template.md`. The PR body format must **strictly match** the template structure. Do not deviate from the template format.
When filling out the template:
- Replace `#XXXX` with the actual issue number, or keep as `#XXXX` if no issue exists (for small fixes)
- Fill in all sections with relevant information gathered from commits and context
- Mark the appropriate "Type of Change" checkbox(es)
- Complete the "Pre-flight Checklist" items that apply
### Create PR with gh CLI
```bash
gh pr create --title "PR_TITLE" --body "PR_BODY" --base main
```
Alternatively, create as draft if the user wants review before marking ready:
```bash
gh pr create --title "PR_TITLE" --body "PR_BODY" --base main --draft
```
## Post-Creation
After creating the PR:
1. **Display the PR URL** so the user can review it
2. **Remind about CI checks**: Tests and linting will run automatically
3. **Suggest next steps**:
- Add reviewers if needed: `gh pr edit --add-reviewer USERNAME`
- Add labels if needed: `gh pr edit --add-label "bug"`
## Error Handling
### Common Issues
1. **No commits ahead of main**: The branch has no changes to submit
- Ask if the user meant to work on a different branch
2. **Branch not pushed**: Remote doesn't have the branch
- Push the branch first: `git push -u origin HEAD`
3. **PR already exists**: A PR for this branch already exists
- Show the existing PR: `gh pr view`
- Ask if they want to update it instead
4. **Merge conflicts**: Branch conflicts with base
- Guide user through resolving conflicts or rebasing
## Summary Checklist
Before finalizing, ensure:
- [ ] `gh` CLI is installed and authenticated
- [ ] Working directory is clean
- [ ] All commits are pushed
- [ ] Branch is up-to-date with base branch
- [ ] Related issue number is identified, or placeholder is used
- [ ] PR description follows the template exactly
- [ ] Appropriate type of change is selected
- [ ] Pre-flight checklist items are addressed
+33
View File
@@ -0,0 +1,33 @@
# CLI Development
The CLI lives in `cli-ts/` and uses React Ink for terminal UI.
- If needed, look at `cli-ts/src/constants/colors.ts` for re-used terminal colors, e.g. `COLORS.primaryBlue` highlight color (selections, spinners, success states).
- Never use `dimColor` with gray (e.g. `<Text color="gray" dimColor>`) - it's too hard to read. Use `color="gray"` for secondary text and normal foreground (no color) for primary text.
- When thinking about how to handle state or messages from core, look at webview for how it communicates with the vs code extension.
- When updating the webview, consider and suggest to the user to update the CLI TUI since we want to provide a similar experience to our terminal users as we do our vs code extension users.
## Adding New API Providers
When adding a new API provider to the extension, you must also update the CLI:
1. **Update `cli-ts/src/components/ModelPicker.tsx`**: Add the provider to the `providerModels` map so `getDefaultModelId()` returns the correct default model. Import the models and default ID from `@shared/api`:
```typescript
import { newProviderDefaultModelId, newProviderModels } from "@/shared/api"
export const providerModels = {
// ...existing providers
"new-provider": { models: newProviderModels, defaultId: newProviderDefaultModelId },
}
```
2. **Use `applyProviderConfig()` for auth flows**: When implementing OAuth or other auth flows for the provider, use the shared utility at `cli-ts/src/utils/provider-config.ts`:
```typescript
import { applyProviderConfig } from "../utils/provider-config"
// After successful auth:
await applyProviderConfig({ providerId: "new-provider", controller })
```
This handles setting provider, default model, API key mapping, state persistence, and rebuilding the API handler.
3. **Provider-specific auth**: If the provider uses OAuth (like `openai-codex`), add handling in `SettingsPanelContent.tsx`'s `handleProviderSelect` callback. See the existing Codex OAuth flow as a reference.
+194
View File
@@ -0,0 +1,194 @@
This file is the secret sauce for working effectively in this codebase. It captures tribal knowledge—the nuanced, non-obvious patterns that make the difference between a quick fix and hours of back-and-forth & human intervention.
**When to add to this file:**
- User had to intervene, correct, or hand-hold
- Multiple back-and-forth attempts were needed to get something working
- You discovered something that required reading many files to understand
- A change touched files you wouldn't have guessed
- Something worked differently than you expected
- User explicitly asks to "add this to CLAUDE.md"
**Proactively suggest additions** when any of the above happen—don't wait to be asked.
**What NOT to add:** Stuff you can figure out from reading a few files, obvious patterns, or standard practices. This file should be high-signal, not comprehensive.
## Miscellaneous
- This is a VS Code extension—check `package.json` for available scripts before trying to verify builds (e.g., `npm run compile`, not `npm run build`).
- When creating PRs, if the change is user-facing and significant enough to warrant a changelog entry, run `npm run changeset` and create a patch changeset. Never create minor or major version bumps. Skip changesets for trivial fixes, internal refactors, or minor UI tweaks that users wouldn't notice.
- When adding new feature flags, see this PR as a reference https://github.com/cline/cline/pull/7566
- Additional instructions about making requests: @.clinerules/network.md
## gRPC/Protobuf Communication
The extension and webview communicate via gRPC-like protocol over VS Code message passing.
**Proto files live in `proto/`** (e.g., `proto/cline/task.proto`, `proto/cline/ui.proto`)
- Each feature domain has its own `.proto` file
- For simple data, use shared types in `proto/cline/common.proto` (`StringRequest`, `Empty`, `Int64Request`)
- For complex data, define custom messages in the feature's `.proto` file
- Naming: Services `PascalCaseService`, RPCs `camelCase`, Messages `PascalCase`
- For streaming responses, use `stream` keyword (see `subscribeToAuthCallback` in `account.proto`)
**Run `npm run protos`** after any proto changes—generates types in:
- `src/shared/proto/` - Shared type definitions
- `src/generated/grpc-js/` - Service implementations
- `src/generated/nice-grpc/` - Promise-based clients
- `src/generated/hosts/` - Generated handlers
**Adding new enum values** (like a new `ClineSay` type) requires updating conversion mappings in `src/shared/proto-conversions/cline-message.ts`
**Adding new RPC methods** requires:
- Handler in `src/core/controller/<domain>/`
- Call from webview via generated client: `UiServiceClient.scrollToSettings(StringRequest.create({ value: "browser" }))`
**Example—the `explain-changes` feature touched:**
- `proto/cline/task.proto` - Added `ExplainChangesRequest` message and `explainChanges` RPC
- `proto/cline/ui.proto` - Added `GENERATE_EXPLANATION = 29` to `ClineSay` enum
- `src/shared/ExtensionMessage.ts` - Added `ClineSayGenerateExplanation` type
- `src/shared/proto-conversions/cline-message.ts` - Added mapping for new say type
- `src/core/controller/task/explainChanges.ts` - Handler implementation
- `webview-ui/src/components/chat/ChatRow.tsx` - UI rendering
## Adding a New API Provider
When adding a new provider (e.g., "openai-codex"), you must update the proto conversion layer in THREE places or the provider will silently reset to Anthropic:
1. `proto/cline/models.proto` - Add to the `ApiProvider` enum (e.g., `OPENAI_CODEX = 40;`)
2. `convertApiProviderToProto()` in `src/shared/proto-conversions/models/api-configuration-conversion.ts` - Add case mapping string to proto enum
3. `convertProtoToApiProvider()` in the same file - Add case mapping proto enum back to string
**Why this matters:** Without these, the provider string hits the `default` case and returns `ANTHROPIC`. The webview, provider list, and handler all work fine, but the state silently resets when it round-trips through proto serialization. No error is thrown.
**Other files to update when adding a provider:**
- `src/shared/api.ts` - Add to `ApiProvider` union type, define models
- `src/shared/providers/providers.json` - Add to provider list for dropdown
- `src/core/api/index.ts` - Register handler in `createHandlerForProvider()`
- `webview-ui/src/components/settings/utils/providerUtils.ts` - Add cases in `getModelsForProvider()` and `normalizeApiConfiguration()`
- `webview-ui/src/utils/validate.ts` - Add validation case
- `webview-ui/src/components/settings/ApiOptions.tsx` - Render provider component
## Responses API Providers (OpenAI Codex, OpenAI Native)
Providers using OpenAI's Responses API require native tool calling. XML tools don't work with the Responses API.
**Symptoms of broken native tool calling:**
- Tools get called multiple times (e.g., `ask_followup_question` asks the same question twice)
- Tool arguments get duplicated or malformed
- The model responds but tools aren't recognized
**Root causes to check:**
1. **Provider missing from `isNextGenModelProvider()`** in `src/utils/model-utils.ts`. The native variant matchers (e.g., `native-gpt-5/config.ts`) call this function. If your provider isn't in the list, the matcher returns false and falls back to XML tools.
2. **Model missing `apiFormat: ApiFormat.OPENAI_RESPONSES`** in its model info (`src/shared/api.ts`). This property signals that the model requires native tool calling. The task runner in `src/core/task/index.ts` checks this and forces `enableNativeToolCalls: true` regardless of user settings.
**When adding a new Responses API provider:**
1. Add provider to `isNextGenModelProvider()` list in `src/utils/model-utils.ts`
2. Set `apiFormat: ApiFormat.OPENAI_RESPONSES` on all models that use the Responses API
3. The variant matcher and task runner will handle the rest automatically
## Adding Tools to System Prompt
This is tricky—multiple prompt variants and configs. **Always search for existing similar tools first and follow their pattern.** Look at the full chain from prompt definition → variant configs → handler → UI before implementing.
1. **Add to `ClineDefaultTool` enum** in `src/shared/tools.ts`
2. **Tool definition** in `src/core/prompts/system-prompt/tools/` (create file like `generate_explanation.ts`)
- Define variants for each `ModelFamily` (generic, next-gen, xs, etc.)
- Export variants array (e.g., `export const my_tool_variants = [GENERIC, NATIVE_NEXT_GEN, XS]`)
- **Fallback behavior**: If a variant isn't defined for a model family, `ClineToolSet.getToolByNameWithFallback()` automatically falls back to GENERIC. So you only need to export `[GENERIC]` unless the tool needs model-specific behavior.
3. **Register in `src/core/prompts/system-prompt/tools/init.ts`** - Import and spread into `allToolVariants`
4. **Add to variant configs** - Each model family has its own config in `src/core/prompts/system-prompt/variants/*/config.ts`. Add your tool's enum to the `.tools()` list:
- `generic/config.ts`, `next-gen/config.ts`, `gpt-5/config.ts`, `native-gpt-5/config.ts`, `native-gpt-5-1/config.ts`, `native-next-gen/config.ts`, `gemini-3/config.ts`, `glm/config.ts`, `hermes/config.ts`, `xs/config.ts`
- **Important**: If you add to a variant's config, make sure the tool spec exports a variant for that ModelFamily (or relies on GENERIC fallback)
5. **Create handler** in `src/core/task/tools/handlers/`
6. **Wire up in `ToolExecutor.ts`** if needed for execution flow
7. **Add to tool parsing** in `src/core/assistant-message/index.ts` if needed
8. **If tool has UI feedback**: add `ClineSay` enum in proto, update `src/shared/ExtensionMessage.ts`, update `src/shared/proto-conversions/cline-message.ts`, update `webview-ui/src/components/chat/ChatRow.tsx`
## Modifying System Prompt
**Read these first:** `src/core/prompts/system-prompt/README.md`, `tools/README.md`, `__tests__/README.md`
System prompt is modular: **components** (reusable sections) + **variants** (model-specific configs) + **templates** (with `{{PLACEHOLDER}}` resolution).
**Key directories:**
- `components/` - Shared sections: `rules.ts`, `capabilities.ts`, `editing_files.ts`, etc.
- `variants/` - Model-specific: `generic/`, `next-gen/`, `xs/`, `gpt-5/`, `gemini-3/`, `hermes/`, `glm/`, etc.
- `templates/` - Template engine and placeholder definitions
**Variant tiers (ask user which to modify):**
- **Next-gen** (Claude 4, GPT-5, Gemini 2.5): `next-gen/`, `native-next-gen/`, `native-gpt-5/`, `native-gpt-5-1/`, `gemini-3/`, `gpt-5/`
- **Standard** (default fallback): `generic/`
- **Local/small models**: `xs/`, `hermes/`, `glm/`
**How overrides work:** Variants can override components via `componentOverrides` in their `config.ts`, or provide a custom template in `template.ts` (e.g., `next-gen/template.ts` exports `rules_template`). If no override, the shared component from `components/` is used.
**Example: Adding a rule to RULES section**
1. Check if variant overrides rules: look for `rules_template` in `variants/*/template.ts` or `componentOverrides.RULES` in `config.ts`
2. If shared: modify `components/rules.ts`
3. If overridden: modify that variant's template
4. XS variant is special—has heavily condensed inline content in `template.ts`
**After any changes, regenerate snapshots:**
```bash
UPDATE_SNAPSHOTS=true npm run test:unit
```
Snapshots live in `__tests__/__snapshots__/`. Tests validate across model families and context variations (browser, MCP, focus chain).
## Modifying Default Slash Commands
Three places need updates:
- `src/core/slash-commands/index.ts` - Command definitions
- `src/core/prompts/commands.ts` - System prompt integration
- `webview-ui/src/utils/slash-commands.ts` - Webview autocomplete
## Adding New Global State Keys
Adding a new key to global state requires updates in multiple places. Missing any step causes silent failures.
Required steps:
1. Type definition in `src/shared/storage/state-keys.ts` - Add to `GlobalState` or `Settings` interface
2. Read from globalState in `src/core/storage/utils/state-helpers.ts`:
- Add `const myKey = context.globalState.get<GlobalStateAndSettings["myKey"]>("myKey")` in `readGlobalStateFromDisk()`
- Add to the return object: `myKey: myKey ?? defaultValue,`
3. StateManager handles read/write via `setGlobalState()`/`getGlobalStateKey()` after initialization
Common mistake: Adding only the return value without the `context.globalState.get()` call. This compiles but the value is always `undefined` on load.
## StateManager Cache vs Direct globalState Access
StateManager uses an in-memory cache populated during `StateManager.initialize(context)` in `common.ts`. For most state, use `controller.stateManager.setGlobalState()`/`getGlobalStateKey()`.
Exception: State needed immediately at extension startup (before cache is ready)
When Window A sets state and immediately opens Window B, the new window's StateManager cache is populated from `context.globalState` during initialization. If you need to read state in Window B right at startup (e.g., in `common.ts` during `initialize()`), read directly from `context.globalState.get()` instead of StateManager's cache.
Example pattern (see `lastShownAnnouncementId` and `worktreeAutoOpenPath`):
```typescript
// Writing (normal pattern)
controller.stateManager.setGlobalState("myKey", value)
// Reading at startup in common.ts (bypass cache)
const value = context.globalState.get<string>("myKey")
```
This is only needed for cross-window state read during the brief startup window before StateManager cache is fully usable. Normal state access after initialization should use StateManager.
## ChatRow Cancelled/Interrupted States
When a ChatRow displays a loading/in-progress state (spinner), you must handle what happens when the task is cancelled. This is non-obvious because cancellation doesn't update the message content—you have to infer it from context.
**The pattern:**
1. A message has a `status` field (e.g., `"generating"`, `"complete"`, `"error"`) stored in `message.text` as JSON
2. When cancelled mid-operation, the status stays `"generating"` forever—no one updates it
3. To detect cancellation, check TWO conditions:
- `!isLast` — if this message is no longer the last message, something else happened after it (interrupted)
- `lastModifiedMessage?.ask === "resume_task" || "resume_completed_task"` — task was just cancelled and is waiting to resume
**Example from `generate_explanation`:**
```tsx
const wasCancelled =
explanationInfo.status === "generating" &&
(!isLast ||
lastModifiedMessage?.ask === "resume_task" ||
lastModifiedMessage?.ask === "resume_completed_task")
const isGenerating = explanationInfo.status === "generating" && !wasCancelled
```
**Why both checks?**
- `!isLast` catches: cancelled → resumed → did other stuff → this old message is stale
- `lastModifiedMessage?.ask === "resume_task"` catches: just cancelled, hasn't resumed yet, this message is still technically "last"
**See also:** `BrowserSessionRow.tsx` uses similar pattern with `isLastApiReqInterrupted` and `isLastMessageResume`.
**Backend side:** When streaming is cancelled, clean up properly (close tabs, clear comments, etc.) by checking `taskState.abort` after the streaming function returns.
+90
View File
@@ -0,0 +1,90 @@
# Networking & Proxy Support
To ensure Cline works correctly in all environments (VSCode, JetBrains, CLI) and with various network configurations (especially corporate proxies), strictly follow these guidelines for all network activity.
In extension code, do NOT use the global `fetch` or a default `axios` instance. (Note, `shared/net.ts` is exempt from these rules because it sets up the fetch wrappers.) In Webview code, you SHOULD use global `fetch`.
Global `fetch` and default `axios` do not automatically pick up proxy configurations in all environments (specifically JetBrains and CLI). You MUST use the provided utilities in `@/shared/net` which handle proxy agent configuration. In the webview, the browser/embedder handles proxies.
## Guidelines
### 1. Using `fetch`
Instead of `fetch(...)`, import the proxy-aware wrapper:
```typescript
import { fetch } from '@/shared/net'
// Usage is identical to global fetch
const response = await fetch('https://api.example.com/data')
```
### 2. Using `axios`
When using `axios`, you must apply the settings from `getAxiosSettings()`:
```typescript
import axios from 'axios'
import { getAxiosSettings } from '@/shared/net'
const response = await axios.get('https://api.example.com/data', {
headers: { 'Authorization': '...' },
...getAxiosSettings() // <--- CRITICAL: Injects the proxy agent if needed
})
```
### 3. Third-Party Clients (OpenAI, Ollama, etc.)
Most API client libraries allow you to customize the `fetch` implementation. You **MUST** pass the proxy-aware `fetch` to these clients.
**Example (OpenAI):**
```typescript
import OpenAI from "openai"
import { fetch } from "@/shared/net"
this.client = new OpenAI({
apiKey: '...',
fetch, // <--- CRITICAL: Pass our fetch wrapper
})
```
### 4. Tests
Use `mockFetchForTesting` to mock the underlying fetch implementation.
**Example (callback):**
```
import { mockFetchForTesting } from "@/shared/net"
...
let mockFetch = ...
mockFetchForTesting(mockFetch, () => {
// This calls mockFetch
fetch('https://foo.example').then(...)
})
// Original fetch is restored immediately when the call returns.
```
**Example (Promise):**
```
import { mockFetchForTesting } from "@/shared/net"
...
let mockFetch = ...
await mockFetchForTesting(mockFetch, async () => {
await ...
// This calls mockFetch
await fetch('https://foo.example')
...
})
// Original fetch is restored when the Promise from the callback settles
```
## Verification
If you are adding a new network call or integration:
1. Check `@/shared/net.ts` is imported.
2. Ensure `fetch` or `getAxiosSettings` is being used.
3. Verify that third-party clients are configured to use the custom fetch.
@@ -0,0 +1,29 @@
# Address PR Comments
Review and address all comments on the current branch's PR.
## Steps
1. Get the current branch name and find the associated PR:
```bash
gh pr view --json number,title,body
```
2. Understand the PR context:
- Get the full diff: `git diff origin/main...HEAD`
- Read the changed files to understand what the PR is doing
- Read related files if needed to understand the broader context
- Understand the intent and spirit of the changes, not just the code
3. Fetch all PR comments:
- Inline comments: `gh api repos/{owner}/{repo}/pulls/{pr_number}/comments`
- General comments: `gh pr view {pr_number} --json comments,reviews`
4. Present a summary of all comments with your recommendation for each (apply, skip, or respond). Ignore bot noise (changeset-bot, CI status, etc.).
5. **Wait for my approval** before proceeding.
6. After approval:
- Apply code changes and commit
- Reply to comments that were addressed or intentionally skipped
- Push commits
@@ -0,0 +1,49 @@
# Find Best Reviewers for Current Branch
Analyze my current branch to find the best people to review my PR based on **domain expertise** and git history.
## Steps
1. Get the current branch name and verify it's not `main`
2. Get the diff between the current branch and `origin/main`:
- Use `git diff origin/main...HEAD --name-only` to get changed files
- Use `git diff origin/main...HEAD` to understand the nature/spirit of the changes
3. **Identify the domain/feature area** being changed:
- Read the diff carefully to understand WHAT is being changed conceptually (e.g., "slash commands", "authentication", "API client", "UI components")
- This semantic understanding is crucial for finding the right reviewers
4. Find domain experts by searching for related files and their contributors:
- Identify all files related to the feature/domain (not just the ones changed)
- Example: if changing slash commands, find ALL slash-command related files across the codebase
- Use `git log --format="%an <%ae>" -- <related-files-pattern>` to find who has expertise in that domain
5. For additional context, also gather:
- `git blame -L <start>,<end> origin/main -- <file-path>` for exact lines changed
- Recent commit activity on related files
6. Score and rank contributors by:
- **Highest weight: Domain expertise** - who has the most commits to files in this feature area (even files not touched by this PR)
- **Medium weight: Direct file expertise** - commits to the specific files being changed
- **Lower weight: Line-level ownership** - authored the exact lines being modified
7. Exclude myself (check against my git config user.email)
8. Present the top 5 reviewers as an ordered list
## Output Format
Output an ordered list:
1. **Name** - Domain expert: 15 commits to slash-command related files, authored core parsing logic
2. **Name** - 8 commits to affected files, recently added the feature being modified
3. ...
## Commands Reference
```bash
git config user.email
git diff origin/main...HEAD --name-only
git diff origin/main...HEAD
# Find related files for a domain (adjust pattern based on what you learn from the diff)
find . -type f \( -name "*slash-command*" -o -name "*SlashCommand*" \) | head -20
# Get contributors for related files
find . -type f \( -name "*slash-command*" -o -name "*SlashCommand*" \) -print0 | xargs -0 git log --format="%an <%ae>" -- | sort | uniq -c | sort -rn
git log --format="%an <%ae>" -- <file> | sort | uniq -c | sort -rn
git blame -L 10,20 origin/main -- <file>
```
Do NOT ask questions - analyze the changes, identify the domain, and output the reviewer list.
+194
View File
@@ -0,0 +1,194 @@
# Hotfix Release
Create a hotfix release by cherry-picking specific commits from main onto the latest release tag.
## Overview
This workflow helps you:
1. Select specific commits from main to include in a hotfix
2. Create a release notes commit on main (changelog + version bump)
3. Cherry-pick everything onto the latest release tag
4. Tag and push the new release
## Step 1: Setup and Gather Information
First, ensure we're on main and up to date:
```bash
git checkout main && git pull origin main
```
Get the latest release tag:
```bash
git tag --sort=-v:refname | head -1
```
## Step 2: Present Commits Since Last Release
Show all commits on main since the last release tag:
```bash
LAST_TAG=$(git tag --sort=-v:refname | head -1)
git log ${LAST_TAG}..HEAD --oneline --format="%h %s (%an)"
```
Also get the commit messages already on the tag (to identify previously cherry-picked commits). Note: Run these as separate commands to avoid shell parsing issues with parentheses in author names:
```bash
LAST_TAG=$(git tag --sort=-v:refname | head -1)
PREV_TAG=$(git tag --sort=-v:refname | head -2 | tail -1)
```
```bash
git log $PREV_TAG..$LAST_TAG --oneline --format="%s"
```
**Present the list** to the user in a numbered format with commit hash, subject, and author. For any commits whose subject line already appears in the tag's history (previously cherry-picked in an earlier hotfix) or are "Release Notes" commits, add `(already in previous hotfix)` or `(release notes - skip)` after them so the user knows to skip those.
Ask which commits to include in the hotfix.
Use the ask_followup_question tool to let the user specify which commits they want (by number or hash).
## Step 3: Analyze Selected Commits
For each selected commit:
1. Get the full commit message: `git show --no-patch --format="%B" <hash>`
2. Get the diff to understand the change: `git show <hash> --stat`
3. Find the associated PR if any: `gh pr list --search "<hash>" --state merged --json number,title --jq '.[0]'`
Build a mental model of what these changes do for the changelog.
## Step 4: Determine New Version Number
Parse the current version from package.json and the last tag:
```bash
LAST_TAG=$(git tag --sort=-v:refname | head -1)
echo "Last release: $LAST_TAG"
cat package.json | grep '"version"'
```
Hotfixes always increment the patch version (e.g., 3.40.0 -> 3.40.1, or 3.40.1 -> 3.40.2).
**Ask the user to confirm the new version number.**
## Step 5: Create Release Notes Commit on Main
On the main branch, create a commit that updates:
1. **CHANGELOG.md** - Add a new section for the hotfix version at the top:
```markdown
## [3.40.1]
- Description of fix 1
- Description of fix 2
```
Write clear, user-friendly descriptions based on your analysis of the commits.
2. **package.json** - Update the version field to the new version
3. **Delete changesets** for the commits being included in the hotfix. This prevents the changeset bot from including duplicate entries in the next regular release.
Find and delete the changeset files associated with the selected commits:
```bash
ls .changeset/
```
Each changeset file in `.changeset/` corresponds to a PR. Read them to identify which ones belong to the commits you're hotfixing, then delete those files.
**Skip running `npm run install:all`** - the automation handles outdated lockfiles.
Commit with message format: `v{VERSION} Release Notes (hotfix)`
In the commit body, mention:
- This is for a hotfix release
- List the cherry-picked commits that will be included
```bash
git add CHANGELOG.md package.json .changeset/
git commit -m "v3.40.1 Release Notes (hotfix)
Hotfix release including:
- <commit1-hash>: <description>
- <commit2-hash>: <description>
"
```
Push to main:
```bash
git push origin main
```
## Step 6: Build the Hotfix on the Tag
Checkout the last release tag (detached HEAD):
```bash
LAST_TAG=$(git tag --sort=-v:refname | head -1)
git checkout $LAST_TAG
```
Cherry-pick the selected commits in order:
```bash
git cherry-pick <commit1-hash>
git cherry-pick <commit2-hash>
# ... etc
```
Finally, cherry-pick the release notes commit you just pushed to main:
```bash
# Get the hash of the release notes commit (should be HEAD of main)
RELEASE_NOTES_COMMIT=$(git rev-parse main)
git cherry-pick $RELEASE_NOTES_COMMIT
```
## Step 7: Tag and Push
After all cherry-picks are applied successfully:
```bash
# Tag the new release
git tag v{VERSION}
# Push the tag to remote
git push origin v{VERSION}
```
## Step 8: Return to Main and Summary
Return to main branch:
```bash
git checkout main
```
**Copy a Slack announcement message to clipboard** with the version and PR links for each included fix:
```
VS Code Hotfix v{VERSION} Published
- Description of fix 1 https://github.com/cline/cline/pull/{PR_NUMBER}
- Description of fix 2 https://github.com/cline/cline/pull/{PR_NUMBER}
```
Present a final summary:
- New version: v{VERSION}
- Tag pushed: yes
- Commits included: (list them)
- Slack message copied to clipboard: yes
Remind the user to:
1. Manually trigger the publish release GitHub Action at: https://github.com/cline/cline/actions/workflows/publish.yml (paste `v{VERSION}` as the tag)
2. Post the Slack message to announce the hotfix
## Important Notes
- This workflow does NOT create a release branch - only tags
- The release notes commit goes to main first, then gets cherry-picked to the tag
- This keeps main's history accurate while allowing hotfix releases from tags
- If cherry-pick conflicts occur, resolve them before continuing
+232
View File
@@ -0,0 +1,232 @@
# Release
Prepare and publish a release from the open changeset PR.
## Overview
This workflow helps you:
1. Find and checkout the open changeset PR
2. Clean up the changelog (fix version format, wordsmith entries)
3. Push changes back to the PR branch
4. Merge with proper commit message format
5. Tag and push the release (after verifying the commit)
6. Trigger the publish workflow
7. Update GitHub release notes
8. Provide final summary with Slack announcement
## Step 1: Find the Changeset PR
Look for the open changeset PR:
```bash
gh pr list --search "Changeset version bump" --state open --json number,title,headRefName,url
```
If no PR is found, inform the user there's no changeset PR ready. They may need to:
- Merge PRs with changesets to main first
- Manually trigger the Changeset Converter workflow at: https://github.com/cline/cline/actions/workflows/changeset-converter.yml
## Step 2: Gather PR Information
Get the PR details:
```bash
PR_NUMBER=<number from step 1>
gh pr view $PR_NUMBER --json body,files,headRefName
```
Checkout the PR branch:
```bash
git fetch origin changeset-release/main
git checkout changeset-release/main
```
If the branch has diverged from remote, reset to the remote version:
```bash
git reset --hard origin/changeset-release/main
```
## Step 3: Analyze the Changes
Read the current CHANGELOG.md to see what the automation generated:
```bash
head -50 CHANGELOG.md
```
Get the version from package.json:
```bash
cat package.json | grep '"version"'
```
**Present to the user:**
- The version number that will be released
- The raw changelog entries from the changeset PR
- Whether this is a patch, minor, or major release
## Step 4: Clean Up the Changelog
The changelog needs these fixes:
1. **Add brackets to version number**: Change `## 3.44.1` to `## [3.44.1]`
2. **No category headers**: Don't use `### Added`, `### Fixed`, etc. Just a flat list of bullet points.
3. **Order entries from most important to least important**:
- Lead with major new features or significant fixes users care about
- End with minor fixes or internal changes
4. **Write user-friendly descriptions**:
- This is for end users, not developers—explain what changed in plain language
- Remove commit hashes from the beginning of lines (the automation adds these)
- Look at the actual commit diffs (`git show <hash>`) and PRs to understand what changed
- Write colorful descriptions that explain the value and impact, not just technical details
- Consolidate related changes into single entries when appropriate
**Ask the user** to review the proposed changelog changes before applying them. Show them:
- Current (raw) changelog section
- Proposed (cleaned) changelog section
Once approved, apply the changes to CHANGELOG.md.
## Step 5: Commit and Push Changes
After making changelog edits:
```bash
git add CHANGELOG.md
git commit -m "Clean up changelog formatting"
git push origin changeset-release/main
```
## Step 6: Merge the PR
**Ask the user to confirm** they're ready to merge.
Merge the PR with the proper commit message format:
```bash
VERSION=<version from package.json>
gh pr merge $PR_NUMBER --squash --subject "v${VERSION} Release Notes" --body ""
```
**If merge is blocked by branch protection:**
- Users with admin privileges can add the `--admin` flag to bypass
- Users without admin privileges need to get the PR approved through normal review first before merging
## Step 7: Tag the Release
After the merge completes, checkout main and pull:
```bash
git checkout main
git pull origin main
```
**IMPORTANT: Verify the latest commit is the release commit before tagging:**
```bash
git log -1 --oneline
```
Confirm the commit message matches `v{VERSION} Release Notes` (e.g., `v3.44.1 Release Notes`). Do NOT blindly tag HEAD without verification.
Once verified, tag and push:
```bash
VERSION=<version>
git tag v${VERSION}
git push origin v${VERSION}
```
## Step 8: Trigger Publish Workflow
**Copy the tag to clipboard** so the user can easily paste it into the GitHub Actions workflow:
```bash
echo -n "v{VERSION}" | pbcopy
```
**Tell the user to trigger the publish workflow:**
1. Go to: https://github.com/cline/cline/actions/workflows/publish.yml
2. Select **"release"** for release-type
3. Paste **`v{VERSION}`** as the tag (already in clipboard)
**Wait for the user** to confirm the publish workflow has completed before proceeding.
## Step 9: Update GitHub Release Notes
Once the user confirms the publish workflow is done, fetch the auto-generated release content:
```bash
VERSION=<version>
gh release view v${VERSION} --json body --jq '.body'
```
The auto-generated release has:
- `## What's Changed` - PR list (we'll replace this with our changelog)
- `## New Contributors` - First-time contributors (keep this if present)
- `**Full Changelog**` - Comparison link (keep this)
Build the new release body:
1. Start with `## What's Changed` header
2. Add our changelog content (from CHANGELOG.md for this version)
3. Keep the `## New Contributors` section if it exists
4. Keep the `**Full Changelog**` link
Update the release:
```bash
gh release edit v${VERSION} --notes "<new body content>"
```
Verify the release was updated:
```bash
gh release view v${VERSION}
```
## Step 10: Final Summary
**Copy a Slack announcement message to clipboard** (include the full changelog, not just highlights):
```bash
echo "VS Code v{VERSION} Released
- Changelog entry 1
- Changelog entry 2
- Changelog entry 3" | pbcopy
```
**Present a final summary:**
- Version released: v{VERSION}
- PR merged: #{PR_NUMBER}
- Tag pushed: v{VERSION}
- Release: https://github.com/cline/cline/releases/tag/v{VERSION}
- Slack message copied to clipboard
**Final reminder:**
Post the Slack message to announce the release
## Handling Edge Cases
### No changesets found
If the changeset PR body shows no changes, inform the user they need to merge PRs with changesets first.
### Merge conflicts
If there are conflicts on the changeset branch, help the user resolve them:
```bash
git fetch origin main
git rebase origin/main
# resolve conflicts
git push origin changeset-release/main --force-with-lease
```
### User wants to add more changes
If the user wants to include additional PRs before releasing:
1. Ask them to merge those PRs to main first
2. The changeset automation will update the PR automatically
3. Re-run this workflow after the PR is updated
+28 -3
View File
@@ -72,12 +72,12 @@ POSTHOG_TELEMETRY_ENABLED=true # Enable PostHog telemetry (default: tru
# Example configurations:
#
# Console debugging (logs only):
# OTEL_TELEMETRY_ENABLED=1
# OTEL_TELEMETRY_ENABLED=true
# OTEL_LOGS_EXPORTER=console
# TEL_DEBUG_DIAGNOSTICS=true
#
# OTLP with gRPC (insecure, for local testing):
# OTEL_TELEMETRY_ENABLED=1
# OTEL_TELEMETRY_ENABLED=true
# OTEL_LOGS_EXPORTER=otlp
# OTEL_EXPORTER_OTLP_PROTOCOL=grpc
# OTEL_EXPORTER_OTLP_ENDPOINT=localhost:4317
@@ -85,12 +85,37 @@ POSTHOG_TELEMETRY_ENABLED=true # Enable PostHog telemetry (default: tru
# OTEL_EXPORTER_OTLP_HEADERS=authorization=Bearer your-token
#
# OTLP with HTTP/JSON (production):
# OTEL_TELEMETRY_ENABLED=1
# OTEL_TELEMETRY_ENABLED=true
# OTEL_LOGS_EXPORTER=otlp
# OTEL_EXPORTER_OTLP_PROTOCOL=http/json
# OTEL_EXPORTER_OTLP_ENDPOINT=https://otel.example.com
# OTEL_EXPORTER_OTLP_HEADERS=authorization=Bearer your-token
# ============================================================================
# OBJECT STORE CONFIGURATION
# ============================================================================
# TO ENABLE S3 OR R2 STORAGE, UNCOMMENT AND FILL IN THE FOLLOWING:
# CLINE_STORAGE_ADAPTER="s3" # Options: "s3" or "r2"
# CLINE_STORAGE_BUCKET="cline"
# CLINE_STORAGE_ACCESS_KEY_ID="key"
# CLINE_STORAGE_SECRET_ACCESS_KEY="secrets"
#
# [OPTIONAL FIELDS FOR R2]
# CLINE_STORAGE_ACCOUNT_ID = "account-id"
# Default R2 endpoint (if not set): "https://<CLINE_STORAGE_ACCOUNT_ID>.r2.cloudflarestorage.com"
# CLINE_STORAGE_ENDPOINT = "http://localhost:8333"
#
# [OPTIONAL FIELDS FOR S3]
# CLINE_STORAGE_REGION = "us-west-1" # AWS Bucket Region (default: "us-east-1")
# Default S3 endpoint (if not set): "https://s3.<CLINE_STORAGE_REGION>.amazonaws.com"
# CLINE_STORAGE_ENDPOINT = "http://localhost:8333"
#
# [OPTIONAL FIELDS FOR ALL STORAGE TYPES]
# CLINE_STORAGE_SYNC_INTERVAL_MS = 30000 # Interval for sync worker in milliseconds
# CLINE_STORAGE_SYNC_MAX_RETRIES = 5 # Max retries for failed sync operations
# CLINE_STORAGE_SYNC_BATCH_SIZE = 10 # Number of files to sync in each batch
# CLINE_STORAGE_SYNC_BACKFILL_ENABLED = false # Enable backfill of existing data on startup
# ============================================================================
# OPTIONAL DEVELOPMENT SETTINGS
# ============================================================================
-1
View File
@@ -1,4 +1,3 @@
/docs/
/.github/ @saoudrizwan @garoth @sjf
/README.md @saoudrizwan @nickbaumann98
/src/core/storage/ @celestial-vault
+1 -1
View File
@@ -58,7 +58,7 @@ jobs:
cache: "npm"
- name: Install Dependencies
run: npm install changeset
run: npm ci
# Check if there are any new changesets to process
- name: Check for changesets
+173
View File
@@ -0,0 +1,173 @@
name: Claude Issue Triage
on:
issues:
types: [opened]
# Manual trigger for backfilling existing issues. Run from terminal:
# gh workflow run claude-issue-triage.yml -f issue_number=1234
# Or batch process:
# gh issue list --state open --limit 10 --json number --jq '.[].number' | while read num; do
# gh workflow run claude-issue-triage.yml -f issue_number=$num
# sleep 60
# done
workflow_dispatch:
inputs:
issue_number:
description: 'Issue number to triage'
required: true
type: string
jobs:
claude-issue-triage:
runs-on: ubuntu-latest
timeout-minutes: 120
# SECURITY: These permissions are intentionally restrictive.
# - contents: read -> Claude can read the codebase but CANNOT write/push any code
# - issues: write -> Claude can comment and add labels (the only write access needed)
# - pull-requests: read -> Claude can view PR context but CANNOT create PRs
# This ensures that even if a malicious user attempts prompt injection via issue content,
# Claude cannot modify repository code, create branches, or open PRs.
permissions:
contents: read
issues: write
pull-requests: read
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Run Issue Response & Triage
id: triage
uses: anthropics/claude-code-action@v1
with:
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
github_token: ${{ secrets.GITHUB_TOKEN }}
allowed_non_write_users: "*"
# Allow all tools - security is enforced by GitHub permissions above (contents: read, issues: write)
claude_args: --model claude-opus-4-5-20251101 --allowedTools "Bash,Read,Write,Edit,Glob,Grep,WebFetch,WebSearch"
prompt: |
You're a GitHub issue first responder for the open source Cline repository.
**Issue:** #${{ github.event.issue.number || inputs.issue_number }}
**Title:** ${{ github.event.issue.title || 'See issue details below' }}
**Author:** @${{ github.event.issue.user.login || 'See issue details below' }}
## Your job
Investigate this issue thoroughly, then post a single helpful comment that helps the user and gives maintainers the context they need.
## Investigation
Start by reading the full issue:
gh issue view ${{ github.event.issue.number || inputs.issue_number }}
### Search for duplicates and related issues
Search thoroughly for existing issues that match this one:
gh issue list --search "<keywords from the issue>" --state all --limit 30
gh issue list --search "<error messages>" --state all --limit 20
gh issue list --search "<affected feature/component>" --state all --limit 20
For each relevant issue you find, read it including its comments:
gh issue view <number> --comments
You're looking for:
- **Duplicates**: Issues describing the same problem. Link to them and explain why you think they're duplicates. If closed, check how they were resolved - the solution might apply here.
- **Related issues**: Similar problems or context that could help. Pull useful information from their comments (workarounds others found, debugging steps that helped, maintainer explanations). Link to them and explain the connection.
If there are closed issues with solutions, surface those solutions prominently - this might immediately solve the user's problem.
### Analyze recent changes (ALWAYS DO THIS)
Many issues are regressions from recent releases. **Always** check what changed recently:
gh release list --limit 10
gh pr list --state merged --limit 50 --json number,title,mergedAt,author,body
Look for PRs merged in the last few weeks that might correlate with the issue. If you find a likely connection:
gh pr view <number>
gh pr diff <number>
git log --since="1 month ago" --oneline -- <relevant paths>
git show <commit>
**Always include your findings in your comment:**
- If you find a regression, call it out explicitly: which PR/commit likely caused it, who authored it, what changed, and suggest a fix direction if you can see one.
- If you don't find anything related, still mention it: "I analyzed recent PRs and releases but didn't find any changes that seem related to this issue."
### Search the codebase
Find the relevant code:
- Use grep/find to locate code related to the issue
- Key areas: `src/api/` (providers/models), `src/core/prompts/` (tools/prompts), platform-specific code for VS Code vs JetBrains
### Find documentation
Cline docs are at **https://docs.cline.bot/** and built with Mintlify from the `docs/` directory.
The URL structure maps directly to the file structure:
- `docs/getting-started/selecting-your-model.mdx` → https://docs.cline.bot/getting-started/selecting-your-model
- `docs/troubleshooting.mdx` → https://docs.cline.bot/troubleshooting
- Headings become anchors: `## Which Model` → `#which-model`
Search the `docs/` directory to find relevant documentation, then construct URLs to link users to:
```bash
ls docs/
grep -r "keyword" docs/ --include="*.mdx" -l
```
### Identify subject matter experts
For issues that clearly need engineering attention:
git log --since="6 months ago" --format="%an" -- <relevant paths> | sort | uniq -c | sort -rn | head -5
Cross-reference with GitHub usernames. Include in your response (@mention, do NOT assign):
| SME | Reason |
|-----|--------|
| @username1 | Authored PR #X which modified this area |
| @username2 | Primary contributor to affected file |
## Weak model detection
Many issues are caused by users running small or non-frontier models that don't tool-call reliably. Signs include:
- Model failing to use tools correctly
- Nonsensical or malformed responses
- User is running a small/local model or older model version
If this looks like a weak model issue, kindly suggest they try reproducing with Claude Sonnet and report back if it persists. Link to https://docs.cline.bot/getting-started/selecting-your-model if helpful. Still label and triage normally.
## Your comment
Write a single comment as a helpful community member. Be conversational, not robotic. Include what's relevant:
- **Helpful response** - Answer their question, suggest a fix, provide a workaround. If you found solutions in related closed issues, surface those prominently.
- **Duplicates and related issues** - Link to any you found and explain why they're duplicates/related. Summarize useful context from their comments.
- **Regression analysis** - If this looks like a regression, explain what change likely caused it, link to the PR/commit, and tag the author.
- **Clarifying questions** - If you need more info, ask specific questions. Don't ask for things already provided.
- **SME table** - Include the table above if this needs engineering attention. Don't tag people for questions with obvious answers or weak-model issues.
- **Context for maintainers** - Relevant code paths, what you found. Keep it concise.
- **Docs links** - If there's relevant documentation, link to it naturally in your response as a recommendation (e.g., "For more details, check out [the Ollama setup guide](url)"). Do NOT add a "Sources" section at the end - integrate doc links into your response where they're helpful.
- **Possible Duplicates section** - ALWAYS include a "Possible Duplicates" section at the end of your comment listing issues that might be duplicates so maintainers can quickly close if appropriate. If none found, say "No obvious duplicates found."
## Labels
First, retrieve all available labels and read their descriptions to understand what each is for:
gh label list --json name,description --limit 100
Then apply the appropriate labels based on your analysis. Only use labels from the list above—do not create new labels.
gh issue edit ${{ github.event.issue.number || inputs.issue_number }} --add-label "label1,label2"
If your regression analysis found a likely culprit (a recent PR/commit that probably caused this issue), add the "Regression" label:
gh issue edit ${{ github.event.issue.number || inputs.issue_number }} --add-label "Regression"
IMPORTANT: After posting your comment, add the "Bot Responded" label to indicate this issue has received an automated response:
gh issue edit ${{ github.event.issue.number || inputs.issue_number }} --add-label "Bot Responded"
## Remember
- **This is a one-time automated response** - you will NOT see their reply or respond again. Never say things like "I can help you", "let me know", "once I have that info", or "I can give you more targeted help" - you won't be there to follow up. If you ask clarifying questions, frame them for the maintainers who will follow up, e.g., "If you can share X, that would help the maintainers diagnose this."
- Don't be formulaic. Respond to what the issue actually needs.
- Surface solutions from past issues - often the fastest path to helping.
- Connecting regressions to specific changes is extremely valuable.
- Link issues with #number so they're clickable.
+272
View File
@@ -0,0 +1,272 @@
name: Claude PR Review
on:
pull_request:
types: [opened, ready_for_review]
# Manual trigger for backfilling existing PRs. Run from terminal:
# gh workflow run claude-pr-review.yml -f pr_number=1234
# Or batch process open PRs:
# gh pr list --state open --limit 10 --json number --jq '.[].number' | while read num; do
# gh workflow run claude-pr-review.yml -f pr_number=$num
# sleep 60
# done
workflow_dispatch:
inputs:
pr_number:
description: 'PR number to review'
required: true
type: string
jobs:
claude-pr-review:
# Runs on PR opened/ready_for_review (skips drafts) or manual trigger for backfilling
if: |
(github.event_name == 'pull_request' && github.event.pull_request.draft == false) ||
github.event_name == 'workflow_dispatch'
runs-on: ubuntu-latest
timeout-minutes: 120
# SECURITY: These permissions are intentionally restrictive.
# - contents: read -> Claude can read the codebase but CANNOT write/push any code
# - pull-requests: write -> Claude can post reviews and inline suggestions
# - issues: read -> Claude can search for related issues
# NOTE: Even with pull-requests: write, Claude CANNOT merge PRs because branch protection
# requires 1 approval from a Code Owner. The GITHUB_TOKEN cannot bypass this.
permissions:
contents: read
pull-requests: write
issues: read
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Get PR number
id: pr
run: |
if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
echo "number=${{ inputs.pr_number }}" >> $GITHUB_OUTPUT
else
echo "number=${{ github.event.pull_request.number }}" >> $GITHUB_OUTPUT
fi
- name: Run PR Review
id: review
uses: anthropics/claude-code-action@v1
with:
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
github_token: ${{ secrets.GITHUB_TOKEN }}
allowed_non_write_users: "*"
claude_args: --model claude-opus-4-5-20251101 --allowedTools "Bash,Read,Write,Edit,Glob,Grep,WebFetch,WebSearch"
prompt: |
You're a GitHub PR reviewer for the open source Cline repository. Your goal is to give the PR author helpful feedback and give maintainers the context they need to review efficiently.
PR: #${{ steps.pr.outputs.number }}
## Gather context
```bash
# Get full PR details
gh pr view ${{ steps.pr.outputs.number }} --json number,title,body,author,createdAt,updatedAt,isDraft,labels,commits,files,additions,deletions,changedFiles,baseRefName,headRefName,mergeable,reviewDecision
# Get the diff
gh pr diff ${{ steps.pr.outputs.number }}
# Check CI status
gh pr checks ${{ steps.pr.outputs.number }}
# Get existing review comments (to understand context and your previous feedback)
gh api repos/${{ github.repository }}/pulls/${{ steps.pr.outputs.number }}/comments --jq '.[] | {user: .user.login, body: .body, path: .path, created_at: .created_at}'
# Get conversation comments
gh pr view ${{ steps.pr.outputs.number }} --comments
```
If this is a re-review (workflow_dispatch event):
Read your previous comments carefully. Understand what you asked for before.
Check if new commits or comments address your previous feedback.
## Check contributing guidelines
Flag (but don't block) if:
- Missing changeset - For user-facing changes, check if there's a `.changeset/` file:
```bash
gh pr diff ${{ steps.pr.outputs.number }} --name-only | grep '.changeset/' || echo "No changeset found"
```
If missing, ask them to run `npm run changeset`
- Missing tests - New features should have tests
## Find related issues and PRs
Search thoroughly for context that might help with the review:
```bash
# Find related issues for context
gh issue list --search "<keywords from the PR>" --state all --limit 30
gh issue list --search "<error messages or feature names>" --state all --limit 20
# Find similar PRs for reference
gh pr list --search "<keywords>" --state all --limit 30
```
For each relevant issue or PR you find, read it including comments:
```bash
gh issue view <number> --comments
gh pr view <number> --comments
```
Look for:
- Open issues this PR might fix that weren't linked in the description
- Similar PRs that went through review - what feedback did they get? What patterns did they follow?
- Context from maintainer discussions that could inform your review
## Find subject matter experts
For files changed in this PR, find who knows the code best:
```bash
# Get files changed
gh pr diff ${{ steps.pr.outputs.number }} --name-only
# For each relevant path, find contributors
git log --since="6 months ago" --format="%an" -- <path> | sort | uniq -c | sort -rn | head -5
```
Cross-reference git authors with GitHub usernames. Include an SME table in your response:
| SME | Reason |
|-----|--------|
| @username1 | Authored PR #X which modified this area |
| @username2 | Primary contributor to affected file (15 commits in 6 months) |
| @username3 | Reviewed similar PR #Y with extensive feedback |
## Deep code review
This is the most important part. Don't just look for syntax issues - understand what the PR is trying to achieve and whether the implementation is the right approach.
Step 1: Understand the intent
Read the PR description and understand what the author is trying to accomplish. What problem are they solving? What feature are they adding?
Step 2: Form your own opinion first
Before analyzing their code, think about how YOU would implement this feature or fix. What files would you touch? What patterns would you follow? What edge cases would you handle?
Step 3: Compare approaches
Now look at their implementation. How does it compare to what you would have done?
- Is their approach better in some ways? Note what they did well.
- Is their approach missing something? Be specific about what and why.
- Are there edge cases they haven't considered?
- Does it follow the patterns established in similar parts of the codebase?
Step 4: Look at the bigger picture
- What other files or systems does this change interact with?
- Could this break anything else?
- Is there additional work needed beyond this PR to complete the feature?
- Does this fit well with the overall architecture?
Step 5: Find reference implementations
Look for similar changes in the codebase:
```bash
git log --oneline --all --grep="<relevant keywords>" | head -20
git log --oneline -- <similar files> | head -20
```
If this is adding a new API provider, look at how other providers are implemented.
If this is adding a new feature, look at how similar features were added.
Note where their implementation aligns with or diverges from established patterns.
Step 6: Standard code review checks
- DRY: Is there duplicated code that could be extracted?
- Error handling: Are errors handled appropriately?
- Security: Any injection risks, credential exposure, unsafe dependencies?
- Performance: Any obvious inefficiencies, memory leaks, N+1 patterns?
- Types: Is TypeScript used correctly? Any unsafe type assertions?
- Naming: Are variables and functions named clearly?
- Comments: Is complex logic explained? Are there outdated comments?
## Inline code suggestions
For specific code improvements, use GitHub's suggestion syntax via `gh api`.
This creates suggestions the author can commit with one click.
Single-line suggestion:
```bash
gh api repos/${{ github.repository }}/pulls/${{ steps.pr.outputs.number }}/reviews \
-X POST \
-f commit_id="$(gh pr view ${{ steps.pr.outputs.number }} --json headRefOid -q .headRefOid)" \
-f event="COMMENT" \
-f body="" \
-F comments='[
{
"path": "src/example.ts",
"line": 42,
"body": "Consider simplifying:\n\n```suggestion\nconst result = items.filter(Boolean);\n```"
}
]'
```
Multi-line suggestion (replacing lines 40-45):
```bash
gh api repos/${{ github.repository }}/pulls/${{ steps.pr.outputs.number }}/reviews \
-X POST \
-f commit_id="$(gh pr view ${{ steps.pr.outputs.number }} --json headRefOid -q .headRefOid)" \
-f event="COMMENT" \
-f body="" \
-F comments='[
{
"path": "src/example.ts",
"start_line": 40,
"line": 45,
"body": "This can be simplified:\n\n```suggestion\nconst simplified = doThing();\n```"
}
]'
```
Use inline suggestions for concrete improvements. Use regular comments for questions or broader feedback.
## Post your review
After your investigation, post a single helpful comment that helps the author and gives maintainers context.
Start with a warm thank you for their contribution. Be conversational, not robotic.
Include what's relevant:
- In-depth explanation of what the PR does - Be comprehensive. A maintainer should be able to read this section and fully understand the author's intent, why they made the changes, how they implemented it, and what files/systems are affected. Don't just summarize - explain.
- Related issues/PRs you found that provide useful context (link to them)
- Your review findings (issues to address, suggestions, etc.)
- Clear next steps for the author
Include a "For Maintainers" section with:
- Anything else useful to help the maintainer resolve this PR
- Related issues/PRs with context on why they're relevant
- Open issues this PR might fix that weren't linked in the description
- Your recommendation: merge as-is, needs changes, needs discussion, close, etc.
- SME table - who should review this and why
For the SME table:
| SME | Reason |
|-----|--------|
| @username | Primary contributor to affected files |
## Update labels
Add appropriate labels based on your analysis:
```bash
gh label list --json name,description --limit 100
gh pr edit ${{ steps.pr.outputs.number }} --add-label "label1,label2"
```
When done, add the reviewed label:
```bash
gh pr edit ${{ steps.pr.outputs.number }} --add-label "Bot Reviewed"
```
## Remember
- This is a one-time automated response - you will NOT see their reply or respond again. Never say things like "let me know if you have questions", "I can help you with", or "feel free to ask" - you won't be there to follow up. Frame any questions for the maintainers who will follow up.
- Be helpful and welcoming - Many contributors are new to the project
- Be specific - Point to exact lines and suggest fixes, don't give vague feedback
- Think deeply - Don't just surface-level review, understand the intent and evaluate the approach
- Use inline suggestions - Make it easy for authors to accept changes
- You're a first-pass reviewer - A human maintainer will do final approval
+312
View File
@@ -0,0 +1,312 @@
name: Cline PR Code Review
on:
pull_request:
types:
[opened, ready_for_review]
# Manual trigger for backfilling existing PRs. Run from terminal:
# gh workflow run cline-pr-review.yml -f pr_number=1234
# Or batch process open PRs:
# gh pr list --state open --limit 10 --json number --jq '.[].number' | while read num; do
# gh workflow run cline-pr-review.yml -f pr_number=$num
# sleep 60
# done
workflow_dispatch:
inputs:
pr_number:
description: "PR number to review"
required: true
type: string
concurrency:
group: pr-review-${{ github.event.pull_request.number || inputs.pr_number }}
cancel-in-progress: true
jobs:
cline-pr-review:
# Runs on PR opened/ready_for_review (skips drafts) or manual trigger for backfilling
if: |
(github.event_name == 'pull_request' && github.event.pull_request.draft == false) ||
github.event_name == 'workflow_dispatch'
runs-on: ubuntu-latest
timeout-minutes: 60
# SECURITY: These permissions are intentionally restrictive.
# - contents: read -> cline can read the codebase but CANNOT write/push any code
# - pull-requests: write -> cline can post reviews and inline suggestions
# - issues: read -> cline can search for related issues
# NOTE: Even with pull-requests: write, cline CANNOT merge PRs because branch protection
# requires 1 approval from a Code Owner. The GITHUB_TOKEN cannot bypass this.
permissions:
contents: read
pull-requests: write
issues: read
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version: 22
cache: "npm"
- name: Install and Verify Cline CLI
run: |
npx cline version # verify installation
- name: Configure Cline with Anthropic
run: |
npx cline auth --provider anthropic \
--apikey "${{ secrets.ANTHROPIC_API_KEY }}" \
--modelid claude-opus-4-5-20251101
- name: Get PR number
id: pr
run: |
if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
echo "number=${{ inputs.pr_number }}" >> $GITHUB_OUTPUT
else
echo "number=${{ github.event.pull_request.number }}" >> $GITHUB_OUTPUT
fi
- name: Review PR with Cline
env:
PR_NUMBER: ${{ steps.pr.outputs.number }}
GITHUB_REPO: ${{ github.repository }}
GH_TOKEN: ${{ github.token }}
CLINE_COMMAND_PERMISSIONS: |
{
"allow": [
"gh pr diff *",
"gh pr view *",
"gh pr checks *",
"gh pr list *",
"gh label list *",
"gh issue list *",
"gh issue view *",
"git log *",
"gh pr comment ${{ steps.pr.outputs.number }} *",
"gh pr edit ${{ steps.pr.outputs.number }} *",
"gh api repos/${{ github.repository }}/pulls/${{ steps.pr.outputs.number }}/comments *",
"gh api repos/${{ github.repository }}/pulls/${{ steps.pr.outputs.number }}/reviews *"
]
}
run: |
npx cline --yolo 'You'\''re a GitHub PR reviewer for the open source Cline repository. Your goal is to give the PR author helpful feedback and give maintainers the context they need to review efficiently.
PR: #'"${PR_NUMBER}"'
## Gather context
```bash
# Get full PR details
gh pr view '"${PR_NUMBER}"' --json number,title,body,author,createdAt,updatedAt,isDraft,labels,commits,files,additions,deletions,changedFiles,baseRefName,headRefName,mergeable,reviewDecision
# Get the diff
gh pr diff '"${PR_NUMBER}"'
# Check CI status
gh pr checks '"${PR_NUMBER}"'
# Get existing review comments (to understand context and your previous feedback)
gh api repos/'"${GITHUB_REPO}"'/pulls/'"${PR_NUMBER}"'/comments --jq '\''.[] | {user: .user.login, body: .body, path: .path, created_at: .created_at}'\''
# Get conversation comments
gh pr view '"${PR_NUMBER}"' --comments
```
If this is a re-review (workflow_dispatch event):
Read your previous comments carefully. Understand what you asked for before.
Check if new commits or comments address your previous feedback.
## Check contributing guidelines
Flag (but don'\''t block) if:
- Missing changeset - For user-facing changes, check if there'\''s a `.changeset/` file:
```bash
gh pr diff '"${PR_NUMBER}"' --name-only | grep '\''.changeset/'\'' || echo '\''No changeset found'\''
```
If missing, ask them to run `npm run changeset`
- Missing tests - New features should have tests
## Find related issues and PRs
Search thoroughly for context that might help with the review:
```bash
# Find related issues for context
gh issue list --search '\''<keywords from the PR>'\'' --state all --limit 30
gh issue list --search '\''<error messages or feature names>'\'' --state all --limit 20
# Find similar PRs for reference
gh pr list --search '\''<keywords>'\'' --state all --limit 30
```
For each relevant issue or PR you find, read it including comments:
```bash
gh issue view <number> --comments
gh pr view <number> --comments
```
Look for:
- Open issues this PR might fix that weren'\''t linked in the description
- Similar PRs that went through review - what feedback did they get? What patterns did they follow?
- Context from maintainer discussions that could inform your review
## Find subject matter experts
For files changed in this PR, find who knows the code best:
```bash
# Get files changed
gh pr diff '"${PR_NUMBER}"' --name-only
# For each relevant path, find contributors
git log --since='\''6 months ago'\'' --format='\''%an'\'' -- <path> | sort | uniq -c | sort -rn | head -5
```
Cross-reference git authors with GitHub usernames. Include an SME table in your response:
| SME | Reason |
|-----|--------|
| @username1 | Authored PR #X which modified this area |
| @username2 | Primary contributor to affected file (15 commits in 6 months) |
| @username3 | Reviewed similar PR #Y with extensive feedback |
## Bash command usage
Don'\''t use operators like `|`, `&&`, or `;` - run each command separately and analyze the output.
When referencing command outputs, quote them properly to avoid formatting issues.
## Deep code review
This is the most important part. Don'\''t just look for syntax issues - understand what the PR is trying to achieve and whether the implementation is the right approach.
Step 1: Understand the intent
Read the PR description and understand what the author is trying to accomplish. What problem are they solving? What feature are they adding?
Step 2: Form your own opinion first
Before analyzing their code, think about how YOU would implement this feature or fix. What files would you touch? What patterns would you follow? What edge cases would you handle?
Step 3: Compare approaches
Now look at their implementation. How does it compare to what you would have done?
- Is their approach better in some ways? Note what they did well.
- Is their approach missing something? Be specific about what and why.
- Are there edge cases they haven'\''t considered?
- Does it follow the patterns established in similar parts of the codebase?
Step 4: Look at the bigger picture
- What other files or systems does this change interact with?
- Could this break anything else?
- Is there additional work needed beyond this PR to complete the feature?
- Does this fit well with the overall architecture?
Step 5: Find reference implementations
Look for similar changes in the codebase:
```bash
git log --oneline --all --grep='\''<relevant keywords>'\'' | head -20
git log --oneline -- <similar files> | head -20
```
If this is adding a new API provider, look at how other providers are implemented.
If this is adding a new feature, look at how similar features were added.
Note where their implementation aligns with or diverges from established patterns.
Step 6: Standard code review checks
- DRY: Is there duplicated code that could be extracted?
- Error handling: Are errors handled appropriately?
- Security: Any injection risks, credential exposure, unsafe dependencies?
- Performance: Any obvious inefficiencies, memory leaks, N+1 patterns?
- Types: Is TypeScript used correctly? Any unsafe type assertions?
- Naming: Are variables and functions named clearly?
- Comments: Is complex logic explained? Are there outdated comments?
## Inline code suggestions
For specific code improvements, use GitHub'\''s suggestion syntax via `gh api`.
This creates suggestions the author can commit with one click.
Single-line suggestion:
```bash
gh api repos/'"${GITHUB_REPO}"'/pulls/'"${PR_NUMBER}"'/reviews \
-X POST \
-f commit_id="$(gh pr view '"${PR_NUMBER}"' --json headRefOid -q .headRefOid)" \
-f event='\''COMMENT'\'' \
-f body='\'''\'' \
-F comments='\''[
{
"path": "src/example.ts",
"line": 42,
"body": "Consider simplifying:\n\n```suggestion\nconst result = items.filter(Boolean);\n```"
}
]'\''
```
Multi-line suggestion (replacing lines 40-45):
```bash
gh api repos/'"${GITHUB_REPO}"'/pulls/'"${PR_NUMBER}"'/reviews \
-X POST \
-f commit_id="$(gh pr view '"${PR_NUMBER}"' --json headRefOid -q .headRefOid)" \
-f event='\''COMMENT'\'' \
-f body='\'''\'' \
-F comments='\''[
{
"path": "src/example.ts",
"start_line": 40,
"line": 45,
"body": "This can be simplified:\n\n```suggestion\nconst simplified = doThing();\n```"
}
]'\''
```
Use inline suggestions for concrete improvements. Use regular comments for questions or broader feedback.
## Post your review
After your investigation, post a single helpful comment that helps the author and gives maintainers context.
Start with a warm thank you for their contribution. Be conversational, not robotic.
Include what'\''s relevant:
- In-depth explanation of what the PR does - Be comprehensive. A maintainer should be able to read this section and fully understand the author'\''s intent, why they made the changes, how they implemented it, and what files/systems are affected. Don'\''t just summarize - explain.
- Related issues/PRs you found that provide useful context (link to them)
- Your review findings (issues to address, suggestions, etc.)
- Clear next steps for the author
Include a '\''For Maintainers'\'' section with:
- Anything else useful to help the maintainer resolve this PR
- Related issues/PRs with context on why they'\''re relevant
- Open issues this PR might fix that weren'\''t linked in the description
- Your recommendation: merge as-is, needs changes, needs discussion, close, etc.
- SME table - who should review this and why
For the SME table:
| SME | Reason |
|-----|--------|
| @username | Primary contributor to affected files |
## Update labels
Add appropriate labels based on your analysis:
```bash
gh label list --json name,description --limit 100
gh pr edit '"${PR_NUMBER}"' --add-label '\''label1,label2'\''
```
When done, add the reviewed label:
```bash
gh pr edit '"${PR_NUMBER}"' --add-label '\''Bot Reviewed'\''
```
## Remember
- This is a one-time automated response - you will NOT see their reply or respond again. Never say things like '\''let me know if you have questions'\'', '\''I can help you with'\'', or '\''feel free to ask'\'' - you won'\''t be there to follow up. Frame any questions for the maintainers who will follow up.
- Be helpful and welcoming - Many contributors are new to the project
- Be specific - Point to exact lines and suggest fixes, don'\''t give vague feedback
- Think deeply - Don'\''t just surface-level review, understand the intent and evaluate the approach
- Use inline suggestions - Make it easy for authors to accept changes
- You'\''re a first-pass reviewer - A human maintainer will do final approval'
+112
View File
@@ -0,0 +1,112 @@
name: Publish NPM Release
on:
workflow_dispatch:
inputs:
confirm_publish:
description: 'Type "publish" to confirm you want to publish to NPM'
required: true
type: string
permissions:
contents: read
checks: write # Required by test workflow
pull-requests: write # Required by test workflow
jobs:
test:
uses: ./.github/workflows/test.yml
publish-npm-release:
needs: test
name: Publish Cline CLI to NPM
if: github.repository == 'cline/cline' && github.ref == 'refs/heads/main' && github.event.inputs.confirm_publish == 'publish'
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version: '20.x'
registry-url: 'https://registry.npmjs.org'
# Cache root dependencies
- name: Cache root dependencies
uses: actions/cache@v4
id: root-cache
with:
path: node_modules
key: ${{ runner.os }}-npm-${{ hashFiles('package-lock.json') }}
# Cache cli-ts dependencies
- name: Cache cli-ts dependencies
uses: actions/cache@v4
id: cli-ts-cache
with:
path: cli-ts/node_modules
key: ${{ runner.os }}-npm-cli-ts-${{ hashFiles('cli-ts/package-lock.json') }}
- name: Install root dependencies
if: steps.root-cache.outputs.cache-hit != 'true'
run: npm ci --include=optional
- name: Install cli-ts dependencies
if: steps.cli-ts-cache.outputs.cache-hit != 'true'
run: cd cli-ts && npm ci
- name: Generate Protos
run: npm run protos
- name: Read release version
id: version
run: |
# Read version from cli-ts/package.json
VERSION=$(node -p "require('./cli-ts/package.json').version")
echo "Release version: $VERSION"
echo "version=$VERSION" >> $GITHUB_OUTPUT
- name: Clean previous builds
run: rm -rf dist-standalone
- name: Build and package CLI
env:
TELEMETRY_SERVICE_API_KEY: ${{ secrets.TELEMETRY_SERVICE_API_KEY }}
ERROR_SERVICE_API_KEY: ${{ secrets.ERROR_SERVICE_API_KEY }}
CLINE_ENVIRONMENT: production
OTEL_TELEMETRY_ENABLED: "1"
OTEL_METRICS_EXPORTER: otlp
OTEL_LOGS_EXPORTER: otlp
OTEL_EXPORTER_OTLP_PROTOCOL: ${{ secrets.OTEL_EXPORTER_OTLP_PROTOCOL }}
OTEL_EXPORTER_OTLP_ENDPOINT: ${{ secrets.OTEL_EXPORTER_OTLP_ENDPOINT }}
OTEL_EXPORTER_OTLP_HEADERS: ${{ secrets.OTEL_EXPORTER_OTLP_HEADERS }}
POSTHOG_TELEMETRY_ENABLED: "true"
run: node scripts/package-npm.mjs
- name: Verify build output
run: |
echo "Checking dist-standalone directory..."
ls -la dist-standalone/
echo "Checking dist-standalone/dist..."
ls -la dist-standalone/dist/
echo "Checking package.json in dist-standalone..."
cat dist-standalone/package.json
- name: Publish to NPM with latest tag
env:
NODE_AUTH_TOKEN: ${{ secrets.NPM_RELEASE_TOKEN }}
run: |
echo "Publishing version ${{ steps.version.outputs.version }} to NPM with tag 'latest'..."
cd dist-standalone
npm publish --tag latest --access public
- name: Summary
run: |
echo "✅ Successfully published cline@${{ steps.version.outputs.version }} to NPM with tag 'latest'"
echo ""
echo "📦 Install with: npm install -g cline"
echo "🔗 NPM: https://www.npmjs.com/package/cline/v/${{ steps.version.outputs.version }}"
+152
View File
@@ -0,0 +1,152 @@
name: Publish NPM Nightly
on:
schedule:
- cron: '0 12 * * *' # 4 AM PST (UTC-8) = 12 UTC
workflow_dispatch:
permissions:
contents: read
checks: write # Required by test workflow
pull-requests: write # Required by test workflow
jobs:
test:
uses: ./.github/workflows/test.yml
publish-npm-nightly:
needs: test
name: Publish Cline CLI (Nightly) to NPM
if: github.repository == 'cline/cline' && github.ref == 'refs/heads/main'
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Check for recent commits
id: check_commits
run: |
if [ $(git rev-list --count HEAD --since="24 hours ago") -eq 0 ]; then
echo "No commits in last 24 hours, skipping publish"
echo "skip=true" >> $GITHUB_OUTPUT
else
echo "Found recent commits, proceeding with publish"
echo "skip=false" >> $GITHUB_OUTPUT
fi
- name: Setup Node.js
if: steps.check_commits.outputs.skip != 'true'
uses: actions/setup-node@v4
with:
node-version: '20.x'
registry-url: 'https://registry.npmjs.org'
# Cache root dependencies
- name: Cache root dependencies
if: steps.check_commits.outputs.skip != 'true'
uses: actions/cache@v4
id: root-cache
with:
path: node_modules
key: ${{ runner.os }}-npm-${{ hashFiles('package-lock.json') }}
# Cache cli-ts dependencies
- name: Cache cli-ts dependencies
if: steps.check_commits.outputs.skip != 'true'
uses: actions/cache@v4
id: cli-ts-cache
with:
path: cli-ts/node_modules
key: ${{ runner.os }}-npm-cli-ts-${{ hashFiles('cli-ts/package-lock.json') }}
- name: Install root dependencies
if: steps.check_commits.outputs.skip != 'true' && steps.root-cache.outputs.cache-hit != 'true'
run: npm ci --include=optional
- name: Install cli-ts dependencies
if: steps.check_commits.outputs.skip != 'true' && steps.cli-ts-cache.outputs.cache-hit != 'true'
run: cd cli-ts && npm ci
- name: Generate Protos
if: steps.check_commits.outputs.skip != 'true'
run: npm run protos
- name: Generate nightly version with timestamp
if: steps.check_commits.outputs.skip != 'true'
id: version
run: |
# Read base version from cli-ts/package.json (e.g., "2.0.0")
BASE_VERSION=$(node -p "require('./cli-ts/package.json').version")
# Generate timestamp (Unix epoch seconds)
TIMESTAMP=$(date +%s)
# Create unique nightly version: 2.0.0-nightly.1736365200
VERSION="${BASE_VERSION}-nightly.${TIMESTAMP}"
echo "Base version: $BASE_VERSION"
echo "Generated nightly version: $VERSION"
echo "version=$VERSION" >> $GITHUB_OUTPUT
- name: Update cli-ts/package.json with nightly version
if: steps.check_commits.outputs.skip != 'true'
run: |
# Update version with timestamp-based nightly version
node -e "
const fs = require('fs');
const pkg = JSON.parse(fs.readFileSync('cli-ts/package.json', 'utf8'));
pkg.version = '${{ steps.version.outputs.version }}';
fs.writeFileSync('cli-ts/package.json', JSON.stringify(pkg, null, '\t'));
"
echo "Using version ${{ steps.version.outputs.version }} for build"
cat cli-ts/package.json | grep '"version"'
- name: Clean previous builds
if: steps.check_commits.outputs.skip != 'true'
run: rm -rf dist-standalone
- name: Build and package CLI
if: steps.check_commits.outputs.skip != 'true'
env:
TELEMETRY_SERVICE_API_KEY: ${{ secrets.TELEMETRY_SERVICE_API_KEY }}
ERROR_SERVICE_API_KEY: ${{ secrets.ERROR_SERVICE_API_KEY }}
CLINE_ENVIRONMENT: production
OTEL_TELEMETRY_ENABLED: "1"
OTEL_METRICS_EXPORTER: otlp
OTEL_LOGS_EXPORTER: otlp
OTEL_EXPORTER_OTLP_PROTOCOL: ${{ secrets.OTEL_EXPORTER_OTLP_PROTOCOL }}
OTEL_EXPORTER_OTLP_ENDPOINT: ${{ secrets.OTEL_EXPORTER_OTLP_ENDPOINT }}
OTEL_EXPORTER_OTLP_HEADERS: ${{ secrets.OTEL_EXPORTER_OTLP_HEADERS }}
POSTHOG_TELEMETRY_ENABLED: "true"
run: node scripts/package-npm.mjs
- name: Verify build output
if: steps.check_commits.outputs.skip != 'true'
run: |
echo "Checking dist-standalone directory..."
ls -la dist-standalone/
echo "Checking dist-standalone/dist..."
ls -la dist-standalone/dist/
echo "Checking package.json in dist-standalone..."
cat dist-standalone/package.json
- name: Publish to NPM with nightly tag
if: steps.check_commits.outputs.skip != 'true'
env:
NODE_AUTH_TOKEN: ${{ secrets.NPM_RELEASE_TOKEN }}
run: |
echo "Publishing version ${{ steps.version.outputs.version }} to NPM with tag 'nightly'..."
cd dist-standalone
npm publish --tag nightly --access public
- name: Summary
if: steps.check_commits.outputs.skip != 'true'
run: |
echo "✅ Successfully published cline@${{ steps.version.outputs.version }} to NPM with tag 'nightly'"
echo ""
echo "📦 Install with: npm install -g cline@nightly"
echo "🔗 NPM: https://www.npmjs.com/package/cline/v/${{ steps.version.outputs.version }}"
+2 -2
View File
@@ -74,8 +74,8 @@ jobs:
CLINE_ENVIRONMENT: production
# OpenTelemetry production defaults (can be overridden at runtime)
OTEL_TELEMETRY_ENABLED: ${{ secrets.OTEL_TELEMETRY_ENABLED }}
OTEL_LOGS_EXPORTER: console,otlp
OTEL_METRICS_EXPORTER: console,otlp
OTEL_LOGS_EXPORTER: otlp
OTEL_METRICS_EXPORTER: otlp
OTEL_EXPORTER_OTLP_PROTOCOL: ${{ secrets.OTEL_EXPORTER_OTLP_PROTOCOL }}
OTEL_EXPORTER_OTLP_ENDPOINT: ${{ secrets.OTEL_EXPORTER_OTLP_ENDPOINT }}
OTEL_EXPORTER_OTLP_HEADERS: ${{ secrets.OTEL_EXPORTER_OTLP_HEADERS }}
+23 -12
View File
@@ -36,6 +36,8 @@ jobs:
- uses: actions/checkout@v4
with:
ref: ${{ github.event.inputs.tag }}
fetch-depth: 0
fetch-tags: true
- name: Setup Node.js
uses: actions/setup-node@v4
@@ -99,8 +101,8 @@ jobs:
ERROR_SERVICE_API_KEY: ${{ secrets.ERROR_SERVICE_API_KEY }}
# OpenTelemetry production defaults (can be overridden at runtime)
OTEL_TELEMETRY_ENABLED: ${{ secrets.OTEL_TELEMETRY_ENABLED }}
OTEL_LOGS_EXPORTER: console,otlp
OTEL_METRICS_EXPORTER: console,otlp
OTEL_LOGS_EXPORTER: otlp
OTEL_METRICS_EXPORTER: otlp
OTEL_EXPORTER_OTLP_PROTOCOL: ${{ secrets.OTEL_EXPORTER_OTLP_PROTOCOL }}
OTEL_EXPORTER_OTLP_ENDPOINT: ${{ secrets.OTEL_EXPORTER_OTLP_ENDPOINT }}
OTEL_EXPORTER_OTLP_HEADERS: ${{ secrets.OTEL_EXPORTER_OTLP_HEADERS }}
@@ -116,22 +118,31 @@ jobs:
echo "Successfully published release version ${{ steps.get_version.outputs.version }} to VS Code Marketplace and Open VSX Registry"
fi
# - name: Get Changelog Entry
# id: changelog
# uses: mindsers/changelog-reader-action@v2
# with:
# # This expects a standard Keep a Changelog format
# # "latest" means it will read whichever is the most recent version
# # set in "## [1.2.3] - 2025-01-28" style
# version: latest
- name: Get Previous Tag
id: prev_tag
run: |
CURRENT_TAG="${{ steps.validate_tag.outputs.tag }}"
PREV_TAG=$(git describe --tags --abbrev=0 "$CURRENT_TAG^" 2>/dev/null || echo "")
echo "prev_tag=$PREV_TAG" >> $GITHUB_OUTPUT
- name: Get Changelog Entry
id: changelog
run: |
# Get content between first ## [ and second ## [
CONTENT=$(awk '/^## \[/{if(found) exit; found=1; next} found{print}' CHANGELOG.md)
echo "content<<EOF" >> $GITHUB_OUTPUT
echo "$CONTENT" >> $GITHUB_OUTPUT
echo "EOF" >> $GITHUB_OUTPUT
- name: Create GitHub Release
uses: softprops/action-gh-release@v1
with:
tag_name: ${{ steps.validate_tag.outputs.tag }}
files: "*.vsix"
# body: ${{ steps.changelog.outputs.content }}
generate_release_notes: true
body: |
${{ steps.changelog.outputs.content }}
**Full Changelog**: https://github.com/${{ github.repository }}/compare/${{ steps.prev_tag.outputs.prev_tag }}...${{ steps.validate_tag.outputs.tag }}
prerelease: ${{ github.event.inputs.release-type == 'pre-release' }}
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+3 -12
View File
@@ -187,20 +187,11 @@ jobs:
if: steps.webview-cache.outputs.cache-hit != 'true'
run: cd webview-ui && npm ci
- name: Setup Go
uses: actions/setup-go@v5
with:
go-version: '1.24'
cache-dependency-path: cli/go.sum
- name: Build CLI binaries
run: npm run compile-cli-all-platforms
- name: Download ripgrep binaries
run: npm run download-ripgrep
- name: Compile NPM package
run: npm run compile-standalone-npm
- name: Compile Standalone
run: npm run compile-standalone
- name: Install testing platform dependencies
if: steps.testing-platform-cache.outputs.cache-hit != 'true'
@@ -213,7 +204,7 @@ jobs:
# This prevents the job from showing as failed and avoids distracting developers
# until the integration tests are ready to be enforced.
run: |
npm run test:tp-orchestrator -- tests/specs/ --count=1 --coverage || true
npm run test:tp-orchestrator -- tests/specs/ --count=1 --coverage
- name: Save Coverage Reports
uses: actions/upload-artifact@v4
+55 -11
View File
@@ -1,17 +1,26 @@
name: Trigger Jetbrains Plugin <-> Cline Tests
on:
pull_request:
types: [opened, synchronize, reopened]
pull_request_target:
types: [opened, reopened]
issue_comment:
types: [created]
permissions:
contents: read
pull-requests: read
concurrency:
group: jetbrains-trigger-${{ github.event.number }}
group: jetbrains-trigger-${{ github.event.pull_request.number || github.event.issue.number }}
cancel-in-progress: true
jobs:
trigger-integration-test:
name: Run Tests
runs-on: ubuntu-latest
# Run on PR open/reopen, or when someone comments /test-jetbrains on a PR
if: |
github.event_name == 'pull_request_target' ||
(github.event_name == 'issue_comment' &&
github.event.issue.pull_request &&
contains(github.event.comment.body, '/test-jetbrains'))
steps:
- name: Generate GitHub App Token
id: app-token
@@ -22,7 +31,39 @@ jobs:
owner: cline
repositories: intellij-plugin
- name: Get PR details (for issue_comment trigger)
id: pr-details
if: github.event_name == 'issue_comment'
env:
GH_TOKEN: ${{ github.token }}
run: |
PR_DATA=$(gh api repos/${{ github.repository }}/pulls/${{ github.event.issue.number }})
echo "head_ref=$(echo "$PR_DATA" | jq -r '.head.ref')" >> $GITHUB_OUTPUT
echo "head_sha=$(echo "$PR_DATA" | jq -r '.head.sha')" >> $GITHUB_OUTPUT
echo "title=$(echo "$PR_DATA" | jq -r '.title')" >> $GITHUB_OUTPUT
echo "html_url=$(echo "$PR_DATA" | jq -r '.html_url')" >> $GITHUB_OUTPUT
- name: Sanitize untrusted inputs
id: sanitize
env:
RAW_BRANCH_NAME: ${{ github.event_name == 'pull_request_target' && github.head_ref || steps.pr-details.outputs.head_ref }}
RAW_PR_TITLE: ${{ github.event_name == 'pull_request_target' && github.event.pull_request.title || steps.pr-details.outputs.title }}
run: |
# Sanitize branch name for JSON
BRANCH_NAME_JSON=$(jq -n --arg b "$RAW_BRANCH_NAME" '$b')
echo "branch_name=$BRANCH_NAME_JSON" >> $GITHUB_OUTPUT
# Sanitize PR title for JSON
PR_TITLE_JSON=$(jq -n --arg t "$RAW_PR_TITLE" '$t')
echo "pr_title=$PR_TITLE_JSON" >> $GITHUB_OUTPUT
- name: Trigger IntelliJ Plugin Integration Test
env:
BRANCH_NAME: ${{ steps.sanitize.outputs.branch_name }}
PR_TITLE: ${{ steps.sanitize.outputs.pr_title }}
PR_NUMBER: ${{ github.event.pull_request.number || github.event.issue.number }}
PR_SHA: ${{ github.event_name == 'pull_request_target' && github.event.pull_request.head.sha || steps.pr-details.outputs.head_sha }}
PR_URL: ${{ github.event_name == 'pull_request_target' && github.event.pull_request.html_url || steps.pr-details.outputs.html_url }}
run: |
curl -X POST \
-H "Authorization: Bearer ${{ steps.app-token.outputs.token }}" \
@@ -34,20 +75,23 @@ jobs:
{
"event_type": "cline-pr-check",
"client_payload": {
"pr_number": "${{ github.event.number }}",
"branch_name": "${{ github.head_ref }}",
"pr_number": "$PR_NUMBER",
"branch_name": $BRANCH_NAME,
"action": "${{ github.event.action }}",
"sha": "${{ github.event.pull_request.head.sha }}",
"pr_title": ${{ toJSON(github.event.pull_request.title) }},
"pr_url": "${{ github.event.pull_request.html_url }}"
"sha": "$PR_SHA",
"pr_title": $PR_TITLE,
"pr_url": "$PR_URL"
}
}
EOF
- name: Log trigger details
env:
PR_NUMBER: ${{ github.event.pull_request.number || github.event.issue.number }}
PR_SHA: ${{ github.event_name == 'pull_request_target' && github.event.pull_request.head.sha || steps.pr-details.outputs.head_sha }}
run: |
echo "Triggered IntelliJ Plugin integration test for:"
echo " PR #${{ github.event.number }}: ${{ github.event.pull_request.title }}"
echo " Branch: ${{ github.head_ref }}"
echo " PR #$PR_NUMBER"
echo " Trigger: ${{ github.event_name }}"
echo " Action: ${{ github.event.action }}"
echo " SHA: ${{ github.event.pull_request.head.sha }}"
echo " SHA: $PR_SHA"
+12
View File
@@ -8,12 +8,14 @@ tmp
.DS_Store
.idea
.husky/_/
pnpm-lock.yaml
.clineignore
.venv
.actrc
CLAUDE.local.md
webview-ui/src/**/*.js
webview-ui/src/**/*.js.map
@@ -27,6 +29,10 @@ coverage-unit
*evals.env
.env
.secrets
.github/act/.secrets
.worktrees
## Generated files ##
src/generated/
@@ -35,3 +41,9 @@ webview-ui/src/services/grpc-client.ts
# E2E Tests
test-results
/.github/act
/pkg
.secrets
*.tsbuildinfo
+16 -4
View File
@@ -12,7 +12,10 @@
"args": [
"--extensionDevelopmentPath=${workspaceFolder}",
"--disable-workspace-trust",
"--disable-extensions", // Avoid conflicts with installed extensions
"--disable-extension",
"saoudrizwan.claude-dev", // Avoid conflicts with installed Cline
"--disable-extension",
"saoudrizwan.cline-nightly", // Avoid conflicts with installed Cline Nightly
"${workspaceFolder}"
],
"outFiles": [
@@ -33,7 +36,10 @@
"args": [
"--extensionDevelopmentPath=${workspaceFolder}",
"--disable-workspace-trust",
"--disable-extensions", // Avoid conflicts with installed extensions
"--disable-extension",
"saoudrizwan.claude-dev", // Avoid conflicts with installed Cline
"--disable-extension",
"saoudrizwan.cline-nightly", // Avoid conflicts with installed Cline Nightly
"${workspaceFolder}"
],
"outFiles": [
@@ -54,7 +60,10 @@
"args": [
"--extensionDevelopmentPath=${workspaceFolder}",
"--disable-workspace-trust",
"--disable-extensions", // Avoid conflicts with installed extensions
"--disable-extension",
"saoudrizwan.claude-dev", // Avoid conflicts with installed Cline
"--disable-extension",
"saoudrizwan.cline-nightly", // Avoid conflicts with installed Cline Nightly
"${workspaceFolder}"
],
"outFiles": [
@@ -77,7 +86,10 @@
"--user-data-dir=${workspaceFolder}/dist/tmp/user",
"--profile-temp",
"--sync=off",
"--disable-extensions", // Avoid conflicts with installed extensions
"--disable-extension",
"saoudrizwan.claude-dev", // Avoid conflicts with installed Cline
"--disable-extension",
"saoudrizwan.cline-nightly", // Avoid conflicts with installed Cline Nightly
"--extensionDevelopmentPath=${workspaceFolder}",
"${workspaceFolder}"
],
+3 -1
View File
@@ -27,5 +27,7 @@
"source.removeUnused.biome": "always",
"source.removeUnusedImports": "always",
"source.organizeImports.biome": "always"
}
},
// Disable auto-forwarding ports to prevent Simple Browser from opening the Vite dev server
"remote.autoForwardPorts": false
}
+2 -3
View File
@@ -1,6 +1,8 @@
# Default
.vscode/**
.vscode-test/**
.worktrees/**
CLAUDE.local.md
out/
dist-standalone/
node_modules/
@@ -40,9 +42,6 @@ buf.yaml
.changeset/
.clinerules/
# Include specific file needed for Background Exec mode
!standalone/runtime-files/vscode/enhanced-terminal.js
# Ignore all webview-ui files except the build directory (https://github.com/microsoft/vscode-webview-ui-toolkit-samples/blob/main/frameworks/hello-world-react-cra/.vscodeignore)
webview-ui/src/**
webview-ui/public/**
+1
View File
@@ -0,0 +1 @@
.gitignore
+278 -1
View File
@@ -1,5 +1,280 @@
# Changelog
## [3.53.1]
### Fixed
- Bug in responses API
## [3.53.0]
### Fixed
- Removed grok model from free tier
## [3.52.0]
### Added
- Users with ChatGPT Plus or Pro subscriptions can now use GPT-5 models directly through Cline without needing an API key. Authentication is handled via OAuth through OpenAI's authentication system.
- Grok models are now moving out of free tier and into paid plans.
- Introduces comprehensive Jupyter Notebook support for Cline, enabling AI-assisted editing of `.ipynb` files with full cell-level context awareness.
### Fixed
- Bugs in DiffViewProvider for file editing
- Ollama's recommended models to use correct identifiers
## [3.51.0]
### Added
- Adding OpenAI gpt-5.2-codex model to the model picker
## [3.50.0]
### Added
- Add gpt-5.2-codex OpenAI model support
- Add create-pull-request skill
### Fixed
- Fix the selection of remotely configured providers
- Fix act_mode_respond to prevent consecutive calls
- Fix invalid tool call IDs when switching between model formats
## [3.49.1]
### Added
- Add telemetry to track usage of skills feature
- Add version headers to Cline backend requests
- Phase in Responses API usage instead of defaulting for every supported model
### Fixed
- Fix workflow slash command search to be case-insensitive
- Fix model display in ModelPickerModal when using LiteLLM
- Fix LiteLLM model fetching with default base URL
- Fix crash when OpenAI-compatible APIs send usage chunks with empty or null choices arrays at end of streaming
- Fix model ID for Kat Coder Pro Free model
## [3.49.0]
- Enable configuring an OTEL collector at runtime
- Removing Minimax-2.1 from free model list as the free trial has ended
- Improved image display in MCP responses
- Auto-sync remote MCP servers from remote config to local settings
## [3.48.0]
### Added
- Add Skills system for reusable, on-demand agent instructions
- Add new websearch tooling in Cline provider
- Add zai-glm-4.7 to Cerebras model list
- Add model refresh and improve reasoning support for Vercel AI Gateway
### Fixed
- Revert #8341 due to regressions in diff view/document truncation (see #8423, #8429)
- Fixed extension crash when using context menu selector
## [3.47.0]
### Added
- Added experimental support for Background Edits (allows editing files in background without opening the diff view)
- Updated free model to MiniMax M2.1 (replacing MiniMax M2)
- Added support for Azure based identity authentication in OpenAI Compatible provider and Azure OpenAI
- Add `supportsReasoning` property to Baseten models
### Fixed
- Prevent expired token usage in authenticated requests
- Exclude binary files without extensions from diffs
- Preserve file endings and trailing newlines
- Fix Cerebras rate limiting
- Fix Auto Compact for Claude Code provider
- Make Workspace and Favorites history filters independent
- Fix remote MCP server connection failures (404 response handling)
- Disable native tool calling for Deepseek 3.2 speciale
- Show notification instead of opening sidebar on update
- Fix Baseten model selector
### Refactored
- Modify prompts for parallel tool usage in Claude and Gemini 3 models
## [3.46.1]
### Fixed
- Remove GLM 4.6 from free models
## [3.46.0]
### Added
- Added GLM 4.7 model
- Enhanced background terminal execution with command tracking, log file output, zombie process prevention (10-minute timeout), and clickable log paths in UI
- Apply Patch tool for GPT-5+ models (replacing current diff edit tools)
### Fixed
- Duplicate error messages during streaming for Diff Edit tool when Parallel Tool Calling is not enabled
- Banner carousel styling and dismiss functionality
- Typos in Gemini system prompt overrides
- Model picker favorites ordering, star toggle, and keyboard navigation for OpenRouter and Vercel AI Gateway providers
- Fetch remote config values from the cache
### Refactored
- Anthropic handler to use metadata for reasoning support
- Bedrock provider to use metadata for reasoning support
## [3.45.1]
- Fixed MCP settings race condition where toggling auto-approve or changing timeout settings would cause the UI to flash and revert
## [3.45.0]
- Added Gemini 3 Flash Preview model
## [3.44.2]
- Polished the model picker UI with checkmarks for selected models, tooltips on Plan/Act tabs, and consistent arrow pointers across all popup modals
- Improved WhatsNew modal responsiveness and cleaned up redundant UI elements
- Fixed GLM models outputting garbled text in thinking tags—reasoning is now properly disabled for these models
## [3.44.1]
- Fixed a critical bug where local MCP servers stopped connecting after v3.42.0—all user-configured stdio-based MCP servers should now work again
- Fixed remotely configured API keys not being extracted correctly for enterprise users
- Added support for dynamic tool instructions that adapt based on runtime context, laying groundwork for future context-aware features
## [3.44.0]
## Added
- Updating minor version to show a proper banner for the release
## [3.43.1]
### Patch Changes
- Fix GLM-4.6 Model reference id
## [3.43.0]
### Added
- GLM-4.6
- kat-coder-pro
- Add parsing of env variable patterns to the mcpconfig.json
### Fixed
- TLS Proxy support issues for VSCode
- Add supportsReasoning flag to OpenAI reasoning models
- Fix thinking not available for some models in the OpenAI provider
- Fix invalid signature field issues when switching between Gemini and Anthropic providers
- Extract OpenRouter model filtering into reusable utility and use it in different model pickers
- Fix a11y for auto approve checkbox
- Improve ModelPickerModal provider list layout
### Refactored
- Migrate WhatsNewModal to new shared dialogue component
## [3.42.0]
### Added
- Expose `getAvailableSlashCommands` rpc endpoint to UI clients
- Made slash command menu and context menu accessible and screenreader-friendly
- Made expanding/collapsing UI components accessible
### Fixed
- Devstral OpenRouter model ID and routing issues
- Incorrect pricing display for Devstral model in the extension
## [3.41.0]
### Added
- OpenAI GPT-5.2
- Devstral-2512 (formerly stealth model "Microwave")
- Improvements to chat modal model picker
- Amazon Nova 2 Lite
- DeepSeek 3.2 to native tool calling allow list
- Responses API support for Codex models in OpenAI provider (requires native tool calling)
- Xmas Special Santa Cline
- Welcome screen UI enhancements
### Fixed
- Initial checkpoint commit now non-blocking for improved responsiveness in large repositories
- Gemini Vertex models erroring when thinking parameters are not supported
- Restrictive file permissions for secrets.json
- Ollama streaming requests not aborting when task is cancelled
### Refactored
- OpenAI provider to centralize temperature configuration and include missing GPT-5 model settings
- OpenAI native handler to use metadata for model capabilities
- Vertex provider to use metadata for model capabilities
## [3.40.2]
- Fix logout on network errors during token refresh (e.g., opening laptop while offline)
## [3.40.1]
- Fix cost calculation display for Anthropic API requests
## [3.40.0]
- Fix highlighted text flashing when task header is collapsed
- Add X-Cerebras-3rd-Party-Integration header to Cerebras API requests
- Add microwave family system prompt configuration
- Remove tooltips from auto approve menu
- Fix Standalone, ensure cwd is the install dir to find resources reliably
- Fix a bug where terminal commands with double quotes are broken when "Terminal Execution Mode" is set to "Background Exec"
- Add support for slash commands anywhere in a message, not just at the beginning. This matches the behavior of @ mentions for a more flexible input experience.
- Add bottom padding to the last message to fix last response text getting cut off by auto approve settings bar.
- Add default thinking level for Gemini 3 Pro models in Gemini provider
## [3.39.2]
- Fix for microwave model and thinking settings
## [3.39.1]
- Fix Openrouter and Cline Provider model info
## [3.39.0]
- Add Explain Changes feature
- Add microwave Stealth model
- Add Tabbed Model Picker with Recommended and Free tabs
- Add support to View remote rules and workflows in the editor
- Enable NTC (Native Tool Calling) by default
- Bug fixes and improvements for LiteLLM provider
## [3.38.3]
- Task export feature now opens the task directory, allowing easy access to the full task files
- Add Grok 4.1 and Grok Code to XAI provider
- Enabled native tool calling for Baseten and Kimi K2 models
- Add thinking level to Gemini 3.0 Pro preview
- Expanded Hooks functionality
- Removed Task Timeline from Task Header
- Bug fix for slash commands
- Bug fixes for Vertex provider
- Bug fixes for thinking/reasoning issues across multiple providers when using native tool calling
- Bug fixes for terminal usage on Windows devices
## [3.38.2]
- Add Claude Opus 4.5
@@ -7,19 +282,21 @@
## [3.38.1]
### Fixed
- Fixed handling of 'signature' field in sanitizeAnthropicContentBlock to properly preserve it when thinking is enabled, as required by Anthropic's API.
## [3.38.0]
### Added
- Gemini 3 Pro Preview model
- AquaVoice Avalon model for voice-to-text dictation
### Fixed
- Automatic context truncation when AWS Bedrock token usage rate limits are exceeded
- Removed new_task tool from system prompts, updated slash command prompts, and added helper function for native tool calling validation
## [3.37.1]
- Comprehensive changes to better support GPT 5.1 - System prompt, tools, deep-planning, focus chain, etc.
+3
View File
@@ -0,0 +1,3 @@
@.clinerules/general.md
@.clinerules/network.md
@.clinerules/cli.md
+5
View File
@@ -141,6 +141,11 @@ For example, when working with a local web server, you can use 'Restore Workspac
To contribute to the project, start with our [Contributing Guide](CONTRIBUTING.md) to learn the basics. You can also join our [Discord](https://discord.gg/cline) to chat with other contributors in the `#contributors` channel. If you're looking for full-time work, check out our open positions on our [careers page](https://cline.bot/join-us)!
## Enterprise
Get the same Cline experience with enterprise-grade controls: SSO (SAML/OIDC), global policies and configuration, observability with audit trails, private networking (VPC/private link), and self-hosted or on-prem deployments, and enterprise support. Learn more at our [enterprise page](https://cline.bot/enterprise) or [talk to us](https://cline.bot/contact-sales).
## License
[Apache 2.0 © 2025 Cline Bot Inc.](./LICENSE)
+28 -1
View File
@@ -44,7 +44,7 @@
"style": {
"useNodejsImportProtocol": "off",
"useImportType": "off",
"useBlockStatements": "warn",
"useBlockStatements": "off",
"useNamingConvention": "off",
"useThrowOnlyError": "info",
"useConsistentArrayType": "off",
@@ -147,6 +147,33 @@
"src/dev/grit/vscode-api.grit"
]
},
{
// Do not use console logging directly, use the Logger service instead.
"plugins": [
"src/dev/grit/console-log.grit"
],
"includes": [
"**",
"!**/esbuild.*",
"!**/*.mts",
"!**/webview-ui/**",
"!**/evals/**",
"!**/standalone/**",
"!**/e2e/**",
"!**/test/**",
"!**/__tests__/**",
"!**/*.test.ts",
"!**/*.stories.ts",
"!src/dev/**",
"!**/*.mjs",
"!**/*.js",
"!**/scripts/**",
"!**/*.tsx",
"!**/testing-platform/**",
// ACP mode must redirect console to stderr - this is intentional
"!cli-ts/src/acp/index.ts"
]
},
{
"includes": [
"**",
+354
View File
@@ -0,0 +1,354 @@
# Cline CLI (TypeScript)
A TypeScript CLI implementation of Cline that reuses the core TypeScript codebase. This allows you to run Cline tasks directly from the terminal while sharing the same underlying functionality as the VS Code extension.
## Features
- **Reuses Core Codebase**: Shares the same Controller, Task, and API handling as the VS Code extension
- **Terminal Output**: Displays Cline messages directly in your terminal with colored output
- **Task History**: Access your task history from the command line
- **Configurable**: Use custom configuration directories and working directories
- **Image Support**: Attach images to your prompts using file paths or inline references
## Prerequisites
- Node.js 20.x or later
- npm or yarn
- The parent Cline project dependencies installed
## Installation
From the repository root:
```bash
# Install all dependencies first
npm run install:all
# Ensure protos are generated
npm run protos
# Build the CLI
npm run build:cli
```
Or install the CLI globally:
```bash
# Install all dependencies first
npm run install:all
# Ensure protos are generated
npm run protos
# Build and link the CLI globally
cd cli-ts
npm install
npm run link
```
## Usage
### Interactive Mode (Default)
When you run `cline` without any command, it launches an interactive welcome prompt:
```bash
# Launch interactive mode
cline
# Or run a task directly
cline "Create a hello world function in Python"
# With options
cline -v --thinking "Analyze this codebase"
```
### Commands
#### `task` (alias: `t`)
Run a new task with a prompt.
```bash
cline task "Create a hello world function in Python"
cline t "Create a hello world function"
```
**Options:**
| Option | Description |
|--------|-------------|
| `-a, --act` | Run in act mode |
| `-p, --plan` | Run in plan mode |
| `-y, --yolo` | Enable yolo mode (auto-approve actions) |
| `-m, --model <model>` | Model to use for the task |
| `-i, --images <paths...>` | Image file paths to include with the task |
| `-v, --verbose` | Show verbose output including reasoning |
| `-c, --cwd <path>` | Working directory for the task |
| `--config <path>` | Path to Cline configuration directory |
| `-t, --thinking` | Enable extended thinking (1024 token budget) |
**Examples:**
```bash
# Run in plan mode with verbose output
cline task -p -v "Design a REST API"
# Use a specific model with yolo mode
cline task -m claude-sonnet-4-5-20250929 -y "Refactor this function"
# Include images with your prompt
cline task -i screenshot.png diagram.jpg "Fix the UI based on these images"
# Or use inline image references in the prompt
cline task "Fix the layout shown in @./screenshot.png"
# Enable extended thinking for complex tasks
cline task -t "Architect a microservices system"
# Specify working directory
cline task -c /path/to/project "Add unit tests"
```
#### `history` (alias: `h`)
List task history with pagination support.
```bash
cline history
cline h
```
**Options:**
| Option | Description |
|--------|-------------|
| `-n, --limit <number>` | Number of tasks to show (default: 10) |
| `-p, --page <number>` | Page number, 1-based (default: 1) |
| `--config <path>` | Path to Cline configuration directory |
**Examples:**
```bash
# Show last 10 tasks (default)
cline history
# Show 20 tasks
cline history -n 20
# Show page 2 with 5 tasks per page
cline history -n 5 -p 2
```
#### `config`
Show current configuration including global and workspace state.
```bash
cline config
```
**Options:**
| Option | Description |
|--------|-------------|
| `--config <path>` | Path to Cline configuration directory |
#### `auth`
Authenticate a provider and configure what model is used.
```bash
cline auth
```
**Options:**
| Option | Description |
|--------|-------------|
| `-p, --provider <id>` | Provider ID for quick setup (e.g., openai-native, anthropic) |
| `-k, --apikey <key>` | API key for the provider |
| `-m, --modelid <id>` | Model ID to configure (e.g., gpt-4o, claude-sonnet-4-5-20250929) |
| `-b, --baseurl <url>` | Base URL (optional, only for openai provider) |
| `-v, --verbose` | Show verbose output |
| `-c, --cwd <path>` | Working directory for the task |
| `--config <path>` | Path to Cline configuration directory |
**Examples:**
```bash
# Interactive authentication
cline auth
# Quick setup with provider and API key
cline auth -p anthropic -k sk-ant-xxxxx
# Full quick setup with model
cline auth -p openai-native -k sk-xxxxx -m gpt-4o
# OpenAI-compatible provider with custom base URL
cline auth -p openai -k your-api-key -b https://api.example.com/v1
```
### Global Options
These options are available for the default command (running a task directly):
| Option | Description |
|--------|-------------|
| `-v, --verbose` | Show verbose output |
| `-c, --cwd <path>` | Working directory |
| `--config <path>` | Configuration directory |
| `--thinking` | Enable extended thinking (1024 token budget) |
## Development
For active development, at the root of this repo:
1. **Initial setup:**
```bash
npm run install:all
npm run protos
```
2. **Make changes to cli-ts:**
```bash
npm run cli:dev
# or
cd cli-ts && npm run dev
```
3. **Test your changes:**
```bash
cline [your-command] # In a new Terminal
```
4. **When done:**
```bash
npm run cli:unlink
```
### Build
```bash
cd cli-ts
# Development build with source maps
npm run build
# Production build (minified)
npm run build:production
```
### Watch Mode
```bash
npm run watch
```
### Type Checking
```bash
npm run typecheck
```
## Publish
#### 1. Publish to npm
```bash
npm publish
```
#### 2. Update the Homebrew formula
```bash
npm run update-brew-formula
```
#### 3. Test the formula locally
```bash
# Create a local tap
brew tap-new cline/local
cp ./cli-ts/cline.rb "$(brew --repository)/Library/Taps/cline/homebrew-local/Formula/cline.rb"
# Build from Source
brew install --build-from-source cline/local/cline
# Install from your local tap
brew install cline/local/cline
# Clean up when done
brew untap cline/local
```
#### 4. If using a tap, commit and push
```bash
git add cline.rb
git commit -m "Update cline to v2.0.0"
git push
```
## Architecture
The CLI reuses the core Cline TypeScript codebase:
- **Controller** (`@core/controller`): Manages task lifecycle and state
- **Task** (`@core/task`): Executes Cline tasks using the AI API
- **StateManager** (`@core/storage`): Handles persistent state storage
CLI-specific implementations:
- `cli-host-bridge.ts`: CLI implementations of host bridge services
- `cli-webview-provider.ts`: WebviewProvider that outputs to terminal
- `cli-comment-review.ts`: Comment review controller for terminal
- `vscode-context.ts`: Mock VSCode extension context
- `display.ts`: Terminal output formatting utilities
## Configuration
The CLI stores its data in `~/.cline/data/` by default:
- `globalState.json`: Global settings and state
- `secrets.json`: API keys and secrets
- `workspace/`: Workspace-specific state
- `tasks/`: Task history and conversation data
Override with the `--config` option or `CLINE_DIR` environment variable.
## Comparison with Go CLI
This TypeScript CLI differs from the Go CLI (`cli/` directory):
| Feature | Go CLI | TypeScript CLI |
|---------|--------|----------------|
| Language | Go | TypeScript |
| Core sharing | Uses gRPC to communicate | Direct imports |
| Startup time | Fast | Moderate |
| Dependencies | Standalone binary | Requires Node.js |
| Best for | Production deployment | Development, debugging |
Choose the TypeScript CLI when you need to debug or modify the core Cline logic. Choose the Go CLI for production deployment with faster startup.
## Troubleshooting
### Build Errors
If you encounter build errors, ensure you've:
1. Run `npm install` in the repository root
2. Run `npm run protos` to generate proto files
3. Have all peer dependencies installed
### Missing Dependencies
The CLI imports from the parent project. If you see import errors:
```bash
cd .. # Go to repository root
npm install
npm run protos
```
### Permission Denied
Make the CLI executable:
```bash
chmod +x dist/cli.js
```
+20
View File
@@ -0,0 +1,20 @@
# IMPORTANT: `npm run postpublish` to update this file after publishing a new version of the package
class Cline < Formula
desc "Autonomous coding agent CLI - capable of creating/editing files, running commands, and more"
homepage "https://cline.bot"
url "https://registry.npmjs.org/cline/-/cline-2.0.0.tgz" # GET from https://registry.npmjs.org/cline/latest tarball URL
sha256 "65bae90401191aeeabfbbc0b315e816aea96742043ba85b90671bf5e19d0761e"
license "Apache-2.0"
depends_on "node@20"
def install
system "npm", "install", *std_npm_args(prefix: false)
bin.install_symlink Dir["#{libexec}/bin/*"]
end
test do
# Test that the binary exists and is executable
assert_match version.to_s, shell_output("#{bin}/cline --version")
end
end
+272
View File
@@ -0,0 +1,272 @@
import fs from "node:fs"
import path from "node:path"
import { fileURLToPath } from "node:url"
import dotenv from "dotenv"
import * as esbuild from "esbuild"
const __filename = fileURLToPath(import.meta.url)
const __dirname = path.dirname(__filename)
const rootDir = path.resolve(__dirname, "..")
// Load .env from repo root
dotenv.config({ path: path.join(rootDir, ".env") })
const production = process.argv.includes("--production")
const watch = process.argv.includes("--watch")
/**
* Plugin to resolve path aliases from the parent project
*/
const aliasResolverPlugin: esbuild.Plugin = {
name: "alias-resolver",
setup(build) {
const aliases = {
"@": path.resolve(rootDir, "src"),
"@core": path.resolve(rootDir, "src/core"),
"@integrations": path.resolve(rootDir, "src/integrations"),
"@services": path.resolve(rootDir, "src/services"),
"@shared": path.resolve(rootDir, "src/shared"),
"@utils": path.resolve(rootDir, "src/utils"),
"@packages": path.resolve(rootDir, "src/packages"),
"@hosts": path.resolve(rootDir, "src/hosts"),
"@generated": path.resolve(rootDir, "src/generated"),
"@api": path.resolve(rootDir, "src/core/api"),
}
// For each alias entry, create a resolver
Object.entries(aliases).forEach(([alias, aliasPath]) => {
const aliasRegex = new RegExp(`^${alias}($|/.*)`)
build.onResolve({ filter: aliasRegex }, (args) => {
const importPath = args.path.replace(alias, aliasPath)
// First, check if the path exists as is
if (fs.existsSync(importPath)) {
const stats = fs.statSync(importPath)
if (stats.isDirectory()) {
// If it's a directory, try to find index files
const extensions = [".ts", ".tsx", ".js", ".jsx"]
for (const ext of extensions) {
const indexFile = path.join(importPath, `index${ext}`)
if (fs.existsSync(indexFile)) {
return { path: indexFile }
}
}
} else {
// It's a file that exists, so return it
return { path: importPath }
}
}
// If the path doesn't exist, try appending extensions
const extensions = [".ts", ".tsx", ".js", ".jsx"]
for (const ext of extensions) {
const pathWithExtension = `${importPath}${ext}`
if (fs.existsSync(pathWithExtension)) {
return { path: pathWithExtension }
}
}
// Handle .js -> .ts extension mapping (common in ESM TypeScript projects)
if (importPath.endsWith(".js")) {
const tsPath = importPath.replace(/\.js$/, ".ts")
if (fs.existsSync(tsPath)) {
return { path: tsPath }
}
const tsxPath = importPath.replace(/\.js$/, ".tsx")
if (fs.existsSync(tsxPath)) {
return { path: tsxPath }
}
}
// If nothing worked, return the original path and let esbuild handle the error
return { path: importPath }
})
})
},
}
/**
* Plugin to redirect vscode imports to our shim
*/
const vscodeStubPlugin: esbuild.Plugin = {
name: "vscode-stub",
setup(build) {
// Redirect 'vscode' imports to our shim
build.onResolve({ filter: /^vscode$/ }, () => {
return { path: path.join(__dirname, "src", "vscode-shim.ts") }
})
},
}
const esbuildProblemMatcherPlugin: esbuild.Plugin = {
name: "esbuild-problem-matcher",
setup(build) {
build.onStart(() => {
console.log("[cli-ts esbuild] Build started...")
})
build.onEnd((result) => {
result.errors.forEach(({ text, location }) => {
console.error(`✘ [ERROR] ${text}`)
if (location) {
console.error(` ${location.file}:${location.line}:${location.column}:`)
}
})
console.log("[cli-ts esbuild] Build finished")
})
},
}
// Plugin to stub out optional devtools module
const stubOptionalModulesPlugin: esbuild.Plugin = {
name: "stub-optional-modules",
setup(build) {
build.onResolve({ filter: /^react-devtools-core$/ }, () => {
return { path: path.join(__dirname, "src", "stub-devtools.js"), external: false }
})
},
}
const copyWasmFiles: esbuild.Plugin = {
name: "copy-wasm-files",
setup(build) {
build.onEnd(() => {
const destDir = path.join(__dirname, "dist")
// Ensure dist directory exists
if (!fs.existsSync(destDir)) {
fs.mkdirSync(destDir, { recursive: true })
}
// tree sitter
const sourceDir = path.join(rootDir, "node_modules", "web-tree-sitter")
// Copy tree-sitter.wasm
const treeSitterWasm = path.join(sourceDir, "tree-sitter.wasm")
if (fs.existsSync(treeSitterWasm)) {
fs.copyFileSync(treeSitterWasm, path.join(destDir, "tree-sitter.wasm"))
}
// Copy language-specific WASM files
const languageWasmDir = path.join(rootDir, "node_modules", "tree-sitter-wasms", "out")
const languages = [
"typescript",
"tsx",
"python",
"rust",
"javascript",
"go",
"cpp",
"c",
"c_sharp",
"ruby",
"java",
"php",
"swift",
"kotlin",
]
if (fs.existsSync(languageWasmDir)) {
languages.forEach((lang) => {
const filename = `tree-sitter-${lang}.wasm`
const sourcePath = path.join(languageWasmDir, filename)
if (fs.existsSync(sourcePath)) {
fs.copyFileSync(sourcePath, path.join(destDir, filename))
}
})
}
})
},
}
const buildEnvVars: Record<string, string> = {
"process.env.IS_STANDALONE": JSON.stringify("true"),
"process.env.IS_CLI": JSON.stringify("true"),
}
const buildTimeEnvs = [
"TELEMETRY_SERVICE_API_KEY",
"ERROR_SERVICE_API_KEY",
"POSTHOG_TELEMETRY_ENABLED",
"OTEL_TELEMETRY_ENABLED",
"OTEL_LOGS_EXPORTER",
"OTEL_METRICS_EXPORTER",
"OTEL_EXPORTER_OTLP_PROTOCOL",
"OTEL_EXPORTER_OTLP_ENDPOINT",
"OTEL_EXPORTER_OTLP_HEADERS",
"OTEL_METRIC_EXPORT_INTERVAL",
"CLINE_ENVIRONMENT",
]
buildTimeEnvs.forEach((envVar) => {
if (process.env[envVar]) {
console.log(`[cli-ts esbuild] ${envVar} env var is set`)
buildEnvVars[`process.env.${envVar}`] = JSON.stringify(process.env[envVar])
}
})
if (production) {
buildEnvVars["process.env.IS_DEV"] = "false"
}
const config: esbuild.BuildOptions = {
entryPoints: [path.join(__dirname, "src", "index.ts")],
bundle: true,
minify: production,
sourcemap: !production,
logLevel: "silent",
define: buildEnvVars,
tsconfig: path.join(__dirname, "tsconfig.json"),
plugins: [copyWasmFiles, aliasResolverPlugin, vscodeStubPlugin, stubOptionalModulesPlugin, esbuildProblemMatcherPlugin],
format: "esm",
sourcesContent: false,
platform: "node",
target: "node20",
outfile: path.join(__dirname, "dist", "cli.mjs"),
// These modules need to load files from the module directory at runtime
external: [
"@grpc/reflection",
"grpc-health-check",
"better-sqlite3",
"ink",
"ink-spinner",
"ink-picture",
"react",
"aws4fetch",
"pino",
"pino-roll",
],
supported: { "top-level-await": true },
banner: {
js: `#!/usr/bin/env node
// Suppress all Node.js warnings (deprecation, experimental, etc.)
process.emitWarning = () => {};
import { createRequire as _createRequire } from 'module';
import { fileURLToPath as _fileURLToPath } from 'url';
import { dirname as _dirname } from 'path';
const require = _createRequire(import.meta.url);
const __filename = _fileURLToPath(import.meta.url);
const __dirname = _dirname(__filename);`,
},
}
async function main() {
const ctx = await esbuild.context(config)
if (watch) {
await ctx.watch()
console.log("[cli-ts] Watching for changes...")
} else {
await ctx.rebuild()
await ctx.dispose()
// Make the output executable
const outfile = path.join(__dirname, "dist", "cli.mjs")
if (fs.existsSync(outfile)) {
fs.chmodSync(outfile, "755")
}
}
}
main().catch((e) => {
console.error(e)
process.exit(1)
})
+384
View File
@@ -0,0 +1,384 @@
.\" Automatically generated by Pandoc 3.8.3
.\"
.TH "CLINE" "1" "January 2026" "Cline CLI 2.0" "User Commands"
.SH NAME
cline \- AI coding assistant in your terminal
.SH SYNOPSIS
\f[B]cline\f[R] [\f[I]prompt\f[R]] [\f[I]options\f[R]]
.PP
\f[B]cline\f[R] \f[I]command\f[R] [\f[I]options\f[R]]
[\f[I]arguments\f[R]]
.SH DESCRIPTION
\f[B]cline\f[R] is a command\-line interface for the Cline AI coding
assistant.
It provides the same powerful AI capabilities as the VS Code extension,
directly in your terminal.
.PP
Cline is an autonomous AI agent that can read, write, and execute code
across your projects.
He can create and edit files, run terminal commands, use a headless
browser, and more\(emall while asking for your approval before taking
actions.
.PP
The CLI supports both interactive mode (with a rich terminal UI) and
plain text mode (for piped input and scripted workflows).
.SH MODES OF OPERATION
\f[B]Interactive Mode\f[R] : When you run \f[B]cline\f[R] without
arguments, it launches an interactive welcome prompt with a rich
terminal UI.
You can type your task, view conversation history, and interact with
Cline in real\-time.
.PP
\f[B]Task Mode\f[R] : Run \f[B]cline \(lqprompt\(rq\f[R] or \f[B]cline
task \(lqprompt\(rq\f[R] to immediately start a task.
If stdin is a TTY, you\(cqll see the interactive UI.
If stdin is piped or output is redirected, the CLI automatically
switches to plain text mode.
.PP
\f[B]Plain Text Mode\f[R] : Activated automatically when stdin is piped,
output is redirected, or \f[B]\-\-json\f[R]/\f[B]\-\-yolo\f[R] flags are
used.
Outputs clean text without the Ink UI, suitable for scripting and CI/CD
pipelines.
.SH AGENT BEHAVIOR
Cline operates in two primary modes:
.PP
\f[B]ACT MODE\f[R] : Cline actively uses tools to accomplish tasks.
He can read files, write code, execute commands, use a headless browser,
and more.
This is the default mode for task execution.
.PP
\f[B]PLAN MODE\f[R] : Cline gathers information and creates a detailed
plan before implementation.
He explores the codebase, asks clarifying questions, and presents a
strategy for user approval before switching to ACT MODE.
.SH COMMANDS
.SS task (alias: t)
Run a new task with a prompt.
.PP
\f[B]cline task\f[R] \f[I]prompt\f[R] [\f[I]options\f[R]]
.PP
\f[B]cline t\f[R] \f[I]prompt\f[R] [\f[I]options\f[R]] : Create and run
a new task.
Options:
.PP
\f[B]\-a\f[R], \f[B]\-\-act\f[R] : Run in act mode (default)
.PP
\f[B]\-p\f[R], \f[B]\-\-plan\f[R] : Run in plan mode
.PP
\f[B]\-y\f[R], \f[B]\-\-yolo\f[R] : Enable yolo/yes mode (auto\-approve
all actions, output in plain mode, exit process automatically when task
complete)
.PP
\f[B]\-m\f[R], \f[B]\-\-model\f[R] \f[I]model\f[R] : Model to use for
the task
.PP
\f[B]\-i\f[R], \f[B]\-\-images\f[R] \f[I]paths\&...\f[R] : Image file
paths to include with the task
.PP
\f[B]\-v\f[R], \f[B]\-\-verbose\f[R] : Show verbose output including
reasoning
.PP
\f[B]\-c\f[R], \f[B]\-\-cwd\f[R] \f[I]path\f[R] : Working directory for
the task
.PP
\f[B]\-\-config\f[R] \f[I]path\f[R] : Path to Cline configuration
directory
.PP
\f[B]\-\-thinking\f[R] : Enable extended thinking (1024 token budget)
.PP
\f[B]\-\-json\f[R] : Output messages as JSON instead of styled text
.SS history (alias: h)
List task history with pagination.
.PP
\f[B]cline history\f[R] [\f[I]options\f[R]]
.PP
\f[B]cline h\f[R] [\f[I]options\f[R]] : Display previous tasks.
Options:
.PP
\f[B]\-n\f[R], \f[B]\-\-limit\f[R] \f[I]number\f[R] : Number of tasks to
show (default: 10)
.PP
\f[B]\-p\f[R], \f[B]\-\-page\f[R] \f[I]number\f[R] : Page number,
1\-based (default: 1)
.PP
\f[B]\-\-config\f[R] \f[I]path\f[R] : Path to Cline configuration
directory
.SS config
Show current configuration.
.PP
\f[B]cline config\f[R] [\f[I]options\f[R]] : Display global and
workspace state.
Options:
.PP
\f[B]\-\-config\f[R] \f[I]path\f[R] : Path to Cline configuration
directory
.SS auth
Authenticate a provider and configure the model.
.PP
\f[B]cline auth\f[R] [\f[I]options\f[R]] : Launch interactive
authentication wizard, or use quick setup flags.
Options:
.PP
\f[B]\-p\f[R], \f[B]\-\-provider\f[R] \f[I]id\f[R] : Provider ID for
quick setup (e.g., openai\-native, anthropic, openrouter)
.PP
\f[B]\-k\f[R], \f[B]\-\-apikey\f[R] \f[I]key\f[R] : API key for the
provider
.PP
\f[B]\-m\f[R], \f[B]\-\-modelid\f[R] \f[I]id\f[R] : Model ID to
configure (e.g., gpt\-4o, claude\-sonnet\-4\-5\-20250929)
.PP
\f[B]\-b\f[R], \f[B]\-\-baseurl\f[R] \f[I]url\f[R] : Base URL (optional,
for OpenAI\-compatible providers)
.PP
\f[B]\-v\f[R], \f[B]\-\-verbose\f[R] : Show verbose output
.PP
\f[B]\-c\f[R], \f[B]\-\-cwd\f[R] \f[I]path\f[R] : Working directory
.PP
\f[B]\-\-config\f[R] \f[I]path\f[R] : Path to Cline configuration
directory
.SS update
Check for updates and install if available.
.PP
\f[B]cline update\f[R] [\f[I]options\f[R]] : Check npm for newer
versions.
Options:
.PP
\f[B]\-v\f[R], \f[B]\-\-verbose\f[R] : Show verbose output
.SS version
Show the CLI version number.
.PP
\f[B]cline version\f[R]
.SS dev
Developer tools and utilities.
.PP
\f[B]cline dev log\f[R] : Open the log file for debugging.
.SH DEFAULT COMMAND OPTIONS
When running \f[B]cline\f[R] with just a prompt (no subcommand), these
options are available:
.PP
\f[B]\-a\f[R], \f[B]\-\-act\f[R] : Run in act mode (default)
.PP
\f[B]\-p\f[R], \f[B]\-\-plan\f[R] : Run in plan mode
.PP
\f[B]\-y\f[R], \f[B]\-\-yolo\f[R] : Enable yolo mode (auto\-approve all
actions).
Also forces plain text output mode.
.PP
\f[B]\-m\f[R], \f[B]\-\-model\f[R] \f[I]model\f[R] : Model to use for
the task
.PP
\f[B]\-v\f[R], \f[B]\-\-verbose\f[R] : Show verbose output
.PP
\f[B]\-c\f[R], \f[B]\-\-cwd\f[R] \f[I]path\f[R] : Working directory
.PP
\f[B]\-\-config\f[R] \f[I]path\f[R] : Configuration directory
.PP
\f[B]\-\-thinking\f[R] : Enable extended thinking (1024 token budget)
.PP
\f[B]\-\-json\f[R] : Output messages as JSON instead of styled text.
Forces plain text mode.
.SH JSON OUTPUT FORMAT
When using \f[B]\-\-json\f[R], each message is output as a JSON object
with these fields:
.PP
\f[B]Required fields:\f[R]
.IP \(bu 2
\f[B]type\f[R]: \(lqask\(rq or \(lqsay\(rq
.IP \(bu 2
\f[B]text\f[R]: message text
.IP \(bu 2
\f[B]ts\f[R]: Unix epoch timestamp in milliseconds
.PP
\f[B]Optional fields:\f[R]
.IP \(bu 2
\f[B]reasoning\f[R]: reasoning text
.IP \(bu 2
\f[B]say\f[R]: say subtype (when type is \(lqsay\(rq)
.IP \(bu 2
\f[B]ask\f[R]: ask subtype (when type is \(lqask\(rq)
.IP \(bu 2
\f[B]partial\f[R]: streaming flag
.IP \(bu 2
\f[B]images\f[R]: list of image URIs
.IP \(bu 2
\f[B]files\f[R]: list of file paths
.SH EXAMPLES
.SS Basic Usage
.IP
.EX
\f[I]# Launch interactive mode\f[R]
cline
\f[I]# Run a task directly\f[R]
cline \(dqCreate a hello world function in Python\(dq
\f[I]# Run with verbose output and extended thinking\f[R]
cline \-v \-\-thinking \(dqAnalyze this codebase architecture\(dq
.EE
.SS Mode Selection
.IP
.EX
\f[I]# Run in plan mode (gather info before acting)\f[R]
cline \-p \(dqDesign a REST API for user management\(dq
\f[I]# Run in act mode with auto\-approval (yolo)\f[R]
cline \-y \(dqFix the typo in README.md\(dq
.EE
.SS Using Specific Models
.IP
.EX
\f[I]# Use a specific model\f[R]
cline \-m claude\-sonnet\-4\-5\-20250929 \(dqRefactor this function\(dq
\f[I]# Quick auth setup with model\f[R]
cline auth \-p anthropic \-k sk\-ant\-xxxxx \-m claude\-sonnet\-4\-5\-20250929
.EE
.SS Including Images
.IP
.EX
\f[I]# Include images with explicit flag\f[R]
cline task \-i screenshot.png diagram.jpg \(dqFix the UI based on these images\(dq
\f[I]# Or use inline image references in the prompt\f[R]
cline \(dqFix the layout shown in \(at./screenshot.png\(dq
.EE
.SS Piped Input
.IP
.EX
\f[I]# Pipe file contents to Cline\f[R]
cat README.md \f[B]|\f[R] cline \(dqSummarize this document\(dq
\f[I]# Pipe with additional prompt\f[R]
echo \(dqfunction add(a, b) { return a + b }\(dq \f[B]|\f[R] cline \(dqAdd TypeScript types to this\(dq
\f[I]# Combine piped input with a prompt\f[R]
git diff \f[B]|\f[R] cline \(dqReview these changes and suggest improvements\(dq
.EE
.SS Scripting and Automation
.IP
.EX
\f[I]# JSON output for parsing\f[R]
cline \-\-json \(dqWhat files are in this directory?\(dq \f[B]|\f[R] jq \(aq.text\(aq
\f[I]# Yolo mode for automated workflows (auto\-approves all actions), forces plain text output\f[R]
cline \-y \(dqRun the test suite and fix any failures\(dq
.EE
.SS Task History
.IP
.EX
\f[I]# List recent tasks\f[R]
cline history
\f[I]# Show more tasks with pagination\f[R]
cline history \-n 20 \-p 2
.EE
.SS Authentication
.IP
.EX
\f[I]# Interactive authentication wizard\f[R]
cline auth
\f[I]# Quick setup for Anthropic\f[R]
cline auth \-p anthropic \-k sk\-ant\-api\-xxxxx
\f[I]# Quick setup for OpenAI\f[R]
cline auth \-p openai\-native \-k sk\-xxxxx \-m gpt\-4o
\f[I]# OpenAI\-compatible provider with custom base URL\f[R]
cline auth \-p openai \-k your\-api\-key \-b https://api.example.com/v1
.EE
.SH ENVIRONMENT
\f[B]CLINE_DIR\f[R] : Override the default configuration directory.
When set, Cline stores all data in this directory instead of
\f[CR]\(ti/.cline/data/\f[R].
.PP
\f[B]CLINE_COMMAND_PERMISSIONS\f[R] : JSON configuration for restricting
which shell commands Cline can execute.
When set, commands are validated against allow/deny patternks before
execution.
When not set, all commands are allowed.
.PP
Format:
\f[CR]{\(dqallow\(dq: [\(dqpattern1\(dq, \(dqpattern2\(dq], \(dqdeny\(dq: [\(dqpattern3\(dq], \(dqallowRedirects\(dq: true}\f[R]
.PP
\f[B]Fields:\f[R]
.IP \(bu 2
\f[B]allow\f[R] (array of strings): Glob patterns for allowed commands.
If specified, only matching commands are permitted.
Uses \f[CR]*\f[R] to match any characters and \f[CR]?\f[R] to match a
single character.
Setting allow on anything will deny all others.
.IP \(bu 2
\f[B]deny\f[R] (array of strings): Glob patterns for denied commands.
Deny rules take precedence over allow rules.
.IP \(bu 2
\f[B]allowRedirects\f[R] (boolean): Whether to allow shell redirects
(\f[CR]>\f[R], \f[CR]>>\f[R], \f[CR]<\f[R], etc.).
Defaults to false.
.PP
\f[B]Rule evaluation:\f[R]
.IP "1." 3
Check for dangerous characters (backticks outside single quotes,
unquoted newlines)
.IP "2." 3
Parse command into segments split by operators (\f[CR]&&\f[R],
\f[CR]||\f[R], \f[CR]|\f[R], \f[CR];\f[R])
.IP "3." 3
If redirects detected and \f[CR]allowRedirects\f[R] is not true, command
is denied
.IP "4." 3
Each segment is validated against deny rules first, then allow rules
.IP "5." 3
Subshell contents (\f[CR]$(...)\f[R] and \f[CR](...)\f[R]) are
recursively validated
.IP "6." 3
All segments must pass for the command to be allowed
.PP
\f[B]Examples:\f[R]
.IP
.EX
\f[I]# Allow only npm and git commands.\f[R]
export CLINE_COMMAND_PERMISSIONS=\(aq{\(dqallow\(dq: [\(dqnpm *\(dq, \(dqgit *\(dq]}\(aq
\f[I]# Allow development commands but deny dangerous ones. Deny not strictly required here since allow is set.\f[R]
export CLINE_COMMAND_PERMISSIONS=\(aq{\(dqallow\(dq: [\(dqnpm *\(dq, \(dqgit *\(dq, \(dqnode *\(dq], \(dqdeny\(dq: [\(dqrm \-rf *\(dq, \(dqsudo *\(dq]}\(aq
\f[I]# Allow file operations with redirects\f[R]
export CLINE_COMMAND_PERMISSIONS=\(aq{\(dqallow\(dq: [\(dqcat *\(dq, \(dqecho *\(dq], \(dqallowRedirects\(dq: true}\(aq
.EE
.SH FILES
\f[B]\(ti/.cline/data/\f[R] : Default configuration directory
containing:
.PP
\f[B]globalState.json\f[R] : Global settings and state
.PP
\f[B]secrets.json\f[R] : API keys and secrets (stored securely)
.PP
\f[B]workspace/\f[R] : Workspace\-specific state
.PP
\f[B]tasks/\f[R] : Task history and conversation data
.PP
\f[B]\(ti/.cline/log/\f[R] : Log files for debugging.
View with \f[CR]cline dev log\f[R].
.SH BUGS
Report bugs at: \c
.UR https://github.com/cline/cline/issues
.UE \c
.PP
For real\-time help, join the Discord community at: \c
.UR https://discord.gg/cline
.UE \c
.SH SEE ALSO
Full documentation: \c
.UR https://docs.cline.bot
.UE \c
.PP
VS Code extension: \c
.UR https://marketplace.visualstudio.com/items?itemName=saoudrizwan.claude-dev
.UE \c
.SH AUTHORS
Cline is developed by Cline Bot Inc.\ and the open source community.
.SH COPYRIGHT
Copyright © 2025 Cline Bot Inc.\ Licensed under the Apache License 2.0.
+340
View File
@@ -0,0 +1,340 @@
---
title: CLINE
section: 1
header: User Commands
footer: Cline CLI 2.0
date: January 2026
---
# NAME
cline - AI coding assistant in your terminal
# SYNOPSIS
**cline** [*prompt*] [*options*]
**cline** *command* [*options*] [*arguments*]
# DESCRIPTION
**cline** is a command-line interface for the Cline AI coding assistant. It provides the same powerful AI capabilities as the VS Code extension, directly in your terminal.
Cline is an autonomous AI agent that can read, write, and execute code across your projects. He can create and edit files, run terminal commands, use a headless browser, and more—all while asking for your approval before taking actions.
The CLI supports both interactive mode (with a rich terminal UI) and plain text mode (for piped input and scripted workflows).
# MODES OF OPERATION
**Interactive Mode** : When you run **cline** without arguments, it launches an interactive welcome prompt with a rich terminal UI. You can type your task, view conversation history, and interact with Cline in real-time.
**Task Mode** : Run **cline "prompt"** or **cline task "prompt"** to immediately start a task. If stdin is a TTY, you'll see the interactive UI. If stdin is piped or output is redirected, the CLI automatically switches to plain text mode.
**Plain Text Mode** : Activated automatically when stdin is piped, output is redirected, or **\--json**/**\--yolo** flags are used. Outputs clean text without the Ink UI, suitable for scripting and CI/CD pipelines.
# AGENT BEHAVIOR
Cline operates in two primary modes:
**ACT MODE** : Cline actively uses tools to accomplish tasks. He can read files, write code, execute commands, use a headless browser, and more. This is the default mode for task execution.
**PLAN MODE** : Cline gathers information and creates a detailed plan before implementation. He explores the codebase, asks clarifying questions, and presents a strategy for user approval before switching to ACT MODE.
# COMMANDS
## task (alias: t)
Run a new task with a prompt.
**cline task** *prompt* [*options*]
**cline t** *prompt* [*options*] : Create and run a new task. Options:
**-a**, **\--act** : Run in act mode (default)
**-p**, **\--plan** : Run in plan mode
**-y**, **\--yolo** : Enable yolo/yes mode (auto-approve all actions, output in plain mode, exit process automatically when task complete)
**-m**, **\--model** *model* : Model to use for the task
**-i**, **\--images** *paths...* : Image file paths to include with the task
**-v**, **\--verbose** : Show verbose output including reasoning
**-c**, **\--cwd** *path* : Working directory for the task
**\--config** *path* : Path to Cline configuration directory
**\--thinking** : Enable extended thinking (1024 token budget)
**\--json** : Output messages as JSON instead of styled text
## history (alias: h)
List task history with pagination.
**cline history** [*options*]
**cline h** [*options*] : Display previous tasks. Options:
**-n**, **\--limit** *number* : Number of tasks to show (default: 10)
**-p**, **\--page** *number* : Page number, 1-based (default: 1)
**\--config** *path* : Path to Cline configuration directory
## config
Show current configuration.
**cline config** [*options*] : Display global and workspace state. Options:
**\--config** *path* : Path to Cline configuration directory
## auth
Authenticate a provider and configure the model.
**cline auth** [*options*] : Launch interactive authentication wizard, or use quick setup flags. Options:
**-p**, **\--provider** *id* : Provider ID for quick setup (e.g., openai-native, anthropic, openrouter)
**-k**, **\--apikey** *key* : API key for the provider
**-m**, **\--modelid** *id* : Model ID to configure (e.g., gpt-4o, claude-sonnet-4-5-20250929)
**-b**, **\--baseurl** *url* : Base URL (optional, for OpenAI-compatible providers)
**-v**, **\--verbose** : Show verbose output
**-c**, **\--cwd** *path* : Working directory
**\--config** *path* : Path to Cline configuration directory
## update
Check for updates and install if available.
**cline update** [*options*] : Check npm for newer versions. Options:
**-v**, **\--verbose** : Show verbose output
## version
Show the CLI version number.
**cline version**
## dev
Developer tools and utilities.
**cline dev log** : Open the log file for debugging.
# DEFAULT COMMAND OPTIONS
When running **cline** with just a prompt (no subcommand), these options are available:
**-a**, **\--act** : Run in act mode (default)
**-p**, **\--plan** : Run in plan mode
**-y**, **\--yolo** : Enable yolo mode (auto-approve all actions). Also forces plain text output mode.
**-m**, **\--model** *model* : Model to use for the task
**-v**, **\--verbose** : Show verbose output
**-c**, **\--cwd** *path* : Working directory
**\--config** *path* : Configuration directory
**\--thinking** : Enable extended thinking (1024 token budget)
**\--json** : Output messages as JSON instead of styled text. Forces plain text mode.
# JSON OUTPUT FORMAT
When using **\--json**, each message is output as a JSON object with these fields:
**Required fields:**
- **type**: "ask" or "say"
- **text**: message text
- **ts**: Unix epoch timestamp in milliseconds
**Optional fields:**
- **reasoning**: reasoning text
- **say**: say subtype (when type is "say")
- **ask**: ask subtype (when type is "ask")
- **partial**: streaming flag
- **images**: list of image URIs
- **files**: list of file paths
# EXAMPLES
## Basic Usage
```bash
# Launch interactive mode
cline
# Run a task directly
cline "Create a hello world function in Python"
# Run with verbose output and extended thinking
cline -v --thinking "Analyze this codebase architecture"
```
## Mode Selection
```bash
# Run in plan mode (gather info before acting)
cline -p "Design a REST API for user management"
# Run in act mode with auto-approval (yolo)
cline -y "Fix the typo in README.md"
```
## Using Specific Models
```bash
# Use a specific model
cline -m claude-sonnet-4-5-20250929 "Refactor this function"
# Quick auth setup with model
cline auth -p anthropic -k sk-ant-xxxxx -m claude-sonnet-4-5-20250929
```
## Including Images
```bash
# Include images with explicit flag
cline task -i screenshot.png diagram.jpg "Fix the UI based on these images"
# Or use inline image references in the prompt
cline "Fix the layout shown in @./screenshot.png"
```
## Piped Input
```bash
# Pipe file contents to Cline
cat README.md | cline "Summarize this document"
# Pipe with additional prompt
echo "function add(a, b) { return a + b }" | cline "Add TypeScript types to this"
# Combine piped input with a prompt
git diff | cline "Review these changes and suggest improvements"
```
## Scripting and Automation
```bash
# JSON output for parsing
cline --json "What files are in this directory?" | jq '.text'
# Yolo mode for automated workflows (auto-approves all actions), forces plain text output
cline -y "Run the test suite and fix any failures"
```
## Task History
```bash
# List recent tasks
cline history
# Show more tasks with pagination
cline history -n 20 -p 2
```
## Authentication
```bash
# Interactive authentication wizard
cline auth
# Quick setup for Anthropic
cline auth -p anthropic -k sk-ant-api-xxxxx
# Quick setup for OpenAI
cline auth -p openai-native -k sk-xxxxx -m gpt-4o
# OpenAI-compatible provider with custom base URL
cline auth -p openai -k your-api-key -b https://api.example.com/v1
```
# ENVIRONMENT
**CLINE_DIR** : Override the default configuration directory. When set, Cline stores all data in this directory instead of `~/.cline/data/`.
**CLINE_COMMAND_PERMISSIONS** : JSON configuration for restricting which shell commands Cline can execute. When set, commands are validated against allow/deny patternks before execution. When not set, all commands are allowed.
Format: `{"allow": ["pattern1", "pattern2"], "deny": ["pattern3"], "allowRedirects": true}`
**Fields:**
- **allow** (array of strings): Glob patterns for allowed commands. If specified, only matching commands are permitted. Uses `*` to match any characters and `?` to match a single character. Setting allow on anything will deny all others.
- **deny** (array of strings): Glob patterns for denied commands. Deny rules take precedence over allow rules.
- **allowRedirects** (boolean): Whether to allow shell redirects (`>`, `>>`, `<`, etc.). Defaults to false.
**Rule evaluation:**
1. Check for dangerous characters (backticks outside single quotes, unquoted newlines)
2. Parse command into segments split by operators (`&&`, `||`, `|`, `;`)
3. If redirects detected and `allowRedirects` is not true, command is denied
4. Each segment is validated against deny rules first, then allow rules
5. Subshell contents (`$(...)` and `(...)`) are recursively validated
6. All segments must pass for the command to be allowed
**Examples:**
```bash
# Allow only npm and git commands.
export CLINE_COMMAND_PERMISSIONS='{"allow": ["npm *", "git *"]}'
# Allow development commands but deny dangerous ones. Deny not strictly required here since allow is set.
export CLINE_COMMAND_PERMISSIONS='{"allow": ["npm *", "git *", "node *"], "deny": ["rm -rf *", "sudo *"]}'
# Allow file operations with redirects
export CLINE_COMMAND_PERMISSIONS='{"allow": ["cat *", "echo *"], "allowRedirects": true}'
```
# CONFIGURATION FILES
```
~/.cline/
├── data/ # Default configuration directory
│ ├── globalState.json # Global settings and state
│ ├── secrets.json # API keys and secrets (stored securely)
│ ├── workspace/ # Workspace-specific state
│ └── tasks/ # Task history and conversation data
└── log/ # Log files for debugging
```
View logs with `cline dev log`.
# BUGS
Report bugs at: <https://github.com/cline/cline/issues>
For real-time help, join the Discord community at: <https://discord.gg/cline>
# SEE ALSO
Full documentation: <https://docs.cline.bot>
VS Code extension: <https://marketplace.visualstudio.com/items?itemName=saoudrizwan.claude-dev>
# AUTHORS
Cline is developed by Cline Bot Inc. and the open source community.
# COPYRIGHT
Copyright © 2025 Cline Bot Inc. Licensed under the Apache License 2.0.
+2950
View File
File diff suppressed because it is too large Load Diff
+81
View File
@@ -0,0 +1,81 @@
{
"name": "@cline/cli",
"version": "2.0.0",
"description": "Autonomous coding agent CLI - capable of creating/editing files, running commands, using the browser, and more",
"main": "dist/cli.mjs",
"bin": {
"cline": "./dist/cli.mjs"
},
"type": "module",
"engines": {
"node": ">=20.0.0"
},
"scripts": {
"prepublishOnly": "npm run build:production",
"package:brew": "node ./scripts/update-brew-formula.mts",
"package": "npm pack --pack-destination ./dist",
"build": "node esbuild.mts",
"build:production": "node esbuild.mts --production",
"watch": "node esbuild.mts --watch",
"dev": "IS_DEV=true && npm run link && npm run watch ; npm run unlink",
"clean": "rimraf dist",
"typecheck": "tsc --noEmit",
"link": "npm run build && npm link",
"unlink": "npm unlink -g @cline/cli && npm unlink -g cline",
"test": "vitest",
"test:run": "vitest run"
},
"keywords": [
"cline",
"claude",
"dev",
"mcp",
"openrouter",
"coding",
"agent",
"autonomous",
"chatgpt",
"sonnet",
"ai",
"llama",
"cli"
],
"author": {
"name": "Cline Bot Inc."
},
"license": "Apache-2.0",
"repository": {
"type": "git",
"url": "https://github.com/cline/cline"
},
"homepage": "https://cline.bot",
"bugs": {
"url": "https://github.com/cline/cline/issues"
},
"devDependencies": {
"@types/node": "20.x",
"@types/prompts": "^2.4.9",
"@types/react": "^19.2.9",
"dotenv": "^16.4.5",
"esbuild": "^0.25.0",
"ink-testing-library": "^4.0.0",
"rimraf": "^6.0.1",
"typescript": "^5.4.5",
"vitest": "^4.0.17"
},
"dependencies": {
"@agentclientprotocol/sdk": "^0.13.1",
"aws4fetch": "^1.0.20",
"chalk": "^5.3.0",
"commander": "^12.1.0",
"ink": "npm:@jrichman/ink@6.4.7",
"ink-picture": "^1.3.3",
"ink-spinner": "^5.0.0",
"ora": "^8.0.1",
"nanoid": "^5.1.6",
"pino": "^10.0.0",
"pino-roll": "^4.0.0",
"prompts": "^2.4.2",
"react": "^19.2.3"
}
}
+81
View File
@@ -0,0 +1,81 @@
#!/usr/bin/env node
import { execSync } from "node:child_process"
import { createHash } from "node:crypto"
import { readFile, unlink, writeFile } from "node:fs/promises"
import { dirname, join } from "node:path"
import { fileURLToPath } from "node:url"
const __filename = fileURLToPath(import.meta.url)
const __dirname = dirname(__filename)
const CLI_DIR = join(__dirname, "..")
const FORMULA_PATH = join(CLI_DIR, "cline.rb")
interface PackageJson {
version: string
}
async function getLocalVersion(): Promise<string> {
const packageJson = JSON.parse(await readFile(join(CLI_DIR, "package.json"), "utf-8")) as PackageJson
return packageJson.version
}
async function packAndGetSHA256(version: string): Promise<string> {
console.log("Packing local package...")
execSync("npm run package", { cwd: CLI_DIR, stdio: "inherit" })
const tarballPath = join(CLI_DIR, "dist", `cline-cli-${version}.tgz`)
console.log(`Computing SHA256 for ${tarballPath}...`)
const buffer = await readFile(tarballPath)
const sha256 = createHash("sha256").update(buffer).digest("hex")
// Clean up the tarball
await unlink(tarballPath)
return sha256
}
async function updateFormula(version: string, sha256: string) {
console.log("Updating Homebrew formula...")
let formula = await readFile(FORMULA_PATH, "utf-8")
const tarballUrl = `https://registry.npmjs.org/cline/-/cline-${version}.tgz`
// Update URL - matches pattern like: url "https://registry.npmjs.org/cline/-/cline-1.0.10.tgz"
formula = formula.replace(/url "https:\/\/registry\.npmjs\.org\/cline\/-\/cline-[\d.]+\.tgz"/, `url "${tarballUrl}"`)
// Update SHA256
formula = formula.replace(/sha256 "[a-f0-9]+"/, `sha256 "${sha256}"`)
await writeFile(FORMULA_PATH, formula, "utf-8")
}
async function main() {
try {
const version = await getLocalVersion()
console.log(`\nLocal version: ${version}`)
const sha256 = await packAndGetSHA256(version)
console.log(`SHA256: ${sha256}`)
const tarballUrl = `https://registry.npmjs.org/cline/-/cline-${version}.tgz`
console.log(`Tarball URL: ${tarballUrl}`)
await updateFormula(version, sha256)
console.log("\n✓ Homebrew formula updated successfully!")
console.log("\nNext steps:")
console.log("1. Review the changes in cline.rb")
console.log("2. Test locally: brew install --build-from-source ./cline.rb")
console.log("3. Commit and push to your homebrew tap repository")
} catch (error) {
const errorMessage = error instanceof Error ? error.message : String(error)
console.error(`\n✗ Error: ${errorMessage}\n`)
process.exit(1)
}
}
main()
+248
View File
@@ -0,0 +1,248 @@
/**
* ACP-based implementation of DiffViewProvider that uses the ACP client's
* filesystem capabilities for reading and writing files.
*
* This provider attempts to use the ACP client's fs/read_text_file and
* fs/write_text_file methods when available, falling back to the
* FileEditProvider's local filesystem implementation otherwise.
*
* @module acp
*/
import type * as acp from "@agentclientprotocol/sdk"
import { workspaceResolver } from "@core/workspace"
import { createDirectoriesForFile } from "@utils/fs"
import { getCwd } from "@utils/path"
import * as fs from "fs/promises"
import * as iconv from "iconv-lite"
import { HostProvider } from "@/hosts/host-provider"
import { FileEditProvider } from "@/integrations/editor/FileEditProvider"
import { detectEncoding } from "@/integrations/misc/extract-text"
import type { FileDiagnostics } from "@/shared/proto/index.cline"
import { Logger } from "@/shared/services/Logger"
/**
* A function that resolves the current session ID.
* This is used by ACPDiffViewProvider to get the session ID at runtime,
* since the provider may be created before a session exists.
*/
export type SessionIdResolver = () => string | undefined
/**
* A DiffViewProvider implementation that uses the ACP client's filesystem
* capabilities when available, with fallback to local filesystem operations.
*
* This class extends FileEditProvider and overrides the file I/O methods to
* use the ACP protocol's fs/read_text_file and fs/write_text_file requests
* when the client supports these capabilities. This allows the editor (client)
* to handle file operations, which enables features like:
* - Reading unsaved editor state
* - Tracking file modifications in the editor
* - Proper integration with the client's undo/redo stack
*/
export class ACPDiffViewProvider extends FileEditProvider {
private readonly connection: acp.AgentSideConnection
private readonly clientCapabilities: acp.ClientCapabilities | undefined
private readonly sessionIdResolver: SessionIdResolver
/**
* Creates a new ACPDiffViewProvider.
*
* @param connection - The ACP agent-side connection for making requests
* @param clientCapabilities - The client's advertised capabilities
* @param sessionIdResolver - A function that returns the current session ID
*/
constructor(
connection: acp.AgentSideConnection,
clientCapabilities: acp.ClientCapabilities | undefined,
sessionIdResolver: SessionIdResolver,
) {
super()
this.connection = connection
this.clientCapabilities = clientCapabilities
this.sessionIdResolver = sessionIdResolver
}
/**
* Gets the current session ID, or throws if no session is active.
*/
private getSessionId(): string {
const sessionId = this.sessionIdResolver()
if (!sessionId) {
throw new Error("No active ACP session. Cannot perform file operation.")
}
return sessionId
}
/**
* Check if the client supports file read operations.
*/
private canReadFile(): boolean {
return this.clientCapabilities?.fs?.readTextFile === true
}
/**
* Check if the client supports file write operations.
*/
private canWriteFile(): boolean {
return this.clientCapabilities?.fs?.writeTextFile === true
}
/**
* Opens a file for editing, using ACP fs capabilities when available.
*
* If the client supports fs/read_text_file, this method will read the file
* content via the ACP connection, which may include unsaved editor state.
* Otherwise, it falls back to the FileEditProvider's local fs implementation.
*/
override async open(relPath: string, options?: { displayPath?: string }): Promise<void> {
// If we can't read files via ACP, fall back to FileEditProvider
if (!this.canReadFile()) {
Logger.debug("[ACPDiffViewProvider] Client does not support fs.readTextFile, falling back to local fs")
return super.open(relPath, options)
}
// Set up state - this replicates the DiffViewProvider.open() logic
// but uses ACP for file reading instead of local fs
this.isEditing = true
const cwd = await getCwd()
const absolutePathResolved = workspaceResolver.resolveWorkspacePath(cwd, relPath, "ACPDiffViewProvider.open.absolutePath")
this.absolutePath = typeof absolutePathResolved === "string" ? absolutePathResolved : absolutePathResolved.absolutePath
this.relPath = options?.displayPath ?? relPath
const fileExists = this.editType === "modify"
// Read file content
if (fileExists) {
// Try to save any dirty state in the editor first
try {
await HostProvider.workspace.saveOpenDocumentIfDirty({
filePath: this.absolutePath!,
})
} catch {
// Ignore errors - the host may not support this
}
// Read file content via ACP
try {
Logger.debug("[ACPDiffViewProvider] Reading file via ACP:", this.absolutePath)
const response = await this.connection.readTextFile({
sessionId: this.getSessionId(),
path: this.absolutePath!,
})
this.originalContent = response.content
// ACP always returns UTF-8 text content
this.fileEncoding = "utf8"
Logger.debug("[ACPDiffViewProvider] Read file successfully, length:", response.content.length)
} catch (error) {
// If ACP read fails, fall back to local fs
Logger.debug("[ACPDiffViewProvider] ACP read failed, falling back to local fs:", error)
const fileBuffer = await fs.readFile(this.absolutePath!)
this.fileEncoding = await detectEncoding(fileBuffer)
this.originalContent = iconv.decode(fileBuffer, this.fileEncoding)
}
} else {
this.originalContent = ""
this.fileEncoding = "utf8"
}
// Create directories for new files
const createdDirs = await createDirectoriesForFile(this.absolutePath!)
// Store for potential cleanup - access via the private field workaround
;(this as any).createdDirs = createdDirs
// Make sure the file exists before we proceed
if (!fileExists) {
// For new files, write via ACP if possible, otherwise local fs
if (this.canWriteFile()) {
try {
await this.connection.writeTextFile({
sessionId: this.getSessionId(),
path: this.absolutePath!,
content: "",
})
} catch {
// Fall back to local fs
await fs.writeFile(this.absolutePath!, "")
}
} else {
await fs.writeFile(this.absolutePath!, "")
}
}
// Get diagnostics before editing
let preDiagnostics: FileDiagnostics[] = []
try {
preDiagnostics = (await HostProvider.workspace.getDiagnostics({})).fileDiagnostics
} catch {
preDiagnostics = []
}
;(this as any).preDiagnostics = preDiagnostics
// Call the parent's openDiffEditor to set up in-memory document content
await this.openDiffEditor()
await this.scrollEditorToLine(0)
;(this as any).streamedLines = []
}
/**
* Scrolls the editor to a specific line.
* No-op for file-based providers, but needed for protected access.
*/
protected override async scrollEditorToLine(_line: number): Promise<void> {
// No-op: No visual editor to scroll
}
/**
* Opens the diff editor.
*/
protected override async openDiffEditor(): Promise<void> {
// Set up in-memory document content from the original content
// no-op: No visual editor to open
}
/**
* Saves the document content, using ACP fs capabilities when available.
*
* If the client supports fs/write_text_file, this method will write the file
* content via the ACP connection. Otherwise, it falls back to the
* FileEditProvider's local fs implementation.
*/
protected override async saveDocument(): Promise<Boolean> {
// If we can't write files via ACP, fall back to FileEditProvider
if (!this.canWriteFile()) {
Logger.debug("[ACPDiffViewProvider] Client does not support fs.writeTextFile, falling back to local fs")
return super.saveDocument()
}
const content = await this.getContent()
if (!this.absolutePath || content === undefined) {
return false
}
try {
Logger.debug("[ACPDiffViewProvider] Writing file via ACP:", {
path: this.absolutePath,
contentLength: content.length,
})
await this.connection.writeTextFile({
sessionId: this.getSessionId(),
path: this.absolutePath,
content: content,
})
Logger.debug("[ACPDiffViewProvider] Write file successfully")
return true
} catch (error) {
// If ACP write fails, fall back to local fs
Logger.debug("[ACPDiffViewProvider] ACP write failed, falling back to local fs:", error)
return super.saveDocument()
}
}
}
@@ -0,0 +1,402 @@
/**
* ACP Host Bridge Client Provider
*
* Implements HostBridgeClientProvider for ACP mode, providing stub implementations
* of the 4 required service clients. These clients conform to the interfaces in
* host-bridge-client-types.ts and will use ACP connection capabilities where applicable.
*
* @module acp
*/
import type * as acp from "@agentclientprotocol/sdk"
import type {
DiffServiceClientInterface,
EnvServiceClientInterface,
WindowServiceClientInterface,
WorkspaceServiceClientInterface,
} from "@generated/hosts/host-bridge-client-types"
import type { HostBridgeClientProvider, StreamingCallbacks } from "@hosts/host-provider-types"
import * as proto from "@shared/proto/index"
import { ClineClient } from "@/shared/cline"
import { Logger } from "@/shared/services/Logger"
/**
* Function type that resolves the current session ID.
* Returns undefined if no session is active.
*/
export type SessionIdResolver = () => string | undefined
/**
* Function type that resolves the current working directory.
* Returns undefined if no cwd is available (will fall back to process.cwd()).
*/
export type CwdResolver = () => string | undefined
/**
* ACP implementation of DiffService client.
*
* Handles diff operations for the ACP environment. Most operations are stubs
* that will be implemented in the next phase using ACP extension methods or
* the fs capabilities (readTextFile/writeTextFile).
*/
class ACPDiffServiceClient implements DiffServiceClientInterface {
async openDiff(_request: proto.host.OpenDiffRequest): Promise<proto.host.OpenDiffResponse> {
// Next phase: Could use ACP client capabilities to open a diff view in the editor.
// This would involve sending an ACP extension notification/request to the client
// to display a side-by-side diff of the original vs modified content.
Logger.debug("[ACPDiffServiceClient] openDiff called (stub)")
return proto.host.OpenDiffResponse.create({})
}
async getDocumentText(request: proto.host.GetDocumentTextRequest): Promise<proto.host.GetDocumentTextResponse> {
// Next phase: Use connection.readTextFile if clientCapabilities.fs.readTextFile is available.
// This would read the current document content from the editor, including any unsaved changes.
// For now, return empty content.
Logger.debug("[ACPDiffServiceClient] getDocumentText called (stub)", { diffId: request.diffId })
return proto.host.GetDocumentTextResponse.create({ content: "" })
}
async replaceText(_request: proto.host.ReplaceTextRequest): Promise<proto.host.ReplaceTextResponse> {
// Next phase: Use connection.writeTextFile if clientCapabilities.fs.writeTextFile is available.
// This would replace text in the document at the specified range.
Logger.debug("[ACPDiffServiceClient] replaceText called (stub)")
return proto.host.ReplaceTextResponse.create({})
}
async scrollDiff(_request: proto.host.ScrollDiffRequest): Promise<proto.host.ScrollDiffResponse> {
// Next phase: Send ACP extension notification to scroll the diff view to a specific line.
// No visual editor in ACP mode by default, so this is a no-op.
Logger.debug("[ACPDiffServiceClient] scrollDiff called (stub)")
return proto.host.ScrollDiffResponse.create({})
}
async truncateDocument(_request: proto.host.TruncateDocumentRequest): Promise<proto.host.TruncateDocumentResponse> {
// Next phase: Read file using readTextFile, truncate content, write back using writeTextFile.
// This is used to truncate a document to a specific line count.
Logger.debug("[ACPDiffServiceClient] truncateDocument called (stub)")
return proto.host.TruncateDocumentResponse.create({})
}
async saveDocument(_request: proto.host.SaveDocumentRequest): Promise<proto.host.SaveDocumentResponse> {
// Next phase: Use connection.writeTextFile to persist the document to disk.
// This saves the current document content to the file system.
Logger.debug("[ACPDiffServiceClient] saveDocument called (stub)")
return proto.host.SaveDocumentResponse.create({})
}
async closeAllDiffs(_request: proto.host.CloseAllDiffsRequest): Promise<proto.host.CloseAllDiffsResponse> {
// Next phase: Send ACP extension notification to close all diff views in the editor.
// No visual diff views in ACP mode by default, so this is a no-op.
Logger.debug("[ACPDiffServiceClient] closeAllDiffs called (stub)")
return proto.host.CloseAllDiffsResponse.create({})
}
async openMultiFileDiff(_request: proto.host.OpenMultiFileDiffRequest): Promise<proto.host.OpenMultiFileDiffResponse> {
// Next phase: Send ACP extension notification to open a multi-file diff view.
// This would display changes across multiple files in the editor.
Logger.debug("[ACPDiffServiceClient] openMultiFileDiff called (stub)")
return proto.host.OpenMultiFileDiffResponse.create({})
}
}
/**
* ACP implementation of EnvService client.
*
* Handles environment operations like clipboard access, version info, and telemetry.
* Most operations are stubs that will be implemented using ACP extension methods.
*/
class ACPEnvServiceClient implements EnvServiceClientInterface {
private readonly version: string
constructor(
_clientCapabilities: acp.ClientCapabilities | undefined,
_sessionIdResolver: SessionIdResolver,
version: string = "1.0.0",
) {
this.version = version
}
async debugLog(request: proto.cline.StringRequest): Promise<proto.cline.Empty> {
Logger.debug(request.value)
return proto.cline.Empty.create()
}
async clipboardWriteText(_request: proto.cline.StringRequest): Promise<proto.cline.Empty> {
Logger.debug("[ACPEnvServiceClient] clipboardWriteText called (stub)")
return proto.cline.Empty.create()
}
async clipboardReadText(_request: proto.cline.EmptyRequest): Promise<proto.cline.String> {
Logger.debug("[ACPEnvServiceClient] clipboardReadText called (stub)")
return proto.cline.String.create({ value: "" })
}
async getHostVersion(_request: proto.cline.EmptyRequest): Promise<proto.host.GetHostVersionResponse> {
// Return version info for the ACP agent.
return proto.host.GetHostVersionResponse.create({
version: this.version,
platform: "Cline ACP Agent",
clineType: ClineClient.Cli,
})
}
async getIdeRedirectUri(_request: proto.cline.EmptyRequest): Promise<proto.cline.String> {
Logger.debug("[ACPEnvServiceClient] getIdeRedirectUri called (stub)")
return proto.cline.String.create({ value: "" })
}
async getTelemetrySettings(_request: proto.cline.EmptyRequest): Promise<proto.host.GetTelemetrySettingsResponse> {
// Return telemetry as disabled by default in ACP mode.
return proto.host.GetTelemetrySettingsResponse.create({
isEnabled: proto.host.Setting.DISABLED,
})
}
subscribeToTelemetrySettings(
_request: proto.cline.EmptyRequest,
callbacks: StreamingCallbacks<proto.host.TelemetrySettingsEvent>,
): () => void {
// Send initial telemetry settings (disabled) and return unsubscribe function.
callbacks.onResponse(
proto.host.TelemetrySettingsEvent.create({
isEnabled: proto.host.Setting.DISABLED,
}),
)
// Return no-op unsubscribe function
return () => {}
}
async shutdown(_request: proto.cline.EmptyRequest): Promise<proto.cline.Empty> {
// Next phase: Graceful ACP connection shutdown.
// This would cleanly close the ACP connection and release resources.
Logger.debug("[ACPEnvServiceClient] shutdown called (stub)")
return proto.cline.Empty.create()
}
}
/**
* ACP implementation of WindowService client.
*
* Handles window/UI operations like showing documents, dialogs, and messages.
* Most operations are stubs that will be implemented using ACP extension methods.
*/
class ACPWindowServiceClient implements WindowServiceClientInterface {
constructor(_clientCapabilities: acp.ClientCapabilities | undefined, _sessionIdResolver: SessionIdResolver) {}
async showTextDocument(request: proto.host.ShowTextDocumentRequest): Promise<proto.host.TextEditorInfo> {
// Next phase: Send ACP extension request to open document in the editor.
// This would tell the ACP client to open the specified file.
Logger.debug("[ACPWindowServiceClient] showTextDocument called (stub)", { path: request.path })
return proto.host.TextEditorInfo.create({
documentPath: request.path,
})
}
async showOpenDialogue(_request: proto.host.ShowOpenDialogueRequest): Promise<proto.host.SelectedResources> {
// Next phase: Send ACP extension request for file picker dialog.
// This would display a file open dialog in the ACP client.
Logger.debug("[ACPWindowServiceClient] showOpenDialogue called (stub)")
return proto.host.SelectedResources.create({ paths: [] })
}
async showMessage(request: proto.host.ShowMessageRequest): Promise<proto.host.SelectedResponse> {
// Next phase: Send ACP extension notification to show message in the editor.
// This would display an information/warning/error message to the user.
Logger.debug("[ACPWindowServiceClient] showMessage called (stub)", {
message: request.message,
type: request.type,
})
return proto.host.SelectedResponse.create({})
}
async showInputBox(_request: proto.host.ShowInputBoxRequest): Promise<proto.host.ShowInputBoxResponse> {
// Next phase: Send ACP extension request for input dialog.
// This would display an input box for user text entry.
Logger.debug("[ACPWindowServiceClient] showInputBox called (stub)")
return proto.host.ShowInputBoxResponse.create({ response: "" })
}
async showSaveDialog(_request: proto.host.ShowSaveDialogRequest): Promise<proto.host.ShowSaveDialogResponse> {
// Next phase: Send ACP extension request for save dialog.
// This would display a file save dialog in the ACP client.
Logger.debug("[ACPWindowServiceClient] showSaveDialog called (stub)")
return proto.host.ShowSaveDialogResponse.create({ selectedPath: "" })
}
async openFile(request: proto.host.OpenFileRequest): Promise<proto.host.OpenFileResponse> {
// Next phase: Send ACP extension request to open file in the editor.
// This would open the specified file in the ACP client's editor.
Logger.debug("[ACPWindowServiceClient] openFile called (stub)", { filePath: request.filePath })
return proto.host.OpenFileResponse.create({})
}
async openSettings(_request: proto.host.OpenSettingsRequest): Promise<proto.host.OpenSettingsResponse> {
// Next phase: Send ACP extension request to open settings panel.
// This would open the settings/preferences in the ACP client.
Logger.debug("[ACPWindowServiceClient] openSettings called (stub)")
return proto.host.OpenSettingsResponse.create({})
}
async getOpenTabs(_request: proto.host.GetOpenTabsRequest): Promise<proto.host.GetOpenTabsResponse> {
// Next phase: Send ACP extension request to list open tabs/documents.
// This would return a list of currently open files in the editor.
Logger.debug("[ACPWindowServiceClient] getOpenTabs called (stub)")
return proto.host.GetOpenTabsResponse.create({ paths: [] })
}
async getVisibleTabs(_request: proto.host.GetVisibleTabsRequest): Promise<proto.host.GetVisibleTabsResponse> {
// Next phase: Send ACP extension request to list visible tabs.
// This would return a list of visible tabs/panes in the editor.
Logger.debug("[ACPWindowServiceClient] getVisibleTabs called (stub)")
return proto.host.GetVisibleTabsResponse.create({ paths: [] })
}
async getActiveEditor(_request: proto.host.GetActiveEditorRequest): Promise<proto.host.GetActiveEditorResponse> {
// Next phase: Send ACP extension request to get active editor info.
// This would return information about the currently focused editor.
Logger.debug("[ACPWindowServiceClient] getActiveEditor called (stub)")
return proto.host.GetActiveEditorResponse.create({})
}
}
/**
* ACP implementation of WorkspaceService client.
*
* Handles workspace operations like getting paths, diagnostics, and terminal commands.
* Uses the cwdResolver to get the current working directory, falling back to process.cwd().
*/
class ACPWorkspaceServiceClient implements WorkspaceServiceClientInterface {
private readonly _clientCapabilities: acp.ClientCapabilities | undefined
private readonly cwdResolver: CwdResolver
constructor(
clientCapabilities: acp.ClientCapabilities | undefined,
_sessionIdResolver: SessionIdResolver,
cwdResolver: CwdResolver,
) {
this._clientCapabilities = clientCapabilities
this.cwdResolver = cwdResolver
}
/**
* Get the current working directory, using the resolver if available,
* otherwise falling back to process.cwd().
*/
private getCwd(): string {
return this.cwdResolver() ?? process.cwd()
}
async getWorkspacePaths(_request: proto.host.GetWorkspacePathsRequest): Promise<proto.host.GetWorkspacePathsResponse> {
// Return the current working directory from the resolver.
const cwd = this.getCwd()
Logger.debug("[ACPWorkspaceServiceClient] getWorkspacePaths called", { cwd })
return proto.host.GetWorkspacePathsResponse.create({
paths: [cwd],
})
}
async saveOpenDocumentIfDirty(
_request: proto.host.SaveOpenDocumentIfDirtyRequest,
): Promise<proto.host.SaveOpenDocumentIfDirtyResponse> {
// Next phase: Use ACP extension or fs.writeTextFile to save dirty documents.
// This would save any unsaved changes in the specified document.
Logger.debug("[ACPWorkspaceServiceClient] saveOpenDocumentIfDirty called (stub)")
return proto.host.SaveOpenDocumentIfDirtyResponse.create({})
}
async getDiagnostics(_request: proto.host.GetDiagnosticsRequest): Promise<proto.host.GetDiagnosticsResponse> {
// Next phase: Send ACP extension request for diagnostics (errors, warnings).
// This would return linting/compilation errors from the ACP client.
Logger.debug("[ACPWorkspaceServiceClient] getDiagnostics called (stub)")
return proto.host.GetDiagnosticsResponse.create({ fileDiagnostics: [] })
}
async openProblemsPanel(_request: proto.host.OpenProblemsPanelRequest): Promise<proto.host.OpenProblemsPanelResponse> {
// Next phase: Send ACP extension notification to open the problems panel.
// This would show the diagnostics/problems view in the editor.
Logger.debug("[ACPWorkspaceServiceClient] openProblemsPanel called (stub)")
return proto.host.OpenProblemsPanelResponse.create({})
}
async openInFileExplorerPanel(
request: proto.host.OpenInFileExplorerPanelRequest,
): Promise<proto.host.OpenInFileExplorerPanelResponse> {
// Next phase: Send ACP extension notification to reveal file in explorer.
// This would highlight/reveal the specified path in the file tree.
Logger.debug("[ACPWorkspaceServiceClient] openInFileExplorerPanel called (stub)", { path: request.path })
return proto.host.OpenInFileExplorerPanelResponse.create({})
}
async openClineSidebarPanel(
_request: proto.host.OpenClineSidebarPanelRequest,
): Promise<proto.host.OpenClineSidebarPanelResponse> {
// Next phase: Send ACP extension notification to open Cline sidebar.
// This would show the Cline panel/sidebar in the editor.
Logger.debug("[ACPWorkspaceServiceClient] openClineSidebarPanel called (stub)")
return proto.host.OpenClineSidebarPanelResponse.create({})
}
async openTerminalPanel(_request: proto.host.OpenTerminalRequest): Promise<proto.host.OpenTerminalResponse> {
// Next phase: Send ACP extension notification or use createTerminal capability.
// This would open/show the terminal panel in the editor.
Logger.debug("[ACPWorkspaceServiceClient] openTerminalPanel called (stub)")
return proto.host.OpenTerminalResponse.create({})
}
async executeCommandInTerminal(
request: proto.host.ExecuteCommandInTerminalRequest,
): Promise<proto.host.ExecuteCommandInTerminalResponse> {
// Next phase: Use connection.createTerminal if clientCapabilities.terminal is available.
// This would execute the specified command in a terminal via the ACP client.
// The ACP SDK provides createTerminal() which returns a TerminalHandle with
// methods like currentOutput(), waitForExit(), kill(), and release().
Logger.debug("[ACPWorkspaceServiceClient] executeCommandInTerminal called (stub)", {
command: request.command,
hasTerminalCapability: this._clientCapabilities?.terminal,
})
return proto.host.ExecuteCommandInTerminalResponse.create({})
}
async openFolder(request: proto.host.OpenFolderRequest): Promise<proto.host.OpenFolderResponse> {
// Next phase: Send ACP extension request to change workspace/folder.
// This would open a new folder/workspace in the ACP client.
Logger.debug("[ACPWorkspaceServiceClient] openFolder called (stub)", { path: request.path })
return proto.host.OpenFolderResponse.create({ success: true })
}
}
/**
* ACP Host Bridge Client Provider
*
* Provides the 4 service clients required by HostBridgeClientProvider interface,
* implemented for the ACP environment. Uses the ACP connection and client capabilities
* to delegate operations to the ACP client where possible.
*/
export class ACPHostBridgeClientProvider implements HostBridgeClientProvider {
workspaceClient: WorkspaceServiceClientInterface
envClient: EnvServiceClientInterface
windowClient: WindowServiceClientInterface
diffClient: DiffServiceClientInterface
/**
* Creates a new ACPHostBridgeClientProvider.
*
* @param connection - The ACP agent-side connection for making requests
* @param clientCapabilities - The client's advertised capabilities
* @param sessionIdResolver - Function that returns the current session ID
* @param cwdResolver - Function that returns the current working directory
* @param debug - Whether to enable debug logging
* @param version - Version string for getHostVersion (optional)
*/
constructor(
clientCapabilities: acp.ClientCapabilities | undefined,
sessionIdResolver: SessionIdResolver,
cwdResolver: CwdResolver,
version: string = "1.0.0",
) {
this.workspaceClient = new ACPWorkspaceServiceClient(clientCapabilities, sessionIdResolver, cwdResolver)
this.envClient = new ACPEnvServiceClient(clientCapabilities, sessionIdResolver, version)
this.windowClient = new ACPWindowServiceClient(clientCapabilities, sessionIdResolver)
this.diffClient = new ACPDiffServiceClient()
}
}
+157
View File
@@ -0,0 +1,157 @@
/**
* AcpAgent - Thin wrapper that bridges stdio connection to ClineAgent.
*
* This class wraps the ClineAgent and connects it to an ACP AgentSideConnection
* for stdio-based communication. It:
* - Wires up the permission handler to call connection.requestPermission()
* - Subscribes to ClineAgent session events and forwards them to connection.sessionUpdate()
* - Delegates all acp.Agent methods to the internal ClineAgent
*
* For programmatic usage without stdio, use ClineAgent directly.
*
* @module acp
*/
import type * as acp from "@agentclientprotocol/sdk"
import { Logger } from "@/shared/services/Logger.js"
import { ClineAgent } from "../agent/ClineAgent.js"
import type { AcpAgentOptions, SessionUpdateType } from "../agent/types.js"
/**
* ACP Agent wrapper that bridges stdio connection to ClineAgent.
*
* This is the class used by runAcpMode() for stdio-based ACP communication.
* It creates an internal ClineAgent and wires up the connection for:
* - Permission requests (via connection.requestPermission)
* - Session updates (via connection.sessionUpdate)
*/
export class AcpAgent implements acp.Agent {
private readonly connection: acp.AgentSideConnection
private readonly clineAgent: ClineAgent
/** Track which sessions we've subscribed to for event forwarding */
private readonly subscribedSessions: Set<string> = new Set()
constructor(connection: acp.AgentSideConnection, options: AcpAgentOptions) {
this.connection = connection
// Create the internal ClineAgent
this.clineAgent = new ClineAgent(options)
// Wire up the permission handler to use the connection
this.clineAgent.setPermissionHandler(async (request, resolve) => {
try {
Logger.debug("[AcpAgent] Forwarding permission request to connection")
const response = await this.connection.requestPermission({
sessionId: this.getCurrentSessionId() ?? "",
toolCall: request.toolCall,
options: request.options,
})
resolve(response)
} catch (error) {
Logger.debug("[AcpAgent] Error requesting permission:", error)
resolve({ outcome: "rejected" as unknown as acp.RequestPermissionOutcome })
}
})
}
/**
* Get the current active session ID from the ClineAgent.
*/
private getCurrentSessionId(): string | undefined {
// Find the session that's currently processing
for (const [sessionId, session] of this.clineAgent.sessions) {
if (session.controller?.task) {
return sessionId
}
}
// Fall back to the first session if none is actively processing
const firstSession = this.clineAgent.sessions.keys().next()
return firstSession.done ? undefined : firstSession.value
}
/**
* Subscribe to session events and forward them to the connection.
*/
private subscribeToSessionEvents(sessionId: string): void {
if (this.subscribedSessions.has(sessionId)) {
return
}
const emitter = this.clineAgent.emitterForSession(sessionId)
// Forward session update by adding the sessionUpdate discriminator
const forwardSessionUpdate = <K extends SessionUpdateType>(eventName: K) => {
emitter.on(eventName, (payload: Record<string, unknown>) => {
const update = {
sessionUpdate: eventName,
...payload,
} as acp.SessionUpdate
this.connection.sessionUpdate({ sessionId, update }).catch((error) => {
Logger.error(`[AcpAgent] Error forwarding ${eventName}:`, error)
})
})
}
// Forward all standard session updates
forwardSessionUpdate("agent_message_chunk")
forwardSessionUpdate("agent_thought_chunk")
forwardSessionUpdate("tool_call")
forwardSessionUpdate("tool_call_update")
forwardSessionUpdate("available_commands_update")
forwardSessionUpdate("plan")
forwardSessionUpdate("current_mode_update")
forwardSessionUpdate("user_message_chunk")
forwardSessionUpdate("config_option_update")
forwardSessionUpdate("session_info_update")
// Handle errors specially (not part of ACP SessionUpdate)
emitter.on("error", (error) => {
Logger.error("[AcpAgent] Session error:", error)
})
this.subscribedSessions.add(sessionId)
}
// ============================================================
// acp.Agent Interface Implementation - Delegate to ClineAgent
// ============================================================
async initialize(params: acp.InitializeRequest): Promise<acp.InitializeResponse> {
return await this.clineAgent.initialize(params, this.connection)
}
async newSession(params: acp.NewSessionRequest): Promise<acp.NewSessionResponse> {
const response = await this.clineAgent.newSession(params)
// Subscribe to events for this new session
this.subscribeToSessionEvents(response.sessionId)
return response
}
async prompt(params: acp.PromptRequest): Promise<acp.PromptResponse> {
// Ensure we're subscribed to this session's events
this.subscribeToSessionEvents(params.sessionId)
return this.clineAgent.prompt(params)
}
async cancel(params: acp.CancelNotification): Promise<void> {
return this.clineAgent.cancel(params)
}
async setSessionMode(params: acp.SetSessionModeRequest): Promise<acp.SetSessionModeResponse> {
return this.clineAgent.setSessionMode(params)
}
async unstable_setSessionModel(params: acp.SetSessionModelRequest): Promise<acp.SetSessionModelResponse> {
return this.clineAgent.unstable_setSessionModel(params)
}
async authenticate(params: acp.AuthenticateRequest): Promise<acp.AuthenticateResponse> {
return this.clineAgent.authenticate(params)
}
async shutdown(): Promise<void> {
this.subscribedSessions.clear()
return this.clineAgent.shutdown()
}
}
File diff suppressed because it is too large Load Diff
+143
View File
@@ -0,0 +1,143 @@
/**
* Entry point for ACP (Agent Client Protocol) mode.
*
* When the CLI is invoked with `--acp`, this module sets up the ACP connection
* and runs Cline as an ACP-compliant agent communicating over stdio.
*
* This module exports:
* - `ClineAgent` - Decoupled agent for programmatic use (no stdio dependency)
* - `AcpAgent` - Thin wrapper that bridges stdio connection to ClineAgent
* - `ClineSessionEmitter` - Typed EventEmitter for per-session events
* - `runAcpMode` - Function to run Cline in stdio-based ACP mode
*
* @module acp
*/
import { AgentSideConnection, ndJsonStream } from "@agentclientprotocol/sdk"
import { Logger } from "@/shared/services/Logger"
import { version as CLI_VERSION } from "../../../package.json"
import { AcpAgent } from "./AcpAgent.js"
import { nodeToWebReadable, nodeToWebWritable } from "./streamUtils.js"
// Re-export classes for programmatic use
export { ClineAgent } from "../agent/ClineAgent.js"
export { ClineSessionEmitter } from "../agent/ClineSessionEmitter.js"
// Re-export types
export type {
AcpAgentOptions,
AcpSessionState,
ClineAcpSession,
ClineAgentOptions,
ClineSessionEvents,
PermissionHandler,
PermissionResolver,
} from "../agent/types.js"
export { AcpAgent } from "./AcpAgent.js"
/** Original console methods for restoration if needed */
const originalConsole = {
log: console.log,
info: console.info,
warn: console.warn,
debug: console.debug,
error: console.error,
}
/**
* Redirect all console output to stderr.
*
* In ACP mode, stdout is reserved exclusively for JSON-RPC communication.
* All logging must go to stderr to avoid corrupting the protocol stream.
*/
function redirectConsoleToStderr(): void {
console.log = (...args) => console.error(...args)
console.info = (...args) => console.error(...args)
console.warn = (...args) => console.error(...args)
console.debug = (...args) => console.error(...args)
// console.error already goes to stderr
}
/**
* Restore console methods to their original behavior.
*/
export function restoreConsole(): void {
console.log = originalConsole.log
console.info = originalConsole.info
console.warn = originalConsole.warn
console.debug = originalConsole.debug
console.error = originalConsole.error
}
export interface AcpModeOptions {
/** Path to Cline configuration directory */
config?: string
/** Working directory (default: process.cwd()) */
cwd?: string
/** Enable verbose/debug logging to stderr */
verbose?: boolean
}
/**
* Run Cline in ACP mode.
*
* This function:
* 1. Redirects console output to stderr (stdout reserved for JSON-RPC)
* 2. Sets up the ndJsonStream for stdio communication
* 3. Creates the AgentSideConnection with our AcpAgent factory
* 4. Initializes the CLI infrastructure (StateManager, Controller, etc.)
* 5. Keeps the process alive until the connection closes
*
* @param options - Configuration options for ACP mode
*/
export async function runAcpMode(options: AcpModeOptions = {}): Promise<void> {
redirectConsoleToStderr()
const outputStream = nodeToWebWritable(process.stdout)
const inputStream = nodeToWebReadable(process.stdin)
const stream = ndJsonStream(outputStream, inputStream)
let agent: AcpAgent | null = null
new AgentSideConnection((conn) => {
agent = new AcpAgent(conn, {
version: CLI_VERSION,
debug: Boolean(options.verbose),
})
return agent
}, stream)
let isShuttingDown = false
const shutdown = async () => {
if (isShuttingDown) {
// Force exit on second signal
process.exit(1)
}
isShuttingDown = true
try {
await agent?.shutdown()
restoreConsole()
} catch (error) {
Logger.error("[ACP] Error during shutdown:", error)
}
process.exit(0)
}
process.on("SIGINT", shutdown)
process.on("SIGTERM", shutdown)
// Keep the process alive
// The ndJsonStream will handle stdin events automatically.
// We need to ensure the process doesn't exit while waiting for input.
process.stdin.resume()
// Handle stdin end (client disconnected)
process.stdin.on("end", shutdown)
// Handle stdin errors
process.stdin.on("error", async (error) => {
Logger.error("[ACP] stdin error:", error)
await shutdown()
})
Logger.info("[ACP] Process is now listening for ACP requests on stdin")
}
+54
View File
@@ -0,0 +1,54 @@
/**
* Stream conversion utilities for ACP mode.
*
* The ACP SDK's ndJsonStream function expects Web Streams (ReadableStream/WritableStream),
* but Node.js provides its own stream types. These utilities convert between them.
*
* @module acp/streamUtils
*/
import type { Readable, Writable } from "node:stream"
/**
* Convert a Node.js Writable stream to a Web WritableStream.
*
* Used to convert process.stdout for ACP output.
*
* @param nodeStream - Node.js Writable stream (e.g., process.stdout)
* @returns Web WritableStream compatible with ndJsonStream
*/
export function nodeToWebWritable(nodeStream: Writable): WritableStream<Uint8Array> {
return new WritableStream<Uint8Array>({
write(chunk) {
return new Promise<void>((resolve, reject) => {
nodeStream.write(Buffer.from(chunk), (err) => {
if (err) {
reject(err)
} else {
resolve()
}
})
})
},
})
}
/**
* Convert a Node.js Readable stream to a Web ReadableStream.
*
* Used to convert process.stdin for ACP input.
*
* @param nodeStream - Node.js Readable stream (e.g., process.stdin)
* @returns Web ReadableStream compatible with ndJsonStream
*/
export function nodeToWebReadable(nodeStream: Readable): ReadableStream<Uint8Array> {
return new ReadableStream<Uint8Array>({
start(controller) {
nodeStream.on("data", (chunk: Buffer) => {
controller.enqueue(new Uint8Array(chunk))
})
nodeStream.on("end", () => controller.close())
nodeStream.on("error", (err) => controller.error(err))
},
})
}
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,274 @@
/**
* Tests for ClineSessionEmitter - Typed EventEmitter for per-session ACP events.
*/
import { beforeEach, describe, expect, it, vi } from "vitest"
import { ClineSessionEmitter } from "./ClineSessionEmitter.js"
import type { SessionUpdatePayload } from "./types.js"
describe("ClineSessionEmitter", () => {
let emitter: ClineSessionEmitter
beforeEach(() => {
emitter = new ClineSessionEmitter()
})
describe("on/emit", () => {
it("should emit and receive agent_message_chunk events", () => {
const listener = vi.fn()
const payload: SessionUpdatePayload<"agent_message_chunk"> = {
content: { type: "text", text: "Hello, world!" },
}
emitter.on("agent_message_chunk", listener)
emitter.emit("agent_message_chunk", payload)
expect(listener).toHaveBeenCalledTimes(1)
expect(listener).toHaveBeenCalledWith(payload)
})
it("should emit and receive agent_thought_chunk events", () => {
const listener = vi.fn()
const payload: SessionUpdatePayload<"agent_thought_chunk"> = {
content: { type: "text", text: "Thinking..." },
}
emitter.on("agent_thought_chunk", listener)
emitter.emit("agent_thought_chunk", payload)
expect(listener).toHaveBeenCalledTimes(1)
expect(listener).toHaveBeenCalledWith(payload)
})
it("should emit and receive tool_call events", () => {
const listener = vi.fn()
const payload: SessionUpdatePayload<"tool_call"> = {
toolCallId: "test-tool-call-id",
title: "Test Tool Call",
status: "in_progress",
}
emitter.on("tool_call", listener)
emitter.emit("tool_call", payload)
expect(listener).toHaveBeenCalledTimes(1)
expect(listener).toHaveBeenCalledWith(payload)
})
it("should emit and receive tool_call_update events", () => {
const listener = vi.fn()
const payload: SessionUpdatePayload<"tool_call_update"> = {
toolCallId: "test-tool-call-id",
status: "completed",
rawOutput: { result: "success" },
}
emitter.on("tool_call_update", listener)
emitter.emit("tool_call_update", payload)
expect(listener).toHaveBeenCalledTimes(1)
expect(listener).toHaveBeenCalledWith(payload)
})
it("should emit and receive available_commands_update events", () => {
const listener = vi.fn()
const payload: SessionUpdatePayload<"available_commands_update"> = {
availableCommands: [{ name: "test", description: "Test command" }],
}
emitter.on("available_commands_update", listener)
emitter.emit("available_commands_update", payload)
expect(listener).toHaveBeenCalledTimes(1)
expect(listener).toHaveBeenCalledWith(payload)
})
it("should emit and receive current_mode_update events", () => {
const listener = vi.fn()
const payload: SessionUpdatePayload<"current_mode_update"> = {
currentModeId: "act",
}
emitter.on("current_mode_update", listener)
emitter.emit("current_mode_update", payload)
expect(listener).toHaveBeenCalledTimes(1)
expect(listener).toHaveBeenCalledWith(payload)
})
it("should emit and receive plan events", () => {
const listener = vi.fn()
const payload: SessionUpdatePayload<"plan"> = {
entries: [{ content: "Step 1", status: "pending", priority: "high" }],
}
emitter.on("plan", listener)
emitter.emit("plan", payload)
expect(listener).toHaveBeenCalledTimes(1)
expect(listener).toHaveBeenCalledWith(payload)
})
it("should emit and receive error events", () => {
const listener = vi.fn()
const error = new Error("Test error")
emitter.on("error", listener)
emitter.emit("error", error)
expect(listener).toHaveBeenCalledTimes(1)
expect(listener).toHaveBeenCalledWith(error)
})
})
describe("multiple listeners", () => {
it("should support multiple listeners for the same event", () => {
const listener1 = vi.fn()
const listener2 = vi.fn()
const payload: SessionUpdatePayload<"agent_message_chunk"> = {
content: { type: "text", text: "Hello" },
}
emitter.on("agent_message_chunk", listener1)
emitter.on("agent_message_chunk", listener2)
emitter.emit("agent_message_chunk", payload)
expect(listener1).toHaveBeenCalledTimes(1)
expect(listener2).toHaveBeenCalledTimes(1)
})
it("should call listeners in order of registration", () => {
const order: number[] = []
const listener1 = vi.fn(() => order.push(1))
const listener2 = vi.fn(() => order.push(2))
const payload: SessionUpdatePayload<"agent_message_chunk"> = {
content: { type: "text", text: "Hello" },
}
emitter.on("agent_message_chunk", listener1)
emitter.on("agent_message_chunk", listener2)
emitter.emit("agent_message_chunk", payload)
expect(order).toEqual([1, 2])
})
})
describe("off", () => {
it("should remove a specific listener", () => {
const listener = vi.fn()
const payload: SessionUpdatePayload<"agent_message_chunk"> = {
content: { type: "text", text: "Hello" },
}
emitter.on("agent_message_chunk", listener)
emitter.off("agent_message_chunk", listener)
emitter.emit("agent_message_chunk", payload)
expect(listener).not.toHaveBeenCalled()
})
it("should only remove the specified listener", () => {
const listener1 = vi.fn()
const listener2 = vi.fn()
const payload: SessionUpdatePayload<"agent_message_chunk"> = {
content: { type: "text", text: "Hello" },
}
emitter.on("agent_message_chunk", listener1)
emitter.on("agent_message_chunk", listener2)
emitter.off("agent_message_chunk", listener1)
emitter.emit("agent_message_chunk", payload)
expect(listener1).not.toHaveBeenCalled()
expect(listener2).toHaveBeenCalledTimes(1)
})
})
describe("once", () => {
it("should only call the listener once", () => {
const listener = vi.fn()
const payload: SessionUpdatePayload<"agent_message_chunk"> = {
content: { type: "text", text: "Hello" },
}
emitter.once("agent_message_chunk", listener)
emitter.emit("agent_message_chunk", payload)
emitter.emit("agent_message_chunk", payload)
expect(listener).toHaveBeenCalledTimes(1)
})
})
describe("removeAllListeners", () => {
it("should remove all listeners for a specific event", () => {
const listener1 = vi.fn()
const listener2 = vi.fn()
const payload: SessionUpdatePayload<"agent_message_chunk"> = {
content: { type: "text", text: "Hello" },
}
emitter.on("agent_message_chunk", listener1)
emitter.on("agent_message_chunk", listener2)
emitter.removeAllListeners("agent_message_chunk")
emitter.emit("agent_message_chunk", payload)
expect(listener1).not.toHaveBeenCalled()
expect(listener2).not.toHaveBeenCalled()
})
it("should remove all listeners when no event is specified", () => {
const listener1 = vi.fn()
const listener2 = vi.fn()
emitter.on("agent_message_chunk", listener1)
emitter.on("tool_call", listener2)
emitter.removeAllListeners()
emitter.emit("agent_message_chunk", { content: { type: "text", text: "Hello" } })
emitter.emit("tool_call", { toolCallId: "test", title: "Test" })
expect(listener1).not.toHaveBeenCalled()
expect(listener2).not.toHaveBeenCalled()
})
})
describe("listenerCount", () => {
it("should return the correct number of listeners", () => {
const listener1 = vi.fn()
const listener2 = vi.fn()
expect(emitter.listenerCount("agent_message_chunk")).toBe(0)
emitter.on("agent_message_chunk", listener1)
expect(emitter.listenerCount("agent_message_chunk")).toBe(1)
emitter.on("agent_message_chunk", listener2)
expect(emitter.listenerCount("agent_message_chunk")).toBe(2)
emitter.off("agent_message_chunk", listener1)
expect(emitter.listenerCount("agent_message_chunk")).toBe(1)
})
})
describe("chaining", () => {
it("should support method chaining", () => {
const listener = vi.fn()
const result = emitter.on("agent_message_chunk", listener).on("error", vi.fn()).off("error", vi.fn())
expect(result).toBe(emitter)
})
})
describe("emit return value", () => {
it("should return true when there are listeners", () => {
emitter.on("agent_message_chunk", vi.fn())
const result = emitter.emit("agent_message_chunk", { content: { type: "text", text: "Hello" } })
expect(result).toBe(true)
})
it("should return false when there are no listeners", () => {
const result = emitter.emit("agent_message_chunk", { content: { type: "text", text: "Hello" } })
expect(result).toBe(false)
})
})
})
+114
View File
@@ -0,0 +1,114 @@
/**
* Typed EventEmitter for per-session ACP events.
*
* This class provides a type-safe wrapper around Node's EventEmitter
* for emitting and subscribing to session-specific ACP events.
*
* @module acp
*/
import { EventEmitter } from "events"
import type { ClineSessionEvents } from "./types.js"
/**
* Type-safe EventEmitter for ClineAgent session events.
*
* Each session has its own emitter instance, allowing consumers to
* subscribe to events for specific sessions without filtering.
*
* @example
* ```typescript
* const agent = new ClineAgent({ version: "1.0.0" })
* const session = await agent.newSession({ cwd: "/path/to/project" })
*
* // Subscribe to session events
* agent.session(session.sessionId).on("agent_message_chunk", (content) => {
* console.log("Agent says:", content.text)
* })
*
* agent.session(session.sessionId).on("tool_call", (toolCall) => {
* console.log("Tool called:", toolCall.toolName)
* })
* ```
*/
export class ClineSessionEmitter {
private readonly emitter: EventEmitter
constructor() {
this.emitter = new EventEmitter()
// Increase max listeners since we may have many event types
this.emitter.setMaxListeners(20)
}
/**
* Subscribe to a session event.
*
* @param event - The event name to subscribe to
* @param listener - The callback function to invoke when the event is emitted
* @returns This emitter instance for chaining
*/
on<K extends keyof ClineSessionEvents>(event: K, listener: ClineSessionEvents[K]): this {
this.emitter.on(event, listener as (...args: unknown[]) => void)
return this
}
/**
* Subscribe to a session event for a single invocation.
*
* @param event - The event name to subscribe to
* @param listener - The callback function to invoke when the event is emitted
* @returns This emitter instance for chaining
*/
once<K extends keyof ClineSessionEvents>(event: K, listener: ClineSessionEvents[K]): this {
this.emitter.once(event, listener as (...args: unknown[]) => void)
return this
}
/**
* Unsubscribe from a session event.
*
* @param event - The event name to unsubscribe from
* @param listener - The callback function to remove
* @returns This emitter instance for chaining
*/
off<K extends keyof ClineSessionEvents>(event: K, listener: ClineSessionEvents[K]): this {
this.emitter.off(event, listener as (...args: unknown[]) => void)
return this
}
/**
* Emit a session event.
*
* @param event - The event name to emit
* @param args - The arguments to pass to the event listeners
* @returns True if the event had listeners, false otherwise
*/
emit<K extends keyof ClineSessionEvents>(event: K, ...args: Parameters<ClineSessionEvents[K]>): boolean {
return this.emitter.emit(event, ...args)
}
/**
* Remove all listeners for a specific event or all events.
*
* @param event - Optional event name to remove listeners for
* @returns This emitter instance for chaining
*/
removeAllListeners<K extends keyof ClineSessionEvents>(event?: K): this {
if (event) {
this.emitter.removeAllListeners(event)
} else {
this.emitter.removeAllListeners()
}
return this
}
/**
* Get the number of listeners for a specific event.
*
* @param event - The event name to count listeners for
* @returns The number of listeners
*/
listenerCount<K extends keyof ClineSessionEvents>(event: K): number {
return this.emitter.listenerCount(event)
}
}
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
+356
View File
@@ -0,0 +1,356 @@
/**
* Permission handling for ACP integration.
*
* This module handles the translation between ACP permission requests/responses
* and Cline's internal permission system. It maps ClineAsk types to appropriate
* ACP permission options and translates user responses back to Cline's format.
*
* @module acp/permissionHandler
*/
import type * as acp from "@agentclientprotocol/sdk"
import type { ClineAsk } from "@shared/ExtensionMessage"
import type { ClineAskResponse } from "@shared/WebviewMessage"
import { Logger } from "@/shared/services/Logger.js"
import type { AcpSessionState, ClinePermissionOption } from "./types.js"
/**
* Standard permission options for operations that support "always allow".
* Used for commands, tools, and MCP server operations.
*/
const STANDARD_PERMISSION_OPTIONS: ClinePermissionOption[] = [
{ kind: "allow_once", optionId: "allow_once", name: "Allow Once" },
{ kind: "allow_always", optionId: "allow_always", name: "Always Allow" },
{ kind: "reject_once", optionId: "reject_once", name: "Reject" },
]
/**
* Permission options for operations that don't support "always allow".
* Used for browser actions and other one-time operations.
*/
const RESTRICTED_PERMISSION_OPTIONS: ClinePermissionOption[] = [
{ kind: "allow_once", optionId: "allow_once", name: "Allow Once" },
{ kind: "reject_once", optionId: "reject_once", name: "Reject" },
]
/**
* Mapping of ClineAsk types to their permission option sets.
*/
const ASK_TYPE_PERMISSION_MAP: Partial<Record<ClineAsk, ClinePermissionOption[]>> = {
// Commands support "always allow" for auto-approval
command: STANDARD_PERMISSION_OPTIONS,
// Tool operations support "always allow"
tool: STANDARD_PERMISSION_OPTIONS,
// MCP server operations support "always allow"
use_mcp_server: STANDARD_PERMISSION_OPTIONS,
// Browser actions are one-time, no "always allow"
browser_action_launch: RESTRICTED_PERMISSION_OPTIONS,
// Command output continuation - simple allow/reject
command_output: RESTRICTED_PERMISSION_OPTIONS,
}
/**
* ClineAsk types that require permission handling.
* Other ask types (like followup, plan_mode_respond) don't need permission UI.
*/
const PERMISSION_REQUIRING_ASK_TYPES: Set<ClineAsk> = new Set([
"command",
"tool",
"browser_action_launch",
"use_mcp_server",
"command_output",
])
/**
* Result of handling a permission response.
*/
export interface PermissionHandlerResult {
/** Cline's internal response type */
response: ClineAskResponse
/** Optional text to pass with the response */
text?: string
/** Whether "always allow" was selected (for auto-approval tracking) */
alwaysAllow?: boolean
/** Whether the request was cancelled */
cancelled?: boolean
}
/**
* Check if a ClineAsk type requires permission handling.
*
* @param askType - The ClineAsk type to check
* @returns True if the ask type requires permission UI
*/
export function requiresPermission(askType: ClineAsk): boolean {
return PERMISSION_REQUIRING_ASK_TYPES.has(askType)
}
/**
* Get the appropriate permission options for a ClineAsk type.
*
* @param askType - The ClineAsk type
* @returns Array of permission options, or undefined if the ask type doesn't require permission
*/
export function getPermissionOptionsForAskType(askType: ClineAsk): acp.PermissionOption[] | undefined {
const options = ASK_TYPE_PERMISSION_MAP[askType]
if (!options) {
return undefined
}
// Convert to ACP PermissionOption format
return options.map((opt) => ({
kind: opt.kind,
optionId: opt.optionId,
name: opt.name,
}))
}
/**
* Handle an ACP permission response and translate it to Cline's format.
*
* @param response - The ACP permission response from the client
* @param askType - The original ClineAsk type that triggered the permission request
* @returns The translated result for Cline's handleWebviewAskResponse
*/
export function handlePermissionResponse(response: acp.RequestPermissionResponse, askType: ClineAsk): PermissionHandlerResult {
// Check if cancelled
if (response.outcome.outcome === "cancelled") {
return {
response: "noButtonClicked",
cancelled: true,
}
}
// Get the selected option ID
const optionId = response.outcome.optionId
// Translate the option to Cline's response format
switch (optionId) {
case "allow_once":
return {
response: "yesButtonClicked",
alwaysAllow: false,
}
case "allow_always":
return {
response: "yesButtonClicked",
alwaysAllow: true,
}
case "reject_once":
case "reject_always":
return {
response: "noButtonClicked",
alwaysAllow: false,
}
default:
// Unknown option ID - treat as rejection for safety
Logger.error(`[permissionHandler] Unknown permission option: ${optionId}`)
return {
response: "noButtonClicked",
}
}
}
/**
* Create a permission request for an ACP tool call.
*
* @param toolCall - The ACP tool call that needs permission
* @param askType - The Cline ask type
* @returns The permission request options, or null if no permission needed
*/
export function createPermissionRequest(
toolCall: acp.ToolCall,
askType: ClineAsk,
): { toolCall: acp.ToolCall; options: acp.PermissionOption[] } | null {
const options = getPermissionOptionsForAskType(askType)
if (!options) {
return null
}
return {
toolCall,
options,
}
}
/**
* Track "always allow" decisions for auto-approval.
* This maintains a set of tool/command patterns that have been auto-approved.
*/
export class AutoApprovalTracker {
/** Set of auto-approved command prefixes */
private autoApprovedCommands: Set<string> = new Set()
/** Set of auto-approved tool names */
private autoApprovedTools: Set<string> = new Set()
/** Set of auto-approved MCP servers */
private autoApprovedMcpServers: Set<string> = new Set()
/**
* Record an "always allow" decision for a permission request.
*
* @param askType - The Cline ask type that was auto-approved
* @param identifier - The identifier for the operation (command, tool name, etc.)
*/
recordAlwaysAllow(askType: ClineAsk, identifier: string): void {
switch (askType) {
case "command":
// Store the first word of the command as the key
const commandPrefix = identifier.split(" ")[0]
this.autoApprovedCommands.add(commandPrefix)
break
case "tool":
this.autoApprovedTools.add(identifier)
break
case "use_mcp_server":
this.autoApprovedMcpServers.add(identifier)
break
}
}
/**
* Check if an operation has been auto-approved.
*
* @param askType - The Cline ask type
* @param identifier - The identifier for the operation
* @returns True if the operation was previously auto-approved
*/
isAutoApproved(askType: ClineAsk, identifier: string): boolean {
switch (askType) {
case "command":
const commandPrefix = identifier.split(" ")[0]
return this.autoApprovedCommands.has(commandPrefix)
case "tool":
return this.autoApprovedTools.has(identifier)
case "use_mcp_server":
return this.autoApprovedMcpServers.has(identifier)
default:
return false
}
}
/**
* Clear all auto-approval records.
*/
clear(): void {
this.autoApprovedCommands.clear()
this.autoApprovedTools.clear()
this.autoApprovedMcpServers.clear()
}
}
/**
* Process a pending permission request for a session.
*
* This function coordinates the permission flow:
* 1. Checks if the operation is already auto-approved
* 2. If not, requests permission from the ACP client
* 3. Tracks "always allow" decisions
* 4. Returns the translated result for Cline
*
* @param requestPermission - Function to request permission from the ACP client
* @param sessionId - The session ID
* @param toolCall - The tool call requiring permission
* @param askType - The Cline ask type
* @param identifier - Identifier for auto-approval tracking
* @param autoApprovalTracker - The auto-approval tracker
* @returns The permission handler result
*/
export async function processPermissionRequest(
requestPermission: (
sessionId: string,
toolCall: acp.ToolCall,
options: acp.PermissionOption[],
) => Promise<acp.RequestPermissionResponse>,
sessionId: string,
toolCall: acp.ToolCall,
askType: ClineAsk,
identifier: string,
autoApprovalTracker?: AutoApprovalTracker,
): Promise<PermissionHandlerResult> {
// Check if already auto-approved
if (autoApprovalTracker?.isAutoApproved(askType, identifier)) {
return {
response: "yesButtonClicked",
alwaysAllow: true,
}
}
// Get permission options for this ask type
const options = getPermissionOptionsForAskType(askType)
if (!options) {
// No permission options defined - allow by default
return {
response: "yesButtonClicked",
}
}
// Request permission from the ACP client
const response = await requestPermission(sessionId, toolCall, options)
// Handle the response
const result = handlePermissionResponse(response, askType)
// Track "always allow" decisions
if (result.alwaysAllow && autoApprovalTracker) {
autoApprovalTracker.recordAlwaysAllow(askType, identifier)
}
return result
}
/**
* Get the identifier for auto-approval tracking from a tool call.
*
* @param toolCall - The ACP tool call
* @param askType - The Cline ask type
* @returns The identifier string for auto-approval tracking
*/
export function getAutoApprovalIdentifier(toolCall: acp.ToolCall, askType: ClineAsk): string {
const rawInput = toolCall.rawInput as Record<string, unknown> | undefined
switch (askType) {
case "command":
return (rawInput?.command as string) || toolCall.title
case "tool":
// Try to get tool name from raw input or title
return (rawInput?.tool as string) || toolCall.title
case "use_mcp_server":
return (rawInput?.serverName as string) || toolCall.title
default:
return toolCall.toolCallId
}
}
/**
* Update the session state's pending tool call after permission is handled.
*
* @param sessionState - The session state to update
* @param toolCallId - The tool call ID that was handled
* @param approved - Whether the permission was approved
*/
export function updateSessionStateAfterPermission(sessionState: AcpSessionState, toolCallId: string, approved: boolean): void {
// Remove from pending tool calls
sessionState.pendingToolCalls.delete(toolCallId)
// Clear current tool call ID if it matches
if (sessionState.currentToolCallId === toolCallId && !approved) {
sessionState.currentToolCallId = undefined
}
}
+247
View File
@@ -0,0 +1,247 @@
/**
* Custom types and extensions for ACP integration with Cline CLI.
*
* This file extends the base ACP types with Cline-specific functionality.
*/
import type * as acp from "@agentclientprotocol/sdk"
import type { Controller } from "@/core/controller"
// ============================================================
// Session Update Type Utilities
// ============================================================
/**
* Extract the sessionUpdate discriminator value from a SessionUpdate variant.
*/
export type SessionUpdateType = acp.SessionUpdate["sessionUpdate"]
/**
* Extract the payload type for a given sessionUpdate discriminator value.
* This removes the `sessionUpdate` discriminator field from the type.
*/
export type SessionUpdatePayload<T extends SessionUpdateType> = Omit<
Extract<acp.SessionUpdate, { sessionUpdate: T }>,
"sessionUpdate"
>
// ============================================================
// Permission Handler Callback Types
// ============================================================
/**
* Callback to resolve a permission request with the user's response.
*/
export type PermissionResolver = (response: acp.RequestPermissionResponse) => void
/**
* Handler function for permission requests.
* Called when the agent needs permission for a tool call.
* The handler should present the request to the user and call resolve() with their response.
*/
export type PermissionHandler = (request: Omit<acp.RequestPermissionRequest, "sessionId">, resolve: PermissionResolver) => void
// ============================================================
// Session Event Emitter Types
// ============================================================
/**
* Maps ACP SessionUpdate types to their event listener signatures.
* Uses the sessionUpdate discriminator to derive event names and payload types.
*/
export type ClineSessionEvents = {
[K in SessionUpdateType]: (payload: SessionUpdatePayload<K>) => void
} & {
/** Error event for session-level errors (not part of ACP SessionUpdate) */
error: (error: Error) => void
}
// ============================================================
// ClineAgent Options (decoupled from connection)
// ============================================================
/**
* Options for creating a ClineAgent instance (decoupled from connection).
*/
export interface ClineAgentOptions {
/** CLI version string */
version: string
/** Whether debug logging is enabled */
debug?: boolean
}
// Re-export common ACP types for convenience
export type {
Agent,
AgentSideConnection,
AudioContent,
CancelNotification,
ContentBlock,
ImageContent,
InitializeRequest,
InitializeResponse,
LoadSessionRequest,
LoadSessionResponse,
McpServer,
ModelInfo,
NewSessionRequest,
NewSessionResponse,
PermissionOption,
PermissionOptionKind,
PromptRequest,
PromptResponse,
ReadTextFileRequest,
ReadTextFileResponse,
RequestPermissionRequest,
RequestPermissionResponse,
SessionConfigOption,
SessionModelState,
SessionNotification,
SessionUpdate,
SetSessionConfigOptionRequest,
SetSessionConfigOptionResponse,
SetSessionModelRequest,
SetSessionModelResponse,
SetSessionModeRequest,
SetSessionModeResponse,
StopReason,
TextContent,
ToolCall,
ToolCallStatus,
ToolCallUpdate,
ToolKind,
WriteTextFileRequest,
WriteTextFileResponse,
} from "@agentclientprotocol/sdk"
/**
* Cline-specific agent capabilities extending the ACP base capabilities.
*/
export interface ClineAgentCapabilities {
/** Support for loading sessions from disk */
loadSession: boolean
/** Prompt capabilities for the agent */
promptCapabilities: {
/** Support for image inputs */
image: boolean
/** Support for audio inputs */
audio: boolean
/** Support for embedded context (file resources) */
embeddedContext: boolean
}
/** MCP server passthrough capabilities */
mcpCapabilities: {
/** Support for HTTP MCP servers */
http: boolean
/** Support for SSE MCP servers */
sse: boolean
}
}
/**
* Cline agent info for ACP initialization response.
*/
export interface ClineAgentInfo {
name: "cline"
title: "Cline"
version: string
}
/**
* Extended session data stored by Cline for ACP sessions.
* Maps to Cline's task history structure.
*/
export interface ClineAcpSession {
/** Unique session/task ID */
sessionId: string
/** Working directory for the session */
cwd: string
/** Current mode (plan/act) */
mode: "plan" | "act"
/** MCP servers passed from the client */
mcpServers: acp.McpServer[]
/** Timestamp when session was created */
createdAt: number
/** Timestamp of last activity */
lastActivityAt: number
/** Whether this session was loaded from history (needs resume on first prompt) */
isLoadedFromHistory?: boolean
/** Controller instance for this session (manages task execution) */
controller?: Controller
/** Model ID override for plan mode (format: "provider/modelId") */
planModeModelId?: string
/** Model ID override for act mode (format: "provider/modelId") */
actModeModelId?: string
}
/**
* Permission option as presented to the ACP client.
*/
export interface ClinePermissionOption {
kind: acp.PermissionOptionKind
name: string
optionId: string
}
/**
* Mapping of Cline message types to their ACP session update equivalents.
*/
export type ClineToAcpUpdateMapping = {
/** Text messages from the agent */
text: "agent_message_chunk"
/** Reasoning/thinking from the agent */
reasoning: "agent_thought_chunk"
/** Markdown content from the agent */
markdown: "agent_message_chunk"
/** Tool execution */
tool: "tool_call"
/** Command execution */
command: "tool_call"
/** Command output */
command_output: "tool_call_update"
/** Task completion */
completion_result: "end_turn"
/** Error messages */
error: "tool_call_update" | "error"
}
/**
* Options for creating an ACP agent instance.
*/
export interface AcpAgentOptions {
/** CLI version string */
version: string
/** Whether debug logging is enabled */
debug?: boolean
}
/**
* Result of translating a Cline message to ACP session update(s).
* A single Cline message may produce multiple ACP updates.
*/
export interface TranslatedMessage {
/** The session updates to send */
updates: acp.SessionUpdate[]
/** Whether this message requires a permission request */
requiresPermission?: boolean
/** Permission request details if required */
permissionRequest?: Omit<acp.RequestPermissionRequest, "sessionId">
/** The toolCallId that was created/used (for tracking across streaming updates) */
toolCallId?: string
}
/**
* State tracking for an active ACP session within Cline.
*/
export interface AcpSessionState {
/** Session ID */
sessionId: string
/** Whether the session is currently processing a prompt */
isProcessing: boolean
/** Current tool call ID being executed (if any) */
currentToolCallId?: string
/** Whether the session has been cancelled */
cancelled: boolean
/** Accumulated tool calls for permission batching */
pendingToolCalls: Map<string, acp.ToolCall>
}
+194
View File
@@ -0,0 +1,194 @@
/**
* Account info view component
* Shows current provider, and for Cline provider: credit balance and organization name
*/
import { Box, Text } from "ink"
import React, { useCallback, useEffect, useState } from "react"
import { Controller } from "@/core/controller"
import { StateManager } from "@/core/storage/StateManager"
import { ClineAccountService } from "@/services/account/ClineAccountService"
import { AuthService, ClineAccountOrganization } from "@/services/auth/AuthService"
import { LoadingSpinner } from "./Spinner"
interface AccountInfoViewProps {
controller: Controller
}
/**
* Capitalize provider name for display
*/
function capitalize(str: string): string {
return str
.split("-")
.map((word) => word.charAt(0).toUpperCase() + word.slice(1))
.join(" ")
}
/**
* Format balance as currency (balance is in microcredits, divide by 10000)
*/
function formatBalance(balance: number | null): string {
if (balance === null || balance === undefined) {
return "..."
}
return `$${(balance / 1000000).toFixed(2)}`
}
export const AccountInfoView: React.FC<AccountInfoViewProps> = React.memo(({ controller }) => {
const [provider, setProvider] = useState<string | null>(null)
const [balance, setBalance] = useState<number | null>(null)
const [organization, setOrganization] = useState<ClineAccountOrganization | null>(null)
const [email, setEmail] = useState<string | null>(null)
const [isLoading, setIsLoading] = useState(true)
const [error, setError] = useState<string | null>(null)
const fetchAccountInfo = useCallback(async () => {
try {
setIsLoading(true)
setError(null)
// Get current provider from state
const stateManager = StateManager.get()
const mode = stateManager.getGlobalSettingsKey("mode") as string
const providerKey = mode === "act" ? "actModeApiProvider" : "planModeApiProvider"
const currentProvider = stateManager.getGlobalSettingsKey(providerKey) as string
setProvider(currentProvider || "cline")
// If using Cline provider, fetch additional info
if (currentProvider === "cline") {
const authService = AuthService.getInstance(controller)
// Wait for auth to be restored - poll until we have auth info or timeout
let authInfo = authService.getInfo()
let attempts = 0
const maxAttempts = 20 // 2 seconds max
while (!authInfo?.user?.uid && attempts < maxAttempts) {
await new Promise((resolve) => setTimeout(resolve, 100))
authInfo = authService.getInfo()
attempts++
}
// Get user info
if (authInfo?.user?.email) {
setEmail(authInfo.user.email)
} else {
// User not logged in to Cline
setEmail(null)
setIsLoading(false)
return
}
// Get organization info
const organizations = authService.getUserOrganizations()
if (organizations) {
const activeOrg = organizations.find((org) => org.active)
if (activeOrg) {
setOrganization(activeOrg)
}
}
// Fetch credit balance
try {
const accountService = ClineAccountService.getInstance()
const activeOrgId = authService.getActiveOrganizationId()
if (activeOrgId) {
// Fetch organization balance
const orgBalance = await accountService.fetchOrganizationCreditsRPC(activeOrgId)
if (orgBalance?.balance !== undefined) {
setBalance(orgBalance.balance)
}
} else {
// Fetch personal balance
const balanceData = await accountService.fetchBalanceRPC()
if (balanceData?.balance !== undefined) {
setBalance(balanceData.balance)
}
}
} catch {
// Balance fetch failed, but we can still show other info
// Don't log to console as it pollutes CLI output
}
}
} catch (err) {
setError(err instanceof Error ? err.message : "Failed to load account info")
} finally {
setIsLoading(false)
}
}, [controller])
useEffect(() => {
fetchAccountInfo()
}, [fetchAccountInfo])
if (isLoading) {
return (
<Box>
<LoadingSpinner />
<Text color="gray"> Loading account info...</Text>
</Box>
)
}
if (error) {
return (
<Box>
<Text color="red">Error: {error}</Text>
</Box>
)
}
// If not using Cline provider, just show the provider name
if (provider !== "cline") {
return (
<Box>
<Text color="gray">Provider: </Text>
<Text color="cyan">{capitalize(provider || "Not configured")}</Text>
</Box>
)
}
// Cline provider but not logged in
if (!email) {
return (
<Box>
<Text color="gray">Provider: </Text>
<Text color="cyan">Cline</Text>
<Text color="gray"> </Text>
<Text color="yellow">Not logged in (run 'cline auth' to sign in)</Text>
</Box>
)
}
// Cline provider - show full account info
return (
<Box flexDirection="column">
<Box>
<Text color="gray">Provider: </Text>
<Text color="cyan">Cline</Text>
{email && (
<Box>
<Text color="gray"> </Text>
<Text color="white">{email}</Text>
</Box>
)}
</Box>
<Box>
{organization ? (
<Box>
<Text color="gray">Organization: </Text>
<Text color="magenta">{organization.name}</Text>
</Box>
) : (
<Box>
<Text color="gray">Account: </Text>
<Text color="white">Personal</Text>
</Box>
)}
<Text color="gray"> Credits: </Text>
<Text color="green">{formatBalance(balance)}</Text>
</Box>
</Box>
)
})
+337
View File
@@ -0,0 +1,337 @@
/**
* Action buttons component for CLI
* Shows primary/secondary buttons above the input field
* Supports keyboard navigation (1/2 for buttons, arrows to navigate, esc to cancel)
*/
import type { ClineMessage } from "@shared/ExtensionMessage"
import { Box, Text } from "ink"
import React from "react"
import { COLORS } from "../constants/colors"
import { useTerminalSize } from "../hooks/useTerminalSize"
import { isFileSaveTool, parseToolFromMessage } from "../utils/tools"
/**
* Button action types that determine the behavior
*/
export type ButtonActionType =
| "approve" // Send yesButtonClicked
| "reject" // Send noButtonClicked
| "proceed" // Send messageResponse or yesButtonClicked
| "new_task" // Start a new task
| "cancel" // Cancel streaming
| "retry" // Retry the last action
/**
* Button configuration for different message states
*/
export interface ButtonConfig {
sendingDisabled: boolean
enableButtons: boolean
primaryText?: string
secondaryText?: string
primaryAction?: ButtonActionType
secondaryAction?: ButtonActionType
}
/**
* Centralized button state configurations based on task lifecycle
*/
const BUTTON_CONFIGS: Record<string, ButtonConfig> = {
// Error recovery states
api_req_failed: {
sendingDisabled: true,
enableButtons: true,
primaryText: "Retry",
secondaryText: "Start New Task",
primaryAction: "retry",
secondaryAction: "new_task",
},
mistake_limit_reached: {
sendingDisabled: false,
enableButtons: true,
primaryText: "Proceed Anyways",
secondaryText: "Start New Task",
primaryAction: "proceed",
secondaryAction: "new_task",
},
// Tool approval states
tool_approve: {
sendingDisabled: false,
enableButtons: true,
primaryText: "Approve",
secondaryText: "Reject",
primaryAction: "approve",
secondaryAction: "reject",
},
tool_save: {
sendingDisabled: false,
enableButtons: true,
primaryText: "Save",
secondaryText: "Reject",
primaryAction: "approve",
secondaryAction: "reject",
},
// Command execution states
command: {
sendingDisabled: false,
enableButtons: true,
primaryText: "Run Command",
secondaryText: "Reject",
primaryAction: "approve",
secondaryAction: "reject",
},
command_output: {
sendingDisabled: false,
enableButtons: true,
primaryText: "Proceed While Running",
secondaryText: undefined,
primaryAction: "proceed",
secondaryAction: undefined,
},
// Browser and external tool states
browser_action_launch: {
sendingDisabled: false,
enableButtons: true,
primaryText: "Approve",
secondaryText: "Reject",
primaryAction: "approve",
secondaryAction: "reject",
},
use_mcp_server: {
sendingDisabled: false,
enableButtons: true,
primaryText: "Approve",
secondaryText: "Reject",
primaryAction: "approve",
secondaryAction: "reject",
},
followup: {
sendingDisabled: false,
enableButtons: false,
primaryText: undefined,
secondaryText: undefined,
primaryAction: undefined,
secondaryAction: undefined,
},
plan_mode_respond: {
sendingDisabled: false,
enableButtons: false,
primaryText: undefined,
secondaryText: undefined,
primaryAction: undefined,
secondaryAction: undefined,
},
// Task lifecycle states
completion_result: {
sendingDisabled: false,
enableButtons: true,
primaryText: "Start New Task",
secondaryText: undefined,
primaryAction: "new_task",
secondaryAction: undefined,
},
resume_task: {
sendingDisabled: false,
enableButtons: true,
primaryText: "Resume Task",
secondaryText: "Exit",
primaryAction: "proceed",
secondaryAction: "reject",
},
resume_completed_task: {
sendingDisabled: false,
enableButtons: true,
primaryText: "Start New Task",
secondaryText: "Exit",
primaryAction: "new_task",
secondaryAction: "reject",
},
new_task: {
sendingDisabled: false,
enableButtons: true,
primaryText: "Start New Task with Context",
secondaryText: undefined,
primaryAction: "new_task",
secondaryAction: undefined,
},
// Streaming/partial states
partial: {
sendingDisabled: true,
enableButtons: true,
primaryText: undefined,
secondaryText: "Cancel",
primaryAction: undefined,
secondaryAction: "cancel",
},
// Default states
default: {
sendingDisabled: false,
enableButtons: false,
primaryText: undefined,
secondaryText: undefined,
primaryAction: undefined,
secondaryAction: undefined,
},
api_req_active: {
sendingDisabled: true,
enableButtons: true,
primaryText: undefined,
secondaryText: "Cancel",
primaryAction: undefined,
secondaryAction: "cancel",
},
}
const errorTypes = ["api_req_failed", "mistake_limit_reached"]
/**
* Get button configuration based on message type and state
*/
export function getButtonConfig(message: ClineMessage | undefined, isStreaming: boolean = false): ButtonConfig {
if (!message) {
return BUTTON_CONFIGS.default
}
const isError = message?.ask ? errorTypes.includes(message.ask) : false
// Special case: command_output should show "Proceed While Running" button even while streaming
if (message.type === "ask" && message.ask === "command_output") {
return BUTTON_CONFIGS.command_output
}
// Handle partial/streaming messages first
if (isStreaming && !isError) {
return BUTTON_CONFIGS.partial
}
// Handle ask messages (user interaction required)
if (message.type === "ask") {
switch (message.ask) {
// Error recovery states
case "api_req_failed":
return BUTTON_CONFIGS.api_req_failed
case "mistake_limit_reached":
return BUTTON_CONFIGS.mistake_limit_reached
// Tool approval (most common)
case "tool": {
const toolInfo = parseToolFromMessage(message.text)
if (toolInfo && isFileSaveTool(toolInfo.toolName)) {
return BUTTON_CONFIGS.tool_save
}
return BUTTON_CONFIGS.tool_approve
}
// Command execution
case "command":
return BUTTON_CONFIGS.command
case "command_output":
return BUTTON_CONFIGS.command_output
// Standard approvals
case "followup":
return BUTTON_CONFIGS.followup
case "browser_action_launch":
return BUTTON_CONFIGS.browser_action_launch
case "use_mcp_server":
return BUTTON_CONFIGS.use_mcp_server
case "plan_mode_respond":
return BUTTON_CONFIGS.plan_mode_respond
// Task lifecycle
case "completion_result":
return BUTTON_CONFIGS.completion_result
case "resume_task":
return BUTTON_CONFIGS.resume_task
case "resume_completed_task":
return BUTTON_CONFIGS.resume_completed_task
case "new_task":
return BUTTON_CONFIGS.new_task
default:
return BUTTON_CONFIGS.tool_approve
}
}
// Handle say messages
if (message.type === "say" && message.say === "api_req_started") {
return BUTTON_CONFIGS.api_req_active
}
if (message.type === "say" && message.say === "command_output") {
return BUTTON_CONFIGS.command_output
}
return BUTTON_CONFIGS.partial
}
interface ActionButtonsProps {
config: ButtonConfig
mode?: "act" | "plan"
}
/**
* Determine which buttons are actually visible based on config
* Cancel is hidden in the CLI (ThinkingIndicator handles that with esc)
*/
export function getVisibleButtons(config: ButtonConfig) {
const hiddenActions = ["cancel"]
const hasPrimary = !!config.primaryText && !hiddenActions.includes(config.primaryAction || "")
const hasSecondary = !!config.secondaryText && !hiddenActions.includes(config.secondaryAction || "")
return { hasPrimary, hasSecondary }
}
/**
* Action buttons component
* Shows primary and/or secondary buttons based on config
* Buttons take full width (one button = full, two buttons = half each)
* Does not show cancel-only buttons (ThinkingIndicator handles that with esc)
*/
export const ActionButtons: React.FC<ActionButtonsProps> = ({ config, mode = "act" }) => {
if (!config.enableButtons) {
return null
}
const { hasPrimary, hasSecondary } = getVisibleButtons(config)
if (!hasPrimary && !hasSecondary) {
return null
}
// Calculate button widths based on terminal width
const { columns: terminalWidth } = useTerminalSize()
const buttonCount = (hasPrimary ? 1 : 0) + (hasSecondary ? 1 : 0)
const gapWidth = buttonCount > 1 ? 1 : 0 // 1 char gap between buttons
const availableWidth = terminalWidth - 2 - gapWidth // 1 space padding on each side
const buttonWidth = Math.floor(availableWidth / buttonCount)
const modeColor = mode === "plan" ? "yellow" : COLORS.primaryBlue
const renderButton = (text: string, shortcut: string) => {
const label = ` ${text} (${shortcut}) `
const padding = Math.max(0, buttonWidth - label.length)
const leftPad = Math.floor(padding / 2)
const rightPad = padding - leftPad
const paddedLabel = " ".repeat(leftPad) + label + " ".repeat(rightPad)
return (
<Text backgroundColor={modeColor} color="black">
{paddedLabel}
</Text>
)
}
return (
<Box flexDirection="row" gap={1} marginLeft={1} width="100%">
{hasPrimary && renderButton(config.primaryText!, "1")}
{hasSecondary && renderButton(config.secondaryText!, hasPrimary ? "2" : "1")}
</Box>
)
}
+74
View File
@@ -0,0 +1,74 @@
/**
* Reusable API key input component
* Shows a password-masked input field for entering API keys
*/
import { Box, Text, useInput } from "ink"
import React from "react"
import { COLORS } from "../constants/colors"
import { useStdinContext } from "../context/StdinContext"
import { isMouseEscapeSequence } from "../utils/input"
interface ApiKeyInputProps {
providerName: string
value: string
onChange: (value: string) => void
onSubmit: (value: string) => void
onCancel: () => void
isActive?: boolean
}
export const ApiKeyInput: React.FC<ApiKeyInputProps> = ({
providerName,
value,
onChange,
onSubmit,
onCancel,
isActive = true,
}) => {
const { isRawModeSupported } = useStdinContext()
useInput(
(input, key) => {
// Filter out mouse escape sequences
if (isMouseEscapeSequence(input)) {
return
}
if (key.escape) {
onCancel()
return
}
if (key.return) {
onSubmit(value)
return
}
if (key.backspace || key.delete) {
onChange(value.slice(0, -1))
return
}
if (input && !key.ctrl && !key.meta) {
onChange(value + input)
}
},
{ isActive: isRawModeSupported && isActive },
)
return (
<Box flexDirection="column">
<Text bold color={COLORS.primaryBlue}>
{providerName} API Key
</Text>
<Box marginTop={1}>
<Text color="gray">Paste your API key below</Text>
</Box>
<Box marginTop={1}>
<Text color="white">{"•".repeat(value.length)}</Text>
<Text inverse> </Text>
</Box>
<Box marginTop={1}>
<Text color="gray">Enter to save, Esc to cancel</Text>
</Box>
</Box>
)
}
+126
View File
@@ -0,0 +1,126 @@
import { Text } from "ink"
import { render } from "ink-testing-library"
import React from "react"
import { beforeEach, describe, expect, it, vi } from "vitest"
import { App } from "./App"
// Mock the child components to isolate App routing logic
vi.mock("./ChatView", () => ({
ChatView: ({ taskId, controller }: any) =>
React.createElement(Text, null, `ChatView: ${taskId || "no-id"} controller=${controller ? "present" : "none"}`),
}))
vi.mock("./TaskJsonView", () => ({
TaskJsonView: ({ taskId, verbose }: any) =>
React.createElement(Text, null, `TaskJsonView: ${taskId || "no-id"} verbose=${String(verbose)}`),
}))
vi.mock("./HistoryView", () => ({
HistoryView: ({ items }: any) => React.createElement(Text, null, `HistoryView: ${items?.length || 0} items`),
}))
vi.mock("./ConfigView", () => ({
ConfigView: ({ dataDir }: any) => React.createElement(Text, null, `ConfigView: ${dataDir}`),
}))
vi.mock("./AuthView", () => ({
AuthView: ({ quickSetup }: any) => React.createElement(Text, null, `AuthView: ${quickSetup?.provider || "no-provider"}`),
}))
vi.mock("../context/TaskContext", () => ({
TaskContextProvider: ({ children }: any) => children,
}))
vi.mock("../context/StdinContext", () => ({
StdinProvider: ({ children }: any) => children,
}))
// Mock useTerminalSize to prevent EventEmitter memory leak warnings from resize listeners
vi.mock("../hooks/useTerminalSize", () => ({
useTerminalSize: () => ({ columns: 80, rows: 24, resizeKey: 0 }),
}))
describe("App", () => {
const mockController = {
dispose: vi.fn(),
stateManager: { flushPendingState: vi.fn() },
}
beforeEach(() => {
vi.clearAllMocks()
})
describe("view routing", () => {
it("should render ChatView when view is task", () => {
const { lastFrame } = render(<App controller={mockController} taskId="test-task" view="task" />)
expect(lastFrame()).toContain("ChatView")
expect(lastFrame()).toContain("test-task")
})
it("should render TaskJsonView when view is task with jsonOutput", () => {
const { lastFrame } = render(<App controller={mockController} jsonOutput={true} taskId="test-task" view="task" />)
expect(lastFrame()).toContain("TaskJsonView")
expect(lastFrame()).toContain("test-task")
})
it("should render HistoryView when view is history", () => {
const historyItems = [
{ id: "1", ts: Date.now(), task: "Task 1" },
{ id: "2", ts: Date.now(), task: "Task 2" },
]
const { lastFrame } = render(<App controller={mockController} historyItems={historyItems} view="history" />)
expect(lastFrame()).toContain("HistoryView")
expect(lastFrame()).toContain("2 items")
})
it("should render ConfigView when view is config", () => {
const { lastFrame } = render(
<App dataDir="/path/to/config" globalState={{ key: "value" }} view="config" workspaceState={{}} />,
)
expect(lastFrame()).toContain("ConfigView")
expect(lastFrame()).toContain("/path/to/config")
})
it("should render AuthView when view is auth", () => {
const { lastFrame } = render(<App authQuickSetup={{ provider: "openai" }} controller={mockController} view="auth" />)
expect(lastFrame()).toContain("AuthView")
expect(lastFrame()).toContain("openai")
})
it("should render ChatView when view is welcome", () => {
const { lastFrame } = render(
<App controller={mockController} onWelcomeExit={() => {}} onWelcomeSubmit={() => {}} view="welcome" />,
)
expect(lastFrame()).toContain("ChatView")
})
})
describe("default props", () => {
it("should use default verbose=false with jsonOutput", () => {
const { lastFrame } = render(<App controller={mockController} jsonOutput={true} view="task" />)
expect(lastFrame()).toContain("verbose=false")
})
it("should use empty array for historyItems by default", () => {
const { lastFrame } = render(<App controller={mockController} view="history" />)
expect(lastFrame()).toContain("0 items")
})
})
describe("props passing", () => {
it("should pass verbose to TaskJsonView", () => {
const { lastFrame } = render(<App controller={mockController} jsonOutput={true} verbose={true} view="task" />)
expect(lastFrame()).toContain("verbose=true")
})
it("should pass taskId to ChatView", () => {
const { lastFrame } = render(<App controller={mockController} taskId="my-task-123" view="task" />)
expect(lastFrame()).toContain("my-task-123")
})
it("should pass controller to ChatView", () => {
const { lastFrame } = render(<App controller={mockController} view="task" />)
expect(lastFrame()).toContain("controller=present")
})
})
})
+279
View File
@@ -0,0 +1,279 @@
/**
* Main App component for Ink CLI
* Routes between different views (task, history, config)
*/
import { Box } from "ink"
import React, { ReactNode, useCallback, useState } from "react"
import { StdinProvider } from "../context/StdinContext"
import { TaskContextProvider } from "../context/TaskContext"
import { useTerminalSize } from "../hooks/useTerminalSize"
import { AuthView } from "./AuthView"
import { ChatView } from "./ChatView"
import { ConfigView } from "./ConfigView"
import { HistoryView } from "./HistoryView"
import { TaskJsonView } from "./TaskJsonView"
export type ViewType = "task" | "history" | "config" | "auth" | "welcome"
interface HistoryPagination {
page: number
totalPages: number
totalCount: number
limit: number
}
interface HookInfo {
name: string
enabled: boolean
absolutePath: string
}
interface WorkspaceHooks {
workspaceName: string
hooks: HookInfo[]
}
interface SkillInfo {
name: string
description: string
path: string
enabled: boolean
}
interface AppProps {
view: ViewType
taskId?: string
controller?: any
// Output Style
verbose?: boolean
jsonOutput?: boolean
// Status Callbacks
onComplete?: () => void
onError?: () => void
// For history view
historyItems?: Array<{ id: string; ts: number; task?: string; totalCost?: number; modelId?: string }>
historyAllItems?: Array<{ id: string; ts: number; task?: string; totalCost?: number; modelId?: string }>
historyPagination?: HistoryPagination
onHistoryPageChange?: (page: number) => void
// For config view
dataDir?: string
globalState?: Record<string, any>
workspaceState?: Record<string, any>
// Rules toggles
globalClineRulesToggles?: Record<string, boolean>
localClineRulesToggles?: Record<string, boolean>
localCursorRulesToggles?: Record<string, boolean>
localWindsurfRulesToggles?: Record<string, boolean>
localAgentsRulesToggles?: Record<string, boolean>
onToggleRule?: (isGlobal: boolean, rulePath: string, enabled: boolean, ruleType: string) => void
// Workflow toggles
globalWorkflowToggles?: Record<string, boolean>
localWorkflowToggles?: Record<string, boolean>
onToggleWorkflow?: (isGlobal: boolean, workflowPath: string, enabled: boolean) => void
// Hooks
hooksEnabled?: boolean
globalHooks?: HookInfo[]
workspaceHooks?: WorkspaceHooks[]
onToggleHook?: (isGlobal: boolean, hookName: string, enabled: boolean, workspaceName?: string) => void
// Skills
skillsEnabled?: boolean
globalSkills?: SkillInfo[]
localSkills?: SkillInfo[]
onToggleSkill?: (isGlobal: boolean, skillPath: string, enabled: boolean) => void
// For auth view
authQuickSetup?: {
provider?: string
apikey?: string
modelid?: string
baseurl?: string
}
// For welcome view
onWelcomeSubmit?: (prompt: string, imagePaths: string[]) => void
onWelcomeExit?: () => void
initialPrompt?: string
initialImages?: string[]
// Stdin support
isRawModeSupported?: boolean
// Robot position (calculated before Ink mounts)
robotTopRow?: number
}
export const App: React.FC<AppProps> = ({
view: initialView,
taskId,
verbose = false,
jsonOutput = false,
controller,
onComplete,
onError,
historyItems = [],
historyAllItems,
historyPagination,
onHistoryPageChange,
dataDir = "",
globalState = {},
workspaceState = {},
// Rules
globalClineRulesToggles,
localClineRulesToggles,
localCursorRulesToggles,
localWindsurfRulesToggles,
localAgentsRulesToggles,
onToggleRule,
// Workflows
globalWorkflowToggles,
localWorkflowToggles,
onToggleWorkflow,
// Hooks
hooksEnabled,
globalHooks,
workspaceHooks,
onToggleHook,
// Skills
skillsEnabled,
globalSkills,
localSkills,
onToggleSkill,
authQuickSetup,
onWelcomeSubmit,
onWelcomeExit,
initialPrompt,
initialImages,
isRawModeSupported = true,
robotTopRow,
}) => {
const { resizeKey } = useTerminalSize()
const [currentView, setCurrentView] = useState<ViewType>(initialView)
const [selectedTaskId, setSelectedTaskId] = useState<string | undefined>(taskId)
const handleSelectTask = useCallback((taskId: string) => {
setSelectedTaskId(taskId)
setCurrentView("task")
}, [])
const handleNavigateToWelcome = useCallback(() => {
setCurrentView("welcome")
}, [])
// Handle welcome submit when navigating internally (e.g., from auth -> welcome)
const _handleInternalWelcomeSubmit = useCallback(
async (prompt: string, imagePaths: string[]) => {
if (onWelcomeSubmit) {
// If external handler provided, use it
onWelcomeSubmit(prompt, imagePaths)
} else if (controller && prompt.trim()) {
// Otherwise, start a task directly via controller
setCurrentView("task")
// Convert image paths to data URLs if needed
const imageDataUrls =
imagePaths.length > 0
? await Promise.all(
imagePaths.map(async (p) => {
try {
const fs = await import("fs/promises")
const path = await import("path")
const data = await fs.readFile(p)
const ext = path.extname(p).toLowerCase().slice(1)
const mimeType = ext === "jpg" ? "jpeg" : ext
return `data:image/${mimeType};base64,${data.toString("base64")}`
} catch {
return null
}
}),
)
: []
const validImages = imageDataUrls.filter((img): img is string => img !== null)
await controller.initTask(prompt.trim(), validImages.length > 0 ? validImages : undefined)
}
},
[onWelcomeSubmit, controller],
)
let content: ReactNode
switch (currentView) {
case "history":
content = (
<HistoryView
allItems={historyAllItems}
controller={controller}
items={historyItems}
onPageChange={onHistoryPageChange}
onSelectTask={handleSelectTask}
pagination={historyPagination}
/>
)
break
case "config":
content = (
<ConfigView
dataDir={dataDir}
globalClineRulesToggles={globalClineRulesToggles}
globalHooks={globalHooks}
globalSkills={globalSkills}
globalState={globalState}
globalWorkflowToggles={globalWorkflowToggles}
hooksEnabled={hooksEnabled}
localAgentsRulesToggles={localAgentsRulesToggles}
localClineRulesToggles={localClineRulesToggles}
localCursorRulesToggles={localCursorRulesToggles}
localSkills={localSkills}
localWindsurfRulesToggles={localWindsurfRulesToggles}
localWorkflowToggles={localWorkflowToggles}
onToggleHook={onToggleHook}
onToggleRule={onToggleRule}
onToggleSkill={onToggleSkill}
onToggleWorkflow={onToggleWorkflow}
skillsEnabled={skillsEnabled}
workspaceHooks={workspaceHooks}
workspaceState={workspaceState}
/>
)
break
case "auth":
content = (
<AuthView
controller={controller}
onComplete={onComplete}
onError={onError}
onNavigateToWelcome={handleNavigateToWelcome}
quickSetup={authQuickSetup}
/>
)
break
case "task":
case "welcome":
content = (
<TaskContextProvider controller={controller}>
{jsonOutput ? (
<TaskJsonView onComplete={onComplete} onError={onError} taskId={selectedTaskId} verbose={verbose} />
) : (
<ChatView
controller={controller}
initialImages={initialImages}
initialPrompt={initialPrompt}
onComplete={onComplete}
onError={onError}
onExit={onWelcomeExit}
robotTopRow={robotTopRow}
taskId={selectedTaskId}
/>
)}
</TaskContextProvider>
)
break
default:
content = null
}
return (
<StdinProvider isRawModeSupported={isRawModeSupported}>
<Box key={resizeKey}>{content}</Box>
</StdinProvider>
)
}
File diff suppressed because it is too large Load Diff
+374
View File
@@ -0,0 +1,374 @@
/**
* User input prompt component
* Handles different types of user interactions (text input, confirmations, choices)
*/
import type { ClineAsk } from "@shared/ExtensionMessage"
import { Box, Text, useApp, useInput } from "ink"
import React, { useCallback, useEffect, useRef, useState } from "react"
import { useStdinContext } from "../context/StdinContext"
import { useTaskController } from "../context/TaskContext"
import { useLastCompletedAskMessage } from "../hooks/useStateSubscriber"
import { isMouseEscapeSequence } from "../utils/input"
import { jsonParseSafe } from "../utils/parser"
import { getCliMessagePrefixIcon } from "./MessageRow"
interface AskPromptProps {
onRespond?: (response: string) => void
}
type PromptType = "confirmation" | "text" | "options" | "plan_mode_text" | "completion" | "exit_confirmation" | "none"
function getPromptType(ask: ClineAsk, text: string): PromptType {
switch (ask) {
case "followup": {
const parts = jsonParseSafe(text, {
question: undefined as string | undefined,
options: undefined as string[] | undefined,
})
if (parts.options && parts.options.length > 0) {
return "options"
}
return "text"
}
case "plan_mode_respond": {
const parts = jsonParseSafe(text, {
question: undefined as string | undefined,
options: undefined as string[] | undefined,
})
if (parts.options && parts.options.length > 0) {
return "options"
}
// Plan mode without options - allow text input or toggle to Act mode
return "plan_mode_text"
}
case "completion_result":
// Task completed - allow follow-up question or exit
return "completion"
case "resume_task":
case "resume_completed_task":
return "exit_confirmation"
case "command":
case "tool":
case "browser_action_launch":
case "use_mcp_server":
return "confirmation"
default:
return "none"
}
}
export const AskPrompt: React.FC<AskPromptProps> = ({ onRespond }) => {
const { exit } = useApp()
const { isRawModeSupported } = useStdinContext()
const controller = useTaskController()
const lastAskMessage = useLastCompletedAskMessage()
const [textInput, setTextInput] = useState("")
const [responded, setResponded] = useState(false)
const lastAskTs = useRef<number | null>(null)
// Reset state when ask message changes
useEffect(() => {
if (lastAskMessage && lastAskMessage.ts !== lastAskTs.current) {
lastAskTs.current = lastAskMessage.ts
setTextInput("")
setResponded(false)
}
}, [lastAskMessage])
const sendResponse = useCallback(
async (responseType: string, text?: string) => {
if (responded || !controller?.task) {
return
}
setResponded(true)
try {
await controller.task.handleWebviewAskResponse(responseType, text)
onRespond?.(text || responseType)
} catch {
// Controller may be disposed
}
},
[controller, responded, onRespond],
)
const toggleToActMode = useCallback(async () => {
if (responded || !controller) {
return
}
setResponded(true)
try {
await controller.togglePlanActMode("act")
onRespond?.("Switched to Act mode")
} catch {
// Controller may be disposed
}
}, [controller, responded, onRespond])
// Handle keyboard input
useInput(
(input, key) => {
// Filter out mouse escape sequences
if (isMouseEscapeSequence(input)) {
return
}
if (!lastAskMessage || responded) {
return
}
const ask = lastAskMessage.ask as ClineAsk
const text = lastAskMessage.text || ""
const promptType = getPromptType(ask, text)
if (promptType === "confirmation" || promptType === "exit_confirmation") {
// y/n confirmation
if (input.toLowerCase() === "y") {
sendResponse("yesButtonClicked")
} else if (input.toLowerCase() === "n") {
if (promptType === "exit_confirmation") {
exit()
return
}
sendResponse("noButtonClicked")
}
} else if (promptType === "options") {
// Number selection for options, or free text input
const parts = jsonParseSafe(text, { options: [] as string[] })
if (key.return) {
// Submit free text on Enter
if (textInput.trim()) {
sendResponse("messageResponse", textInput.trim())
}
} else if (key.backspace || key.delete) {
setTextInput((prev) => prev.slice(0, -1))
} else if (input && !key.ctrl && !key.meta) {
// Check if it's a number for option selection (only when no text typed yet)
const num = parseInt(input, 10)
if (textInput === "" && !Number.isNaN(num) && num >= 1 && num <= parts.options.length) {
const selectedOption = parts.options[num - 1]
sendResponse("messageResponse", selectedOption)
} else {
// Regular character input for free text
setTextInput((prev) => prev + input)
}
}
} else if (promptType === "text") {
// Text input mode
if (key.return) {
// Submit on Enter
if (textInput.trim()) {
sendResponse("messageResponse", textInput.trim())
}
} else if (key.backspace || key.delete) {
setTextInput((prev) => prev.slice(0, -1))
} else if (input && !key.ctrl && !key.meta) {
// Regular character input
setTextInput((prev) => prev + input)
}
} else if (promptType === "plan_mode_text") {
// Plan mode text input - allows text response or toggle to Act mode
if (key.return) {
// Submit on Enter
if (textInput.trim()) {
sendResponse("messageResponse", textInput.trim())
} else {
// Empty enter = switch to Act mode
toggleToActMode()
}
} else if (key.backspace || key.delete) {
setTextInput((prev) => prev.slice(0, -1))
} else if (input && !key.ctrl && !key.meta) {
// Regular character input
setTextInput((prev) => prev + input)
}
} else if (promptType === "completion") {
// Task completed - allow follow-up question or exit
if (key.return) {
if (textInput.trim()) {
// Send follow-up question
sendResponse("messageResponse", textInput.trim())
} else {
// Empty enter = confirm completion (exit)
sendResponse("yesButtonClicked")
}
} else if (key.backspace || key.delete) {
setTextInput((prev) => prev.slice(0, -1))
} else if (input && !key.ctrl && !key.meta) {
// Regular character input
setTextInput((prev) => prev + input)
}
}
},
{ isActive: isRawModeSupported && !!lastAskMessage && !responded },
)
if (!lastAskMessage || responded) {
return null
}
const ask = lastAskMessage.ask as ClineAsk
const text = lastAskMessage.text || ""
const promptType = getPromptType(ask, text)
const icon = getCliMessagePrefixIcon(lastAskMessage)
if (promptType === "none") {
return null
}
switch (ask) {
case "followup": {
const parts = jsonParseSafe(text, {
question: undefined as string | undefined,
options: undefined as string[] | undefined,
})
if (parts.options && parts.options.length > 0) {
return (
<Box flexDirection="column" marginTop={1}>
<Text color="cyan">Select an option (enter number):</Text>
{parts.options.map((opt, idx) => (
<Box key={idx} marginLeft={2}>
<Text>{`${idx + 1}. ${opt}`}</Text>
</Box>
))}
<Box marginTop={1}>
<Text>{icon} </Text>
<Text color="cyan">Or type: </Text>
<Text>{textInput}</Text>
<Text inverse> </Text>
</Box>
<Text color="gray">(Enter number to select, or type response + Enter)</Text>
</Box>
)
}
// Text input prompt
return (
<Box flexDirection="column" marginTop={1}>
<Box>
<Text>{icon} </Text>
<Text color="cyan">Reply: </Text>
<Text>{textInput}</Text>
<Text inverse> </Text>
</Box>
<Text color="gray">(Type your response and press Enter)</Text>
</Box>
)
}
case "plan_mode_respond": {
const parts = jsonParseSafe(text, {
question: undefined as string | undefined,
options: undefined as string[] | undefined,
})
if (parts.options && parts.options.length > 0) {
return (
<Box flexDirection="column" marginTop={1}>
<Text color="cyan">Select an option (enter number):</Text>
{parts.options.map((opt, idx) => (
<Box key={idx} marginLeft={2}>
<Text>{`${idx + 1}. ${opt}`}</Text>
</Box>
))}
<Box marginTop={1}>
<Text>{icon} </Text>
<Text color="cyan">Or type: </Text>
<Text>{textInput}</Text>
<Text inverse> </Text>
</Box>
<Text color="gray">(Enter number to select, or type response + Enter)</Text>
</Box>
)
}
// Plan mode text input - show option to switch to Act mode
return (
<Box flexDirection="column" marginTop={1}>
<Box>
<Text>{icon} </Text>
<Text color="cyan">Reply: </Text>
<Text>{textInput}</Text>
<Text inverse> </Text>
</Box>
<Text color="gray">(Type response + Enter, or just Enter to switch to Act mode)</Text>
</Box>
)
}
case "command":
return (
<Box flexDirection="column" marginTop={1}>
<Box>
<Text>{icon} </Text>
<Text color="yellow"> Execute this command? </Text>
<Text color="gray">(y/n)</Text>
</Box>
</Box>
)
case "tool":
return (
<Box flexDirection="column" marginTop={1}>
<Box>
<Text>{icon} </Text>
<Text color="blue"> Use this tool? </Text>
<Text color="gray">(y/n)</Text>
</Box>
</Box>
)
case "completion_result":
return (
<Box flexDirection="column" marginTop={1}>
<Box>
<Text>{icon} </Text>
<Text color="cyan">Follow-up: </Text>
<Text>{textInput}</Text>
<Text inverse> </Text>
</Box>
<Text color="gray">(Type follow-up question + Enter, or q to exit)</Text>
</Box>
)
case "resume_task":
case "resume_completed_task":
return (
<Box flexDirection="column" marginTop={1}>
<Box>
<Text>{icon} </Text>
<Text color="cyan"> Resume task? </Text>
<Text color="gray">(y/n)</Text>
</Box>
</Box>
)
case "browser_action_launch":
return (
<Box flexDirection="column" marginTop={1}>
<Box>
<Text>{icon} </Text>
<Text color="cyan"> Launch browser? </Text>
<Text color="gray">(y/n)</Text>
</Box>
</Box>
)
case "use_mcp_server":
return (
<Box flexDirection="column" marginTop={1}>
<Box>
<Text>{icon} </Text>
<Text color="cyan"> Use MCP server? </Text>
<Text color="gray">(y/n)</Text>
</Box>
</Box>
)
default:
return null
}
}
+991
View File
@@ -0,0 +1,991 @@
/**
* Auth view component
* Handles interactive authentication and provider configuration
*/
import { Box, Text, useApp, useInput } from "ink"
import Spinner from "ink-spinner"
import React, { useCallback, useEffect, useMemo, useState } from "react"
import { StateManager } from "@/core/storage/StateManager"
import { openAiCodexOAuthManager } from "@/integrations/openai-codex/oauth"
import { AuthService } from "@/services/auth/AuthService"
import { API_PROVIDERS_LIST, openAiCodexDefaultModelId, openRouterDefaultModelId } from "@/shared/api"
import { ProviderToApiKeyMap } from "@/shared/storage"
import { openExternal } from "@/utils/env"
import { COLORS } from "../constants/colors"
import { getAllFeaturedModels } from "../constants/featured-models"
import { useStdinContext } from "../context/StdinContext"
import { useScrollableList } from "../hooks/useScrollableList"
import { type DetectedSources, detectImportSources, type ImportSource } from "../utils/import-configs"
import { isMouseEscapeSequence } from "../utils/input"
import { ApiKeyInput } from "./ApiKeyInput"
import { StaticRobotFrame } from "./AsciiMotionCli"
import { type BedrockConfig, BedrockSetup } from "./BedrockSetup"
import { ImportView } from "./ImportView"
import { getDefaultModelId, hasModelPicker, ModelPicker } from "./ModelPicker"
import { getProviderLabel, getProviderOrder } from "./ProviderPicker"
type AuthStep =
| "menu"
| "provider"
| "apikey"
| "modelid"
| "baseurl"
| "saving"
| "success"
| "error"
| "cline_auth"
| "cline_model"
| "openai_codex_auth"
| "bedrock"
| "import"
// Featured models loaded from shared constants
const featuredModels = getAllFeaturedModels()
interface AuthViewProps {
controller: any
onComplete?: () => void
onError?: () => void
onNavigateToWelcome?: () => void
// Quick setup options
quickSetup?: {
provider?: string
apikey?: string
modelid?: string
baseurl?: string
}
}
interface SelectItem {
label: string
value: string
}
/**
* Select component with keyboard navigation
*/
const Select: React.FC<{
items: SelectItem[]
onSelect: (value: string) => void
label?: string
}> = ({ items, onSelect, label }) => {
const { isRawModeSupported } = useStdinContext()
const [selectedIndex, setSelectedIndex] = useState(0)
useInput(
(input, key) => {
if (key.upArrow) {
setSelectedIndex((prev) => (prev > 0 ? prev - 1 : items.length - 1))
} else if (key.downArrow) {
setSelectedIndex((prev) => (prev < items.length - 1 ? prev + 1 : 0))
} else if (key.return) {
onSelect(items[selectedIndex].value)
}
},
{ isActive: isRawModeSupported },
)
return (
<Box flexDirection="column">
{label && (
<Text bold color="cyan">
{label}
</Text>
)}
{items.map((item, index) => (
<Box key={item.value}>
<Text color={index === selectedIndex ? COLORS.primaryBlue : undefined}>
{index === selectedIndex ? " " : " "}
{item.label}
</Text>
</Box>
))}
<Text color="gray">(Use arrow keys to navigate, Enter to select)</Text>
</Box>
)
}
/**
* Text input component - minimal, just the input field
*/
const TextInput: React.FC<{
value: string
onChange: (value: string) => void
onSubmit: (value: string) => void
placeholder?: string
isPassword?: boolean
}> = ({ value, onChange, onSubmit, placeholder, isPassword }) => {
const { isRawModeSupported } = useStdinContext()
useInput(
(input, key) => {
// Filter out mouse escape sequences
if (isMouseEscapeSequence(input)) {
return
}
if (key.return) {
onSubmit(value)
} else if (key.backspace || key.delete) {
onChange(value.slice(0, -1))
} else if (input && !key.ctrl && !key.meta) {
onChange(value + input)
}
},
{ isActive: isRawModeSupported },
)
const displayValue = isPassword ? "•".repeat(value.length) : value
return (
<Box>
<Text color="white">{displayValue || placeholder || ""}</Text>
<Text inverse> </Text>
</Box>
)
}
export const AuthView: React.FC<AuthViewProps> = ({ controller, onComplete, onError, onNavigateToWelcome, quickSetup }) => {
const { exit } = useApp()
const [step, setStep] = useState<AuthStep>(quickSetup ? "saving" : "menu")
const [selectedProvider, setSelectedProvider] = useState<string>(
StateManager.get().getApiConfiguration().actModeApiProvider ||
StateManager.get().getApiConfiguration().planModeApiProvider ||
"",
)
const [apiKey, setApiKey] = useState("")
const [modelId, setModelId] = useState("")
const [baseUrl, setBaseUrl] = useState("")
const [errorMessage, setErrorMessage] = useState("")
const [authStatus, setAuthStatus] = useState<string>("")
const [providerSearch, setProviderSearch] = useState("")
const [providerIndex, setProviderIndex] = useState(0)
const [clineModelIndex, setClineModelIndex] = useState(0)
const [importSources, setImportSources] = useState<DetectedSources>({ codex: false, opencode: false })
const [importSource, setImportSource] = useState<ImportSource | null>(null)
const [bedrockConfig, setBedrockConfig] = useState<BedrockConfig | null>(null)
// Use providers.json order, filtered to only available providers
const sortedProviders = useMemo(() => {
const availableProviders = new Set(API_PROVIDERS_LIST)
return getProviderOrder().filter((p) => availableProviders.has(p))
}, [])
// Main menu items - conditionally include import options
const mainMenuItems: SelectItem[] = useMemo(() => {
const items: SelectItem[] = [{ label: "Sign in with Cline account", value: "cline_auth" }]
// Add OpenAI Codex option for ChatGPT subscribers
items.push({ label: "Sign in with ChatGPT Subscription", value: "openai_codex_auth" })
// Add import options if detected
if (importSources.codex) {
items.push({ label: "Import from Codex CLI", value: "import_codex" })
}
if (importSources.opencode) {
items.push({ label: "Import from OpenCode", value: "import_opencode" })
}
items.push({ label: "Use your own API key", value: "configure_byo" })
items.push({ label: "Exit", value: "exit" })
return items
}, [importSources])
// Provider menu items - filtered by search (searches both ID and display name)
const providerItems: SelectItem[] = useMemo(() => {
const search = providerSearch.toLowerCase()
const filtered = providerSearch
? sortedProviders.filter(
(p) => p.toLowerCase().includes(search) || getProviderLabel(p).toLowerCase().includes(search),
)
: sortedProviders
return filtered.map((p: string) => ({
label: getProviderLabel(p),
value: p,
}))
}, [sortedProviders, providerSearch])
// Use shared scrollable list hook for provider windowing
const TOTAL_PROVIDER_ROWS = 8
const {
visibleStart: providerVisibleStart,
visibleCount: providerVisibleCount,
showTopIndicator: showProviderTopIndicator,
showBottomIndicator: showProviderBottomIndicator,
} = useScrollableList(providerItems.length, providerIndex, TOTAL_PROVIDER_ROWS)
const visibleProviderItems = useMemo(() => {
return providerItems.slice(providerVisibleStart, providerVisibleStart + providerVisibleCount)
}, [providerItems, providerVisibleStart, providerVisibleCount])
// Detect import sources on mount
useEffect(() => {
setImportSources(detectImportSources())
}, [])
// Reset provider index when search changes
useEffect(() => {
setProviderIndex(0)
}, [providerSearch])
// Set default model when entering model step
useEffect(() => {
if (step === "modelid" && hasModelPicker(selectedProvider)) {
setModelId(getDefaultModelId(selectedProvider))
}
}, [step, selectedProvider])
// Handle quick setup
useEffect(() => {
if (quickSetup && step === "saving") {
handleQuickSetup()
}
}, [quickSetup, step])
// Subscribe to auth status updates when in cline_auth step
useEffect(() => {
if (step !== "cline_auth") {
return
}
let cancelled = false
// Create a streaming response handler that receives auth state updates
const responseHandler = async (authState: { user?: { email?: string } }, _isLast?: boolean) => {
if (cancelled) {
return
}
if (authState.user && authState.user.email) {
// Auth succeeded - save configuration and transition to success
const stateManager = StateManager.get()
const mode = stateManager.getGlobalSettingsKey("mode") || "act"
const providerKey = mode === "act" ? "actModeApiProvider" : "planModeApiProvider"
const modelIdKey = mode === "act" ? "actModeApiModelId" : "planModeApiModelId"
const config: Record<string, string> = {
actModeApiProvider: "cline",
[providerKey]: "cline",
[modelIdKey]: openRouterDefaultModelId,
}
stateManager.setApiConfiguration(config)
stateManager.flushPendingState()
setSelectedProvider("cline")
setModelId(config[modelIdKey])
setStep("cline_model")
}
}
// Subscribe to auth status updates
const authService = AuthService.getInstance(controller)
authService.subscribeToAuthStatusUpdate(controller, {}, responseHandler, `cli-auth-${Date.now()}`)
return () => {
cancelled = true
}
}, [step, controller])
const handleQuickSetup = async () => {
if (!quickSetup) {
return
}
try {
const { provider, apikey, modelid, baseurl } = quickSetup
// Validate required parameters
if (!provider || !apikey || !modelid) {
setErrorMessage("Quick setup requires --provider, --apikey, and --modelid flags")
setStep("error")
return
}
const normalizedProvider = provider.toLowerCase().trim()
if (!sortedProviders.includes(normalizedProvider)) {
setErrorMessage(`Invalid provider '${provider}'. Supported providers: ${sortedProviders.join(", ")}`)
setStep("error")
return
}
if (normalizedProvider === "bedrock") {
setErrorMessage(
"Bedrock provider is not supported for quick setup due to complex authentication requirements. Please use interactive setup.",
)
setStep("error")
return
}
if (baseurl && !["openai", "openai-native"].includes(normalizedProvider)) {
setErrorMessage("Base URL is only supported for OpenAI and OpenAI-compatible providers")
setStep("error")
return
}
// Save configuration
const stateManager = StateManager.get()
const config: Record<string, string> = {
actModeApiProvider: normalizedProvider,
planModeApiProvider: normalizedProvider,
actModeApiModelId: modelid,
planModeApiModelId: modelid,
}
// Use provider-specific API key field
const keyField = ProviderToApiKeyMap[normalizedProvider]
if (keyField) {
const fields = Array.isArray(keyField) ? keyField : [keyField]
// Set the first key field for the provider
config[fields[0]] = apikey
} else {
// Fallback to generic apiKey
config.apiKey = apikey
}
if (baseurl) {
config.openAiBaseUrl = baseurl
}
stateManager.setApiConfiguration(config)
await stateManager.flushPendingState()
setSelectedProvider(normalizedProvider)
setModelId(modelid)
setBaseUrl(baseurl || "")
setStep("success")
} catch (error) {
setErrorMessage(error instanceof Error ? error.message : String(error))
setStep("error")
}
}
// Start OpenAI Codex OAuth flow
const startOpenAiCodexAuth = useCallback(async () => {
try {
// Get the authorization URL and start the callback server
const authUrl = openAiCodexOAuthManager.startAuthorizationFlow()
// Open browser to authorization URL (uses cross-platform 'open' package)
await openExternal(authUrl)
// Wait for the callback
await openAiCodexOAuthManager.waitForCallback()
// Success - save configuration
const stateManager = StateManager.get()
const mode = stateManager.getGlobalSettingsKey("mode") || "act"
const providerKey = mode === "act" ? "actModeApiProvider" : "planModeApiProvider"
const modelIdKey = mode === "act" ? "actModeApiModelId" : "planModeApiModelId"
const config: Record<string, string> = {
actModeApiProvider: "openai-codex",
planModeApiProvider: "openai-codex",
[providerKey]: "openai-codex",
[modelIdKey]: openAiCodexDefaultModelId,
}
stateManager.setApiConfiguration(config)
await stateManager.flushPendingState()
setSelectedProvider("openai-codex")
setModelId(openAiCodexDefaultModelId)
setStep("success")
} catch (error) {
openAiCodexOAuthManager.cancelAuthorizationFlow()
setErrorMessage(error instanceof Error ? error.message : String(error))
setStep("error")
}
}, [])
// Start Cline auth flow
const startClineAuth = useCallback(async () => {
try {
setStep("cline_auth")
setAuthStatus("Starting authentication...")
await AuthService.getInstance(controller).createAuthRequest()
} catch (error) {
setErrorMessage(error instanceof Error ? error.message : String(error))
setStep("error")
}
}, [controller])
const handleMainMenuSelect = useCallback(
(value: string) => {
if (value === "exit") {
exit()
onComplete?.()
} else if (value === "cline_auth") {
startClineAuth()
} else if (value === "openai_codex_auth") {
setStep("openai_codex_auth")
startOpenAiCodexAuth()
} else if (value === "configure_byo") {
setStep("provider")
} else if (value === "import_codex") {
setImportSource("codex")
setStep("import")
} else if (value === "import_opencode") {
setImportSource("opencode")
setStep("import")
}
},
[exit, onComplete, startClineAuth, startOpenAiCodexAuth],
)
const handleProviderSelect = useCallback(
(value: string) => {
setSelectedProvider(value)
if (value === "cline") {
startClineAuth()
} else if (value === "openai-codex") {
setStep("openai_codex_auth")
startOpenAiCodexAuth()
} else if (value === "bedrock") {
setStep("bedrock")
} else {
setStep("apikey")
}
},
[startClineAuth, startOpenAiCodexAuth],
)
const handleApiKeySubmit = useCallback(
(value: string) => {
if (!value.trim() || !selectedProvider) {
// Don't allow empty
return
}
// Store in local state - will be saved via StateManager in saveConfiguration
setApiKey(value)
setStep("modelid")
},
[selectedProvider],
)
const saveConfiguration = useCallback(
async (model: string, base: string) => {
try {
const stateManager = StateManager.get()
const config: Record<string, string> = {
actModeApiProvider: selectedProvider,
planModeApiProvider: selectedProvider,
actModeApiModelId: model,
planModeApiModelId: model,
apiProvider: selectedProvider,
}
// Add API key or Bedrock-specific config
if (selectedProvider === "bedrock" && bedrockConfig) {
const bedrockFields: Record<string, unknown> = {
awsAuthentication: bedrockConfig.awsAuthentication,
awsRegion: bedrockConfig.awsRegion,
awsUseCrossRegionInference: bedrockConfig.awsUseCrossRegionInference,
}
if (bedrockConfig.awsProfile !== undefined) bedrockFields.awsProfile = bedrockConfig.awsProfile
if (bedrockConfig.awsAccessKey) bedrockFields.awsAccessKey = bedrockConfig.awsAccessKey
if (bedrockConfig.awsSecretKey) bedrockFields.awsSecretKey = bedrockConfig.awsSecretKey
if (bedrockConfig.awsSessionToken) bedrockFields.awsSessionToken = bedrockConfig.awsSessionToken
Object.assign(config, bedrockFields)
} else if (apiKey) {
const keyField = ProviderToApiKeyMap[selectedProvider as keyof typeof ProviderToApiKeyMap]
if (keyField) {
const fields = Array.isArray(keyField) ? keyField : [keyField]
config[fields[0]] = apiKey
}
}
if (base) {
config.openAiBaseUrl = base
}
stateManager.setApiConfiguration(config)
await stateManager.flushPendingState()
setStep("success")
} catch (error) {
setErrorMessage(error instanceof Error ? error.message : String(error))
setStep("error")
}
},
[selectedProvider, apiKey, bedrockConfig],
)
const handleModelIdSubmit = useCallback(
(value: string) => {
if (value.trim()) {
setModelId(value)
}
// Only show baseurl step for OpenAI-like providers
if (["openai", "openai-native"].includes(selectedProvider)) {
setStep("baseurl")
} else {
setStep("saving")
saveConfiguration(value, "")
}
},
[selectedProvider, saveConfiguration],
)
const handleBaseUrlSubmit = useCallback(
(value: string) => {
setBaseUrl(value)
setStep("saving")
saveConfiguration(modelId, value)
},
[modelId, saveConfiguration],
)
const handleClineModelSelect = useCallback(
(modelId: string) => {
setModelId(modelId)
setStep("saving")
saveConfiguration(modelId, "")
},
[saveConfiguration],
)
const handleBedrockComplete = useCallback((config: BedrockConfig) => {
setBedrockConfig(config)
setStep("modelid")
}, [])
const handleImportComplete = useCallback(() => {
setStep("success")
}, [])
const handleImportCancel = useCallback(() => {
setImportSource(null)
setStep("menu")
}, [])
// Auto-navigate to welcome after success (immediate)
useEffect(() => {
if (step === "success" && onNavigateToWelcome) {
onNavigateToWelcome()
}
}, [step, onNavigateToWelcome])
// Error screen menu items
const errorMenuItems: SelectItem[] = useMemo(() => {
const items: SelectItem[] = [{ label: "Try again", value: "retry" }]
if (onNavigateToWelcome) {
items.push({ label: "Start a task", value: "welcome" })
}
items.push({ label: "Exit", value: "exit" })
return items
}, [onNavigateToWelcome])
const handleErrorMenuSelect = useCallback(
(value: string) => {
if (value === "retry") {
// Reset state and go back to menu
setErrorMessage("")
setApiKey("")
setModelId("")
setBaseUrl("")
setSelectedProvider("")
setStep("menu")
} else if (value === "welcome") {
onNavigateToWelcome?.()
} else if (value === "exit") {
onError?.()
exit()
}
},
[onNavigateToWelcome, onError, exit],
)
// Handle going back to previous step
const goBack = useCallback(() => {
switch (step) {
case "provider":
setProviderSearch("")
setProviderIndex(0)
setStep("menu")
break
case "apikey":
setApiKey("")
setStep("provider")
break
case "modelid":
setModelId("")
// Go back to cline_model if we came from there (Cline provider)
if (selectedProvider === "cline") {
setStep("cline_model")
} else {
setStep("apikey")
}
break
case "baseurl":
setBaseUrl("")
setStep("modelid")
break
case "cline_auth":
setStep("menu")
break
case "openai_codex_auth":
openAiCodexOAuthManager.cancelAuthorizationFlow()
setStep("menu")
break
case "cline_model":
setClineModelIndex(0)
setStep("menu")
break
case "bedrock":
setBedrockConfig(null)
setStep("provider")
break
case "import":
setImportSource(null)
setStep("menu")
break
case "error":
setErrorMessage("")
setStep("menu")
break
// menu, saving, success - no back action
}
}, [step, selectedProvider])
// Render the auth box content based on current step
// Note: "menu" step is rendered separately in the main return for proper menuIndex tracking
const renderAuthContent = () => {
switch (step) {
case "provider": {
return (
<Box flexDirection="column">
<Text color="white">Select a provider</Text>
<Text> </Text>
<Box>
<Text color="gray">Search: </Text>
<Text color="white">{providerSearch}</Text>
<Text inverse> </Text>
</Box>
<Text> </Text>
{showProviderTopIndicator && <Text color="gray">... {providerVisibleStart} more above</Text>}
{visibleProviderItems.map((item, i) => {
const actualIndex = providerVisibleStart + i
return (
<Box key={item.value}>
<Text color={actualIndex === providerIndex ? COLORS.primaryBlue : undefined}>
{actualIndex === providerIndex ? " " : " "}
{item.label}
</Text>
</Box>
)
})}
{showProviderBottomIndicator && (
<Text color="gray">
... {providerItems.length - providerVisibleStart - providerVisibleCount} more below
</Text>
)}
{providerItems.length === 0 && <Text color="gray">No providers match "{providerSearch}"</Text>}
<Text> </Text>
<Text color="gray">Type to search, arrows to navigate, Enter to select, Esc to go back</Text>
</Box>
)
}
case "apikey":
return (
<ApiKeyInput
isActive={step === "apikey"}
onCancel={goBack}
onChange={setApiKey}
onSubmit={handleApiKeySubmit}
providerName={getProviderLabel(selectedProvider)}
value={apiKey}
/>
)
case "modelid":
// Show model picker for providers with static model lists
if (hasModelPicker(selectedProvider)) {
return (
<Box flexDirection="column">
<Text color="white">Select a model</Text>
<Text> </Text>
<ModelPicker
controller={controller}
isActive={step === "modelid"}
onChange={setModelId}
onSubmit={handleModelIdSubmit}
provider={selectedProvider}
/>
<Text> </Text>
<Text color="gray">Type to search, arrows to navigate, Enter to select, Esc to go back</Text>
</Box>
)
}
// Fall back to text input for providers without static model lists
return (
<Box flexDirection="column">
<Text color="white">Model ID</Text>
<Text> </Text>
<Text color="gray">e.g., claude-sonnet-4-20250514, gpt-4o</Text>
<Text> </Text>
<TextInput onChange={setModelId} onSubmit={handleModelIdSubmit} placeholder="model-id" value={modelId} />
<Text> </Text>
<Text color="gray">Enter to continue, Esc to go back</Text>
</Box>
)
case "baseurl":
return (
<Box flexDirection="column">
<Text color="white">Base URL (optional)</Text>
<Text> </Text>
<Text color="gray">For self-hosted or proxy endpoints</Text>
<Text> </Text>
<TextInput
onChange={setBaseUrl}
onSubmit={handleBaseUrlSubmit}
placeholder="https://api.example.com/v1"
value={baseUrl}
/>
<Text> </Text>
<Text color="gray">Enter to skip or continue, Esc to go back</Text>
</Box>
)
case "saving":
return (
<Box>
<Text color={COLORS.primaryBlue}>
<Spinner type="dots" />
</Text>
<Text color="white"> Saving configuration...</Text>
</Box>
)
case "cline_auth":
return (
<Box flexDirection="column">
<Box>
<Text color={COLORS.primaryBlue}>
<Spinner type="dots" />
</Text>
<Text color="white"> Waiting for browser sign-in...</Text>
</Box>
<Text> </Text>
<Text color="gray">Complete sign-in in your browser, then return here.</Text>
<Text> </Text>
<Text color="gray">Esc to cancel</Text>
</Box>
)
case "openai_codex_auth":
return (
<Box flexDirection="column">
<Box>
<Text color={COLORS.primaryBlue}>
<Spinner type="dots" />
</Text>
<Text color="white"> Waiting for ChatGPT sign-in...</Text>
</Box>
<Text> </Text>
<Text color="gray">Sign in with your ChatGPT account in the browser.</Text>
<Text color="gray">Requires ChatGPT Plus, Pro, or Team subscription.</Text>
<Text> </Text>
<Text color="gray">Esc to cancel</Text>
</Box>
)
case "cline_model": {
const allModels = featuredModels
return (
<Box flexDirection="column">
<Text color="white">Choose a model</Text>
<Text> </Text>
{/* Model list */}
{allModels.map((model, i) => (
<Box flexDirection="column" key={model.id} marginBottom={1}>
<Box>
<Text color={i === clineModelIndex ? COLORS.primaryBlue : undefined}>
{i === clineModelIndex ? " " : " "}
</Text>
<Text bold color={i === clineModelIndex ? COLORS.primaryBlue : "white"}>
{model.name}
</Text>
{model.label && (
<>
<Text> </Text>
<Text
backgroundColor={model.label === "FREE" ? "gray" : COLORS.primaryBlue}
color="black">
{" "}
{model.label}{" "}
</Text>
</>
)}
</Box>
<Box paddingLeft={2}>
<Text color="gray">{model.description}</Text>
</Box>
</Box>
))}
{/* Browse all option */}
<Box>
<Text color={clineModelIndex === allModels.length ? COLORS.primaryBlue : "gray"}>
{clineModelIndex === allModels.length ? " " : " "}
Browse all models...
</Text>
</Box>
<Text> </Text>
<Text color="gray">Arrows to navigate, Enter to select</Text>
</Box>
)
}
case "bedrock":
return (
<BedrockSetup
isActive={step === "bedrock"}
onCancel={() => {
setBedrockConfig(null)
setStep("provider")
}}
onComplete={handleBedrockComplete}
/>
)
case "import":
if (!importSource) {
return null
}
return <ImportView onCancel={handleImportCancel} onComplete={handleImportComplete} source={importSource} />
case "error":
return (
<Box flexDirection="column">
<Text bold color="red">
Something went wrong
</Text>
<Text> </Text>
<Text color="yellow">{errorMessage}</Text>
<Text> </Text>
<Select items={errorMenuItems} onSelect={handleErrorMenuSelect} />
</Box>
)
default:
return null
}
}
// For menu step, we need to handle input at the top level
const { isRawModeSupported } = useStdinContext()
const [menuIndex, setMenuIndex] = useState(0)
// Steps that allow going back with escape (apikey handled by ApiKeyInput component)
const canGoBack = [
"provider",
"modelid",
"baseurl",
"cline_auth",
"cline_model",
"openai_codex_auth",
"bedrock",
"error",
].includes(step)
useInput(
(input, key) => {
// Handle escape to go back (except on menu)
if (key.escape && canGoBack) {
goBack()
return
}
if (step === "menu") {
if (key.upArrow) {
setMenuIndex((prev) => (prev > 0 ? prev - 1 : mainMenuItems.length - 1))
} else if (key.downArrow) {
setMenuIndex((prev) => (prev < mainMenuItems.length - 1 ? prev + 1 : 0))
} else if (key.return) {
handleMainMenuSelect(mainMenuItems[menuIndex].value)
}
} else if (step === "provider") {
if (key.upArrow) {
setProviderIndex((prev) => (prev > 0 ? prev - 1 : providerItems.length - 1))
} else if (key.downArrow) {
setProviderIndex((prev) => (prev < providerItems.length - 1 ? prev + 1 : 0))
} else if (key.return) {
if (providerItems[providerIndex]) {
handleProviderSelect(providerItems[providerIndex].value)
}
} else if (key.backspace || key.delete) {
setProviderSearch((prev) => prev.slice(0, -1))
} else if (input && !key.ctrl && !key.meta) {
setProviderSearch((prev) => prev + input)
}
} else if (step === "cline_model") {
const allModels = featuredModels
const maxIndex = allModels.length // includes "Browse all" option
if (key.upArrow) {
setClineModelIndex((prev) => (prev > 0 ? prev - 1 : maxIndex))
} else if (key.downArrow) {
setClineModelIndex((prev) => (prev < maxIndex ? prev + 1 : 0))
} else if (key.return) {
if (clineModelIndex === allModels.length) {
// "Browse all models" selected
setStep("modelid")
} else {
// Featured model selected
handleClineModelSelect(allModels[clineModelIndex].id)
}
}
}
// Note: modelid step input is handled by ModelPicker component
},
{ isActive: isRawModeSupported && (step === "menu" || step === "provider" || step === "cline_model" || canGoBack) },
)
return (
<Box flexDirection="column" paddingLeft={1} paddingRight={1} width="100%">
{/* Cline robot - centered */}
<StaticRobotFrame />
{/* Welcome text - centered */}
<Box justifyContent="center" marginTop={1}>
<Text bold color="white">
Welcome to Cline
</Text>
</Box>
{/* Auth box with border */}
<Box
borderColor="gray"
borderStyle="round"
flexDirection="column"
marginTop={1}
paddingBottom={1}
paddingLeft={2}
paddingRight={2}
paddingTop={1}>
{step === "menu" ? (
<Box flexDirection="column">
<Text color="gray">How would you like to get started?</Text>
<Text> </Text>
{mainMenuItems.map((item, index) => (
<Box key={item.value}>
<Text color={index === menuIndex ? COLORS.primaryBlue : undefined}>
{index === menuIndex ? " " : " "}
{item.label}
</Text>
</Box>
))}
<Text> </Text>
<Text color="gray">Use arrow keys, Enter to select</Text>
</Box>
) : (
renderAuthContent()
)}
</Box>
</Box>
)
}
+381
View File
@@ -0,0 +1,381 @@
import BedrockData from "@shared/providers/bedrock.json"
import { Box, Text, useInput } from "ink"
import React, { useCallback, useMemo, useState } from "react"
import { COLORS } from "../constants/colors"
import { useStdinContext } from "../context/StdinContext"
import { useScrollableList } from "../hooks/useScrollableList"
import { isMouseEscapeSequence } from "../utils/input"
type AuthMethod = "profile" | "credentials" | "default"
type BedrockStep = "auth_method" | "profile_name" | "access_key" | "secret_key" | "session_token" | "region" | "options"
export interface BedrockConfig {
awsAuthentication: string
awsProfile?: string
awsAccessKey?: string
awsSecretKey?: string
awsSessionToken?: string
awsRegion: string
awsUseCrossRegionInference: boolean
}
interface BedrockSetupProps {
isActive: boolean
onComplete: (config: BedrockConfig) => void
onCancel: () => void
}
const AUTH_METHODS: { label: string; value: AuthMethod; description: string }[] = [
{ label: "AWS Profile", value: "profile", description: "Use a named profile from ~/.aws/credentials" },
{ label: "AWS Credentials", value: "credentials", description: "Enter access key, secret key, and optional session token" },
{
label: "Default credential chain",
value: "default",
description: "Resolve from env vars, IAM role, or ~/.aws/credentials",
},
]
const AWS_REGIONS = BedrockData.regions
const REGION_ROWS = 8
/**
* Inline text input for credential fields
*/
const CredentialInput: React.FC<{
label: string
value: string
onChange: (value: string) => void
onSubmit: () => void
onCancel: () => void
isActive: boolean
isPassword?: boolean
placeholder?: string
hint?: string
}> = ({ label, value, onChange, onSubmit, onCancel, isActive, isPassword, placeholder, hint }) => {
const { isRawModeSupported } = useStdinContext()
useInput(
(input, key) => {
if (isMouseEscapeSequence(input)) return
if (key.escape) {
onCancel()
} else if (key.return) {
onSubmit()
} else if (key.backspace || key.delete) {
onChange(value.slice(0, -1))
} else if (input && !key.ctrl && !key.meta) {
onChange(value + input)
}
},
{ isActive: isActive && isRawModeSupported },
)
const displayValue = isPassword && value ? "•".repeat(value.length) : value
// Combine hint and placeholder into description shown above input
const description = hint || (placeholder ? `e.g. ${placeholder}` : undefined)
return (
<Box flexDirection="column">
<Text color="white">{label}</Text>
{description && <Text color="gray">{description}</Text>}
<Text> </Text>
<Box>
<Text color="white">{displayValue}</Text>
<Text inverse> </Text>
</Box>
<Text> </Text>
<Text color="gray">Enter to continue, Esc to go back</Text>
</Box>
)
}
export const BedrockSetup: React.FC<BedrockSetupProps> = ({ isActive, onComplete, onCancel }) => {
const { isRawModeSupported } = useStdinContext()
const [step, setStep] = useState<BedrockStep>("auth_method")
const [authMethodIndex, setAuthMethodIndex] = useState(0)
const [authMethod, setAuthMethod] = useState<AuthMethod>("profile")
// Credential state
const [profileName, setProfileName] = useState("")
const [accessKey, setAccessKey] = useState("")
const [secretKey, setSecretKey] = useState("")
const [sessionToken, setSessionToken] = useState("")
// Region state
const [regionSearch, setRegionSearch] = useState("")
const [regionIndex, setRegionIndex] = useState(0)
// Options state
const [crossRegion, setCrossRegion] = useState(false)
const [optionIndex, setOptionIndex] = useState(0)
// Filtered regions
const filteredRegions = useMemo(() => {
const search = regionSearch.toLowerCase()
return search ? AWS_REGIONS.filter((r) => r.includes(search)) : AWS_REGIONS
}, [regionSearch])
const {
visibleStart: regionVisibleStart,
visibleCount: regionVisibleCount,
showTopIndicator: showRegionTop,
showBottomIndicator: showRegionBottom,
} = useScrollableList(filteredRegions.length, regionIndex, REGION_ROWS)
const visibleRegions = useMemo(
() => filteredRegions.slice(regionVisibleStart, regionVisibleStart + regionVisibleCount),
[filteredRegions, regionVisibleStart, regionVisibleCount],
)
const nextStepAfterAuth = useCallback((method: AuthMethod) => {
setAuthMethod(method)
if (method === "profile") {
setStep("profile_name")
} else if (method === "credentials") {
setStep("access_key")
} else {
// default chain - skip credentials, go to region
setStep("region")
}
}, [])
const goBack = useCallback(() => {
switch (step) {
case "auth_method":
onCancel()
break
case "profile_name":
setStep("auth_method")
break
case "access_key":
setStep("auth_method")
break
case "secret_key":
setStep("access_key")
break
case "session_token":
setStep("secret_key")
break
case "region":
if (authMethod === "profile") setStep("profile_name")
else if (authMethod === "credentials") setStep("session_token")
else setStep("auth_method")
break
case "options":
setStep("region")
break
}
}, [step, authMethod, onCancel])
const finish = useCallback(() => {
const config: BedrockConfig = {
awsAuthentication: authMethod === "default" ? "credentials" : authMethod,
awsRegion: filteredRegions[regionIndex] || "us-east-1",
awsUseCrossRegionInference: crossRegion,
}
if (authMethod === "profile") {
config.awsProfile = profileName || ""
} else if (authMethod === "credentials") {
config.awsAccessKey = accessKey
config.awsSecretKey = secretKey
if (sessionToken) config.awsSessionToken = sessionToken
}
onComplete(config)
}, [authMethod, profileName, accessKey, secretKey, sessionToken, filteredRegions, regionIndex, crossRegion, onComplete])
// Handle input for auth_method, region, and options steps
useInput(
(input, key) => {
if (isMouseEscapeSequence(input)) return
if (step === "auth_method") {
if (key.escape) {
onCancel()
} else if (key.upArrow) {
setAuthMethodIndex((prev) => (prev > 0 ? prev - 1 : AUTH_METHODS.length - 1))
} else if (key.downArrow) {
setAuthMethodIndex((prev) => (prev < AUTH_METHODS.length - 1 ? prev + 1 : 0))
} else if (key.return) {
nextStepAfterAuth(AUTH_METHODS[authMethodIndex].value)
}
} else if (step === "region") {
if (key.escape) {
goBack()
} else if (key.upArrow) {
setRegionIndex((prev) => (prev > 0 ? prev - 1 : filteredRegions.length - 1))
} else if (key.downArrow) {
setRegionIndex((prev) => (prev < filteredRegions.length - 1 ? prev + 1 : 0))
} else if (key.return && filteredRegions.length > 0) {
setStep("options")
} else if (key.backspace || key.delete) {
setRegionSearch((prev) => prev.slice(0, -1))
setRegionIndex(0)
} else if (input && !key.ctrl && !key.meta) {
setRegionSearch((prev) => prev + input)
setRegionIndex(0)
}
} else if (step === "options") {
if (key.escape) {
goBack()
} else if (key.tab || key.return || input === " ") {
// Tab/Enter/Space on checkbox toggles it, on Done button finishes
if (optionIndex === 0) {
setCrossRegion((prev) => !prev)
} else {
finish()
}
} else if (key.upArrow) {
setOptionIndex((prev) => (prev > 0 ? prev - 1 : 1))
} else if (key.downArrow) {
setOptionIndex((prev) => (prev < 1 ? prev + 1 : 0))
}
}
},
{ isActive: isActive && isRawModeSupported && (step === "auth_method" || step === "region" || step === "options") },
)
if (step === "auth_method") {
return (
<Box flexDirection="column">
<Text color="white">Authentication method</Text>
<Text> </Text>
{AUTH_METHODS.map((method, i) => (
<Box flexDirection="column" key={method.value} marginBottom={i < AUTH_METHODS.length - 1 ? 1 : 0}>
<Text color={i === authMethodIndex ? COLORS.primaryBlue : undefined}>
{i === authMethodIndex ? " " : " "}
{method.label}
</Text>
<Box paddingLeft={2}>
<Text color="gray">{method.description}</Text>
</Box>
</Box>
))}
<Text> </Text>
<Text color="gray">Arrows to navigate, Enter to select, Esc to go back</Text>
</Box>
)
}
if (step === "profile_name") {
return (
<CredentialInput
hint="Leave empty to use the default profile"
isActive={isActive}
label="AWS Profile Name"
onCancel={goBack}
onChange={setProfileName}
onSubmit={() => setStep("region")}
placeholder="default"
value={profileName}
/>
)
}
if (step === "access_key") {
return (
<CredentialInput
isActive={isActive}
isPassword
label="AWS Access Key"
onCancel={goBack}
onChange={setAccessKey}
onSubmit={() => {
if (accessKey.trim()) setStep("secret_key")
}}
placeholder="Enter access key..."
value={accessKey}
/>
)
}
if (step === "secret_key") {
return (
<CredentialInput
isActive={isActive}
isPassword
label="AWS Secret Key"
onCancel={goBack}
onChange={setSecretKey}
onSubmit={() => {
if (secretKey.trim()) setStep("session_token")
}}
placeholder="Enter secret key..."
value={secretKey}
/>
)
}
if (step === "session_token") {
return (
<CredentialInput
hint="Optional - for temporary credentials"
isActive={isActive}
isPassword
label="AWS Session Token"
onCancel={goBack}
onChange={setSessionToken}
onSubmit={() => setStep("region")}
placeholder="Enter session token (optional)..."
value={sessionToken}
/>
)
}
if (step === "region") {
return (
<Box flexDirection="column">
<Text color="white">AWS Region</Text>
<Text> </Text>
<Box>
<Text color="gray">Search: </Text>
<Text color="white">{regionSearch}</Text>
<Text inverse> </Text>
</Box>
<Text> </Text>
{showRegionTop && <Text color="gray">... {regionVisibleStart} more above</Text>}
{visibleRegions.map((region, i) => {
const actualIndex = regionVisibleStart + i
return (
<Box key={region}>
<Text color={actualIndex === regionIndex ? COLORS.primaryBlue : undefined}>
{actualIndex === regionIndex ? " " : " "}
{region}
</Text>
</Box>
)
})}
{showRegionBottom && (
<Text color="gray">... {filteredRegions.length - regionVisibleStart - regionVisibleCount} more below</Text>
)}
{filteredRegions.length === 0 && <Text color="gray">No regions match "{regionSearch}"</Text>}
<Text> </Text>
<Text color="gray">Type to search, arrows to navigate, Enter to select, Esc to go back</Text>
</Box>
)
}
if (step === "options") {
return (
<Box flexDirection="column">
<Text color="white">Options</Text>
<Text> </Text>
<Text color={optionIndex === 0 ? COLORS.primaryBlue : undefined}>
{optionIndex === 0 ? " " : " "}
{crossRegion ? "[x]" : "[ ]"} Use cross-region inference
</Text>
<Text> </Text>
<Text color={optionIndex === 1 ? COLORS.primaryBlue : undefined}>
{optionIndex === 1 ? " " : " "}
Done
</Text>
<Text> </Text>
<Text color="gray">Arrows to navigate, Enter to select, Esc to go back</Text>
</Box>
)
}
return null
}
+597
View File
@@ -0,0 +1,597 @@
/**
* Claude Code style chat message component
* Renders messages with:
* - for user messages
* - ⏺ for assistant messages and tool calls
* - ⎿ for tool results (indented)
*/
import { CLINE_ACCOUNT_AUTH_ERROR_MESSAGE } from "@shared/ClineAccount"
import { COMMAND_OUTPUT_STRING } from "@shared/combineCommandSequences"
import type { ClineMessage } from "@shared/ExtensionMessage"
import { Box, Text } from "ink"
import React from "react"
import { COLORS } from "../constants/colors"
import { useTerminalSize } from "../hooks/useTerminalSize"
import { jsonParseSafe } from "../utils/parser"
import { getToolDescription, isFileEditTool, parseToolFromMessage } from "../utils/tools"
import { DiffView } from "./DiffView"
/**
* Render inline markdown: **bold**, *italic*, `code`
* Returns array of React nodes with appropriate styling
*/
function renderInlineMarkdown(text: string): React.ReactNode[] {
const nodes: React.ReactNode[] = []
// Match **bold**, *italic*, or `code` - order matters (** before *)
const regex = /(\*\*[^*]+\*\*|\*[^*]+\*|`[^`]+`)/g
let lastIndex = 0
let match
while ((match = regex.exec(text)) !== null) {
// Add text before match
if (match.index > lastIndex) {
nodes.push(text.slice(lastIndex, match.index))
}
const fullMatch = match[0]
const key = `md-${match.index}`
if (fullMatch.startsWith("**") && fullMatch.endsWith("**")) {
// Bold
nodes.push(
<Text bold key={key}>
{fullMatch.slice(2, -2)}
</Text>,
)
} else if (fullMatch.startsWith("*") && fullMatch.endsWith("*")) {
// Italic
nodes.push(
<Text italic key={key}>
{fullMatch.slice(1, -1)}
</Text>,
)
} else if (fullMatch.startsWith("`") && fullMatch.endsWith("`")) {
// Inline code
nodes.push(<Text key={key}>{fullMatch.slice(1, -1)}</Text>)
}
lastIndex = regex.lastIndex
}
// Add remaining text
if (lastIndex < text.length) {
nodes.push(text.slice(lastIndex))
}
return nodes.length > 0 ? nodes : [text]
}
/**
* Render text with inline markdown support
*/
const MarkdownText: React.FC<{ children: string; color?: string }> = ({ children, color }) => {
const nodes = renderInlineMarkdown(children)
return <Text color={color}>{nodes}</Text>
}
interface ChatMessageProps {
message: ClineMessage
isStreaming?: boolean
mode?: "act" | "plan"
}
/**
* Two-column layout for messages with a dot prefix.
* Keeps content from wrapping under the dot.
*
* For this to work properly, parent containers must have width="100%"
* so flexGrow={1} on the content box has a reference width to fill.
*/
const DotRow: React.FC<{ children: React.ReactNode; color?: string }> = ({ children, color }) => (
<Box flexDirection="row">
<Box width={2}>
<Text color={color}></Text>
</Box>
<Box flexGrow={1}>{children}</Box>
</Box>
)
/**
* Two-column layout for tool results with ⎿ prefix.
* Keeps content from wrapping under the prefix.
*/
const ResultRow: React.FC<{ children: React.ReactNode; isFirst?: boolean }> = ({ children, isFirst }) => (
<Box flexDirection="row">
<Box width={3}>
<Text color="gray">{isFirst ? "⎿ " : " "}</Text>
</Box>
<Box flexGrow={1}>{children}</Box>
</Box>
)
/**
* Get the primary argument to display for a tool (file path, command, url, etc.)
*/
function getToolMainArg(_toolName: string, args: Record<string, unknown>): string {
// File path
if (typeof args.path === "string") return args.path
if (typeof args.file_path === "string") return args.file_path
// Command - truncate long commands
if (typeof args.command === "string") {
return args.command.length > 120 ? args.command.substring(0, 117) + "..." : args.command
}
// Search regex
if (typeof args.regex === "string") return args.regex
// URL
if (typeof args.url === "string") return args.url
// Search query
if (typeof args.query === "string") return args.query
return ""
}
/**
* Render a tool call in webview style: "Cline wants to read this file:" / "Cline read this file:"
*/
const ToolCallText: React.FC<{
toolName: string
args: Record<string, unknown>
mode?: "act" | "plan"
isAsk?: boolean
}> = ({ toolName, args, mode, isAsk = false }) => {
const desc = getToolDescription(toolName)
const actionText = isAsk ? desc.ask : desc.say
const mainArg = getToolMainArg(toolName, args)
const toolColor = mode === "plan" ? "yellow" : COLORS.primaryBlue
return (
<Text>
<Text color={toolColor}>Cline {actionText}</Text>
{mainArg && (
<Text>
<Text color={toolColor}>: </Text>
<Text>{mainArg}</Text>
</Text>
)}
</Text>
)
}
/**
* Truncate text with ellipsis
*/
function truncate(text: string, maxLength: number): string {
if (text.length <= maxLength) return text
return text.substring(0, maxLength - 3) + "..."
}
/**
* Format tool result for display
*/
function formatToolResult(result: string, maxLines: number = 5): string[] {
const lines = result.split("\n")
if (lines.length <= maxLines) {
return lines
}
const displayLines = lines.slice(0, maxLines)
displayLines.push(`... ${lines.length - maxLines} more lines`)
return displayLines
}
export const ChatMessage: React.FC<ChatMessageProps> = ({ message, mode }) => {
const { type, ask, say, text } = message
const toolColor = mode === "plan" ? "yellow" : COLORS.primaryBlue
const { columns: terminalWidth } = useTerminalSize()
// User messages (task, user_feedback)
// If multi-line, extend background to full width for consistent appearance
if (say === "task" || say === "user_feedback") {
const content = "> " + (text || "")
const isMultiLine = content.includes("\n") || content.length > terminalWidth
if (isMultiLine) {
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<Box backgroundColor="blackBright" paddingX={1} width="100%">
<Text color="white">{content}</Text>
</Box>
</Box>
)
}
return (
<Box flexDirection="column" marginBottom={1}>
<Box backgroundColor="blackBright" paddingX={1}>
<Text color="white">{content}</Text>
</Box>
</Box>
)
}
// Assistant text response (hide reasoning traces - they're verbose and clutter the UI)
if (say === "reasoning") {
return null
}
if (say === "text") {
if (!text?.trim()) return null
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<DotRow>
<Text>{text}</Text>
</DotRow>
</Box>
)
}
// Tool calls (ask) and tool results (say)
const isToolAsk = type === "ask" && ask === "tool"
const isToolSay = say === "tool"
if ((isToolAsk || isToolSay) && text) {
const toolInfo = parseToolFromMessage(text)
if (toolInfo) {
const filePath = toolInfo.args.path || toolInfo.args.file_path
// File edit tools - show diff
if (isFileEditTool(toolInfo.toolName) && filePath && toolInfo.args.content) {
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<DotRow color={toolColor}>
<ToolCallText args={toolInfo.args} isAsk={isToolAsk} mode={mode} toolName={toolInfo.toolName} />
</DotRow>
<Box marginLeft={2}>
<DiffView content={toolInfo.args.content} />
</Box>
</Box>
)
}
// Show result content for completed tools, or file path for pending asks
const contentLines =
isToolSay && toolInfo.result?.trim()
? formatToolResult(toolInfo.result, 5)
: isToolAsk && filePath
? [filePath as string]
: []
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<DotRow color={toolColor}>
<ToolCallText args={toolInfo.args} isAsk={isToolAsk} mode={mode} toolName={toolInfo.toolName} />
</DotRow>
{contentLines.length > 0 && (
<Box flexDirection="column" marginLeft={2} width="100%">
{contentLines.map((line, idx) => (
<ResultRow isFirst={idx === 0} key={idx}>
<Text color="gray">{line}</Text>
</ResultRow>
))}
</Box>
)}
</Box>
)
}
// Fallback for unparseable tool messages
if (isToolSay) {
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<DotRow color={toolColor}>
<Text color={toolColor}>{truncate(text, 100)}</Text>
</DotRow>
</Box>
)
}
}
// Command execution (ask or say) - now includes combined output
if ((type === "ask" && ask === "command") || say === "command") {
if (!text) return null
// Parse command and output from combined text
const outputIndex = text.indexOf(COMMAND_OUTPUT_STRING)
const command = outputIndex === -1 ? text : text.slice(0, outputIndex).trim()
const output = outputIndex === -1 ? "" : text.slice(outputIndex + COMMAND_OUTPUT_STRING.length).trim()
const isAsk = type === "ask"
const label = isAsk ? "Cline wants to execute this command: " : "Cline executed this command: "
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<DotRow color={toolColor}>
<Text>
<Text color={toolColor}>{label}</Text>
<Text>{truncate(command, 120)}</Text>
</Text>
</DotRow>
{output && (
<Box flexDirection="column" marginLeft={2} width="100%">
{formatToolResult(output, 8).map((line, idx) => (
<ResultRow isFirst={idx === 0} key={idx}>
<Text color="gray">{line}</Text>
</ResultRow>
))}
</Box>
)}
</Box>
)
}
// Command output - should not appear after combineCommandSequences, but handle as fallback
if (say === "command_output" && text) {
const lines = formatToolResult(text, 8)
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<Box flexDirection="column" marginLeft={2} width="100%">
{lines.map((line, idx) => (
<ResultRow isFirst={idx === 0} key={idx}>
<Text color="gray">{line}</Text>
</ResultRow>
))}
</Box>
</Box>
)
}
// Error messages
if (say === "error" || (type === "ask" && ask === "api_req_failed")) {
// Try to parse error message if it's JSON
let errorMessage = text || "Unknown error"
if (text) {
const parsed = jsonParseSafe(text, { message: undefined as string | undefined })
if (parsed.message) {
errorMessage = parsed.message
}
}
// Check for Cline auth error to show sign-in instructions
const isClineAuthError = errorMessage.includes(CLINE_ACCOUNT_AUTH_ERROR_MESSAGE)
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<DotRow color="red">
<Text color="red" wrap="wrap">
<Text bold>Error</Text>: {errorMessage}
</Text>
</DotRow>
{isClineAuthError && (
<Box marginLeft={2} marginTop={1}>
<Text color="gray">
Run <Text color="cyan">/settings</Text> and go to Account to sign in.
</Text>
</Box>
)}
</Box>
)
}
// Error retry messages
if (say === "error_retry" && text) {
const retryInfo = jsonParseSafe(text, {
failed: false,
attempt: 0,
maxAttempts: 3,
errorMessage: undefined as string | undefined,
})
// Parse nested errorMessage if it's a JSON string
let errorMsg = "Request failed"
if (retryInfo.errorMessage) {
try {
const errorObj = jsonParseSafe(retryInfo.errorMessage, { message: undefined as string | undefined })
errorMsg = errorObj.message || retryInfo.errorMessage
} catch {
errorMsg = retryInfo.errorMessage
}
}
if (retryInfo.failed) {
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<DotRow color="red">
<Text bold color="red">
Failed
</Text>
<Text color="red"> after {retryInfo.maxAttempts} retries</Text>
</DotRow>
<Box marginLeft={2}>
<Text color="red" dimColor>
{errorMsg}
</Text>
</Box>
</Box>
)
}
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<DotRow color="yellow">
<Text bold color="yellow">
Retrying
</Text>
<Text color="yellow">
... (attempt {retryInfo.attempt}/{retryInfo.maxAttempts})
</Text>
</DotRow>
<Box marginLeft={2}>
<Text color="yellow" dimColor>
{errorMsg}
</Text>
</Box>
</Box>
)
}
// Completion result
// Only render ask: "completion_result" if it has text - the empty ask is just for UI confirmation
if (say === "completion_result" || (type === "ask" && ask === "completion_result" && text)) {
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<DotRow color="green">
<Text color="green">Task completed</Text>
</DotRow>
{text && (
<Box marginLeft={2}>
<MarkdownText color="greenBright">{text}</MarkdownText>
</Box>
)}
</Box>
)
}
// API request info (show cost/tokens inline)
if (say === "api_req_started" && text) {
// Skip showing these - they're summarized in the status bar
return null
}
// Browser actions
if (say === "browser_action" || say === "browser_action_launch") {
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<DotRow color={toolColor}>
<Text>
<Text color={toolColor}>Cline used the browser</Text>
{text && (
<Text>
<Text color={toolColor}>: </Text>
<Text>{truncate(text, 50)}</Text>
</Text>
)}
</Text>
</DotRow>
</Box>
)
}
// MCP server
if (say === "mcp_server_request_started") {
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<DotRow color={toolColor}>
<Text>
<Text color={toolColor}>Cline is using an MCP tool</Text>
{text && (
<Text>
<Text color={toolColor}>: </Text>
<Text>{truncate(text, 50)}</Text>
</Text>
)}
</Text>
</DotRow>
</Box>
)
}
// Info messages
if (say === "info") {
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<DotRow color="gray">
<Text color="gray">{text}</Text>
</DotRow>
</Box>
)
}
// Followup questions from assistant
if (type === "ask" && ask === "followup" && text) {
const parsed = jsonParseSafe(text, {
question: undefined as string | undefined,
options: undefined as string[] | undefined,
selected: undefined as string | undefined,
})
if (parsed.question) {
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<DotRow>
<MarkdownText>{parsed.question}</MarkdownText>
</DotRow>
{parsed.options && parsed.options.length > 0 && (
<Box flexDirection="column" paddingLeft={2}>
{parsed.options.map((opt, idx) => {
const isSelected = parsed.selected === opt
return (
<Text color={isSelected ? "green" : toolColor} key={opt}>
{isSelected ? "✓" : `${idx + 1}.`} {opt}
</Text>
)
})}
</Box>
)}
</Box>
)
}
}
// Plan mode response
if (type === "ask" && ask === "plan_mode_respond" && text) {
const parsed = jsonParseSafe(text, { response: undefined as string | undefined })
if (parsed.response) {
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<DotRow color="yellow">
<MarkdownText color="yellow">{parsed.response}</MarkdownText>
</DotRow>
</Box>
)
}
}
// New task request from assistant
if (type === "ask" && ask === "new_task" && text) {
return (
<Box flexDirection="column" marginBottom={1} width="100%">
<DotRow color={COLORS.primaryBlue}>
<Text bold color={COLORS.primaryBlue}>
Cline wants to start a new task:
</Text>
</DotRow>
<Box flexDirection="column" paddingLeft={2}>
<Text color="gray">{text}</Text>
</Box>
</Box>
)
}
// Skip other message types
return null
}
/**
* Render a list of messages in Claude Code style
*/
interface ChatMessageListProps {
messages: ClineMessage[]
maxMessages?: number
}
export const ChatMessageList: React.FC<ChatMessageListProps> = ({ messages, maxMessages }) => {
// Filter out messages we don't want to display
const displayMessages = messages.filter((m) => {
// Skip api_req_finished, they're just markers
if (m.say === "api_req_finished") return false
// Skip empty text messages
if (m.say === "text" && !m.text?.trim()) return false
// Skip checkpoint messages
if (m.say === "checkpoint_created") return false
return true
})
// Optionally limit number of messages shown
const messagesToShow = maxMessages ? displayMessages.slice(-maxMessages) : displayMessages
// Check if last message is streaming
const lastMessage = messagesToShow[messagesToShow.length - 1]
const isLastStreaming = lastMessage?.partial === true
return (
<Box flexDirection="column">
{messagesToShow.map((msg, idx) => (
<ChatMessage isStreaming={idx === messagesToShow.length - 1 && isLastStreaming} key={msg.ts} message={msg} />
))}
</Box>
)
}
+316
View File
@@ -0,0 +1,316 @@
/**
* Tests for ChatView component exit and cleanup behavior
*
* These tests verify that when the user exits (via Ctrl+C or other means),
* the input field is properly hidden before the app terminates.
*/
import { Text } from "ink"
import { render } from "ink-testing-library"
import React from "react"
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest"
import { ChatView } from "./ChatView"
// Helper to wait for async state updates
// Using 60ms since handleExit has a 50ms setTimeout
const delay = (ms: number = 60) => new Promise((resolve) => setTimeout(resolve, ms))
// Type for our exit mock function
type ExitMockFn = ReturnType<typeof vi.fn> & (() => void)
// Track shutdown event state
const shutdownMockState = {
listeners: [] as Array<() => void>,
fire: () => {
shutdownMockState.listeners.forEach((listener) => listener())
},
reset: () => {
shutdownMockState.listeners = []
},
}
// Mock vscode-shim shutdownEvent
vi.mock("../vscode-shim", () => ({
shutdownEvent: {
event: (listener: () => void) => {
shutdownMockState.listeners.push(listener)
return {
dispose: () => {
const idx = shutdownMockState.listeners.indexOf(listener)
if (idx >= 0) shutdownMockState.listeners.splice(idx, 1)
},
}
},
fire: () => shutdownMockState.fire(),
},
}))
// Mock TaskContext
vi.mock("../context/TaskContext", () => ({
useTaskState: vi.fn(() => ({
clineMessages: [],
mode: "act",
})),
useTaskContext: vi.fn(() => ({
controller: null,
})),
}))
// Mock useIsSpinnerActive hook
vi.mock("../hooks/useStateSubscriber", () => ({
useIsSpinnerActive: vi.fn(() => ({
isActive: false,
startTime: null,
})),
}))
// Mock StateManager
vi.mock("@/core/storage/StateManager", () => ({
StateManager: {
get: vi.fn(() => ({
getGlobalSettingsKey: vi.fn((key: string) => {
if (key === "mode") return "act"
if (key === "yoloModeToggled") return false
if (key === "actModeApiModelId") return "claude-sonnet-4-20250514"
return null
}),
setGlobalState: vi.fn(),
})),
},
}))
// Mock child components that aren't under test
vi.mock("./ActionButtons", () => ({
ActionButtons: () => React.createElement(Text, null, "ActionButtons"),
getButtonConfig: vi.fn(() => ({ enableButtons: false })),
}))
vi.mock("./AsciiMotionCli", () => ({
AsciiMotionCli: () => React.createElement(Text, null, "AsciiMotion"),
StaticRobotFrame: () => React.createElement(Text, null, "StaticRobot"),
}))
vi.mock("./ChatMessage", () => ({
ChatMessage: ({ message }: { message?: { ts?: number } }) => React.createElement(Text, null, `Message: ${message?.ts}`),
}))
vi.mock("./FileMentionMenu", () => ({
FileMentionMenu: () => React.createElement(Text, null, "FileMentionMenu"),
}))
vi.mock("./HighlightedInput", () => ({
HighlightedInput: ({ text }: { text?: string }) => React.createElement(Text, null, `Input: ${text}`),
}))
vi.mock("./HistoryPanelContent", () => ({
HistoryPanelContent: () => React.createElement(Text, null, "HistoryPanel"),
}))
vi.mock("./SettingsPanelContent", () => ({
SettingsPanelContent: () => React.createElement(Text, null, "SettingsPanel"),
}))
vi.mock("./SlashCommandMenu", () => ({
SlashCommandMenu: () => React.createElement(Text, null, "SlashMenu"),
}))
vi.mock("./ThinkingIndicator", () => ({
ThinkingIndicator: () => React.createElement(Text, null, "ThinkingIndicator"),
}))
// Mock utility functions
vi.mock("../utils/file-search", () => ({
checkAndWarnRipgrepMissing: vi.fn(() => false),
extractMentionQuery: vi.fn(() => ({ inMentionMode: false, query: "", atIndex: -1 })),
getRipgrepInstallInstructions: vi.fn(() => "brew install ripgrep"),
insertMention: vi.fn((text: string) => text),
searchWorkspaceFiles: vi.fn(async () => []),
}))
vi.mock("../utils/slash-commands", () => ({
extractSlashQuery: vi.fn(() => ({ inSlashMode: false, query: "", slashIndex: -1 })),
filterCommands: vi.fn(() => []),
insertSlashCommand: vi.fn((text: string) => text),
sortCommandsWorkflowsFirst: vi.fn((cmds: unknown[]) => cmds),
}))
vi.mock("../utils/input", () => ({
isMouseEscapeSequence: vi.fn(() => false),
}))
vi.mock("../utils/parser", () => ({
jsonParseSafe: vi.fn((_text: string, defaultValue: unknown) => defaultValue),
parseImagesFromInput: vi.fn((text: string) => ({ prompt: text, imagePaths: [] })),
}))
vi.mock("../utils/tools", () => ({
isFileEditTool: vi.fn(() => false),
parseToolFromMessage: vi.fn(() => null),
}))
vi.mock("../utils/display", () => ({
setTerminalTitle: vi.fn(),
}))
vi.mock("../utils/cursor", () => ({
moveCursorUp: vi.fn((_text: string, pos: number) => pos),
moveCursorDown: vi.fn((_text: string, pos: number) => pos),
}))
vi.mock("@/core/controller/slash/getAvailableSlashCommands", () => ({
getAvailableSlashCommands: vi.fn(async () => ({ commands: [] })),
}))
vi.mock("@/core/controller/task/showTaskWithId", () => ({
showTaskWithId: vi.fn(async () => {}),
}))
vi.mock("@shared/combineCommandSequences", () => ({
combineCommandSequences: vi.fn((messages: unknown[]) => messages),
}))
vi.mock("@shared/getApiMetrics", () => ({
getApiMetrics: vi.fn(() => ({
totalTokensIn: 0,
totalTokensOut: 0,
totalCost: 0,
})),
}))
vi.mock("child_process", () => ({
execSync: vi.fn(() => "main"),
}))
// Helper to create a typed mock for onExit
const createExitMock = (): ExitMockFn => vi.fn() as ExitMockFn
describe("ChatView Exit and Cleanup", () => {
let mockOnExit: ExitMockFn
beforeEach(() => {
vi.clearAllMocks()
shutdownMockState.reset()
mockOnExit = createExitMock()
})
afterEach(() => {
vi.restoreAllMocks()
})
describe("Initial render state", () => {
it("should render with input field, footer, and mode toggle visible", () => {
const { lastFrame } = render(<ChatView onExit={mockOnExit} />)
const frame = lastFrame()
// Input field visible
expect(frame).toContain("Input:")
// Footer with help text
expect(frame).toContain("@ for files")
expect(frame).toContain("/ for commands")
// Mode toggle
expect(frame).toContain("Plan")
expect(frame).toContain("Act")
})
})
describe("Ctrl+C exit handling", () => {
it("should hide input but keep footer, then call onExit", async () => {
const { lastFrame, stdin } = render(<ChatView onExit={mockOnExit} />)
// Verify UI visible before Ctrl+C
expect(lastFrame()).toContain("Input:")
expect(lastFrame()).toContain("@ for files")
// Simulate Ctrl+C
stdin.write("\x03")
// onExit should not be called immediately
expect(mockOnExit).not.toHaveBeenCalled()
// Wait for state update and callback
await delay()
// Input should be hidden, but footer should remain
const frameAfter = lastFrame()
expect(frameAfter).not.toContain("Input:")
expect(frameAfter).toContain("@ for files")
// onExit should have been called
expect(mockOnExit).toHaveBeenCalledTimes(1)
})
})
describe("Shutdown event handling", () => {
it("should subscribe on mount and unsubscribe on unmount", () => {
const { unmount } = render(<ChatView onExit={mockOnExit} />)
expect(shutdownMockState.listeners.length).toBe(1)
unmount()
expect(shutdownMockState.listeners.length).toBe(0)
})
it("should hide UI when shutdown event fires", async () => {
const { lastFrame } = render(<ChatView onExit={mockOnExit} />)
expect(lastFrame()).toContain("Input:")
shutdownMockState.fire()
await delay()
expect(lastFrame()).not.toContain("Input:")
})
})
describe("Edge cases", () => {
it("should handle exit when onExit prop is undefined", async () => {
const { lastFrame, stdin } = render(<ChatView />)
stdin.write("\x03")
await delay()
// Should not throw, UI should still hide
expect(lastFrame()).not.toContain("Input:")
})
it("should handle multiple Ctrl+C presses gracefully", async () => {
const { stdin } = render(<ChatView onExit={mockOnExit} />)
stdin.write("\x03")
stdin.write("\x03")
stdin.write("\x03")
await delay()
expect(mockOnExit).toHaveBeenCalled()
})
})
})
describe("ChatView UI State During Exit", () => {
beforeEach(() => {
vi.clearAllMocks()
shutdownMockState.reset()
})
it("should preserve static content and footer, only hide input during exit", async () => {
const onExit = createExitMock()
const { lastFrame, stdin } = render(<ChatView onExit={onExit} />)
// Footer contains auto-approve toggle
expect(lastFrame()).toContain("Auto-approve")
expect(lastFrame()).toContain("What can I do for you?")
expect(lastFrame()).toContain("Input:")
stdin.write("\x03")
await delay()
const frameAfter = lastFrame()
// Static content should still be present
expect(frameAfter).toContain("What can I do for you?")
// Footer should still be present (only input is hidden)
expect(frameAfter).toContain("Auto-approve")
// Input should be hidden
expect(frameAfter).not.toContain("Input:")
})
})
File diff suppressed because it is too large Load Diff
+38
View File
@@ -0,0 +1,38 @@
/**
* Reusable Checkbox component for settings panels
*/
import { Box, Text } from "ink"
import React from "react"
import { COLORS } from "../constants/colors"
interface CheckboxProps {
/** Label displayed next to the checkbox */
label: string
/** Current checked state */
checked: boolean
/** Whether this checkbox is currently selected/focused */
isSelected?: boolean
/** Optional description shown below the label */
description?: string
}
export const Checkbox: React.FC<CheckboxProps> = ({ label, checked, isSelected = false, description }) => {
return (
<Box flexDirection="column">
<Text>
<Text bold color={isSelected ? COLORS.primaryBlue : undefined}>
{isSelected ? "" : " "}{" "}
</Text>
<Text color={isSelected || checked ? COLORS.primaryBlue : "gray"}>{checked ? "[✓]" : "[ ]"}</Text>
<Text color={isSelected ? COLORS.primaryBlue : "white"}> {label}</Text>
{isSelected && <Text color="gray"> (Tab to toggle)</Text>}
</Text>
{description && (
<Box marginLeft={6}>
<Text color="gray">{description}</Text>
</Box>
)}
</Box>
)
}
+203
View File
@@ -0,0 +1,203 @@
/**
* Checkpoint menu component
* Displays available checkpoints and allows user to select one to restore
*/
import type { ClineMessage } from "@shared/ExtensionMessage"
import { Box, Text, useInput } from "ink"
import React, { useState } from "react"
import { useStdinContext } from "../context/StdinContext"
export type RestoreType = "task" | "workspace" | "taskAndWorkspace"
interface CheckpointOption {
ts: number
hash: string
date: Date
label: string
}
interface CheckpointMenuProps {
messages: ClineMessage[]
onSelect: (messageTs: number, restoreType: RestoreType) => void
onCancel: () => void
}
/**
* Extract checkpoint options from messages
*/
function getCheckpointOptions(messages: ClineMessage[]): CheckpointOption[] {
const options: CheckpointOption[] = []
for (const msg of messages) {
if (msg.lastCheckpointHash) {
options.push({
ts: msg.ts,
hash: msg.lastCheckpointHash,
date: new Date(msg.ts),
label: getCheckpointLabel(msg),
})
}
}
// Sort by timestamp descending (newest first)
return options.sort((a, b) => b.ts - a.ts)
}
/**
* Get a human-readable label for a checkpoint
*/
function getCheckpointLabel(msg: ClineMessage): string {
if (msg.say === "completion_result") {
return "Task completion"
}
if (msg.say === "checkpoint_created") {
return "Checkpoint"
}
if (msg.say === "api_req_started") {
return "API request"
}
return msg.say || msg.ask || "Message"
}
const RESTORE_TYPE_OPTIONS: { type: RestoreType; label: string; description: string }[] = [
{
type: "taskAndWorkspace",
label: "Task + Workspace",
description: "Restore messages and files",
},
{
type: "task",
label: "Task Only",
description: "Delete messages after this point",
},
{
type: "workspace",
label: "Workspace Only",
description: "Restore files only",
},
]
export const CheckpointMenu: React.FC<CheckpointMenuProps> = ({ messages, onSelect, onCancel }) => {
const { isRawModeSupported } = useStdinContext()
const checkpoints = getCheckpointOptions(messages)
const [selectedCheckpoint, setSelectedCheckpoint] = useState(0)
const [selectedRestoreType, setSelectedRestoreType] = useState(0)
const [stage, setStage] = useState<"checkpoint" | "restoreType">("checkpoint")
useInput(
(input, key) => {
if (key.escape) {
if (stage === "restoreType") {
setStage("checkpoint")
} else {
onCancel()
}
return
}
if (stage === "checkpoint") {
if (key.upArrow) {
setSelectedCheckpoint((i) => Math.max(0, i - 1))
} else if (key.downArrow) {
setSelectedCheckpoint((i) => Math.min(checkpoints.length - 1, i + 1))
} else if (key.return && checkpoints.length > 0) {
setStage("restoreType")
}
} else if (stage === "restoreType") {
if (key.upArrow) {
setSelectedRestoreType((i) => Math.max(0, i - 1))
} else if (key.downArrow) {
setSelectedRestoreType((i) => Math.min(RESTORE_TYPE_OPTIONS.length - 1, i + 1))
} else if (key.return) {
const checkpoint = checkpoints[selectedCheckpoint]
const restoreType = RESTORE_TYPE_OPTIONS[selectedRestoreType]
if (checkpoint && restoreType) {
onSelect(checkpoint.ts, restoreType.type)
}
}
}
// Quick number selection for checkpoints
if (stage === "checkpoint") {
const num = parseInt(input, 10)
if (!Number.isNaN(num) && num >= 1 && num <= checkpoints.length) {
setSelectedCheckpoint(num - 1)
setStage("restoreType")
}
}
},
{ isActive: isRawModeSupported },
)
if (checkpoints.length === 0) {
return (
<Box borderColor="yellow" borderStyle="round" flexDirection="column" marginTop={1} paddingLeft={1} paddingRight={1}>
<Text color="yellow">No checkpoints available</Text>
<Text color="gray">Checkpoints are created at task completion points</Text>
<Text color="gray">Press Escape to close</Text>
</Box>
)
}
if (stage === "checkpoint") {
return (
<Box borderColor="cyan" borderStyle="round" flexDirection="column" marginTop={1} paddingLeft={1} paddingRight={1}>
<Text bold color="cyan">
Restore Checkpoint
</Text>
<Text color="gray">Select a checkpoint to restore (/ or number, Enter to select, Escape to cancel)</Text>
<Box flexDirection="column" marginTop={1}>
{checkpoints.map((cp, idx) => {
const isSelected = idx === selectedCheckpoint
const timeStr = cp.date.toLocaleTimeString()
const dateStr = cp.date.toLocaleDateString()
return (
<Box key={cp.ts}>
<Text color={isSelected ? "green" : "gray"}>{isSelected ? "> " : " "}</Text>
<Text color={isSelected ? "white" : "gray"}>{idx + 1}. </Text>
<Text color={isSelected ? "cyan" : undefined}>{cp.label}</Text>
<Text color="gray">
{" "}
- {dateStr} {timeStr}
</Text>
</Box>
)
})}
</Box>
</Box>
)
}
// Stage: restoreType
const selectedCp = checkpoints[selectedCheckpoint]
return (
<Box borderColor="cyan" borderStyle="round" flexDirection="column" marginTop={1} paddingLeft={1} paddingRight={1}>
<Text bold color="cyan">
Restore Type
</Text>
<Text color="gray">
Restoring to: {selectedCp?.label} ({selectedCp?.date.toLocaleString()})
</Text>
<Box flexDirection="column" marginTop={1}>
{RESTORE_TYPE_OPTIONS.map((opt, idx) => {
const isSelected = idx === selectedRestoreType
return (
<Box flexDirection="column" key={opt.type} marginBottom={idx < RESTORE_TYPE_OPTIONS.length - 1 ? 1 : 0}>
<Box>
<Text color={isSelected ? "green" : "gray"}>{isSelected ? "> " : " "}</Text>
<Text bold={isSelected} color={isSelected ? "white" : undefined}>
{opt.label}
</Text>
</Box>
<Box marginLeft={4}>
<Text color="gray">{opt.description}</Text>
</Box>
</Box>
)
})}
</Box>
<Text color="gray">(/ to select, Enter to confirm, Escape to go back)</Text>
</Box>
)
}
+199
View File
@@ -0,0 +1,199 @@
import { Text } from "ink"
import { render } from "ink-testing-library"
import React from "react"
import { beforeEach, describe, expect, it, vi } from "vitest"
// Create stable mock references using vi.hoisted - must be before any imports that use these modules
const { mockIsSettingsKey } = vi.hoisted(() => ({
mockIsSettingsKey: vi.fn((key: string) => key.startsWith("act") || key.startsWith("plan") || key === "mode"),
}))
vi.mock("./TaskView", () => ({
TaskView: ({ taskId, verbose }: any) =>
React.createElement(Text, null, `TaskView: ${taskId || "no-id"} verbose=${String(verbose)}`),
}))
// Mock the state-keys module - must be hoisted before ConfigView import
vi.mock("@shared/storage/state-keys", () => ({
isSettingsKey: mockIsSettingsKey,
SETTINGS_DEFAULTS: {
mode: "act",
actModeApiProvider: "anthropic",
},
GlobalStateAndSettings: {},
GlobalStateAndSettingsKey: {},
LocalState: {},
LocalStateKey: {},
}))
// Import ConfigView after mocks are set up
import { ConfigView } from "./ConfigView"
describe("ConfigView", () => {
const defaultProps = {
dataDir: "/home/user/.cline",
globalState: {},
workspaceState: {},
}
beforeEach(() => {
vi.clearAllMocks()
})
describe("rendering", () => {
it("should render the config header", () => {
const { lastFrame } = render(<ConfigView {...defaultProps} />)
expect(lastFrame()).toContain("Configuration")
})
it("should display the data directory", () => {
const { lastFrame } = render(<ConfigView {...defaultProps} dataDir="/custom/path" />)
expect(lastFrame()).toContain("/custom/path")
})
it("should display global state entries", () => {
const { lastFrame } = render(
<ConfigView
{...defaultProps}
globalState={{
mode: "act",
actModeApiProvider: "anthropic",
}}
/>,
)
expect(lastFrame()).toContain("mode")
expect(lastFrame()).toContain("act")
})
it("should display workspace state entries", () => {
const { lastFrame } = render(
<ConfigView
{...defaultProps}
workspaceState={{
customSetting: "value",
}}
/>,
)
expect(lastFrame()).toContain("customSetting")
expect(lastFrame()).toContain("value")
})
it("should show section headers", () => {
const { lastFrame } = render(
<ConfigView {...defaultProps} globalState={{ mode: "act" }} workspaceState={{ localKey: "localValue" }} />,
)
expect(lastFrame()).toContain("Global Settings")
})
})
describe("value formatting", () => {
it("should format boolean values", () => {
const { lastFrame } = render(<ConfigView {...defaultProps} globalState={{ actModeSomeBool: true }} />)
expect(lastFrame()).toContain("true")
})
it("should format number values", () => {
const { lastFrame } = render(<ConfigView {...defaultProps} globalState={{ actModeNumber: 42 }} />)
expect(lastFrame()).toContain("42")
})
it("should truncate long string values", () => {
const longString = "x".repeat(100)
const { lastFrame } = render(<ConfigView {...defaultProps} globalState={{ actModeLongValue: longString }} />)
expect(lastFrame()).toContain("...")
})
it("should format object values as JSON", () => {
const { lastFrame } = render(<ConfigView {...defaultProps} globalState={{ actModeObj: { nested: "value" } }} />)
expect(lastFrame()).toContain("nested")
})
})
describe("filtering", () => {
it("should exclude taskHistory key", () => {
const { lastFrame } = render(<ConfigView {...defaultProps} globalState={{ taskHistory: [1, 2, 3], mode: "act" }} />)
expect(lastFrame()).not.toContain("taskHistory")
})
it("should exclude empty objects", () => {
const { lastFrame } = render(<ConfigView {...defaultProps} globalState={{ emptyObj: {}, mode: "act" }} />)
expect(lastFrame()).not.toContain("emptyObj")
})
it("should exclude empty arrays", () => {
const { lastFrame } = render(<ConfigView {...defaultProps} globalState={{ emptyArr: [], mode: "act" }} />)
expect(lastFrame()).not.toContain("emptyArr")
})
it("should exclude null/undefined values", () => {
const { lastFrame } = render(
<ConfigView {...defaultProps} globalState={{ nullVal: null, undefinedVal: undefined, mode: "act" }} />,
)
expect(lastFrame()).not.toContain("nullVal")
expect(lastFrame()).not.toContain("undefinedVal")
})
it("should exclude keys ending with Toggles", () => {
const { lastFrame } = render(<ConfigView {...defaultProps} globalState={{ someToggles: { a: true }, mode: "act" }} />)
expect(lastFrame()).not.toContain("someToggles")
})
it("should exclude keys starting with apiConfig_", () => {
const { lastFrame } = render(<ConfigView {...defaultProps} globalState={{ apiConfig_test: "value", mode: "act" }} />)
expect(lastFrame()).not.toContain("apiConfig_test")
})
})
describe("keyboard navigation", () => {
it("should show navigation help text", () => {
const { lastFrame } = render(<ConfigView {...defaultProps} globalState={{ mode: "act" }} />)
expect(lastFrame()).toContain("Navigate")
expect(lastFrame()).toContain("Edit")
})
it("should highlight first item by default", () => {
const { lastFrame } = render(
<ConfigView {...defaultProps} globalState={{ mode: "act", actModeApiProvider: "anthropic" }} />,
)
// The selected indicator
expect(lastFrame()).toContain("")
})
it("should navigate down with arrow key", () => {
const { lastFrame, stdin } = render(
<ConfigView {...defaultProps} globalState={{ actModeFirst: "a", actModeSecond: "b" }} />,
)
// Press down arrow
stdin.write("\x1B[B")
const frame = lastFrame()
expect(frame).toContain("")
})
it("should navigate up with arrow key", () => {
const { lastFrame, stdin } = render(
<ConfigView {...defaultProps} globalState={{ actModeFirst: "a", actModeSecond: "b" }} />,
)
// Press down then up
stdin.write("\x1B[B")
stdin.write("\x1B[A")
expect(lastFrame()).toContain("")
})
})
describe("scrolling", () => {
it("should show scroll indicators when list is long", () => {
const manyEntries: Record<string, string> = {}
for (let i = 0; i < 20; i++) {
manyEntries[`actModeKey${i}`] = `value${i}`
}
const { lastFrame } = render(<ConfigView {...defaultProps} globalState={manyEntries} />)
expect(lastFrame()).toContain("Showing")
})
})
})
+551
View File
@@ -0,0 +1,551 @@
/**
* Interactive config view component for displaying and editing configuration values
* Supports tabs for Settings, Rules, Workflows, Hooks, and Skills
*/
import {
GlobalStateAndSettings,
GlobalStateAndSettingsKey,
LocalState,
LocalStateKey,
SETTINGS_DEFAULTS,
} from "@shared/storage/state-keys"
import { Box, Text, useApp, useInput } from "ink"
import React, { useMemo, useState } from "react"
import { useStdinContext } from "../context/StdinContext"
import {
BooleanSelect,
buildConfigEntries,
buildToggleEntries,
ConfigRow,
HookInfo,
HookRow,
MAX_VISIBLE,
parseValue,
SEPARATOR,
SectionHeader,
SkillInfo,
SkillRow,
TABS,
TabBar,
TabView,
TextInput,
ToggleEntry,
ToggleRow,
WorkspaceHooks,
} from "./ConfigViewComponents"
// ============================================================================
// Types
// ============================================================================
interface ConfigViewProps {
dataDir: string
globalState: Record<string, unknown>
workspaceState: Record<string, unknown>
onUpdateGlobal?: (key: GlobalStateAndSettingsKey, value: GlobalStateAndSettings[GlobalStateAndSettingsKey]) => void
onUpdateWorkspace?: (key: LocalStateKey, value: LocalState[LocalStateKey]) => void
// Rules toggles
globalClineRulesToggles?: Record<string, boolean>
localClineRulesToggles?: Record<string, boolean>
localCursorRulesToggles?: Record<string, boolean>
localWindsurfRulesToggles?: Record<string, boolean>
localAgentsRulesToggles?: Record<string, boolean>
onToggleRule?: (isGlobal: boolean, rulePath: string, enabled: boolean, ruleType: string) => void
// Workflow toggles
globalWorkflowToggles?: Record<string, boolean>
localWorkflowToggles?: Record<string, boolean>
onToggleWorkflow?: (isGlobal: boolean, workflowPath: string, enabled: boolean) => void
// Hooks
hooksEnabled?: boolean
globalHooks?: HookInfo[]
workspaceHooks?: WorkspaceHooks[]
onToggleHook?: (isGlobal: boolean, hookName: string, enabled: boolean, workspaceName?: string) => void
// Skills
skillsEnabled?: boolean
globalSkills?: SkillInfo[]
localSkills?: SkillInfo[]
onToggleSkill?: (isGlobal: boolean, skillPath: string, enabled: boolean) => void
// Open folder callback
onOpenFolder?: (folderType: "rules" | "workflows" | "hooks" | "skills", isGlobal: boolean) => void
}
// ============================================================================
// Main Component
// ============================================================================
export const ConfigView: React.FC<ConfigViewProps> = ({
dataDir,
globalState,
workspaceState,
onUpdateGlobal,
onUpdateWorkspace,
globalClineRulesToggles,
localClineRulesToggles,
localCursorRulesToggles,
localWindsurfRulesToggles,
localAgentsRulesToggles,
onToggleRule,
globalWorkflowToggles,
localWorkflowToggles,
onToggleWorkflow,
hooksEnabled,
globalHooks = [],
workspaceHooks = [],
onToggleHook,
skillsEnabled,
globalSkills = [],
localSkills = [],
onToggleSkill,
onOpenFolder,
}) => {
const { exit } = useApp()
const { isRawModeSupported } = useStdinContext()
const [currentTab, setCurrentTab] = useState<TabView>("settings")
const [isEditing, setIsEditing] = useState(false)
const [selectedIndex, setSelectedIndex] = useState(0)
const [editValue, setEditValue] = useState("")
// Build entries for settings tab
const configEntries = useMemo(
() => [...buildConfigEntries(globalState, "global"), ...buildConfigEntries(workspaceState, "workspace")],
[globalState, workspaceState],
)
// Build entries for rules tab
const ruleEntries = useMemo(() => {
const entries: ToggleEntry[] = []
entries.push(...buildToggleEntries(globalClineRulesToggles, "global", "cline"))
entries.push(...buildToggleEntries(localClineRulesToggles, "workspace", "cline"))
entries.push(...buildToggleEntries(localCursorRulesToggles, "workspace", "cursor"))
entries.push(...buildToggleEntries(localWindsurfRulesToggles, "workspace", "windsurf"))
entries.push(...buildToggleEntries(localAgentsRulesToggles, "workspace", "agents"))
return entries
}, [
globalClineRulesToggles,
localClineRulesToggles,
localCursorRulesToggles,
localWindsurfRulesToggles,
localAgentsRulesToggles,
])
// Build entries for workflows tab
const workflowEntries = useMemo(() => {
const entries: ToggleEntry[] = []
entries.push(...buildToggleEntries(globalWorkflowToggles, "global"))
entries.push(...buildToggleEntries(localWorkflowToggles, "workspace"))
return entries
}, [globalWorkflowToggles, localWorkflowToggles])
// Build flat list of hooks
const hookEntries = useMemo(() => {
const entries: { hook: HookInfo; isGlobal: boolean; workspaceName?: string }[] = []
globalHooks.forEach((hook) => entries.push({ hook, isGlobal: true }))
workspaceHooks.forEach((ws) => {
ws.hooks.forEach((hook) => entries.push({ hook, isGlobal: false, workspaceName: ws.workspaceName }))
})
return entries.sort((a, b) => a.hook.name.localeCompare(b.hook.name))
}, [globalHooks, workspaceHooks])
// Build flat list of skills
const skillEntries = useMemo(() => {
const entries: { skill: SkillInfo; isGlobal: boolean }[] = []
globalSkills.forEach((skill) => entries.push({ skill, isGlobal: true }))
localSkills.forEach((skill) => entries.push({ skill, isGlobal: false }))
return entries.sort((a, b) => a.skill.name.localeCompare(b.skill.name))
}, [globalSkills, localSkills])
// Get current list length based on tab
const currentListLength = useMemo(() => {
switch (currentTab) {
case "settings":
return configEntries.length
case "rules":
return ruleEntries.length
case "workflows":
return workflowEntries.length
case "hooks":
return hookEntries.length
case "skills":
return skillEntries.length
default:
return 0
}
}, [currentTab, configEntries.length, ruleEntries.length, workflowEntries.length, hookEntries.length, skillEntries.length])
// Get available tabs
const availableTabs = useMemo(() => {
return TABS.filter((tab) => {
if (tab.requiresFlag === "hooks") {
return hooksEnabled
}
if (tab.requiresFlag === "skills") {
return skillsEnabled
}
return true
})
}, [hooksEnabled, skillsEnabled])
// Reset selection when changing tabs
const handleTabChange = (newTab: TabView) => {
setCurrentTab(newTab)
setSelectedIndex(0)
setIsEditing(false)
}
// Settings tab handlers
const selectedConfigEntry = configEntries[selectedIndex]
const handleSettingsSave = (value: string | boolean) => {
if (!selectedConfigEntry) {
return
}
const parsed = typeof value === "boolean" ? value : parseValue(value, selectedConfigEntry.type)
if (selectedConfigEntry.source === "global" && onUpdateGlobal) {
onUpdateGlobal(selectedConfigEntry.key as GlobalStateAndSettingsKey, parsed as never)
} else if (selectedConfigEntry.source === "workspace" && onUpdateWorkspace) {
onUpdateWorkspace(selectedConfigEntry.key as LocalStateKey, parsed as never)
}
setIsEditing(false)
}
const handleSettingsReset = () => {
if (!selectedConfigEntry?.isEditable || selectedConfigEntry.source !== "global") {
return
}
const defaultValue = (SETTINGS_DEFAULTS as Record<string, unknown>)[selectedConfigEntry.key]
if (defaultValue !== undefined && onUpdateGlobal) {
onUpdateGlobal(selectedConfigEntry.key as GlobalStateAndSettingsKey, defaultValue as never)
}
}
// Toggle handlers for rules/workflows/hooks/skills
const handleToggle = () => {
if (currentTab === "rules" && ruleEntries[selectedIndex] && onToggleRule) {
const entry = ruleEntries[selectedIndex]
onToggleRule(entry.source === "global", entry.path, !entry.enabled, entry.ruleType || "cline")
} else if (currentTab === "workflows" && workflowEntries[selectedIndex] && onToggleWorkflow) {
const entry = workflowEntries[selectedIndex]
onToggleWorkflow(entry.source === "global", entry.path, !entry.enabled)
} else if (currentTab === "hooks" && hookEntries[selectedIndex] && onToggleHook) {
const entry = hookEntries[selectedIndex]
onToggleHook(entry.isGlobal, entry.hook.name, !entry.hook.enabled, entry.workspaceName)
} else if (currentTab === "skills" && skillEntries[selectedIndex] && onToggleSkill) {
const entry = skillEntries[selectedIndex]
onToggleSkill(entry.isGlobal, entry.skill.path, !entry.skill.enabled)
}
}
// Input handling
useInput(
(input, key) => {
if (input.toLowerCase() === "q" || key.escape) {
exit()
}
// Tab navigation with Tab key or number keys
if (key.tab || (input >= "1" && input <= "5")) {
const targetIdx = key.tab
? (availableTabs.findIndex((t) => t.key === currentTab) + 1) % availableTabs.length
: parseInt(input) - 1
if (targetIdx >= 0 && targetIdx < availableTabs.length) {
handleTabChange(availableTabs[targetIdx].key)
}
return
}
// List navigation (arrow keys and vim-style j/k)
if (key.upArrow || input === "k") {
setSelectedIndex((i) => (i > 0 ? i - 1 : currentListLength - 1))
} else if (key.downArrow || input === "j") {
setSelectedIndex((i) => (i < currentListLength - 1 ? i + 1 : 0))
}
// Tab-specific actions
if (currentTab === "settings") {
if ((key.return || input === "e") && selectedConfigEntry?.isEditable) {
setEditValue(selectedConfigEntry.value !== undefined ? String(selectedConfigEntry.value) : "")
setIsEditing(true)
} else if (input === "r") {
handleSettingsReset()
}
} else if (key.return || input === " ") {
// Toggle for rules/workflows/hooks/skills
handleToggle()
}
// Open folder (for rules/workflows/hooks/skills tabs)
if (input === "o" && onOpenFolder && currentTab !== "settings") {
// Determine if current selection is global or workspace based on the selected entry
let isGlobal = true
if (currentTab === "rules" && ruleEntries[selectedIndex]) {
isGlobal = ruleEntries[selectedIndex].source === "global"
} else if (currentTab === "workflows" && workflowEntries[selectedIndex]) {
isGlobal = workflowEntries[selectedIndex].source === "global"
} else if (currentTab === "hooks" && hookEntries[selectedIndex]) {
isGlobal = hookEntries[selectedIndex].isGlobal
} else if (currentTab === "skills" && skillEntries[selectedIndex]) {
isGlobal = skillEntries[selectedIndex].isGlobal
}
onOpenFolder(currentTab as "rules" | "workflows" | "hooks" | "skills", isGlobal)
}
},
{ isActive: isRawModeSupported && !isEditing },
)
// Scrolling window
const halfVisible = Math.floor(MAX_VISIBLE / 2)
const startIndex = Math.max(0, Math.min(selectedIndex - halfVisible, currentListLength - MAX_VISIBLE))
// Edit mode UI (settings only)
if (isEditing && selectedConfigEntry && currentTab === "settings") {
const header = (
<React.Fragment>
<Text bold color="white">
Edit Configuration
</Text>
<Text color="gray">{SEPARATOR}</Text>
</React.Fragment>
)
if (selectedConfigEntry.type === "boolean") {
return (
<Box flexDirection="column">
{header}
<BooleanSelect
label={selectedConfigEntry.key}
onCancel={() => setIsEditing(false)}
onSelect={handleSettingsSave}
value={Boolean(selectedConfigEntry.value)}
/>
</Box>
)
}
return (
<Box flexDirection="column">
{header}
<TextInput
label={selectedConfigEntry.key}
onCancel={() => setIsEditing(false)}
onChange={setEditValue}
onSubmit={handleSettingsSave}
type={selectedConfigEntry.type}
value={editValue}
/>
</Box>
)
}
// Render tab content
const renderTabContent = () => {
switch (currentTab) {
case "settings": {
const visibleEntries = configEntries.slice(startIndex, startIndex + MAX_VISIBLE)
return (
<React.Fragment>
<Box>
<Text>Data directory: </Text>
<Text color="blue" underline>
{dataDir}
</Text>
</Box>
<Text color="gray">{SEPARATOR}</Text>
<Box flexDirection="column">
{visibleEntries.map((entry, idx) => {
const actualIndex = startIndex + idx
const prevEntry = visibleEntries[idx - 1]
const showHeader = !prevEntry || prevEntry.source !== entry.source
return (
<React.Fragment key={`${entry.source}-${entry.key}`}>
{showHeader && (
<SectionHeader
title={entry.source === "global" ? "Global Settings:" : "Workspace Settings:"}
/>
)}
<ConfigRow entry={entry} isSelected={actualIndex === selectedIndex} />
</React.Fragment>
)
})}
</Box>
</React.Fragment>
)
}
case "rules": {
if (ruleEntries.length === 0) {
return (
<Box>
<Text color="gray">
No rules configured. Add .clinerules files to your workspace or global config.
</Text>
</Box>
)
}
const visibleEntries = ruleEntries.slice(startIndex, startIndex + MAX_VISIBLE)
return (
<Box flexDirection="column">
{visibleEntries.map((entry, idx) => {
const actualIndex = startIndex + idx
const prevEntry = visibleEntries[idx - 1]
const showHeader = !prevEntry || prevEntry.source !== entry.source
return (
<React.Fragment key={`${entry.source}-${entry.path}`}>
{showHeader && (
<SectionHeader title={entry.source === "global" ? "Global Rules:" : "Workspace Rules:"} />
)}
<ToggleRow entry={entry} isSelected={actualIndex === selectedIndex} showType />
</React.Fragment>
)
})}
</Box>
)
}
case "workflows": {
if (workflowEntries.length === 0) {
return (
<Box>
<Text color="gray">No workflows configured. Add workflow files to enable this feature.</Text>
</Box>
)
}
const visibleEntries = workflowEntries.slice(startIndex, startIndex + MAX_VISIBLE)
return (
<Box flexDirection="column">
{visibleEntries.map((entry, idx) => {
const actualIndex = startIndex + idx
const prevEntry = visibleEntries[idx - 1]
const showHeader = !prevEntry || prevEntry.source !== entry.source
return (
<React.Fragment key={`${entry.source}-${entry.path}`}>
{showHeader && (
<SectionHeader
title={entry.source === "global" ? "Global Workflows:" : "Workspace Workflows:"}
/>
)}
<ToggleRow entry={entry} isSelected={actualIndex === selectedIndex} />
</React.Fragment>
)
})}
</Box>
)
}
case "hooks": {
if (hookEntries.length === 0) {
return (
<Box>
<Text color="gray">No hooks configured. Add hook scripts to enable automation.</Text>
</Box>
)
}
const visibleEntries = hookEntries.slice(startIndex, startIndex + MAX_VISIBLE)
return (
<Box flexDirection="column">
{visibleEntries.map((entry, idx) => {
const actualIndex = startIndex + idx
const prevEntry = visibleEntries[idx - 1]
const showHeader =
!prevEntry ||
prevEntry.isGlobal !== entry.isGlobal ||
prevEntry.workspaceName !== entry.workspaceName
let sectionTitle = "Global Hooks:"
if (!entry.isGlobal && entry.workspaceName) {
sectionTitle = `${entry.workspaceName} Hooks:`
}
return (
<React.Fragment key={`${entry.isGlobal}-${entry.workspaceName || ""}-${entry.hook.name}`}>
{showHeader && <SectionHeader title={sectionTitle} />}
<HookRow hook={entry.hook} isSelected={actualIndex === selectedIndex} />
</React.Fragment>
)
})}
</Box>
)
}
case "skills": {
if (skillEntries.length === 0) {
return (
<Box>
<Text color="gray">No skills configured. Add SKILL.md files to enable skills.</Text>
</Box>
)
}
const visibleEntries = skillEntries.slice(startIndex, startIndex + MAX_VISIBLE)
return (
<Box flexDirection="column">
{visibleEntries.map((entry, idx) => {
const actualIndex = startIndex + idx
const prevEntry = visibleEntries[idx - 1]
const showHeader = !prevEntry || prevEntry.isGlobal !== entry.isGlobal
return (
<React.Fragment key={`${entry.isGlobal}-${entry.skill.path}`}>
{showHeader && (
<SectionHeader title={entry.isGlobal ? "Global Skills:" : "Workspace Skills:"} />
)}
<SkillRow isSelected={actualIndex === selectedIndex} skill={entry.skill} />
</React.Fragment>
)
})}
</Box>
)
}
default:
return null
}
}
// Help text based on current tab
const getHelpText = () => {
const base = "↑/↓/j/k Navigate • Tab/1-5 Switch tabs • q/Esc Exit"
if (currentTab === "settings") {
return `${base} • Enter/e Edit • r Reset`
}
const openFolder = onOpenFolder ? " • o Open folder" : ""
return `${base} • Enter/Space Toggle${openFolder}`
}
return (
<Box flexDirection="column">
<Text bold color="white">
Cline Configuration
</Text>
<Text color="gray">{SEPARATOR}</Text>
<TabBar currentTab={currentTab} hooksEnabled={hooksEnabled} skillsEnabled={skillsEnabled} tabs={TABS} />
<Text color="gray">{SEPARATOR}</Text>
{renderTabContent()}
{currentListLength > MAX_VISIBLE && (
<Box marginTop={1}>
<Text color="gray">
{startIndex > 0 ? "↑ " : " "}
Showing {startIndex + 1}-{Math.min(startIndex + MAX_VISIBLE, currentListLength)} of {currentListLength}
{startIndex + MAX_VISIBLE < currentListLength ? " ↓" : " "}
</Text>
</Box>
)}
<Text color="gray">{SEPARATOR}</Text>
<Box flexDirection="column">
<Text color="gray">{getHelpText()}</Text>
{currentTab === "settings" && selectedConfigEntry && !selectedConfigEntry.isEditable && (
<Text color="yellow">This field is read-only ({selectedConfigEntry.type} type or not a setting)</Text>
)}
</Box>
</Box>
)
}
@@ -0,0 +1,381 @@
/**
* Sub-components and types for ConfigView
*/
import { Box, Text, useInput } from "ink"
import React, { useState } from "react"
import { useStdinContext } from "../context/StdinContext"
// ============================================================================
// Types & Constants
// ============================================================================
export type ValueType = "string" | "number" | "boolean" | "object" | "undefined"
export type TabView = "settings" | "rules" | "workflows" | "hooks" | "skills"
export interface ConfigEntry {
key: string
value: unknown
type: ValueType
isEditable: boolean
source: "global" | "workspace"
}
export interface ToggleEntry {
path: string
enabled: boolean
source: "global" | "workspace" | "remote"
ruleType?: string
}
export interface HookInfo {
name: string
enabled: boolean
absolutePath: string
}
export interface WorkspaceHooks {
workspaceName: string
hooks: HookInfo[]
}
export interface SkillInfo {
name: string
description: string
path: string
enabled: boolean
}
export const EXCLUDED_KEYS = new Set([
"taskHistory",
"primaryRootIndex",
"subagentsEnabled",
"subagentTerminalOutputLineLimit",
"welcomeViewCompleted",
"isNewUser",
])
export const EDITABLE_TYPES: Set<ValueType> = new Set(["string", "number", "boolean"])
export const MAX_VISIBLE = 12
export const SEPARATOR = "─".repeat(80)
export const TABS: { key: TabView; label: string; requiresFlag?: "hooks" | "skills" }[] = [
{ key: "settings", label: "Settings" },
{ key: "rules", label: "Rules" },
{ key: "workflows", label: "Workflows" },
{ key: "hooks", label: "Hooks", requiresFlag: "hooks" },
{ key: "skills", label: "Skills", requiresFlag: "skills" },
]
// ============================================================================
// Helper Functions
// ============================================================================
export function getValueType(value: unknown): ValueType {
if (value === undefined || value === null) {
return "undefined"
}
if (typeof value === "boolean") {
return "boolean"
}
if (typeof value === "number") {
return "number"
}
if (typeof value === "object") {
return "object"
}
return "string"
}
export function isExcluded(key: string, value: unknown): boolean {
if (EXCLUDED_KEYS.has(key)) {
return true
}
if (key.endsWith("Toggles") || key.endsWith("ModelInfo")) {
return true
}
if (key.startsWith("apiConfig_") || key.startsWith("last")) {
return true
}
if (value === undefined || value === null) {
return true
}
if (typeof value === "object" && Object.keys(value as object).length === 0) {
return true
}
if (Array.isArray(value) && value.length === 0) {
return true
}
if (typeof value === "string" && value.trim() === "") {
return true
}
return false
}
export function formatValue(value: unknown, maxLen = 50): string {
if (value === undefined || value === null) {
return "<not set>"
}
if (typeof value === "boolean") {
return value ? "true" : "false"
}
if (typeof value === "number") {
return String(value)
}
if (typeof value === "object") {
const json = JSON.stringify(value)
return json.length > maxLen ? json.slice(0, maxLen - 3) + "..." : json
}
const str = String(value)
return str.length > maxLen ? str.slice(0, maxLen - 3) + "..." : str
}
export function parseValue(input: string, type: ValueType): unknown {
if (type === "boolean") {
return input.toLowerCase() === "true" || input === "1"
}
if (type === "number") {
const num = parseFloat(input)
return Number.isNaN(num) ? 0 : num
}
if (type === "object") {
try {
return JSON.parse(input)
} catch {
return {}
}
}
return input
}
// Import isSettingsKey at module level for proper test mocking
import { isSettingsKey } from "@shared/storage/state-keys"
export function buildConfigEntries(state: Record<string, unknown>, source: "global" | "workspace"): ConfigEntry[] {
return Object.entries(state)
.filter(([key, value]) => !isExcluded(key, value))
.sort(([a], [b]) => a.localeCompare(b))
.map(([key, value]) => {
const type = getValueType(value)
const isEditable = EDITABLE_TYPES.has(type) && (source === "workspace" || isSettingsKey(key))
return { key, value, type, isEditable, source }
})
}
export function buildToggleEntries(
toggles: Record<string, boolean> | undefined,
source: "global" | "workspace" | "remote",
ruleType?: string,
): ToggleEntry[] {
if (!toggles) {
return []
}
return Object.entries(toggles)
.sort(([a], [b]) => a.localeCompare(b))
.map(([path, enabled]) => ({ path, enabled, source, ruleType }))
}
export function getFileName(path: string): string {
return path.split("/").pop() || path
}
// ============================================================================
// Sub-components
// ============================================================================
interface TextInputProps {
label: string
onChange: (value: string) => void
onCancel: () => void
onSubmit: (value: string) => void
type: ValueType
value: string
}
export const TextInput: React.FC<TextInputProps> = ({ label, onChange, onCancel, onSubmit, type, value }) => {
const { isRawModeSupported } = useStdinContext()
useInput(
(input, key) => {
if (key.escape) {
onCancel()
} else if (key.return) {
onSubmit(value)
} else if (key.backspace || key.delete) {
onChange(value.slice(0, -1))
} else if (input && !key.ctrl && !key.meta) {
onChange(value + input)
}
},
{ isActive: isRawModeSupported },
)
return (
<Box flexDirection="column" marginTop={1}>
<Text bold color="cyan">
Edit: {label}
</Text>
<Box>
<Text color="white">{value}</Text>
<Text inverse> </Text>
</Box>
<Text color="gray">Type: {type} Enter to save Esc to cancel</Text>
</Box>
)
}
interface BooleanSelectProps {
label: string
onCancel: () => void
onSelect: (value: boolean) => void
value: boolean
}
export const BooleanSelect: React.FC<BooleanSelectProps> = ({ label, onCancel, onSelect, value }) => {
const { isRawModeSupported } = useStdinContext()
const [selected, setSelected] = useState(value)
useInput(
(_input, key) => {
if (key.escape) {
onCancel()
} else if (key.return) {
onSelect(selected)
} else if (key.upArrow || key.downArrow) {
setSelected((prev) => !prev)
}
},
{ isActive: isRawModeSupported },
)
return (
<Box flexDirection="column" marginTop={1}>
<Text bold color="cyan">
Edit: {label}
</Text>
<Box flexDirection="column">
<Text color={selected ? "green" : undefined}>{selected ? " " : " "}true</Text>
<Text color={!selected ? "green" : undefined}>{!selected ? " " : " "}false</Text>
</Box>
<Text color="gray">/ to toggle Enter to save Esc to cancel</Text>
</Box>
)
}
export const ConfigRow: React.FC<{ entry: ConfigEntry; isSelected: boolean }> = ({ entry, isSelected }) => {
const valueColor = entry.type === "boolean" ? (entry.value ? "green" : "red") : "white"
return (
<Box>
<Text color={isSelected ? "cyan" : undefined}>
{isSelected ? " " : " "}
<Text color="cyan">{entry.key}</Text>
<Text color="gray">: </Text>
<Text color={valueColor}>{formatValue(entry.value)}</Text>
{!entry.isEditable && <Text color="gray"> (read-only)</Text>}
</Text>
</Box>
)
}
export const ToggleRow: React.FC<{
entry: ToggleEntry
isSelected: boolean
showType?: boolean
}> = ({ entry, isSelected, showType }) => {
const fileName = getFileName(entry.path)
const typeLabel = entry.ruleType ? ` [${entry.ruleType}]` : ""
return (
<Box>
<Text color={isSelected ? "cyan" : undefined}>
{isSelected ? " " : " "}
<Text color={entry.enabled ? "green" : "red"}>{entry.enabled ? "●" : "○"}</Text>
<Text> </Text>
<Text color="white">{fileName}</Text>
{showType && <Text color="gray">{typeLabel}</Text>}
</Text>
</Box>
)
}
export const HookRow: React.FC<{
hook: HookInfo
isSelected: boolean
}> = ({ hook, isSelected }) => {
return (
<Box>
<Text color={isSelected ? "cyan" : undefined}>
{isSelected ? " " : " "}
<Text color={hook.enabled ? "green" : "red"}>{hook.enabled ? "●" : "○"}</Text>
<Text> </Text>
<Text color="white">{hook.name}</Text>
</Text>
</Box>
)
}
export const SkillRow: React.FC<{
skill: SkillInfo
isSelected: boolean
}> = ({ skill, isSelected }) => {
return (
<Box flexDirection="column">
<Box>
<Text color={isSelected ? "cyan" : undefined}>
{isSelected ? " " : " "}
<Text color={skill.enabled ? "green" : "red"}>{skill.enabled ? "●" : "○"}</Text>
<Text> </Text>
<Text bold color="white">
{skill.name}
</Text>
</Text>
</Box>
{skill.description && (
<Box marginLeft={4}>
<Text color="gray">
{skill.description.length > 60 ? skill.description.slice(0, 57) + "..." : skill.description}
</Text>
</Box>
)}
</Box>
)
}
export const TabBar: React.FC<{
currentTab: TabView
tabs: typeof TABS
hooksEnabled?: boolean
skillsEnabled?: boolean
}> = ({ currentTab, tabs, hooksEnabled, skillsEnabled }) => {
const visibleTabs = tabs.filter((tab) => {
if (tab.requiresFlag === "hooks") {
return hooksEnabled
}
if (tab.requiresFlag === "skills") {
return skillsEnabled
}
return true
})
return (
<Box marginBottom={1}>
{visibleTabs.map((tab, idx) => (
<React.Fragment key={tab.key}>
{idx > 0 && <Text color="gray"> </Text>}
<Text bold={currentTab === tab.key} color={currentTab === tab.key ? "cyan" : "gray"}>
{currentTab === tab.key ? `[${tab.label}]` : tab.label}
</Text>
</React.Fragment>
))}
</Box>
)
}
export const SectionHeader: React.FC<{ title: string }> = ({ title }) => (
<Box marginTop={1}>
<Text bold color="yellow">
{title}
</Text>
</Box>
)
+301
View File
@@ -0,0 +1,301 @@
/**
* Stateful wrapper for ConfigView that handles toggle operations
*/
import { exec } from "node:child_process"
import os from "node:os"
import path from "node:path"
import { RuleScope } from "@shared/proto/cline/file"
import type { GlobalStateAndSettings, GlobalStateAndSettingsKey, LocalState, LocalStateKey } from "@shared/storage/state-keys"
import React, { useCallback, useEffect, useState } from "react"
import type { Controller } from "@/core/controller"
import { HostProvider } from "@/hosts/host-provider"
import { StdinProvider } from "../context/StdinContext"
import { ConfigView } from "./ConfigView"
interface HookInfo {
name: string
enabled: boolean
absolutePath: string
}
interface WorkspaceHooks {
workspaceName: string
hooks: HookInfo[]
}
interface SkillInfo {
name: string
description: string
path: string
enabled: boolean
}
interface ConfigViewWrapperProps {
controller: Controller
dataDir: string
globalState: Record<string, unknown>
workspaceState: Record<string, unknown>
hooksEnabled: boolean
skillsEnabled: boolean
isRawModeSupported?: boolean
}
export const ConfigViewWrapper: React.FC<ConfigViewWrapperProps> = ({
controller,
dataDir,
globalState: initialGlobalState,
workspaceState: initialWorkspaceState,
hooksEnabled,
skillsEnabled,
isRawModeSupported = true,
}) => {
// Settings state (managed locally for UI updates)
const [globalStateLocal, setGlobalStateLocal] = useState<Record<string, unknown>>(initialGlobalState)
const [workspaceStateLocal, setWorkspaceStateLocal] = useState<Record<string, unknown>>(initialWorkspaceState)
// Rules state
const [globalClineRulesToggles, setGlobalClineRulesToggles] = useState<Record<string, boolean>>({})
const [localClineRulesToggles, setLocalClineRulesToggles] = useState<Record<string, boolean>>({})
const [localCursorRulesToggles, setLocalCursorRulesToggles] = useState<Record<string, boolean>>({})
const [localWindsurfRulesToggles, setLocalWindsurfRulesToggles] = useState<Record<string, boolean>>({})
const [localAgentsRulesToggles, setLocalAgentsRulesToggles] = useState<Record<string, boolean>>({})
// Workflow state
const [globalWorkflowToggles, setGlobalWorkflowToggles] = useState<Record<string, boolean>>({})
const [localWorkflowToggles, setLocalWorkflowToggles] = useState<Record<string, boolean>>({})
// Hooks state
const [globalHooks, setGlobalHooks] = useState<HookInfo[]>([])
const [workspaceHooksState, setWorkspaceHooksState] = useState<WorkspaceHooks[]>([])
// Skills state
const [globalSkills, setGlobalSkills] = useState<SkillInfo[]>([])
const [localSkills, setLocalSkills] = useState<SkillInfo[]>([])
// Load initial data
useEffect(() => {
const loadData = async () => {
const { refreshRules } = await import("@/core/controller/file/refreshRules")
const { refreshHooks } = await import("@/core/controller/file/refreshHooks")
const { refreshSkills } = await import("@/core/controller/file/refreshSkills")
const rulesData = await refreshRules(controller, {})
setGlobalClineRulesToggles(rulesData.globalClineRulesToggles?.toggles || {})
setLocalClineRulesToggles(rulesData.localClineRulesToggles?.toggles || {})
setLocalCursorRulesToggles(rulesData.localCursorRulesToggles?.toggles || {})
setLocalWindsurfRulesToggles(rulesData.localWindsurfRulesToggles?.toggles || {})
setLocalAgentsRulesToggles(rulesData.localAgentsRulesToggles?.toggles || {})
setGlobalWorkflowToggles(rulesData.globalWorkflowToggles?.toggles || {})
setLocalWorkflowToggles(rulesData.localWorkflowToggles?.toggles || {})
if (hooksEnabled) {
const hooksData = await refreshHooks(controller, {})
setGlobalHooks(hooksData.globalHooks || [])
setWorkspaceHooksState(hooksData.workspaceHooks || [])
}
if (skillsEnabled) {
const skillsData = await refreshSkills(controller)
setGlobalSkills(skillsData.globalSkills || [])
setLocalSkills(skillsData.localSkills || [])
}
}
loadData()
}, [controller, hooksEnabled, skillsEnabled])
// Toggle handlers
const handleToggleRule = useCallback(
async (isGlobal: boolean, rulePath: string, enabled: boolean, ruleType: string) => {
const { toggleClineRule } = await import("@/core/controller/file/toggleClineRule")
// Determine scope based on isGlobal and rule type
const scope = isGlobal ? RuleScope.GLOBAL : RuleScope.LOCAL
// For non-cline rules, we need different toggle functions
if (ruleType === "cursor") {
// Update local state optimistically
setLocalCursorRulesToggles((prev) => ({ ...prev, [rulePath]: enabled }))
// Cursor rules use toggleCursorRule but we'll just update the state manager directly
const toggles = controller.stateManager.getWorkspaceStateKey("localCursorRulesToggles") || {}
toggles[rulePath] = enabled
controller.stateManager.setWorkspaceState("localCursorRulesToggles", toggles)
} else if (ruleType === "windsurf") {
setLocalWindsurfRulesToggles((prev) => ({ ...prev, [rulePath]: enabled }))
const toggles = controller.stateManager.getWorkspaceStateKey("localWindsurfRulesToggles") || {}
toggles[rulePath] = enabled
controller.stateManager.setWorkspaceState("localWindsurfRulesToggles", toggles)
} else if (ruleType === "agents") {
setLocalAgentsRulesToggles((prev) => ({ ...prev, [rulePath]: enabled }))
const toggles = controller.stateManager.getWorkspaceStateKey("localAgentsRulesToggles") || {}
toggles[rulePath] = enabled
controller.stateManager.setWorkspaceState("localAgentsRulesToggles", toggles)
} else {
// Cline rules
const result = await toggleClineRule(controller, { metadata: undefined, rulePath, enabled, scope })
if (result.globalClineRulesToggles?.toggles) {
setGlobalClineRulesToggles(result.globalClineRulesToggles.toggles)
}
if (result.localClineRulesToggles?.toggles) {
setLocalClineRulesToggles(result.localClineRulesToggles.toggles)
}
}
},
[controller],
)
const handleToggleWorkflow = useCallback(
async (isGlobal: boolean, workflowPath: string, enabled: boolean) => {
const { toggleWorkflow } = await import("@/core/controller/file/toggleWorkflow")
const scope = isGlobal ? RuleScope.GLOBAL : RuleScope.LOCAL
// Optimistic update
if (isGlobal) {
setGlobalWorkflowToggles((prev) => ({ ...prev, [workflowPath]: enabled }))
} else {
setLocalWorkflowToggles((prev) => ({ ...prev, [workflowPath]: enabled }))
}
await toggleWorkflow(controller, { metadata: undefined, workflowPath, enabled, scope })
},
[controller],
)
const handleToggleHook = useCallback(
async (isGlobal: boolean, hookName: string, enabled: boolean, workspaceName?: string) => {
const { toggleHook } = await import("@/core/controller/file/toggleHook")
// Optimistic update
if (isGlobal) {
setGlobalHooks((prev) => prev.map((h) => (h.name === hookName ? { ...h, enabled } : h)))
} else {
setWorkspaceHooksState((prev) =>
prev.map((ws) =>
ws.workspaceName === workspaceName
? { ...ws, hooks: ws.hooks.map((h) => (h.name === hookName ? { ...h, enabled } : h)) }
: ws,
),
)
}
const result = await toggleHook(controller, { metadata: undefined, hookName, isGlobal, enabled, workspaceName })
if (result.hooksToggles) {
setGlobalHooks(result.hooksToggles.globalHooks || [])
setWorkspaceHooksState(result.hooksToggles.workspaceHooks || [])
}
},
[controller],
)
const handleToggleSkill = useCallback(
async (isGlobal: boolean, skillPath: string, enabled: boolean) => {
const { toggleSkill } = await import("@/core/controller/file/toggleSkill")
// Optimistic update
if (isGlobal) {
setGlobalSkills((prev) => prev.map((s) => (s.path === skillPath ? { ...s, enabled } : s)))
} else {
setLocalSkills((prev) => prev.map((s) => (s.path === skillPath ? { ...s, enabled } : s)))
}
await toggleSkill(controller, { metadata: undefined, skillPath, isGlobal, enabled })
},
[controller],
)
const handleOpenFolder = useCallback(
async (folderType: "rules" | "workflows" | "hooks" | "skills", isGlobal: boolean) => {
let folderPath: string
if (isGlobal) {
// Global folders are in dataDir (e.g., ~/.cline/)
const subFolder = folderType === "rules" ? "rules" : folderType
folderPath = path.join(dataDir, subFolder)
} else {
// Local folders are in the workspace
const workspacePaths = await HostProvider.workspace.getWorkspacePaths({})
const primaryWorkspace = workspacePaths.paths[0]
if (!primaryWorkspace) {
return
}
// Local rules/workflows/hooks/skills are in .clinerules or .cline
const subFolder = folderType === "rules" ? "rules" : folderType
folderPath = path.join(primaryWorkspace, ".clinerules", subFolder)
}
// Open folder using platform-specific command
const platform = os.platform()
let command: string
if (platform === "darwin") {
command = `open "${folderPath}"`
} else if (platform === "win32") {
command = `explorer "${folderPath}"`
} else {
command = `xdg-open "${folderPath}"`
}
exec(command, (error) => {
if (error) {
// Folder might not exist, try to create and open
exec(`mkdir -p "${folderPath}" && ${command}`)
}
})
},
[dataDir],
)
// Settings update handlers
const handleUpdateGlobal = useCallback(
async (key: GlobalStateAndSettingsKey, value: GlobalStateAndSettings[GlobalStateAndSettingsKey]) => {
// Update local state for immediate UI feedback
setGlobalStateLocal((prev) => ({ ...prev, [key]: value }))
// Persist to state manager
controller.stateManager.setGlobalState(key, value)
await controller.stateManager.flushPendingState()
},
[controller],
)
const handleUpdateWorkspace = useCallback(
async (key: LocalStateKey, value: LocalState[LocalStateKey]) => {
// Update local state for immediate UI feedback
setWorkspaceStateLocal((prev) => ({ ...prev, [key]: value }))
// Persist to state manager
controller.stateManager.setWorkspaceState(key, value)
await controller.stateManager.flushPendingState()
},
[controller],
)
return (
<StdinProvider isRawModeSupported={isRawModeSupported}>
<ConfigView
dataDir={dataDir}
globalClineRulesToggles={globalClineRulesToggles}
globalHooks={globalHooks}
globalSkills={globalSkills}
globalState={globalStateLocal}
globalWorkflowToggles={globalWorkflowToggles}
hooksEnabled={hooksEnabled}
localAgentsRulesToggles={localAgentsRulesToggles}
localClineRulesToggles={localClineRulesToggles}
localCursorRulesToggles={localCursorRulesToggles}
localSkills={localSkills}
localWindsurfRulesToggles={localWindsurfRulesToggles}
localWorkflowToggles={localWorkflowToggles}
onOpenFolder={handleOpenFolder}
onToggleHook={handleToggleHook}
onToggleRule={handleToggleRule}
onToggleSkill={handleToggleSkill}
onToggleWorkflow={handleToggleWorkflow}
onUpdateGlobal={handleUpdateGlobal}
onUpdateWorkspace={handleUpdateWorkspace}
skillsEnabled={skillsEnabled}
workspaceHooks={workspaceHooksState}
workspaceState={workspaceStateLocal}
/>
</StdinProvider>
)
}
+216
View File
@@ -0,0 +1,216 @@
/**
* DiffView component for displaying file diffs in Ink
* Shows unified diff output with colored lines for additions/deletions
* Supports SEARCH/REPLACE format and ApplyPatch format
*/
import { Box, Text } from "ink"
import React from "react"
interface DiffViewProps {
/** Diff content (SEARCH/REPLACE format, ApplyPatch format, or raw content for new files) */
content?: string
}
interface DiffLine {
type: "add" | "remove" | "context" | "separator"
content: string
}
interface ParsedPatch {
additions: number
deletions: number
lines: DiffLine[]
}
// Constants for format markers
const MARKERS = {
SEARCH_BLOCK: "------- SEARCH",
SEARCH_SEPARATOR: "=======",
REPLACE_BLOCK: "+++++++ REPLACE",
NEW_BEGIN: "*** Begin Patch",
NEW_END: "*** End Patch",
} as const
/**
* Parse SEARCH/REPLACE format into diff lines
* Format: ------- SEARCH\n...\n=======\n...\n+++++++ REPLACE
*/
function parseSearchReplaceFormat(content: string): ParsedPatch {
const result: ParsedPatch = { additions: 0, deletions: 0, lines: [] }
// Find all SEARCH blocks
const searchRegex = /-{7,} SEARCH/g
const searchPositions: number[] = []
let match: RegExpExecArray | null
while ((match = searchRegex.exec(content)) !== null) {
searchPositions.push(match.index)
}
for (let i = 0; i < searchPositions.length; i++) {
// Add separator between blocks
if (i > 0) {
result.lines.push({ type: "separator", content: "" })
}
const start = searchPositions[i]
const end = i < searchPositions.length - 1 ? searchPositions[i + 1] : content.length
const blockContent = content.substring(start, end)
// Extract content after SEARCH marker
const afterSearch = blockContent.substring(MARKERS.SEARCH_BLOCK.length).replace(/^\r?\n/, "")
const separatorIndex = afterSearch.indexOf(MARKERS.SEARCH_SEPARATOR)
if (separatorIndex === -1) {
// Still streaming - only SEARCH block available
const searchContent = afterSearch.trimEnd()
for (const line of searchContent.split("\n")) {
result.lines.push({ type: "remove", content: line })
result.deletions++
}
} else {
// Extract SEARCH block (deletions)
const searchContent = afterSearch.substring(0, separatorIndex).replace(/\r?\n$/, "")
for (const line of searchContent.split("\n")) {
result.lines.push({ type: "remove", content: line })
result.deletions++
}
// Extract REPLACE block (additions)
const afterSeparator = afterSearch.substring(separatorIndex + MARKERS.SEARCH_SEPARATOR.length).replace(/^\r?\n/, "")
const replaceEndIndex = afterSeparator.indexOf(MARKERS.REPLACE_BLOCK)
const replaceContent =
replaceEndIndex !== -1
? afterSeparator.substring(0, replaceEndIndex).replace(/\r?\n$/, "")
: afterSeparator.trimEnd()
for (const line of replaceContent.split("\n")) {
result.lines.push({ type: "add", content: line })
result.additions++
}
}
}
return result
}
/**
* Parse ApplyPatch format into diff lines
* Format: *** Begin Patch\n*** Update File: path\n+line\n-line\n*** End Patch
*/
function parseApplyPatchFormat(content: string): ParsedPatch {
const result: ParsedPatch = { additions: 0, deletions: 0, lines: [] }
const beginIndex = content.indexOf(MARKERS.NEW_BEGIN)
if (beginIndex === -1) return result
const endIndex = content.indexOf(MARKERS.NEW_END)
const contentStart = beginIndex + MARKERS.NEW_BEGIN.length
const contentEnd = endIndex !== -1 ? endIndex : content.length
const patchContent = content.substring(contentStart, contentEnd).trim()
for (const line of patchContent.split("\n")) {
// Skip file header lines
if (line.match(/^\*\*\* (Add|Update|Delete) File:/)) continue
if (line.trim() === "@@") continue
if (line.startsWith("+")) {
const hasSpace = line.startsWith("+ ")
result.lines.push({ type: "add", content: hasSpace ? line.slice(2) : line.slice(1) })
result.additions++
} else if (line.startsWith("-")) {
const hasSpace = line.startsWith("- ")
result.lines.push({ type: "remove", content: hasSpace ? line.slice(2) : line.slice(1) })
result.deletions++
} else if (line.trim()) {
// Context line
result.lines.push({ type: "context", content: line })
}
}
return result
}
/**
* Parse tool content into diff lines
* Detects format and delegates to appropriate parser
*/
function parseToolContent(content: string): ParsedPatch {
// Try SEARCH/REPLACE format first
if (content.includes(MARKERS.SEARCH_BLOCK)) {
return parseSearchReplaceFormat(content)
}
// Try ApplyPatch format
if (content.includes(MARKERS.NEW_BEGIN)) {
return parseApplyPatchFormat(content)
}
// Fallback: treat as new file (all additions)
const lines = content.split("\n")
return {
additions: lines.length,
deletions: 0,
lines: lines.map((line) => ({ type: "add", content: line })),
}
}
// Dim diff colors similar to IDE diff views
const DIFF_COLORS = {
addBg: "rgb(35, 61, 41)", // dark muted green
addFg: "rgb(156, 204, 122)", // light green text
removeBg: "rgb(62, 36, 36)", // dark muted red
removeFg: "rgb(224, 139, 139)", // light red/pink text
} as const
/**
* Render a diff line with full-width background color highlighting
* Uses Box with backgroundColor to handle wrapping properly
*/
const DiffLineRow: React.FC<{ line: DiffLine }> = ({ line }) => {
if (line.type === "separator") {
return <Text> </Text>
}
const prefix = line.type === "add" ? "+" : line.type === "remove" ? "-" : " "
const content = prefix + line.content
switch (line.type) {
case "add":
return (
<Box backgroundColor={DIFF_COLORS.addBg} width="100%">
<Text color={DIFF_COLORS.addFg}>{content}</Text>
</Box>
)
case "remove":
return (
<Box backgroundColor={DIFF_COLORS.removeBg} width="100%">
<Text color={DIFF_COLORS.removeFg}>{content}</Text>
</Box>
)
case "context":
return <Text dimColor>{content}</Text>
default:
return null
}
}
/**
* DiffView component that renders file edits as a diff
* Supports SEARCH/REPLACE format and ApplyPatch format
*/
export const DiffView: React.FC<DiffViewProps> = ({ content }) => {
if (!content) {
return null
}
const parsed = parseToolContent(content)
return (
<Box flexDirection="column" width="100%">
{parsed.lines.map((line, idx) => (
<DiffLineRow key={idx} line={line} />
))}
</Box>
)
}
+83
View File
@@ -0,0 +1,83 @@
/**
* File mention menu component for CLI
* Displays a list of matching files when user types @
*/
import { Box, Text } from "ink"
import React from "react"
import { COLORS } from "../constants/colors"
import { type FileSearchResult, getRipgrepInstallInstructions } from "../utils/file-search"
import { getVisibleWindow } from "../utils/slash-commands"
interface FileMentionMenuProps {
results: FileSearchResult[]
selectedIndex: number
isLoading: boolean
query: string
showRipgrepWarning?: boolean
}
/**
* Truncate path from the left if too long, keeping the filename visible
*/
function truncatePath(filePath: string, maxLength: number = 50): string {
if (filePath.length <= maxLength) {
return filePath
}
return "..." + filePath.slice(-(maxLength - 3))
}
export const FileMentionMenu: React.FC<FileMentionMenuProps> = ({
results,
selectedIndex,
isLoading,
query,
showRipgrepWarning,
}) => {
const ripgrepWarning = showRipgrepWarning && (
<Box marginTop={1}>
<Text color="yellow">ripgrep not found - file search will be slower. </Text>
<Text color="gray">Install: {getRipgrepInstallInstructions()}</Text>
</Box>
)
if (isLoading) {
return (
<Box flexDirection="column" marginBottom={1} paddingLeft={1} paddingRight={1}>
<Text color="gray">Searching files...</Text>
{ripgrepWarning}
</Box>
)
}
if (results.length === 0) {
return (
<Box flexDirection="column" marginBottom={1} paddingLeft={1} paddingRight={1}>
<Text color="gray">{query ? `No files matching "${query}"` : "Type to search files..."}</Text>
{ripgrepWarning}
</Box>
)
}
const { items: visibleResults, startIndex } = getVisibleWindow(results, selectedIndex)
const hasMoreBelow = startIndex + visibleResults.length < results.length
return (
<Box flexDirection="column" marginBottom={1} paddingLeft={1} paddingRight={1}>
{visibleResults.map((result, idx) => {
const isSelected = startIndex + idx === selectedIndex
const displayPath = truncatePath(result.path)
return (
<Box key={result.path}>
<Text color={isSelected ? COLORS.primaryBlue : undefined}>
{isSelected ? "" : " "} {displayPath}
</Text>
</Box>
)
})}
{hasMoreBelow && <Text color="gray">{" "}</Text>}
{ripgrepWarning}
</Box>
)
}
+185
View File
@@ -0,0 +1,185 @@
/**
* Focus Chain / To-Do List component for CLI
* Displays a progress-tracked checklist of tasks
*/
import { isCompletedFocusChainItem, isFocusChainItem, parseFocusChainItem } from "@shared/focus-chain-utils"
import { Box, Text } from "ink"
import React, { useMemo } from "react"
interface TodoInfo {
currentTodo: { text: string; completed: boolean; index: number } | null
currentIndex: number
completedCount: number
totalCount: number
progressPercentage: number
}
interface TodoItem {
text: string
checked: boolean
}
interface FocusChainProps {
focusChainChecklist?: string | null
expanded?: boolean
}
/**
* Parse the focus chain checklist text into TodoInfo
*/
function parseCurrentTodoInfo(text: string): TodoInfo | null {
if (!text) {
return null
}
let completedCount = 0
let totalCount = 0
let firstIncompleteIndex = -1
let firstIncompleteText: string | null = null
const lines = text.split("\n")
for (const rawLine of lines) {
const line = rawLine.trim()
if (isFocusChainItem(line)) {
const isCompleted = isCompletedFocusChainItem(line)
if (isCompleted) {
completedCount++
} else if (firstIncompleteIndex === -1) {
firstIncompleteIndex = totalCount
// Extract text after "- [ ] "
firstIncompleteText = line.substring(5).trim()
}
totalCount++
}
}
if (totalCount === 0) {
return null
}
const currentTodo = firstIncompleteText ? { text: firstIncompleteText, completed: false, index: firstIncompleteIndex } : null
return {
currentTodo,
currentIndex: firstIncompleteIndex >= 0 ? firstIncompleteIndex + 1 : totalCount,
completedCount,
totalCount,
progressPercentage: (completedCount / totalCount) * 100,
}
}
/**
* Parse all todo items from the checklist
*/
function parseTodoItems(text: string): TodoItem[] {
const items: TodoItem[] = []
const lines = text.split("\n")
for (const rawLine of lines) {
const line = rawLine.trim()
const parsed = parseFocusChainItem(line)
if (parsed) {
items.push(parsed)
}
}
return items
}
/**
* Render progress bar
*/
const ProgressBar: React.FC<{ percentage: number; width?: number }> = ({ percentage, width = 20 }) => {
const filled = Math.round((percentage / 100) * width)
const empty = width - filled
const bar = "█".repeat(filled) + "░".repeat(empty)
return (
<Text>
<Text color="green">{bar}</Text>
<Text dimColor> {Math.round(percentage)}%</Text>
</Text>
)
}
/**
* Header view showing current task and progress
*/
const Header: React.FC<{
todoInfo: TodoInfo
}> = ({ todoInfo }) => {
const { currentTodo, currentIndex, totalCount, completedCount } = todoInfo
const isCompleted = completedCount === totalCount
const displayText = isCompleted ? "All tasks completed!" : currentTodo?.text || "To-Do list"
const truncatedText = displayText.length > 50 ? displayText.substring(0, 47) + "..." : displayText
return (
<Box flexDirection="row" gap={1}>
<Text color={isCompleted ? "green" : "cyan"}>
[{currentIndex}/{totalCount}]
</Text>
<Text color={isCompleted ? "green" : undefined}>{truncatedText}</Text>
</Box>
)
}
/**
* Expanded view showing all todo items
*/
const ExpandedList: React.FC<{
items: TodoItem[]
isCompleted: boolean
}> = ({ items, isCompleted }) => {
return (
<Box flexDirection="column" marginLeft={2} marginTop={1}>
{items.map((item, index) => (
<Box key={index}>
<Text color={item.checked ? "green" : "gray"}>{item.checked ? "✓" : "○"} </Text>
<Text color={item.checked ? "green" : undefined} dimColor={item.checked}>
{item.text}
</Text>
</Box>
))}
{isCompleted && (
<Box marginTop={1}>
<Text dimColor italic>
New steps will be generated if you continue the task
</Text>
</Box>
)}
</Box>
)
}
/**
* Main FocusChain component for CLI
* Shows a progress summary of the current to-do list
* Use expanded={true} to show all items (e.g., in verbose mode)
*/
export const FocusChain: React.FC<FocusChainProps> = ({ focusChainChecklist, expanded = false }) => {
const todoInfo = useMemo(
() => (focusChainChecklist ? parseCurrentTodoInfo(focusChainChecklist) : null),
[focusChainChecklist],
)
const todoItems = useMemo(() => (focusChainChecklist ? parseTodoItems(focusChainChecklist) : []), [focusChainChecklist])
// No content to display
if (!todoInfo) {
return null
}
const isCompleted = todoInfo.completedCount === todoInfo.totalCount
return (
<Box borderColor={isCompleted ? "green" : "gray"} borderStyle="round" flexDirection="column" paddingX={1}>
<Header todoInfo={todoInfo} />
<ProgressBar percentage={todoInfo.progressPercentage} />
{expanded && <ExpandedList isCompleted={isCompleted} items={todoItems} />}
</Box>
)
}
+189
View File
@@ -0,0 +1,189 @@
/**
* Highlighted input component for CLI
* Renders text with @ mentions and / commands highlighted, plus a movable cursor
*/
import { mentionRegexGlobal } from "@shared/context-mentions"
import { Text } from "ink"
import React from "react"
interface HighlightedInputProps {
text: string
cursorPos?: number
availableCommands?: string[]
}
// Regex for / commands (at start or after whitespace)
const slashCommandRegex = /(^|\s)(\/[a-zA-Z0-9_.-]+)/g
interface Segment {
text: string
type: "normal" | "mention" | "command"
startIndex: number
}
function parseInput(text: string, availableCommands?: string[]): Segment[] {
const highlights: { start: number; end: number; type: "mention" | "command" }[] = []
// Find all mentions
mentionRegexGlobal.lastIndex = 0
let match
while ((match = mentionRegexGlobal.exec(text)) !== null) {
highlights.push({
start: match.index,
end: match.index + match[0].length,
type: "mention",
})
}
// Find first slash command only (must be complete and valid)
slashCommandRegex.lastIndex = 0
const slashMatch = slashCommandRegex.exec(text)
if (slashMatch) {
const prefix = slashMatch[1] || ""
const commandText = slashMatch[2] // e.g., "/help"
const commandName = commandText.slice(1) // e.g., "help"
const commandStart = slashMatch.index + prefix.length
const commandEnd = commandStart + commandText.length
// Only highlight if command exists in available commands (or if no list provided)
if (!availableCommands || availableCommands.includes(commandName)) {
highlights.push({
start: commandStart,
end: commandEnd,
type: "command",
})
}
}
// Sort highlights by start position
highlights.sort((a, b) => a.start - b.start)
// Build segments
const segments: Segment[] = []
let lastIndex = 0
for (const highlight of highlights) {
// Skip overlapping highlights
if (highlight.start < lastIndex) continue
// Add normal text before this highlight
if (highlight.start > lastIndex) {
segments.push({
text: text.slice(lastIndex, highlight.start),
type: "normal",
startIndex: lastIndex,
})
}
// Add highlighted segment
segments.push({
text: text.slice(highlight.start, highlight.end),
type: highlight.type,
startIndex: highlight.start,
})
lastIndex = highlight.end
}
// Add remaining text
if (lastIndex < text.length) {
segments.push({
text: text.slice(lastIndex),
type: "normal",
startIndex: lastIndex,
})
}
// If no segments (empty or whitespace only), add a single normal segment
if (segments.length === 0 && text.length > 0) {
segments.push({
text: text,
type: "normal",
startIndex: 0,
})
}
return segments
}
export const HighlightedInput: React.FC<HighlightedInputProps> = ({ text, cursorPos, availableCommands }) => {
// If no cursor position provided, just render text with highlights (backward compatible)
if (cursorPos === undefined) {
if (!text) return null
const segments = parseInput(text, availableCommands)
return (
<Text>
{segments.map((segment, idx) => {
if (segment.type === "mention" || segment.type === "command") {
return (
<Text backgroundColor="gray" key={idx}>
{segment.text}
</Text>
)
}
return <Text key={idx}>{segment.text}</Text>
})}
</Text>
)
}
// With cursor position - render cursor within the text
const safeCursorPos = Math.min(Math.max(0, cursorPos), text.length)
const segments = parseInput(text, availableCommands)
// Render segments with cursor
const renderSegmentWithCursor = (segment: Segment, segmentIdx: number) => {
const segmentStart = segment.startIndex
const segmentEnd = segmentStart + segment.text.length
const isHighlighted = segment.type === "mention" || segment.type === "command"
// Check if cursor is within this segment
if (safeCursorPos >= segmentStart && safeCursorPos < segmentEnd) {
// Cursor is in this segment - split it
const localCursorPos = safeCursorPos - segmentStart
const beforeCursor = segment.text.slice(0, localCursorPos)
const cursorChar = segment.text[localCursorPos]
const afterCursor = segment.text.slice(localCursorPos + 1)
if (isHighlighted) {
return (
<Text key={segmentIdx}>
{beforeCursor && <Text backgroundColor="gray">{beforeCursor}</Text>}
<Text backgroundColor="gray" inverse>
{cursorChar}
</Text>
{afterCursor && <Text backgroundColor="gray">{afterCursor}</Text>}
</Text>
)
}
return (
<Text key={segmentIdx}>
{beforeCursor}
<Text inverse>{cursorChar}</Text>
{afterCursor}
</Text>
)
}
// Cursor not in this segment - render normally
if (isHighlighted) {
return (
<Text backgroundColor="gray" key={segmentIdx}>
{segment.text}
</Text>
)
}
return <Text key={segmentIdx}>{segment.text}</Text>
}
// Check if cursor is at the end (past all text)
const cursorAtEnd = safeCursorPos >= text.length
return (
<Text>
{segments.map((segment, idx) => renderSegmentWithCursor(segment, idx))}
{cursorAtEnd && <Text inverse> </Text>}
</Text>
)
}
@@ -0,0 +1,226 @@
/**
* History panel content for inline display in ChatView
* Shows task history with search and keyboard navigation
*/
import { StringRequest } from "@shared/proto/cline/common"
import { GetTaskHistoryRequest } from "@shared/proto/cline/task"
import { Box, Text, useInput } from "ink"
import React, { useCallback, useEffect, useMemo, useState } from "react"
import type { Controller } from "@/core/controller"
import { getTaskHistory } from "@/core/controller/task/getTaskHistory"
import { showTaskWithId } from "@/core/controller/task/showTaskWithId"
import { COLORS } from "../constants/colors"
import { useStdinContext } from "../context/StdinContext"
import { useTerminalSize } from "../hooks/useTerminalSize"
import { isMouseEscapeSequence } from "../utils/input"
import { Panel } from "./Panel"
interface TaskHistoryItem {
id: string
ts: number
task: string
totalCost: number
tokensIn: number
tokensOut: number
isFavorited: boolean
}
interface HistoryPanelContentProps {
onClose: () => void
onSelectTask: (taskId: string) => void
controller: Controller
}
function formatRelativeDate(ts: number): string {
const now = Date.now()
const diff = now - ts
const minutes = Math.floor(diff / 60000)
const hours = Math.floor(diff / 3600000)
const days = Math.floor(diff / 86400000)
if (minutes < 1) return "just now"
if (minutes < 60) return `${minutes}m ago`
if (hours < 24) return `${hours}h ago`
if (days < 7) return `${days}d ago`
return new Date(ts).toLocaleDateString()
}
function formatCost(cost: number): string {
if (cost === 0) return ""
return `$${cost.toFixed(2)}`
}
export const HistoryPanelContent: React.FC<HistoryPanelContentProps> = ({ onClose, onSelectTask, controller }) => {
const { isRawModeSupported } = useStdinContext()
const { rows: terminalRows } = useTerminalSize()
const [items, setItems] = useState<TaskHistoryItem[]>([])
const [searchQuery, setSearchQuery] = useState("")
const [selectedIndex, setSelectedIndex] = useState(0)
const [loading, setLoading] = useState(true)
// Calculate how many items fit in the panel
// Panel has border (2) + header (1) + separator (1) + search bar (1) + hint (1) = 6 lines overhead
// Each item takes 2 lines (text + metadata)
const panelHeight = Math.min(terminalRows - 6, 20) // Cap panel height
const itemHeight = 2
const maxVisible = Math.max(1, Math.floor((panelHeight - 4) / itemHeight) - 2) // 4 lines for search + hints + padding
// Load history
useEffect(() => {
const load = async () => {
setLoading(true)
try {
const request = GetTaskHistoryRequest.create({
sortBy: "newest",
searchQuery: searchQuery || undefined,
})
const result = await getTaskHistory(controller, request)
setItems(
result.tasks.map((t) => ({
id: t.id,
ts: t.ts,
task: t.task,
totalCost: t.totalCost,
tokensIn: t.tokensIn,
tokensOut: t.tokensOut,
isFavorited: t.isFavorited,
})),
)
} catch {
setItems([])
}
setLoading(false)
}
load()
}, [controller, searchQuery])
// Reset selection when search changes
useEffect(() => {
setSelectedIndex(0)
}, [searchQuery])
const handleSelect = useCallback(
async (item: TaskHistoryItem) => {
try {
await showTaskWithId(controller, StringRequest.create({ value: item.id }))
onSelectTask(item.id)
} catch (error) {
console.error("Error opening task:", error)
}
},
[controller, onSelectTask],
)
// Visible window
const scrollOffset = useMemo(() => {
const half = Math.floor(maxVisible / 2)
let start = Math.max(0, selectedIndex - half)
const end = Math.min(items.length, start + maxVisible)
if (end - start < maxVisible) {
start = Math.max(0, end - maxVisible)
}
return start
}, [selectedIndex, maxVisible, items.length])
const visibleItems = items.slice(scrollOffset, scrollOffset + maxVisible)
const showUpIndicator = scrollOffset > 0
const showDownIndicator = scrollOffset + maxVisible < items.length
useInput(
(input, key) => {
if (isMouseEscapeSequence(input)) {
return
}
if (key.escape) {
if (searchQuery) {
setSearchQuery("")
} else {
onClose()
}
return
}
if (key.return && items[selectedIndex]) {
handleSelect(items[selectedIndex])
return
}
if (key.upArrow) {
setSelectedIndex((i) => Math.max(0, i - 1))
return
}
if (key.downArrow) {
setSelectedIndex((i) => Math.min(items.length - 1, i + 1))
return
}
// Backspace for search
if (key.backspace || key.delete) {
setSearchQuery((q) => q.slice(0, -1))
return
}
// Printable characters for search
if (input && !key.ctrl && !key.meta && input.length === 1 && input.charCodeAt(0) >= 32) {
setSearchQuery((q) => q + input)
}
},
{ isActive: isRawModeSupported },
)
const renderContent = () => {
if (loading) {
return <Text color="gray">Loading history...</Text>
}
if (items.length === 0) {
return <Text color="gray">{searchQuery ? "No tasks match your search." : "No task history."}</Text>
}
return (
<Box flexDirection="column">
<Text color="gray">{showUpIndicator ? " ▲" : " "}</Text>
{visibleItems.map((item, idx) => {
const actualIndex = scrollOffset + idx
const isSelected = actualIndex === selectedIndex
const taskText = item.task.replace(/\n/g, " ")
const meta = [formatRelativeDate(item.ts), formatCost(item.totalCost)].filter(Boolean).join(" · ")
return (
<Box flexDirection="column" key={item.id}>
<Box overflow="hidden">
<Text color={isSelected ? COLORS.primaryBlue : undefined} wrap="truncate">
{isSelected ? " " : " "}
{taskText}
</Text>
</Box>
<Box>
<Text color="gray">
{" "}
{meta}
</Text>
</Box>
</Box>
)
})}
<Text color="gray">{showDownIndicator ? " ▼" : " "}</Text>
</Box>
)
}
return (
<Panel label="History">
<Box>
<Text color="gray">Search: </Text>
<Text color="white">{searchQuery}</Text>
<Text inverse> </Text>
</Box>
<Box>
<Text color="gray">{searchQuery ? "Esc to clear" : "Enter to open · Esc to close"}</Text>
</Box>
{renderContent()}
</Panel>
)
}
+223
View File
@@ -0,0 +1,223 @@
import { Text } from "ink"
import { render } from "ink-testing-library"
import React from "react"
import { beforeEach, describe, expect, it, vi } from "vitest"
// Create stable mock reference using vi.hoisted
const { mockShowTaskWithId } = vi.hoisted(() => ({
mockShowTaskWithId: vi.fn().mockResolvedValue(undefined),
}))
vi.mock("./TaskView", () => ({
TaskView: ({ taskId, verbose }: any) =>
React.createElement(Text, null, `TaskView: ${taskId || "no-id"} verbose=${String(verbose)}`),
}))
// Mock the controller dependencies - must be before importing HistoryView
vi.mock("@/core/controller", () => ({
Controller: vi.fn(),
}))
vi.mock("@/core/controller/task/showTaskWithId", () => ({
showTaskWithId: mockShowTaskWithId,
}))
vi.mock("@/shared/proto/cline/common", () => ({
StringRequest: {
create: (data: any) => data,
},
}))
// Mock useTerminalSize to prevent EventEmitter memory leak warnings from resize listeners
vi.mock("../hooks/useTerminalSize", () => ({
useTerminalSize: () => ({ columns: 80, rows: 24, resizeKey: 0 }),
}))
// Import after mocks are set up
import { HistoryView } from "./HistoryView"
describe("HistoryView", () => {
const mockController = {
dispose: vi.fn(),
stateManager: { flushPendingState: vi.fn() },
} as any
const mockItems = [
{ id: "task-1", ts: Date.now() - 3600000, task: "First task" },
{ id: "task-2", ts: Date.now() - 7200000, task: "Second task" },
{ id: "task-3", ts: Date.now() - 10800000, task: "Third task" },
]
beforeEach(() => {
vi.clearAllMocks()
})
describe("rendering", () => {
it("should render the history header", () => {
const { lastFrame } = render(<HistoryView controller={mockController} items={mockItems} />)
expect(lastFrame()).toContain("Task History")
})
it("should show total count in header", () => {
const { lastFrame } = render(<HistoryView controller={mockController} items={mockItems} />)
expect(lastFrame()).toContain("3 total")
})
it("should render task items", () => {
const { lastFrame } = render(<HistoryView controller={mockController} items={mockItems} />)
expect(lastFrame()).toContain("First task")
expect(lastFrame()).toContain("Second task")
expect(lastFrame()).toContain("Third task")
})
it("should show task IDs", () => {
const { lastFrame } = render(<HistoryView controller={mockController} items={mockItems} />)
expect(lastFrame()).toContain("task-1")
expect(lastFrame()).toContain("task-2")
})
it("should show empty message when no items", () => {
const { lastFrame } = render(<HistoryView controller={mockController} items={[]} />)
expect(lastFrame()).toContain("No task history available")
})
it("should show navigation help", () => {
const { lastFrame } = render(<HistoryView controller={mockController} items={mockItems} />)
expect(lastFrame()).toContain("↑↓")
expect(lastFrame()).toContain("Enter")
})
})
describe("task details", () => {
it("should display task cost when available", () => {
const itemsWithCost = [{ id: "task-1", ts: Date.now(), task: "Task", totalCost: 0.0025 }]
const { lastFrame } = render(<HistoryView controller={mockController} items={itemsWithCost} />)
expect(lastFrame()).toContain("Cost:")
expect(lastFrame()).toContain("0.0025")
})
it("should display model ID when available", () => {
const itemsWithModel = [{ id: "task-1", ts: Date.now(), task: "Task", modelId: "claude-sonnet-4-20250514" }]
const { lastFrame } = render(<HistoryView controller={mockController} items={itemsWithModel} />)
expect(lastFrame()).toContain("Model:")
expect(lastFrame()).toContain("claude-sonnet-4-20250514")
})
it("should truncate long task descriptions", () => {
const longTask = "x".repeat(100)
const itemsWithLongTask = [{ id: "task-1", ts: Date.now(), task: longTask }]
const { lastFrame } = render(<HistoryView controller={mockController} items={itemsWithLongTask} />)
expect(lastFrame()).toContain("...")
})
it("should handle missing task text", () => {
const itemsWithoutTask = [{ id: "task-1", ts: Date.now() }]
const { lastFrame } = render(<HistoryView controller={mockController} items={itemsWithoutTask} />)
expect(lastFrame()).toContain("Unknown task")
})
})
describe("selection indicator", () => {
it("should show selection indicator on first item by default", () => {
const { lastFrame } = render(<HistoryView controller={mockController} items={mockItems} />)
expect(lastFrame()).toContain(">")
})
})
describe("keyboard navigation", () => {
it("should navigate down with arrow key", () => {
const { lastFrame, stdin } = render(<HistoryView controller={mockController} items={mockItems} />)
// Press down arrow
stdin.write("\x1B[B")
// Should still render properly
expect(lastFrame()).toContain("Task History")
})
it("should navigate up with arrow key", () => {
const { lastFrame, stdin } = render(<HistoryView controller={mockController} items={mockItems} />)
// Press down then up
stdin.write("\x1B[B")
stdin.write("\x1B[A")
expect(lastFrame()).toContain("Task History")
})
it("should not go below last item", () => {
const { lastFrame, stdin } = render(<HistoryView controller={mockController} items={mockItems} />)
// Press down many times
for (let i = 0; i < 10; i++) {
stdin.write("\x1B[B")
}
expect(lastFrame()).toContain("Task History")
})
it("should not go above first item", () => {
const { lastFrame, stdin } = render(<HistoryView controller={mockController} items={mockItems} />)
// Press up when already at first
stdin.write("\x1B[A")
expect(lastFrame()).toContain("Task History")
})
})
describe("pagination", () => {
it("should show pagination info when provided", () => {
const pagination = {
page: 2,
totalPages: 5,
totalCount: 50,
limit: 10,
}
const { lastFrame } = render(<HistoryView controller={mockController} items={mockItems} pagination={pagination} />)
expect(lastFrame()).toContain("Page 2 of 5")
})
it("should show correct total count from pagination", () => {
const pagination = {
page: 1,
totalPages: 3,
totalCount: 25,
limit: 10,
}
const { lastFrame } = render(<HistoryView controller={mockController} items={mockItems} pagination={pagination} />)
expect(lastFrame()).toContain("25 total")
})
it("should not show page info for single page", () => {
const pagination = {
page: 1,
totalPages: 1,
totalCount: 3,
limit: 10,
}
const { lastFrame } = render(<HistoryView controller={mockController} items={mockItems} pagination={pagination} />)
expect(lastFrame()).not.toContain("Page 1 of 1")
})
})
describe("scrolling", () => {
it("should show scroll indicators for long lists", () => {
const manyItems = Array.from({ length: 20 }, (_, i) => ({
id: `task-${i}`,
ts: Date.now() - i * 3600000,
task: `Task ${i}`,
}))
const { lastFrame, stdin } = render(<HistoryView controller={mockController} items={manyItems} visibleCount={5} />)
// Navigate down a bit
for (let i = 0; i < 5; i++) {
stdin.write("\x1B[B")
}
// Should show "more below" indicator
expect(lastFrame()).toContain("more")
})
})
})
+207
View File
@@ -0,0 +1,207 @@
/**
* History view component
* Displays task history with keyboard navigation
*/
import { Box, Text, useInput } from "ink"
import React, { useCallback, useState } from "react"
import { Controller } from "@/core/controller"
import { showTaskWithId } from "@/core/controller/task/showTaskWithId"
import { StringRequest } from "@/shared/proto/cline/common"
import { useStdinContext } from "../context/StdinContext"
import { useTerminalSize } from "../hooks/useTerminalSize"
interface TaskHistoryItem {
id: string
ts: number
task?: string
totalCost?: number
modelId?: string
}
interface HistoryPagination {
page: number
totalPages: number
totalCount: number
limit: number
}
interface HistoryViewProps {
items: TaskHistoryItem[]
visibleCount?: number
controller: Controller
onSelectTask?: (taskId: string) => void
pagination?: HistoryPagination
onPageChange?: (page: number) => void
/** If provided, all items for internal pagination management */
allItems?: TaskHistoryItem[]
}
/**
* Format separator
*/
function formatSeparator(char: string = "─", width: number = 80): string {
return char.repeat(Math.max(width, 10))
}
export const HistoryView: React.FC<HistoryViewProps> = ({
items,
visibleCount,
controller,
onSelectTask,
pagination,
onPageChange,
allItems,
}) => {
const { isRawModeSupported } = useStdinContext()
const [selectedIndex, setSelectedIndex] = useState(0)
const [internalPage, setInternalPage] = useState(pagination?.page ?? 1)
const { rows: terminalRows } = useTerminalSize()
// Calculate visible count based on terminal height to prevent overflow
// Each item takes ~5 lines (date, id, task text, cost/model, margin)
// Reserve lines for header (title, hint, pagination, separator) and footer (separator)
const headerLines = (pagination?.totalPages ?? 1) > 1 ? 5 : 4
const footerLines = 1
const availableRows = terminalRows - headerLines - footerLines
const itemHeight = 5
const dynamicVisibleCount = Math.max(1, Math.floor(availableRows / itemHeight))
const effectiveVisibleCount = visibleCount ?? dynamicVisibleCount
const onSelect = useCallback(
(item: TaskHistoryItem) => {
// Load the task via controller, then notify parent to switch views
showTaskWithId(controller, StringRequest.create({ value: item.id }))
.then(() => {
onSelectTask?.(item.id)
})
.catch((error) => console.error("Error showing task:", error))
},
[controller, onSelectTask],
)
// Use internal pagination if allItems is provided, otherwise use external
const useInternalPagination = !!allItems
const limit = pagination?.limit ?? 10
const totalCount = allItems?.length ?? pagination?.totalCount ?? items.length
const totalPages = useInternalPagination ? Math.ceil(totalCount / limit) : (pagination?.totalPages ?? 1)
const currentPage = useInternalPagination ? internalPage : (pagination?.page ?? 1)
const hasPrevPage = currentPage > 1
const hasNextPage = currentPage < totalPages
// Get current page items
const pageItems = useInternalPagination ? (allItems ?? []).slice((currentPage - 1) * limit, currentPage * limit) : items
const handlePageChange = useCallback(
(newPage: number) => {
if (useInternalPagination) {
setInternalPage(newPage)
setSelectedIndex(0)
} else if (onPageChange) {
onPageChange(newPage)
setSelectedIndex(0)
}
},
[useInternalPagination, onPageChange],
)
useInput(
(input, key) => {
if (key.upArrow || input === "k") {
setSelectedIndex((prev) => Math.max(0, prev - 1))
} else if (key.downArrow || input === "j") {
setSelectedIndex((prev) => Math.min(pageItems.length - 1, prev + 1))
} else if (key.return && pageItems[selectedIndex]) {
onSelect(pageItems[selectedIndex])
} else if (key.leftArrow && hasPrevPage) {
handlePageChange(currentPage - 1)
} else if (key.rightArrow && hasNextPage) {
handlePageChange(currentPage + 1)
} else if (input === "n" && hasNextPage) {
handlePageChange(currentPage + 1)
} else if (input === "p" && hasPrevPage) {
handlePageChange(currentPage - 1)
}
},
{ isActive: isRawModeSupported },
)
// Calculate visible window around selected item
const halfVisible = Math.floor(effectiveVisibleCount / 2)
let startIndex = Math.max(0, selectedIndex - halfVisible)
const endIndex = Math.min(pageItems.length, startIndex + effectiveVisibleCount)
// Adjust start if we're near the end
if (endIndex - startIndex < effectiveVisibleCount) {
startIndex = Math.max(0, endIndex - effectiveVisibleCount)
}
const visibleTasks = pageItems.slice(startIndex, endIndex)
const showUpIndicator = startIndex > 0
const showDownIndicator = endIndex < pageItems.length
return (
<Box flexDirection="column">
<Text bold color="white">
{"📜 Task History (" + totalCount + " total)"}
</Text>
<Text color="gray">Use /j/k to navigate, Enter to select</Text>
{totalPages > 1 && (
<Box>
<Text color="gray">
Page {currentPage} of {totalPages}{" "}
</Text>
{hasPrevPage ? <Text color="blue">[ prev] </Text> : <Text color="gray">[ prev] </Text>}
{hasNextPage ? <Text color="blue">[next ]</Text> : <Text color="gray">[next ]</Text>}
</Box>
)}
<Text>{formatSeparator()}</Text>
{pageItems.length === 0 ? (
<Text>No task history available.</Text>
) : (
<Box flexDirection="column">
{showUpIndicator && <Text color="gray">{" ↑ " + startIndex + " more above"}</Text>}
{visibleTasks.map((task, index) => {
const actualIndex = startIndex + index
const isSelected = actualIndex === selectedIndex
const date = new Date(task.ts).toLocaleString()
const taskText = task.task?.substring(0, 60) || "Unknown task"
const truncated = (task.task?.length || 0) > 60 ? "..." : ""
return (
<Box flexDirection="column" key={`${task.id}-${actualIndex}`} marginBottom={1}>
<Box>
<Text color={isSelected ? "green" : undefined}>{isSelected ? "> " : " "}</Text>
<Text color="gray">{date}</Text>
</Box>
<Box marginLeft={4}>
<Text color="cyan">{task.id}</Text>
</Box>
<Box marginLeft={4}>
<Text bold={isSelected} color={isSelected ? "white" : undefined}>
{taskText}
{truncated}
</Text>
</Box>
{typeof task.totalCost === "number" && (
<Box marginLeft={4}>
<Text color="gray">Cost: ${task.totalCost ? task.totalCost.toFixed(4) : "0"}</Text>
</Box>
)}
{task.modelId && (
<Box marginLeft={4}>
<Text color="gray">Model: {task.modelId}</Text>
</Box>
)}
</Box>
)
})}
{showDownIndicator && <Text color="gray">{" ↓ " + (pageItems.length - endIndex) + " more below"}</Text>}
</Box>
)}
<Text>{formatSeparator()}</Text>
</Box>
)
}
+215
View File
@@ -0,0 +1,215 @@
/**
* Import view component
* Handles importing API keys from competing CLI agents (Codex, OpenCode)
*/
import { Box, Text, useInput } from "ink"
import React, { useCallback, useEffect, useState } from "react"
import { StateManager } from "@/core/storage/StateManager"
import { COLORS } from "../constants/colors"
import { useStdinContext } from "../context/StdinContext"
import {
getProviderDisplayName,
getSourceDisplayName,
type ImportedKey,
type ImportSource,
importFromCodex,
importFromOpenCode,
} from "../utils/import-configs"
type ImportStep = "select" | "confirm" | "saving" | "error"
interface ImportViewProps {
source: ImportSource
onComplete: () => void
onCancel: () => void
}
export const ImportView: React.FC<ImportViewProps> = ({ source, onComplete, onCancel }) => {
const { isRawModeSupported } = useStdinContext()
const [step, setStep] = useState<ImportStep>("select")
const [keys, setKeys] = useState<ImportedKey[]>([])
const [selectedIndex, setSelectedIndex] = useState(0)
const [confirmIndex, setConfirmIndex] = useState(0)
const [errorMessage, setErrorMessage] = useState("")
// Load keys on mount
useEffect(() => {
const result = source === "codex" ? importFromCodex() : importFromOpenCode()
if (result && result.keys.length > 0) {
setKeys(result.keys)
if (result.keys.length === 1) {
// Only one key, go straight to confirm
setStep("confirm")
}
} else {
setErrorMessage(`Could not read API keys from ${getSourceDisplayName(source)} config`)
setStep("error")
}
}, [source])
const handleConfirm = useCallback(async () => {
try {
setStep("saving")
const selectedKey = keys[selectedIndex]
if (!selectedKey) {
setErrorMessage("No key selected")
setStep("error")
return
}
const stateManager = StateManager.get()
const config: Record<string, string> = {
actModeApiProvider: selectedKey.provider,
planModeApiProvider: selectedKey.provider,
apiProvider: selectedKey.provider,
}
// Set API key
config[selectedKey.keyField] = selectedKey.key
// Set model ID if available
if (selectedKey.modelId) {
config.actModeApiModelId = selectedKey.modelId
config.planModeApiModelId = selectedKey.modelId
}
stateManager.setApiConfiguration(config)
await stateManager.flushPendingState()
onComplete()
} catch (error) {
setErrorMessage(error instanceof Error ? error.message : String(error))
setStep("error")
}
}, [keys, selectedIndex, onComplete])
useInput(
(input, key) => {
if (key.escape) {
if (step === "confirm" && keys.length > 1) {
setStep("select")
setConfirmIndex(0)
} else if (step === "error") {
onCancel()
} else {
onCancel()
}
return
}
if (step === "select") {
if (key.upArrow) {
setSelectedIndex((prev) => (prev > 0 ? prev - 1 : keys.length - 1))
} else if (key.downArrow) {
setSelectedIndex((prev) => (prev < keys.length - 1 ? prev + 1 : 0))
} else if (key.return) {
setStep("confirm")
}
} else if (step === "confirm") {
if (key.upArrow || key.downArrow) {
setConfirmIndex((prev) => (prev === 0 ? 1 : 0))
} else if (key.return) {
if (confirmIndex === 0) {
handleConfirm()
} else {
onCancel()
}
}
} else if (step === "error") {
if (key.return) {
onCancel()
}
}
},
{ isActive: isRawModeSupported && step !== "saving" },
)
const sourceName = getSourceDisplayName(source)
if (step === "select") {
return (
<Box flexDirection="column">
<Text color="white">Select which key to import from {sourceName}</Text>
<Text> </Text>
{keys.map((k, i) => (
<Box key={`${k.provider}-${i}`}>
<Text color={i === selectedIndex ? COLORS.primaryBlue : undefined}>
{i === selectedIndex ? " " : " "}
{getProviderDisplayName(k.provider)}
</Text>
</Box>
))}
<Text> </Text>
<Text color="gray">Arrows to navigate, Enter to select, Esc to go back</Text>
</Box>
)
}
if (step === "confirm") {
const selectedKey = keys[selectedIndex]
const providerName = selectedKey ? getProviderDisplayName(selectedKey.provider) : ""
const maskedKey = selectedKey ? `${selectedKey.key.slice(0, 8)}...${selectedKey.key.slice(-4)}` : ""
return (
<Box flexDirection="column">
<Text color="white">Import API key from {sourceName}?</Text>
<Text> </Text>
<Box>
<Text color="gray">Provider: </Text>
<Text color="white">{providerName}</Text>
</Box>
<Box>
<Text color="gray">API Key: </Text>
<Text color="white">{maskedKey}</Text>
</Box>
{selectedKey?.modelId && (
<Box>
<Text color="gray">Model: </Text>
<Text color="white">{selectedKey.modelId}</Text>
</Box>
)}
<Text> </Text>
<Box>
<Text color={confirmIndex === 0 ? COLORS.primaryBlue : undefined}>
{confirmIndex === 0 ? " " : " "}
Confirm import
</Text>
</Box>
<Box>
<Text color={confirmIndex === 1 ? COLORS.primaryBlue : undefined}>
{confirmIndex === 1 ? " " : " "}
Cancel
</Text>
</Box>
<Text> </Text>
<Text color="gray">Enter to confirm, Esc to go back</Text>
</Box>
)
}
if (step === "saving") {
return (
<Box>
<Text color="white">Importing configuration...</Text>
</Box>
)
}
if (step === "error") {
return (
<Box flexDirection="column">
<Text bold color="red">
Something went wrong
</Text>
<Text> </Text>
<Text color="yellow">{errorMessage}</Text>
<Text> </Text>
<Text color="gray">Press Enter or Esc to go back</Text>
</Box>
)
}
return null
}

Some files were not shown because too many files have changed in this diff Show More