Compare commits

..

62 Commits

Author SHA1 Message Date
Arafatkatze 5d77a9a787 Send to cline provider 2026-01-27 18:28:13 -08:00
cline-test 92ebfce0cb feat(settings): Support linking to recommended or free model picker. 2026-01-27 18:01:44 -08:00
cline-test 8a5042a8bc release(3.55.0): Version bump and update WhatsNewModal 2026-01-27 17:31:11 -08:00
github-actions 726853d679 Updating CHANGELOG.md format 2026-01-27 23:52:40 +00:00
github-actions[bot] 0f52d80e55 changeset version bump 2026-01-27 23:52:38 +00:00
Ara 71af56f493 feat: add Arcee AI Trinity Large Preview to free models (#8897)
Add arcee-ai/trinity-large-preview:free as a new free model option:
- Add to onboarding models with 131k context window and score of 88
- Include in OpenRouterModelPicker free models list
- Update filter to preserve Trinity Large models like Minimax models
2026-01-27 15:51:39 -08:00
Juan Pablo Flores 1167b4f3a6 feat(rules): Conditional rules docs (#8874)
* docs(rules): Initial thoughts on docs for conditional rules.

* docs: restructure Cline Rules documentation into nested structure

Reorganize Cline Rules documentation by:
- Creating a "Cline Rules" group with overview and conditional-rules pages
- Moving conditional-rules.mdx into features/cline-rules/ subdirectory
- Adding URL redirects for backward compatibility
- Streamlining conditional-rules content for clarity and conciseness
- Adding cross-reference link to the overview page

This improves documentation navigation by grouping related rule concepts together and makes the content more accessible with clearer, more concise explanations.

* docs(cline-rules): consolidate rule file format documentation

Reorganize and expand the documentation for supported rule file formats:

- Add new "Supported Rule Files" section with comprehensive table
- Document cross-tool compatibility (Cursor, Windsurf, AGENTS.md)
- Clarify file priority and loading behavior
- Remove separate AGENTS.md section and integrate into unified table

This improves discoverability by showing all supported formats in one
place and makes it clearer how Cline works with rules from different AI
coding tools.

* docs(rules): remove context management note from overview

---------

Co-authored-by: cline-test <132302818+candieduniverse@users.noreply.github.com>
2026-01-27 14:17:29 -08:00
WangXiaolong e8d6370b0c feat(deepseek): add native tool calling support and reasoning_content handling (#7888)
* feat(deepseek): add native tool calling support and reasoning_content passback

- Add DeepSeek to isNextGenModelProvider list to enable native tool calling
- Add isDeepSeekModelFamily function for model identification
- Add addReasoningContent function for DeepSeek Reasoner's reasoning_content field
  - Pass back reasoning_content during tool calling within the same turn
  - Clear reasoning_content when starting a new conversation turn
- Compliant with DeepSeek API documentation for thinking mode with tool calling

* Update src/core/api/transform/r1-format.ts

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

* Update comments for user message handling logic

Clarify reasoning for handling user messages in comments.

* Update src/core/api/transform/r1-format.ts

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

* fix: format code for consistency in isNextGenModelFamily function

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Ara <arafat.da.khan@gmail.com>
2026-01-27 13:24:20 -08:00
Toby White e243376a39 feat: add MCP prompts support (#8066)
* feat: add MCP prompts support

Implement support for MCP prompts as defined in the MCP spec (2025-06-18):
- Add McpPrompt and McpPromptArgument types to shared types
- Update proto definitions with prompt messages
- Update McpHub to fetch prompts list and get individual prompts
- Add prompts to system prompt component for AI awareness
- Add McpPromptRow UI component for displaying prompts
- Update ServerRow with Prompts tab showing available prompts
- Add slash command integration (/mcp:<server>:<prompt>)
- Update regex patterns to support colons in command names

MCP prompts are user-controlled templates that can be invoked via
slash commands to inject contextual messages into the conversation.

* style: alphabetize imports in mcp-server-conversion.ts

Reorder imports to follow project convention of alphabetical ordering.

* feat: add MCP prompts to slash command autocomplete

Wire up mcpServers to SlashCommandMenu so MCP prompt commands appear
in the autocomplete dropdown with their own "MCP Prompts" section.

* test: add unit tests for MCP prompt slash commands

- Add webview slash-commands.test.ts testing getMcpPromptCommands,
  getMatchingSlashCommands, and validateSlashCommand with MCP servers
- Add backend slash-commands tests for formatMcpPromptResponse and
  parseSlashCommands MCP handling
- Export formatMcpPromptResponse for testability
- Add "mcp_prompt" to telemetry captureSlashCommandUsed types

* test: update snapshots and fix backend tests for MCP prompts

- Update system prompt snapshots to include MCP prompts section
- Remove backend tests requiring StateManager initialization
  (tests for unknown server, no fetcher, fetcher errors)
- Core MCP prompt functionality is covered by remaining tests

* fix: change test status to valid 'connecting' value

* chore: remove commented debug line from prompts fetching

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: use Logger instead of console.error for lint compliance

* fix: wire up mcpPromptFetcher callback to parseSlashCommands

The MCP prompt slash commands were not working because the
mcpPromptFetcher callback was never passed to parseSlashCommands.
This adds the callback that wraps mcpHub.getPrompt() to actually
fetch and inject prompt content when using /mcp:server:prompt.

* fix: resolve MCP prompts keyboard navigation and edge cases

- Add mcpServers param to keyboard handler's getMatchingSlashCommands calls
  to fix arrow key navigation and Enter/Tab selection for MCP prompts
- Add null check for connection.client in McpHub.getPrompt()
- Add debug logging when MCP prompt fetch returns null
- Fix regex in shouldShowSlashCommandsMenu to include colons for MCP format

* chore: add changeset for MCP prompts feature

---------

Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Robin Newhouse <robin@cline.bot>
2026-01-27 13:12:02 -08:00
Tomás Barreiro 4f1be9d512 Replace POSTHOG_TELEMETRY_ENABLED with CLINE_TELEMETRY_DISABLED (#8818)
* Replace `POSTHOG_TELEMETRY_ENABLED` with `CLINE_TELEMETRY_DISABLED`

* Update cli/pkg/hostbridge/env.go

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>
2026-01-27 18:17:06 +01:00
Ara 94d36ce719 feat(ui): reduce font size for thinking content (#8892)
Add text-xs class to reasoning content in ThinkingRow component
for improved visual hierarchy and readability.
2026-01-27 08:28:39 -08:00
Bee 5df7498f03 refactor: simplify ThinkingRow expansion state management (#8735)
* refactor: simplify ThinkingRow expansion state management

Remove the responseStarted prop and complex logic that conditionally controlled ThinkingRow visibility during streaming. Simplify to allow ThinkingRow to remain expandable throughout the entire streaming lifecycle instead of forcing it expanded during reasoning and then collapsing after response starts.

Changes:
- Remove ApiReqState type and responseStarted tracking
- Eliminate showStreamingThinking and showCollapsedThinking logic
- Use consistent isExpanded state based only on user toggle
- Always show ThinkingRow title

* remove unused responseStarted

* feat(ui): update thinking UI with improved expand/collapse controls

Changes:
- Replace "Thinking..." with "Working..." status text in non-plan mode
- Switch from ChevronRight to ChevronUp/Down icons for better UX
- Redesign thinking section header with cleaner layout
- Remove preview text when collapsed, show only "Thinking" label
- Add consistent border styling to thinking content
- Implement per-tool thinking expand/collapse state management
- Update icon sizing and styling for better visual consistency

This improves the user experience by making the thinking/reasoning sections more intuitive to expand and collapse, with clearer visual indicators and a more polished appearance.

* add blur

* feat: chevron fix, reasoning change, slight style change

* feat: spacing issues

* keep thinking row expanded during stream

* Reasoning -> Thoughts

* feat: Inline reading of files vs having reading then read list items seperately

* feat: remove extra reading state

* feat: removed reasoning from file expandable file state

---------

Co-authored-by: Jose R. Perez <trupix@gmail.com>
2026-01-27 07:53:03 -08:00
Juan Pablo Flores c2b87252ac Fixes Cannot restore checkpoint more than once #8866 (#8873) 2026-01-27 07:46:43 -08:00
github-actions[bot] be353bb3da v3.54.0 Release Notes (#8840)
- Native tool calls support for Ollama provider
- Sonnet 4.5 is now the default Amazon Bedrock model id

- Prevent infinite retry loops when replace_in_file fails repeatedly. The system now detects repeated failures and provides better guidance to break out of retry cycles.
- Skip diff error UI handling during streaming to prevent flickering. Error handling is deferred until streaming completes.
- Strip notebook cell outputs when extracting text content from Jupyter notebooks, significantly reducing context size sent to the LLM.
- Throttle diff view updates during streaming to reduce UI flickering and improve performance.

- Removed Devstral-2512 free from the free models list
- Removed deprecated zai-glm-4.6 model from Cerebras provider

Co-authored-by: Arafatkatze <arafat.da.khan@gmail.com>
2026-01-27 07:44:49 -08:00
Ara 0a7791de1f feat: remove Mistral Devstral 2512 from free models list (#8889)
Remove mistralai/devstral-2512:free from:
- Onboarding models configuration
- Free models picker in settings
- OpenRouter model filter exception list

The Devstral model is no longer included as a free tier option.
2026-01-27 07:16:55 -08:00
Robin Newhouse 7cca102e14 fix: apply_patch tool now works with OCA provider's gpt5 model ID (#8875) 2026-01-26 22:54:21 -08:00
Bee 4f591de6a9 feat: Adds support for native tool calls to Ollama provider (#8871)
* feat: add support for tool calls in Ollama API

Enhanced OllamaHandler to support tool calls by adding a 'tools' parameter to createMessage. Implements processing of tool call deltas using ToolCallProcessor, enabling handling of function calls made by the model. Added necessary imports for ChatCompletionTool and ToolCallProcessor types.

* add changeset
2026-01-26 17:50:52 -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
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
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
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
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
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
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
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
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
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
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 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
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
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
521 changed files with 8457 additions and 4752 deletions
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Add claude 4.5 haiku
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
fix: finalize document content during approval flow
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Expose --version in cline cli command
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Log Persistence errors to PostHog
-13
View File
@@ -1,13 +0,0 @@
---
"claude-dev": patch
---
feat: add OpenAI Codex (ChatGPT Plus/Pro) provider
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.
Models available:
- gpt-5.2-codex (default)
- gpt-5.1-codex-max
- gpt-5.1-codex-mini
- gpt-5.2
@@ -1,9 +0,0 @@
---
"claude-dev": patch
---
Fix two bugs in DiffViewProvider file editing:
1. **Line boundary validation**: Add `safelyTruncateDocument()` to prevent out-of-bounds line errors on JetBrains hosts (fixes #8423, #8429). The gRPC protocol strictly validates line numbers, causing "truncateDocument INTERNAL: Wrong line" errors when `truncateDocument()` was called with a line number >= document line count.
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. Fixed by extending the replacement range to cover the entire document on final update.
-9
View File
@@ -1,9 +0,0 @@
---
"claude-dev": patch
---
docs: fix outdated Ollama model names in documentation
Updated recommended Ollama models to use correct identifiers:
- Changed qwen3-coder-30b to qwen2.5-coder:32b
- Changed devstral-small to codellama:34b-code
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
OpenAI GPT-5 Codex models are now using Apply Patch tool for diff edits.
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Fix issue where tool call ids are invalid when switching between models using the chat completion format and the responses api format.
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
fix: add chat output on skill use
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Adding telemetry for background exec terminal
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
This pull request introduces comprehensive Jupyter Notebook support for Cline, enabling AI-assisted editing of `.ipynb` files with full cell-level context awareness. The feature allows users to seamlessly work with Jupyter notebooks using Cline's AI capabilities while preserving the notebook's JSON structure.
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
fix: removes retry message from UI after retry succeeds
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Support native tool calling for LM Studio and Ollama provider
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
add claude 4.5 opus into sap provider.
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Limite Vertex and LiteLLM options when they're remote configured
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Fix crash when the Context Menu has a type but no options
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Throttle the remote config fetch
-5
View File
@@ -1,5 +0,0 @@
---
"claude-dev": patch
---
Improve history view filter menu
-5
View File
@@ -1,5 +0,0 @@
---
"cline": patch
---
Add git worktree management UI for running parallel Cline sessions
-7
View File
@@ -16,13 +16,6 @@
TELEMETRY_SERVICE_API_KEY=your-posthog-telemetry-api-key
ERROR_SERVICE_API_KEY=your-posthog-error-tracking-api-key
# ============================================================================
# TELEMETRY PROVIDER CONTROL
# ============================================================================
# Control which telemetry providers are active
POSTHOG_TELEMETRY_ENABLED=true # Enable PostHog telemetry (default: true)
# Set to false to disable Telemetry completely
# ============================================================================
# OPENTELEMETRY (Optional - for advanced telemetry)
# ============================================================================
-1
View File
@@ -97,7 +97,6 @@ jobs:
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: npm run compile-standalone-npm
- name: Generate Protos (Second Pass - Bug Workaround)
-1
View File
@@ -138,7 +138,6 @@ jobs:
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: npm run compile-standalone-npm
- name: Generate Protos (Second Pass - Bug Workaround)
+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
+52 -2
View File
@@ -1,10 +1,60 @@
# Changelog
## [3.55.0]
- Add new model: Arcee Trinity Large Preview
- Add new model: Moonshot Kimi K2.5
- Add MCP prompts support - prompts from connected MCP servers now appear in slash command autocomplete as `/mcp:<server>:<prompt>`
## [3.54.0]
### Added
- Native tool calls support for Ollama provider
- Sonnet 4.5 is now the default Amazon Bedrock model id
### Fixed
- Prevent infinite retry loops when replace_in_file fails repeatedly. The system now detects repeated failures and provides better guidance to break out of retry cycles.
- Skip diff error UI handling during streaming to prevent flickering. Error handling is deferred until streaming completes.
- Strip notebook cell outputs when extracting text content from Jupyter notebooks, significantly reducing context size sent to the LLM.
- Throttle diff view updates during streaming to reduce UI flickering and improve performance.
### Changed
- Removed Mistral's Devstral-2512 free from the free models list
- Removed deprecated zai-glm-4.6 model from Cerebras provider
## [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
- Adding OpenAI gpt-5.2-codex model to the model picker
## [3.50.0]
@@ -1737,4 +1787,4 @@ Add Opus 4.1 through Claude Code
## [0.0.6]
- Initial release
- Initial release
-15
View File
@@ -137,21 +137,6 @@ For example, when working with a local web server, you can use 'Restore Workspac
<img width="2000" height="0" src="https://github.com/user-attachments/assets/ee14e6f7-20b8-4391-9091-8e8e25561929"><br>
<img align="left" width="360" src="https://github.com/user-attachments/assets/7fdf41e6-281a-4b4b-ac19-020b838b6970">
### Worktrees: Parallel Development
Worktrees let you work on multiple branches simultaneously, each in its own folder. This enables Cline to work on tasks in parallel across separate VS Code windows, or lets Cline work independently while you continue coding in your main workspace.
Cline takes over your VS Code window while working on a task. With worktrees, you can:
- **Run Cline in parallel** - Have Cline work on multiple tasks simultaneously
- **Keep working while Cline works** - Let Cline handle a task in a separate worktree while you continue coding
- **Isolate experimental changes** - Test risky changes in a worktree without affecting your main branch
<!-- Transparent pixel to create line break after floating image -->
<img width="2000" height="0" src="https://github.com/user-attachments/assets/ee14e6f7-20b8-4391-9091-8e8e25561929"><br>
## Contributing
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)!
+23
View File
@@ -147,6 +147,29 @@
"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": [
"**",
"!**/webview-ui/**",
"!**/evals/**",
"!**/standalone/**",
"!**/e2e/**",
"!**/test/**",
"!**/__tests__/**",
"!**/*.test.ts",
"!**/*.stories.ts",
"!src/dev/**",
"!**/*.mjs",
"!**/*.js",
"!**/scripts/**",
"!**/*.tsx",
"!**/testing-platform/**"
]
},
{
"includes": [
"**",
+76 -87
View File
@@ -10,11 +10,12 @@ import (
"strings"
"github.com/charmbracelet/huh"
"github.com/charmbracelet/lipgloss"
"github.com/cline/cli/pkg/cli"
"github.com/cline/cli/pkg/cli/auth"
"github.com/cline/cli/pkg/cli/display"
"github.com/cline/cli/pkg/cli/global"
"github.com/cline/cli/pkg/cli/output"
"github.com/cline/cli/pkg/cli/slash"
"github.com/cline/cli/pkg/common"
"github.com/cline/grpc-go/cline"
"github.com/spf13/cobra"
@@ -71,8 +72,6 @@ see the manual page: man cline`,
RunE: func(cmd *cobra.Command, args []string) error {
ctx := cmd.Context()
var instanceAddress string
// Validate workspace paths exist
if err := common.ValidateDirsExist(workspaces); err != nil {
return err
@@ -89,13 +88,13 @@ see the manual page: man cline`,
if global.Config.Verbose {
fmt.Println("Starting new Cline instance...")
}
instance, err := global.Clients.StartNewInstance(ctx, allWorkspaces...)
instance, err := global.Instances.StartNewInstance(ctx, allWorkspaces...)
if err != nil {
return fmt.Errorf("failed to start new instance: %w", err)
}
instanceAddress = instance.Address
global.Config.CoreAddress = instance.CoreAddress
if global.Config.Verbose {
fmt.Printf("Started instance at %s\n\n", instanceAddress)
fmt.Printf("Started instance at %s\n\n", global.Config.CoreAddress)
}
// Set up cleanup on exit
@@ -103,38 +102,35 @@ see the manual page: man cline`,
if global.Config.Verbose {
fmt.Println("\nCleaning up instance...")
}
registry := global.Clients.GetRegistry()
if err := global.KillInstanceByAddress(context.Background(), registry, instanceAddress); err != nil {
registry := global.Instances.GetRegistry()
if err := global.KillInstanceByAddress(context.Background(), registry, global.Config.CoreAddress); err != nil {
if global.Config.Verbose {
fmt.Printf("Warning: Failed to clean up instance: %v\n", err)
}
}
}()
}
// Check if user has credentials configured
if !isUserReadyToUse(ctx, instanceAddress) {
// Create renderer for welcome messages
renderer := display.NewRenderer(global.Config.OutputFormat)
fmt.Printf("\n%s\n\n", renderer.Dim("Hey there! Looks like you're new here. Let's get you set up"))
// Check if user has credentials configured
if !isUserReadyToUse(ctx) {
// Create renderer for welcome messages
renderer := display.NewRenderer(global.Config.OutputFormat)
fmt.Printf("\n%s\n\n", renderer.Dim("Hey there! Looks like you're new here. Let's get you set up"))
if err := auth.HandleAuthMenuNoArgs(ctx); err != nil {
// Check if user cancelled - exit cleanly
if err == huh.ErrUserAborted {
return nil
}
return fmt.Errorf("auth setup failed: %w", err)
if err := auth.HandleAuthMenuNoArgs(ctx); err != nil {
// Check if user cancelled - exit cleanly
if err == huh.ErrUserAborted {
return nil
}
// Re-check after auth wizard
if !isUserReadyToUse(ctx, instanceAddress) {
return fmt.Errorf("credentials still not configured - please run 'cline auth' to complete setup")
}
fmt.Printf("\n%s\n\n", renderer.Dim("✓ Setup complete, you can now use the Cline CLI"))
return fmt.Errorf("auth setup failed: %w", err)
}
} else {
// User specified --address flag, use that
instanceAddress = coreAddress
// Re-check after auth wizard
if !isUserReadyToUse(ctx) {
return fmt.Errorf("credentials still not configured - please run 'cline auth' to complete setup")
}
fmt.Printf("\n%s\n\n", renderer.Dim("✓ Setup complete, you can now use the Cline CLI"))
}
// Get content from both args and stdin
@@ -143,10 +139,13 @@ see the manual page: man cline`,
return fmt.Errorf("failed to read prompt: %w", err)
}
// If no prompt from args or stdin, show interactive input
if prompt == "" {
// If no prompt (or just a mode switch with no message), show interactive input
// Loop to allow mode switches without a message
bannerShown := false
for prompt == "" {
// Pass the mode flag and workspaces to banner so it shows correct info
prompt, err = promptForInitialTask(ctx, instanceAddress, mode, allWorkspaces)
prompt, err = promptForInitialTask(ctx, mode, allWorkspaces, !bannerShown)
bannerShown = true
if err != nil {
// Check if user cancelled - exit cleanly without error
if err == huh.ErrUserAborted {
@@ -154,6 +153,23 @@ see the manual page: man cline`,
}
return err
}
// Check if user entered a mode switch command
if newMode, remaining, isModeSwitch := slash.ParseModeSwitch(prompt); isModeSwitch {
mode = newMode
prompt = remaining
// If just a mode switch with no message, continue loop to re-prompt
if prompt == "" {
renderer := display.NewRenderer(global.Config.OutputFormat)
if mode == "act" {
fmt.Printf("\n%s\n\n", renderer.Success("Switched to act mode"))
} else {
fmt.Printf("\n%s\n\n", renderer.Success("Switched to plan mode"))
}
continue
}
}
if prompt == "" {
return fmt.Errorf("prompt required")
}
@@ -171,7 +187,7 @@ see the manual page: man cline`,
Mode: mode,
Settings: settings,
Yolo: yolo,
Address: instanceAddress,
Address: global.Config.CoreAddress,
Verbose: verbose,
Workspaces: allWorkspaces,
})
@@ -207,51 +223,30 @@ see the manual page: man cline`,
}
}
func promptForInitialTask(ctx context.Context, instanceAddress, modeFlag string, workspaces []string) (string, error) {
// Show session banner before the initial input
showSessionBanner(ctx, instanceAddress, modeFlag, workspaces)
var prompt string
// Create custom theme with mode-colored cursor and title
theme := huh.ThemeCharm()
// Set cursor and title color based on mode
modeColor := lipgloss.Color("3") // Yellow for plan
if modeFlag == "act" {
modeColor = lipgloss.Color("39") // Blue for act
func promptForInitialTask(ctx context.Context, modeFlag string, workspaces []string, showBanner bool) (string, error) {
// Show session banner before the initial input (only on first prompt)
if showBanner {
showSessionBanner(ctx, modeFlag, workspaces)
}
theme.Focused.TextInput.Cursor = theme.Focused.TextInput.Cursor.Foreground(modeColor)
theme.Focused.Title = theme.Focused.Title.Foreground(modeColor)
form := huh.NewForm(
huh.NewGroup(
huh.NewText().
Title("Start a new Cline task").
Description("What would you like Cline to help you with?").
Placeholder("e.g., Create a REST API with authentication...").
Lines(5).
Value(&prompt),
),
).WithWidth(48).WithTheme(theme)
err := form.Run()
prompt, err := output.PromptForInitialTask(
"Start a new Cline task",
"/plan or /act to switch modes\ntab to autocomplete commands\nctrl+e to open editor\nctrl+c to exit",
modeFlag,
slash.NewRegistry(ctx),
)
if err != nil {
// Check if user cancelled with Control-C
if err == huh.ErrUserAborted {
// Return a special error that indicates clean cancellation
// This allows deferred cleanup to run
if err == output.ErrUserAborted {
return "", huh.ErrUserAborted
}
return "", err
}
return strings.TrimSpace(prompt), nil
return prompt, nil
}
// showSessionBanner displays session info before initial prompt
func showSessionBanner(ctx context.Context, instanceAddress, modeFlag string, workspaces []string) {
func showSessionBanner(ctx context.Context, modeFlag string, workspaces []string) {
bannerInfo := display.BannerInfo{
Version: global.CliVersion,
Mode: modeFlag, // Use the mode from command flag, not state
@@ -265,21 +260,18 @@ func showSessionBanner(ctx context.Context, instanceAddress, modeFlag string, wo
bannerInfo.Workdirs = workspaces
// Get provider/model using auth functions (same logic as auth menu)
manager, err := cli.NewTaskManagerForAddress(ctx, instanceAddress)
if err == nil {
if providerList, err := auth.GetProviderConfigurations(ctx, manager); err == nil {
// Show provider/model for the mode we'll be using
var providerDisplay *auth.ProviderDisplay
if bannerInfo.Mode == "plan" && providerList.PlanProvider != nil {
providerDisplay = providerList.PlanProvider
} else if bannerInfo.Mode == "act" && providerList.ActProvider != nil {
providerDisplay = providerList.ActProvider
}
if providerList, err := auth.GetProviderConfigurations(ctx); err == nil {
// Show provider/model for the mode we'll be using
var providerDisplay *auth.ProviderDisplay
if bannerInfo.Mode == "plan" && providerList.PlanProvider != nil {
providerDisplay = providerList.PlanProvider
} else if bannerInfo.Mode == "act" && providerList.ActProvider != nil {
providerDisplay = providerList.ActProvider
}
if providerDisplay != nil {
bannerInfo.Provider = auth.GetProviderIDForEnum(providerDisplay.Provider)
bannerInfo.ModelID = providerDisplay.ModelID
}
if providerDisplay != nil {
bannerInfo.Provider = auth.GetProviderIDForEnum(providerDisplay.Provider)
bannerInfo.ModelID = providerDisplay.ModelID
}
}
@@ -292,25 +284,22 @@ func showSessionBanner(ctx context.Context, instanceAddress, modeFlag string, wo
// isUserReadyToUse checks if the user has completed initial setup
// Returns true if welcomeViewCompleted flag is set OR user is authenticated
// Matches extension logic: welcomeViewCompleted = Boolean(globalState.welcomeViewCompleted || user?.uid)
func isUserReadyToUse(ctx context.Context, instanceAddress string) bool {
manager, err := cli.NewTaskManagerForAddress(ctx, instanceAddress)
func isUserReadyToUse(ctx context.Context) bool {
grpcClient, err := global.GetClientForAddress(ctx, global.Config.CoreAddress)
if err != nil {
return false
}
// Get state
state, err := manager.GetClient().State.GetLatestState(ctx, &cline.EmptyRequest{})
state, err := grpcClient.State.GetLatestState(ctx, &cline.EmptyRequest{})
if err != nil {
return false
}
// Parse state JSON
stateMap := make(map[string]interface{})
if err := json.Unmarshal([]byte(state.StateJson), &stateMap); err != nil {
return false
}
// Check 1: welcomeViewCompleted flag
if welcomeCompleted, ok := stateMap["welcomeViewCompleted"].(bool); ok && welcomeCompleted {
return true
}
+10 -10
View File
@@ -23,7 +23,7 @@ func TestMultiInstanceDefaultUnchanged(t *testing.T) {
if len(out1.CoreInstances) != 1 {
t.Fatalf("expected 1 instance, got %d", len(out1.CoreInstances))
}
firstAddr := out1.CoreInstances[0].Address
firstAddr := out1.CoreInstances[0].CoreAddress
waitForAddressHealthy(t, firstAddr, defaultTimeout)
// Start second instance
@@ -56,29 +56,29 @@ func TestDefaultJsonUpdateAfterRemoval(t *testing.T) {
// Choose second as new default
target := out.CoreInstances[1]
waitForAddressHealthy(t, target.Address, defaultTimeout)
waitForAddressHealthy(t, target.CoreAddress, defaultTimeout)
// Set as default
_ = mustRunCLI(ctx, t, "instance", "use", target.Address)
_ = mustRunCLI(ctx, t, "instance", "use", target.CoreAddress)
// Verify default switched
out = listInstancesJSON(ctx, t)
if out.DefaultInstance != target.Address {
t.Fatalf("default_instance not updated to %s (got %s)", target.Address, out.DefaultInstance)
if out.DefaultInstance != target.CoreAddress {
t.Fatalf("default_instance not updated to %s (got %s)", target.CoreAddress, out.DefaultInstance)
}
// Kill the default instance using runtime PID discovery
corePID := getCorePID(t, target.Address)
corePID := getCorePID(t, target.CoreAddress)
if corePID <= 0 {
t.Fatalf("could not find PID for core process at %s", target.Address)
t.Fatalf("could not find PID for core process at %s", target.CoreAddress)
}
t.Logf("Killing cline-core process PID %d for instance %s", corePID, target.Address)
t.Logf("Killing cline-core process PID %d for instance %s", corePID, target.CoreAddress)
if err := syscall.Kill(corePID, syscall.SIGKILL); err != nil {
t.Fatalf("kill pid %d: %v", corePID, err)
}
// Wait for removal
waitForAddressRemoved(t, target.Address, longTimeout)
waitForAddressRemoved(t, target.CoreAddress, longTimeout)
// Clean up dangling host process (SIGKILL leaves these behind by design)
t.Logf("Cleaning up dangling host process on port %d", target.HostPort())
@@ -91,7 +91,7 @@ func TestDefaultJsonUpdateAfterRemoval(t *testing.T) {
if len(out.CoreInstances) > 0 {
found := false
for _, it := range out.CoreInstances {
if out.DefaultInstance == it.Address {
if out.DefaultInstance == it.CoreAddress {
found = true
break
}
+3 -3
View File
@@ -117,7 +117,7 @@ func listInstancesJSON(ctx context.Context, t *testing.T) common.InstancesOutput
func hasAddress(in common.InstancesOutput, addr string) bool {
for _, it := range in.CoreInstances {
if it.Address == addr {
if it.CoreAddress == addr {
return true
}
}
@@ -126,7 +126,7 @@ func hasAddress(in common.InstancesOutput, addr string) bool {
func getByAddress(in common.InstancesOutput, addr string) (common.CoreInstanceInfo, bool) {
for _, it := range in.CoreInstances {
if it.Address == addr {
if it.CoreAddress == addr {
return it, true
}
}
@@ -313,7 +313,7 @@ func getCorePIDViaRPC(t *testing.T, address string) int {
defer cancel()
// Get client for the address
client, err := global.Clients.GetRegistry().GetClient(ctx, address)
client, err := global.Instances.GetRegistry().GetClient(ctx, address)
if err != nil {
t.Logf("Warning: failed to get client for %s, falling back to lsof: %v", address, err)
return getCorePIDViaLsof(t, address)
+10 -10
View File
@@ -26,7 +26,7 @@ func TestMixedLocalhostVs127Coexist(t *testing.T) {
t.Fatalf("expected at least 1 instance")
}
inst := out.CoreInstances[0]
waitForAddressHealthy(t, inst.Address, defaultTimeout)
waitForAddressHealthy(t, inst.CoreAddress, defaultTimeout)
// Manually add a SQLite entry for the same port but 127.0.0.1 host
addr127 := fmt.Sprintf("127.0.0.1:%d", inst.CorePort())
@@ -37,12 +37,12 @@ func TestMixedLocalhostVs127Coexist(t *testing.T) {
}
// Verify both addresses appear and are healthy
waitForAddressHealthy(t, inst.Address, defaultTimeout)
waitForAddressHealthy(t, inst.CoreAddress, defaultTimeout)
waitForAddressHealthy(t, addr127, defaultTimeout)
out = listInstancesJSON(ctx, t)
if !hasAddress(out, inst.Address) || !hasAddress(out, addr127) {
t.Fatalf("expected both %s and %s present", inst.Address, addr127)
if !hasAddress(out, inst.CoreAddress) || !hasAddress(out, addr127) {
t.Fatalf("expected both %s and %s present", inst.CoreAddress, addr127)
}
}
@@ -58,7 +58,7 @@ func TestStartStopStress(t *testing.T) {
before := listInstancesJSON(ctx, t)
beforeSet := map[string]struct{}{}
for _, it := range before.CoreInstances {
beforeSet[it.Address] = struct{}{}
beforeSet[it.CoreAddress] = struct{}{}
}
// Start a new instance
@@ -69,8 +69,8 @@ func TestStartStopStress(t *testing.T) {
waitFor(t, defaultTimeout, func() (bool, string) {
after := listInstancesJSON(ctx, t)
for _, it := range after.CoreInstances {
if _, ok := beforeSet[it.Address]; !ok {
newAddr = it.Address
if _, ok := beforeSet[it.CoreAddress]; !ok {
newAddr = it.CoreAddress
return true, ""
}
}
@@ -88,12 +88,12 @@ func TestStartStopStress(t *testing.T) {
}
// Get PID using runtime discovery
corePID := getCorePID(t, info.Address)
corePID := getCorePID(t, info.CoreAddress)
if corePID <= 0 {
t.Fatalf("could not find PID for new instance at %s", info.Address)
t.Fatalf("could not find PID for new instance at %s", info.CoreAddress)
}
t.Logf("Killing new instance %s (PID %d) for iteration %d", info.Address, corePID, i)
t.Logf("Killing new instance %s (PID %d) for iteration %d", info.CoreAddress, corePID, i)
if err := syscall.Kill(corePID, syscall.SIGKILL); err != nil {
t.Fatalf("kill pid %d: %v", corePID, err)
}
+1 -1
View File
@@ -55,7 +55,7 @@ func readInstancesFromSQLite(t *testing.T, clineDir string) []common.CoreInstanc
// Create InstanceInfo
info := common.CoreInstanceInfo{
Address: heldBy,
CoreAddress: heldBy,
HostServiceAddress: lockTarget,
Status: grpc_health_v1.HealthCheckResponse_UNKNOWN, // Will be updated by health check
LastSeen: time.Unix(lockedAt/1000, 0), // Convert from milliseconds
+14 -14
View File
@@ -29,7 +29,7 @@ func TestStartAndList(t *testing.T) {
t.Fatalf("expected 1 instance, got %d", len(out.CoreInstances))
}
addr := out.CoreInstances[0].Address
addr := out.CoreInstances[0].CoreAddress
t.Logf("Instance address: %s, status: %s", addr, out.CoreInstances[0].Status)
t.Logf("Waiting for address %s to become healthy...", addr)
@@ -44,8 +44,8 @@ func TestStartAndList(t *testing.T) {
if out.DefaultInstance == "" {
t.Fatalf("default_instance not set")
}
if out.DefaultInstance != out.CoreInstances[0].Address {
t.Fatalf("expected default_instance=%s, got %s", out.CoreInstances[0].Address, out.DefaultInstance)
if out.DefaultInstance != out.CoreInstances[0].CoreAddress {
t.Fatalf("expected default_instance=%s, got %s", out.CoreInstances[0].CoreAddress, out.DefaultInstance)
}
t.Logf("TestStartAndList completed successfully")
@@ -64,7 +64,7 @@ func TestTaskNewDefault(t *testing.T) {
if len(out.CoreInstances) != 1 {
t.Fatalf("expected 1 instance, got %d", len(out.CoreInstances))
}
addr := out.CoreInstances[0].Address
addr := out.CoreInstances[0].CoreAddress
waitForAddressHealthy(t, addr, defaultTimeout)
// Create a new task at default (success is sufficient)
@@ -108,21 +108,21 @@ func TestCrashCleanup(t *testing.T) {
// Test 1: Graceful shutdown (SIGTERM) - should clean up both processes
gracefulTarget := out.CoreInstances[0]
waitForAddressHealthy(t, gracefulTarget.Address, defaultTimeout)
waitForAddressHealthy(t, gracefulTarget.CoreAddress, defaultTimeout)
// Get PID using runtime discovery
gracefulPID := getCorePID(t, gracefulTarget.Address)
gracefulPID := getCorePID(t, gracefulTarget.CoreAddress)
if gracefulPID <= 0 {
t.Fatalf("could not find PID for graceful target at %s", gracefulTarget.Address)
t.Fatalf("could not find PID for graceful target at %s", gracefulTarget.CoreAddress)
}
t.Logf("Testing graceful shutdown (SIGTERM) for instance %s (PID %d)", gracefulTarget.Address, gracefulPID)
t.Logf("Testing graceful shutdown (SIGTERM) for instance %s (PID %d)", gracefulTarget.CoreAddress, gracefulPID)
if err := syscall.Kill(gracefulPID, syscall.SIGTERM); err != nil {
t.Fatalf("kill SIGTERM pid %d: %v", gracefulPID, err)
}
// Wait for registry cleanup
waitForAddressRemoved(t, gracefulTarget.Address, longTimeout)
waitForAddressRemoved(t, gracefulTarget.CoreAddress, longTimeout)
// Verify both core and host ports are freed (no dangling processes)
waitForPortsClosed(t, gracefulTarget.CorePort(), gracefulTarget.HostPort(), defaultTimeout)
@@ -132,21 +132,21 @@ func TestCrashCleanup(t *testing.T) {
// Test 2: Crash cleanup (SIGKILL) - creates dangling host process that we must clean up
crashTarget := out.CoreInstances[1]
waitForAddressHealthy(t, crashTarget.Address, defaultTimeout)
waitForAddressHealthy(t, crashTarget.CoreAddress, defaultTimeout)
// Get PID using runtime discovery
crashPID := getCorePID(t, crashTarget.Address)
crashPID := getCorePID(t, crashTarget.CoreAddress)
if crashPID <= 0 {
t.Fatalf("could not find PID for crash target at %s", crashTarget.Address)
t.Fatalf("could not find PID for crash target at %s", crashTarget.CoreAddress)
}
t.Logf("Testing crash cleanup (SIGKILL) for instance %s (PID %d)", crashTarget.Address, crashPID)
t.Logf("Testing crash cleanup (SIGKILL) for instance %s (PID %d)", crashTarget.CoreAddress, crashPID)
if err := syscall.Kill(crashPID, syscall.SIGKILL); err != nil {
t.Fatalf("kill SIGKILL pid %d: %v", crashPID, err)
}
// Wait for registry cleanup
waitForAddressRemoved(t, crashTarget.Address, longTimeout)
waitForAddressRemoved(t, crashTarget.CoreAddress, longTimeout)
// Verify the instance is removed from SQLite (no file to check anymore)
// The waitForAddressRemoved already confirms the instance is gone from the registry
+58
View File
@@ -298,6 +298,64 @@ cline task view
\f[I]# Start interactive chat with this task\f[R]
cline task chat
.EE
.SH ENVIRONMENT
.TP
\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 patterns before
execution.
When not set, all commands are allowed (backward compatibility).
.RS
.PP
Format:
\f[CR]{"allow": ["pattern1", "pattern2"], "deny": ["pattern3"], "allowRedirects": 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.
.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{"allow": ["npm *", "git *"]}\(aq
\f[I]# Allow development commands but deny dangerous ones\f[R]
export CLINE_COMMAND_PERMISSIONS=\(aq{"allow": ["npm *", "git *", "node *"], "deny": ["rm \-rf *", "sudo *"]}\(aq
\f[I]# Allow file operations with redirects\f[R]
export CLINE_COMMAND_PERMISSIONS=\(aq{"allow": ["cat *", "echo *"], "allowRedirects": true}\(aq
.EE
.RE
.SH ARCHITECTURE
Cline operates on a three\-layer architecture:
.TP
+36
View File
@@ -323,6 +323,42 @@ cline task view
cline task chat
```
# ENVIRONMENT
**CLINE_COMMAND_PERMISSIONS**
: JSON configuration for restricting which shell commands Cline can execute. When set, commands are validated against allow/deny patterns 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}'
```
# ARCHITECTURE
Cline operates on a three-layer architecture:
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "cline",
"version": "1.0.9",
"version": "1.0.10",
"description": "Autonomous coding agent CLI - capable of creating/editing files, running commands, using the browser, and more",
"main": "cline-core.js",
"bin": {
+8 -10
View File
@@ -46,21 +46,21 @@ const (
// It spawns a fresh instance for auth operations and cleans it up when done
func RunAuthFlow(ctx context.Context, args []string) error {
// Spawn a fresh instance for auth operations
instanceInfo, err := global.Clients.StartNewInstance(ctx)
instanceInfo, err := global.Instances.StartNewInstance(ctx)
if err != nil {
return fmt.Errorf("failed to start auth instance: %w", err)
}
// Cleanup when done (success, error, or panic)
defer func() {
verboseLog("Shutting down auth instance at %s", instanceInfo.Address)
if err := global.KillInstanceByAddress(context.Background(), global.Clients.GetRegistry(), instanceInfo.Address); err != nil {
verboseLog("Shutting down auth instance at %s", instanceInfo.CoreAddress)
if err := global.KillInstanceByAddress(context.Background(), global.Instances.GetRegistry(), instanceInfo.CoreAddress); err != nil {
verboseLog("Warning: Failed to kill auth instance: %v", err)
}
}()
// Store instance address in context for all auth handlers to use
authCtx := context.WithValue(ctx, authInstanceAddressKey, instanceInfo.Address)
authCtx := context.WithValue(ctx, authInstanceAddressKey, instanceInfo.CoreAddress)
// Route to existing auth flow
return HandleAuthCommand(authCtx, args)
@@ -108,12 +108,10 @@ func HandleAuthMenuNoArgs(ctx context.Context) error {
// Get current provider config for display
var currentProvider string
var currentModel string
if manager, err := createTaskManager(ctx); err == nil {
if providerList, err := GetProviderConfigurations(ctx, manager); err == nil {
if providerList.ActProvider != nil {
currentProvider = GetProviderDisplayName(providerList.ActProvider.Provider)
currentModel = providerList.ActProvider.ModelID
}
if providerList, err := GetProviderConfigurations(ctx); err == nil {
if providerList.ActProvider != nil {
currentProvider = GetProviderDisplayName(providerList.ActProvider.Provider)
currentModel = providerList.ActProvider.ModelID
}
}
+6 -2
View File
@@ -29,13 +29,17 @@ type ProviderListResult struct {
}
// GetProviderConfigurations retrieves and parses provider configurations from Cline Core state
func GetProviderConfigurations(ctx context.Context, manager *task.Manager) (*ProviderListResult, error) {
func GetProviderConfigurations(ctx context.Context) (*ProviderListResult, error) {
if global.Config.Verbose {
fmt.Println("[DEBUG] Retrieving provider configurations from Cline Core")
}
// Get latest state from Cline Core
state, err := manager.GetClient().State.GetLatestState(ctx, &cline.EmptyRequest{})
grpcClient, err := global.GetDefaultClient(ctx)
if err != nil {
return nil, fmt.Errorf("failed to get provider configs due to unable to get gRPC client: %w", err)
}
state, err := grpcClient.State.GetLatestState(ctx, &cline.EmptyRequest{})
if err != nil {
return nil, fmt.Errorf("failed to get state: %w", err)
}
+5 -6
View File
@@ -215,7 +215,7 @@ func (pw *ProviderWizard) handleAddOcaProvider() error {
// handleListProviders retrieves and displays configured providers
func (pw *ProviderWizard) handleListProviders() error {
result, err := GetProviderConfigurations(pw.ctx, pw.manager)
result, err := GetProviderConfigurations(pw.ctx)
if err != nil {
return fmt.Errorf("failed to retrieve provider configurations: %w", err)
}
@@ -413,7 +413,7 @@ func (pw *ProviderWizard) manualModelEntry(provider cline.ApiProvider) (string,
// handleChangeModel allows changing the model for any configured provider
func (pw *ProviderWizard) handleChangeModel() error {
// Step 1: Get current provider configurations
result, err := GetProviderConfigurations(pw.ctx, pw.manager)
result, err := GetProviderConfigurations(pw.ctx)
if err != nil {
return fmt.Errorf("failed to retrieve provider configurations: %w", err)
}
@@ -585,11 +585,11 @@ func getProviderModelIDFromState(stateData map[string]interface{}, provider clin
return ""
}
// getProviderAPIKeyFromState retrieves the API key for a specific provider from state
// getProviderAPIKeyFromState retrieves the API key for a specific provider from state
func getProviderAPIKeyFromState(stateData map[string]interface{}, provider cline.ApiProvider) string {
// OCA uses account authentication, not API keys. Consider it "present" if authenticated.
if provider == cline.ApiProvider_OCA {
if state, _ := GetLatestOCAState(context.TODO(), 2 * time.Second); state != nil && state.User != nil {
if state, _ := GetLatestOCAState(context.TODO(), 2*time.Second); state != nil && state.User != nil {
// Return a sentinel non-empty string so upstream checks pass.
return "OCA_AUTH_VERIFIED"
}
@@ -648,7 +648,7 @@ func convertMapToOpenRouterModelInfo(data map[string]interface{}) *cline.OpenRou
// handleRemoveProvider allows removing a configured provider by clearing its API key
func (pw *ProviderWizard) handleRemoveProvider() error {
// Step 1: Get current provider configurations
result, err := GetProviderConfigurations(pw.ctx, pw.manager)
result, err := GetProviderConfigurations(pw.ctx)
if err != nil {
return fmt.Errorf("failed to retrieve provider configurations: %w", err)
}
@@ -748,7 +748,6 @@ func (pw *ProviderWizard) clearProviderAPIKey(provider cline.ApiProvider) error
return RemoveProviderPartial(pw.ctx, pw.manager, provider)
}
func signOutOca(ctx context.Context) error {
client, err := global.GetDefaultClient(ctx)
if err != nil {
+3 -3
View File
@@ -40,7 +40,7 @@ func ensureConfigManager(ctx context.Context, address string) error {
}
// Always set the instance we're using as the default
registry := global.Clients.GetRegistry()
registry := global.Instances.GetRegistry()
if err := registry.SetDefaultInstance(instanceAddress); err != nil {
// Log warning but don't fail - this is not critical
fmt.Printf("Warning: failed to set default instance: %v\n", err)
@@ -123,11 +123,11 @@ func setCommand() *cobra.Command {
Use: "set <key=value> [key=value...]",
Aliases: []string{"s"},
Short: "Set configuration variables",
Long: `Set one or more global configuration variables using key=value format.
Long: `Set one or more global configuration variables using key=value format.
This command merges the provided settings with existing values, preserving
unspecified fields. Only the fields you explicitly set will be updated.`,
Args: cobra.MinimumNArgs(1),
Args: cobra.MinimumNArgs(1),
RunE: func(cmd *cobra.Command, args []string) error {
ctx := cmd.Context()
+2 -3
View File
@@ -32,8 +32,8 @@ func NewManager(ctx context.Context, address string) (*Manager, error) {
// Get the actual address being used
clientAddress := address
if address == "" && global.Clients != nil {
clientAddress = global.Clients.GetRegistry().GetDefaultInstance()
if address == "" && global.Instances != nil {
clientAddress = global.Instances.GetRegistry().GetDefaultInstance()
}
return &Manager{
@@ -110,7 +110,6 @@ func (m *Manager) ListSettings(ctx context.Context) error {
"dictationSettings",
"autoCondenseThreshold",
"autoApprovalSettings",
"hooksEnabled",
}
// Render each field using the renderer
+1 -1
View File
@@ -79,7 +79,7 @@ func RenderField(key string, value interface{}, censor bool) error {
"planActSeparateModelsSetting", "enableCheckpointsSetting",
"terminalReuseEnabled", "mcpResponsesCollapsed", "strictPlanModeEnabled",
"useAutoCondense", "yoloModeToggled", "shellIntegrationTimeout",
"terminalOutputLineLimit", "autoCondenseThreshold", "hooksEnabled":
"terminalOutputLineLimit", "autoCondenseThreshold":
fmt.Printf("%s: %s\n", camelToKebab(key), formatValue(value, key, censor))
return nil
@@ -14,21 +14,20 @@ import (
"github.com/cline/grpc-go/cline"
)
// ClineClients manages Cline instances using the new registry system
type ClineClients struct {
registry *ClientRegistry
type ClineInstances struct {
registry *InstanceRegistry
}
// NewClineClients creates a new ClineClients instance
func NewClineClients(configPath string) *ClineClients {
registry := NewClientRegistry(configPath)
return &ClineClients{
// NewClineInstances creates a new ClineInstances instance
func NewClineInstances(configPath string) *ClineInstances {
registry := NewInstanceRegistry(configPath)
return &ClineInstances{
registry: registry,
}
}
// Initialize performs cleanup of stale instances
func (c *ClineClients) Initialize(ctx context.Context) error {
func (c *ClineInstances) Initialize(ctx context.Context) error {
// Clean up stale entries (direct SQLite operations)
_ = c.registry.CleanupStaleInstances(ctx)
@@ -36,7 +35,8 @@ func (c *ClineClients) Initialize(ctx context.Context) error {
}
// StartNewInstance starts a new Cline instance and waits for cline-core to self-register
func (c *ClineClients) StartNewInstance(ctx context.Context, workspaces ...string) (*common.CoreInstanceInfo, error) {
// An "instance" is a pair of cline-core and cline-host processes
func (c *ClineInstances) StartNewInstance(ctx context.Context, workspaces ...string) (*common.CoreInstanceInfo, error) {
// Find available ports
corePort, hostPort, err := common.FindAvailablePortPair()
if err != nil {
@@ -102,7 +102,7 @@ func (c *ClineClients) StartNewInstance(ctx context.Context, workspaces ...strin
if Config.Verbose {
fmt.Println("Services started and registered successfully!")
fmt.Printf(" Address: %s\n", instance.Address)
fmt.Printf(" Address: %s\n", instance.CoreAddress)
fmt.Printf(" Core Port: %d\n", instance.CorePort())
fmt.Printf(" Host Bridge Port: %d\n", instance.HostPort())
fmt.Printf(" Process PID: %d\n", coreCmd.Process.Pid)
@@ -120,7 +120,7 @@ func (c *ClineClients) StartNewInstance(ctx context.Context, workspaces ...strin
}
// StartNewInstanceAtPort starts a new Cline instance at the specified port and waits for self-registration
func (c *ClineClients) StartNewInstanceAtPort(ctx context.Context, corePort int, workspaces ...string) (*common.CoreInstanceInfo, error) {
func (c *ClineInstances) StartNewInstanceAtPort(ctx context.Context, corePort int, workspaces ...string) (*common.CoreInstanceInfo, error) {
// Find available host port (core port + 1000)
hostPort := corePort + 1000
coreAddress := fmt.Sprintf("localhost:%d", corePort)
@@ -189,7 +189,7 @@ func (c *ClineClients) StartNewInstanceAtPort(ctx context.Context, corePort int,
if Config.Verbose {
fmt.Println("Services started and registered successfully!")
fmt.Printf(" Address: %s\n", instance.Address)
fmt.Printf(" Address: %s\n", instance.CoreAddress)
fmt.Printf(" Core Port: %d\n", instance.CorePort())
fmt.Printf(" Host Bridge Port: %d\n", instance.HostPort())
fmt.Printf(" Process PID: %d\n", coreCmd.Process.Pid)
@@ -207,12 +207,12 @@ func (c *ClineClients) StartNewInstanceAtPort(ctx context.Context, corePort int,
}
// GetRegistry returns the client registry
func (c *ClineClients) GetRegistry() *ClientRegistry {
func (c *ClineInstances) GetRegistry() *InstanceRegistry {
return c.registry
}
// EnsureInstanceAtAddress ensures an instance exists at the given address, starting one if needed
func (c *ClineClients) EnsureInstanceAtAddress(ctx context.Context, address string) error {
func (c *ClineInstances) EnsureInstanceAtAddress(ctx context.Context, address string) error {
// Expect host:port everywhere
normalized := address
if normalized == "" {
@@ -230,7 +230,7 @@ func (c *ClineClients) EnsureInstanceAtAddress(ctx context.Context, address stri
return fmt.Errorf("invalid address format %s", address)
}
// Use IPv6-compatible localhost detection
// Use IPv6-compatible localhost detection
if common.IsLocalAddress(host) {
_, err := c.StartNewInstanceAtPort(ctx, port)
if err != nil {
@@ -305,7 +305,7 @@ func startClineHost(hostPort int, workspaces []string) (*exec.Cmd, error) {
}
// KillInstanceByAddress kills a Cline instance by its address
func KillInstanceByAddress(ctx context.Context, registry *ClientRegistry, address string) error {
func KillInstanceByAddress(ctx context.Context, registry *InstanceRegistry, address string) error {
// Check if the instance exists in the registry
_, err := registry.GetInstance(address)
if err != nil {
@@ -355,9 +355,9 @@ func KillInstanceByAddress(ctx context.Context, registry *ClientRegistry, addres
defaultInstance := registry.GetDefaultInstance()
if defaultInstance == address || defaultInstance == "" {
if len(instances) > 0 {
if err := registry.SetDefaultInstance(instances[0].Address); err == nil {
if err := registry.SetDefaultInstance(instances[0].CoreAddress); err == nil {
if Config.Verbose {
fmt.Printf("Updated default instance to: %s\n", instances[0].Address)
fmt.Printf("Updated default instance to: %s\n", instances[0].CoreAddress)
}
}
}
+12 -11
View File
@@ -22,8 +22,8 @@ type GlobalConfig struct {
}
var (
Config *GlobalConfig
Clients *ClineClients
Config *GlobalConfig
Instances *ClineInstances
// Version info - set at build time via ldflags
// Version is the Cline Core version (from root package.json)
@@ -61,11 +61,11 @@ func InitializeGlobalConfig(cfg *GlobalConfig) error {
// Otherwise lipgloss auto-detects terminal capabilities (default behavior)
Config = cfg
Clients = NewClineClients(cfg.ConfigPath)
Instances = NewClineInstances(cfg.ConfigPath)
// Initialize the clients registry
ctx := context.Background()
if err := Clients.Initialize(ctx); err != nil {
if err := Instances.Initialize(ctx); err != nil {
return fmt.Errorf("failed to initialize clients: %w", err)
}
@@ -76,25 +76,25 @@ func InitializeGlobalConfig(cfg *GlobalConfig) error {
func GetDefaultClient(ctx context.Context) (*client.ClineClient, error) {
if Config.CoreAddress != "" && Config.CoreAddress != fmt.Sprintf("localhost:%d", common.DEFAULT_CLINE_CORE_PORT) {
// User specified a specific address, use that
return Clients.GetRegistry().GetClient(ctx, Config.CoreAddress)
return Instances.GetRegistry().GetClient(ctx, Config.CoreAddress)
}
// Use the default instance from registry
return Clients.GetRegistry().GetDefaultClient(ctx)
return Instances.GetRegistry().GetDefaultClient(ctx)
}
// GetClientForAddress returns a client for a specific address
func GetClientForAddress(ctx context.Context, address string) (*client.ClineClient, error) {
return Clients.GetRegistry().GetClient(ctx, address)
return Instances.GetRegistry().GetClient(ctx, address)
}
// EnsureDefaultInstance ensures a default instance exists
func EnsureDefaultInstance(ctx context.Context) error {
if Clients == nil {
if Instances == nil {
return fmt.Errorf("global clients not initialized")
}
registry := Clients.GetRegistry()
registry := Instances.GetRegistry()
// First, check if there are any instances already registered in SQLite
instances := registry.ListInstances()
@@ -108,11 +108,12 @@ func EnsureDefaultInstance(ctx context.Context) error {
if registry.GetDefaultInstance() == "" {
// No instances exist, start a new one
// Note: StartNewInstance will automatically set it as default since it's the first instance
_, err := Clients.StartNewInstance(ctx)
_, err := Instances.StartNewInstance(ctx)
if err != nil {
return fmt.Errorf("failed to start new default instance: %w", err)
}
}
return nil
}
}
+27 -28
View File
@@ -18,28 +18,28 @@ import (
"google.golang.org/grpc/health/grpc_health_v1"
)
// ClientRegistry manages Cline client connections using direct SQLite operations
type ClientRegistry struct {
// InstanceRegistry manages Cline client connections using direct SQLite operations
type InstanceRegistry struct {
lockManager *sqlite.LockManager
configPath string
}
// NewClientRegistry creates a new client registry
func NewClientRegistry(configPath string) *ClientRegistry {
// NewInstanceRegistry creates a new instance registry
func NewInstanceRegistry(configPath string) *InstanceRegistry {
lockManager, err := sqlite.NewLockManager(configPath)
if err != nil {
// Log error but continue - we can still function without SQLite
log.Fatalf("Warning: Failed to initialize SQLite lock manager: %v\n", err)
}
return &ClientRegistry{
return &InstanceRegistry{
lockManager: lockManager,
configPath: configPath,
}
}
// GetDefaultInstance returns the default instance address from settings file
func (r *ClientRegistry) GetDefaultInstance() string {
func (r *InstanceRegistry) GetDefaultInstance() string {
defaultAddr, err := sqlite.GetDefaultInstance(r.configPath)
if err != nil {
return ""
@@ -48,7 +48,7 @@ func (r *ClientRegistry) GetDefaultInstance() string {
}
// SetDefaultInstance sets the default instance (writes default.json)
func (r *ClientRegistry) SetDefaultInstance(address string) error {
func (r *InstanceRegistry) SetDefaultInstance(address string) error {
// Verify the instance exists in SQLite
if r.lockManager != nil {
exists, err := r.lockManager.HasInstanceAtAddress(address)
@@ -64,7 +64,7 @@ func (r *ClientRegistry) SetDefaultInstance(address string) error {
}
// GetInstance returns instance information directly from SQLite
func (r *ClientRegistry) GetInstance(address string) (*common.CoreInstanceInfo, error) {
func (r *InstanceRegistry) GetInstance(address string) (*common.CoreInstanceInfo, error) {
if r.lockManager == nil {
return nil, fmt.Errorf("lock manager not available")
}
@@ -73,7 +73,7 @@ func (r *ClientRegistry) GetInstance(address string) (*common.CoreInstanceInfo,
}
// GetClient returns a connected client for the given address (created on-demand)
func (r *ClientRegistry) GetClient(ctx context.Context, address string) (*client.ClineClient, error) {
func (r *InstanceRegistry) GetClient(ctx context.Context, address string) (*client.ClineClient, error) {
// Verify instance exists in SQLite
if r.lockManager != nil {
exists, err := r.lockManager.HasInstanceAtAddress(address)
@@ -104,7 +104,7 @@ func (r *ClientRegistry) GetClient(ctx context.Context, address string) (*client
}
// GetDefaultClient returns a client for the default instance
func (r *ClientRegistry) GetDefaultClient(ctx context.Context) (*client.ClineClient, error) {
func (r *InstanceRegistry) GetDefaultClient(ctx context.Context) (*client.ClineClient, error) {
defaultAddr := r.GetDefaultInstance()
if defaultAddr == "" {
return nil, fmt.Errorf("no default instance configured")
@@ -117,7 +117,7 @@ func (r *ClientRegistry) GetDefaultClient(ctx context.Context) (*client.ClineCli
// Database is unavailable - Return error instead of attempting cleanup
return nil, fmt.Errorf("cannot verify default instance: database unavailable: %w", err)
}
if !exists {
// Instance doesn't exist in database but config file references it
// This is a stale config - remove it and try to find another instance
@@ -127,14 +127,14 @@ func (r *ClientRegistry) GetDefaultClient(ctx context.Context) (*client.ClineCli
} else {
fmt.Printf("Removed stale default instance config (instance %s not found in database)\n", defaultAddr)
}
// Try to find and set a new default instance
instances := r.ListInstances()
if len(instances) > 0 {
if err := r.EnsureDefaultInstance(instances); err != nil {
return nil, fmt.Errorf("failed to set new default instance: %w", err)
}
// Retry with the new default
newDefaultAddr := r.GetDefaultInstance()
if newDefaultAddr != "" {
@@ -142,7 +142,7 @@ func (r *ClientRegistry) GetDefaultClient(ctx context.Context) (*client.ClineCli
return r.GetClient(ctx, newDefaultAddr)
}
}
return nil, fmt.Errorf("no default instance configured")
}
}
@@ -151,7 +151,7 @@ func (r *ClientRegistry) GetDefaultClient(ctx context.Context) (*client.ClineCli
}
// ListInstances returns all registered instances directly from SQLite
func (r *ClientRegistry) ListInstances() []*common.CoreInstanceInfo {
func (r *InstanceRegistry) ListInstances() []*common.CoreInstanceInfo {
if r.lockManager == nil {
return []*common.CoreInstanceInfo{}
}
@@ -170,7 +170,7 @@ func (r *ClientRegistry) ListInstances() []*common.CoreInstanceInfo {
}
// HasInstanceAtAddress checks if an instance exists at the given address (delegates to SQLite)
func (r *ClientRegistry) HasInstanceAtAddress(address string) bool {
func (r *InstanceRegistry) HasInstanceAtAddress(address string) bool {
if r.lockManager == nil {
return false
}
@@ -185,7 +185,7 @@ func (r *ClientRegistry) HasInstanceAtAddress(address string) bool {
}
// CleanupStaleInstances removes stale instances using direct SQLite operations
func (r *ClientRegistry) CleanupStaleInstances(ctx context.Context) error {
func (r *InstanceRegistry) CleanupStaleInstances(ctx context.Context) error {
if r.lockManager == nil {
return nil
}
@@ -202,15 +202,15 @@ func (r *ClientRegistry) CleanupStaleInstances(ctx context.Context) error {
// Try to gracefully shutdown the paired host process before cleanup
fmt.Printf("Attempting to shutdown dangling host service %s for stale cline core instance %s\n",
instance.HostServiceAddress, instance.Address)
instance.HostServiceAddress, instance.CoreAddress)
r.tryShutdownHostProcess(instance.HostServiceAddress)
// Remove from SQLite database
if err := r.lockManager.RemoveInstanceLock(instance.Address); err != nil {
return fmt.Errorf("failed to remove stale instance %s: %w", instance.Address, err)
if err := r.lockManager.RemoveInstanceLock(instance.CoreAddress); err != nil {
return fmt.Errorf("failed to remove stale instance %s: %w", instance.CoreAddress, err)
}
fmt.Printf("Removed stale instance: %s\n", instance.Address)
fmt.Printf("Removed stale instance: %s\n", instance.CoreAddress)
}
}
@@ -218,8 +218,7 @@ func (r *ClientRegistry) CleanupStaleInstances(ctx context.Context) error {
}
// tryShutdownHostProcess attempts to gracefully shutdown a host process via RPC
// Best effort, don't throw errors i guess
func (r *ClientRegistry) tryShutdownHostProcess(hostServiceAddress string) {
func (r *InstanceRegistry) tryShutdownHostProcess(hostServiceAddress string) {
err := common.RetryOperation(3, 2*time.Second, func() error {
// Create context with timeout
ctx, cancel := context.WithTimeout(context.Background(), 2*time.Second)
@@ -252,7 +251,7 @@ func (r *ClientRegistry) tryShutdownHostProcess(hostServiceAddress string) {
}
// ListInstancesCleaned performs cleanup and returns instances with health checks
func (r *ClientRegistry) ListInstancesCleaned(ctx context.Context) ([]*common.CoreInstanceInfo, error) {
func (r *InstanceRegistry) ListInstancesCleaned(ctx context.Context) ([]*common.CoreInstanceInfo, error) {
// 1. Clean up stale entries (best-effort)
_ = r.CleanupStaleInstances(ctx)
@@ -268,7 +267,7 @@ func (r *ClientRegistry) ListInstancesCleaned(ctx context.Context) ([]*common.Co
}
// EnsureDefaultInstance ensures a default instance is set if instances exist but no default is configured
func (r *ClientRegistry) EnsureDefaultInstance(instances []*common.CoreInstanceInfo) error {
func (r *InstanceRegistry) EnsureDefaultInstance(instances []*common.CoreInstanceInfo) error {
currentDefault := r.GetDefaultInstance()
// If we have no instances, clear any stale default and remove settings file
@@ -283,13 +282,13 @@ func (r *ClientRegistry) EnsureDefaultInstance(instances []*common.CoreInstanceI
// If we have instances but no default, pick the first one
if currentDefault == "" {
return sqlite.SetDefaultInstance(r.configPath, instances[0].Address)
return sqlite.SetDefaultInstance(r.configPath, instances[0].CoreAddress)
}
// Validate current default still exists in the instances
defaultExists := false
for _, instance := range instances {
if instance.Address == currentDefault {
if instance.CoreAddress == currentDefault {
defaultExists = true
break
}
@@ -297,7 +296,7 @@ func (r *ClientRegistry) EnsureDefaultInstance(instances []*common.CoreInstanceI
if !defaultExists {
// Current default doesn't exist, pick a new one from available instances
return sqlite.SetDefaultInstance(r.configPath, instances[0].Address)
return sqlite.SetDefaultInstance(r.configPath, instances[0].CoreAddress)
}
return nil
+25 -25
View File
@@ -92,12 +92,12 @@ func newInstanceKillCommand() *cobra.Command {
return nil
},
RunE: func(cmd *cobra.Command, args []string) error {
if global.Clients == nil {
if global.Instances == nil {
return fmt.Errorf("clients not initialized")
}
ctx := cmd.Context()
registry := global.Clients.GetRegistry()
registry := global.Instances.GetRegistry()
if killAllCLI {
return killAllCLIInstances(ctx, registry)
@@ -112,7 +112,7 @@ func newInstanceKillCommand() *cobra.Command {
return cmd
}
func killAllCLIInstances(ctx context.Context, registry *global.ClientRegistry) error {
func killAllCLIInstances(ctx context.Context, registry *global.InstanceRegistry) error {
// Get all instances from registry
instances, err := registry.ListInstancesCleaned(ctx)
if err != nil {
@@ -135,7 +135,7 @@ func killAllCLIInstances(ctx context.Context, registry *global.ClientRegistry) e
cliInstances = append(cliInstances, instance)
} else {
skippedNonCLI++
fmt.Printf("⊘ Skipping %s instance: %s\n", platform, instance.Address)
fmt.Printf("⊘ Skipping %s instance: %s\n", platform, instance.CoreAddress)
}
}
}
@@ -160,16 +160,16 @@ func killAllCLIInstances(ctx context.Context, registry *global.ClientRegistry) e
// Kill all CLI instances
for _, instance := range cliInstances {
result := killInstanceProcess(ctx, registry, instance.Address)
result := killInstanceProcess(ctx, registry, instance.CoreAddress)
killResults = append(killResults, result)
if result.err != nil {
fmt.Printf("✗ Failed to kill %s: %v\n", instance.Address, result.err)
fmt.Printf("✗ Failed to kill %s: %v\n", instance.CoreAddress, result.err)
} else if result.alreadyDead {
fmt.Printf("⚠ Instance %s appears to be already dead\n", instance.Address)
fmt.Printf("⚠ Instance %s appears to be already dead\n", instance.CoreAddress)
} else {
fmt.Printf("✓ Killed %s (PID %d)\n", instance.Address, result.pid)
killedAddresses[instance.Address] = true
fmt.Printf("✓ Killed %s (PID %d)\n", instance.CoreAddress, result.pid)
killedAddresses[instance.CoreAddress] = true
}
}
@@ -190,8 +190,8 @@ func killAllCLIInstances(ctx context.Context, registry *global.ClientRegistry) e
// Check if any of the killed instances are still in the registry
stillPresent := []string{}
for _, remaining := range remainingInstances {
if killedAddresses[remaining.Address] {
stillPresent = append(stillPresent, remaining.Address)
if killedAddresses[remaining.CoreAddress] {
stillPresent = append(stillPresent, remaining.CoreAddress)
}
}
@@ -247,7 +247,7 @@ type killResult struct {
err error
}
func killInstanceProcess(ctx context.Context, registry *global.ClientRegistry, address string) killResult {
func killInstanceProcess(ctx context.Context, registry *global.InstanceRegistry, address string) killResult {
// Get gRPC client and process info
client, err := registry.GetClient(ctx, address)
if err != nil {
@@ -276,12 +276,12 @@ func newInstanceListCommand() *cobra.Command {
Short: "List all registered Cline instances",
Long: `List all registered Cline instances with their status and connection details.`,
RunE: func(cmd *cobra.Command, args []string) error {
if global.Clients == nil {
if global.Instances == nil {
return fmt.Errorf("clients not initialized")
}
ctx := cmd.Context()
registry := global.Clients.GetRegistry()
registry := global.Instances.GetRegistry()
// Load, cleanup stale local entries, and update health
instances, err := registry.ListInstancesCleaned(ctx)
@@ -310,7 +310,7 @@ func newInstanceListCommand() *cobra.Command {
var rows []instanceRow
for _, instance := range instances {
isDefault := ""
if instance.Address == defaultInstance {
if instance.CoreAddress == defaultInstance {
isDefault = "✓"
}
@@ -324,7 +324,7 @@ func newInstanceListCommand() *cobra.Command {
platform := platformNA
if instance.Status == grpc_health_v1.HealthCheckResponse_SERVING {
// Get PID from core
if client, err := registry.GetClient(ctx, instance.Address); err == nil {
if client, err := registry.GetClient(ctx, instance.CoreAddress); err == nil {
if processInfo, err := client.State.GetProcessInfo(ctx, &cline.EmptyRequest{}); err == nil {
pid = fmt.Sprintf("%d", processInfo.ProcessId)
// Update version from RPC if available
@@ -341,7 +341,7 @@ func newInstanceListCommand() *cobra.Command {
}
rows = append(rows, instanceRow{
address: instance.Address,
address: instance.CoreAddress,
status: instance.Status.String(),
version: instance.Version,
lastSeen: lastSeen,
@@ -428,11 +428,11 @@ func newInstanceDefaultCommand() *cobra.Command {
RunE: func(cmd *cobra.Command, args []string) error {
address := args[0]
if global.Clients == nil {
if global.Instances == nil {
return fmt.Errorf("clients not initialized")
}
registry := global.Clients.GetRegistry()
registry := global.Instances.GetRegistry()
// Verify the instance exists
_, err := registry.GetInstance(address)
@@ -464,34 +464,34 @@ func newInstanceNewCommand() *cobra.Command {
RunE: func(cmd *cobra.Command, args []string) error {
ctx := cmd.Context()
if global.Clients == nil {
if global.Instances == nil {
return fmt.Errorf("clients not initialized")
}
fmt.Println("Starting new Cline instance...")
instance, err := global.Clients.StartNewInstance(ctx)
instance, err := global.Instances.StartNewInstance(ctx)
if err != nil {
return fmt.Errorf("failed to start instance: %w", err)
}
fmt.Printf("Successfully started new instance:\n")
fmt.Printf(" Address: %s\n", instance.Address)
fmt.Printf(" Address: %s\n", instance.CoreAddress)
fmt.Printf(" Core Port: %d\n", instance.CorePort())
fmt.Printf(" Host Bridge Port: %d\n", instance.HostPort())
registry := global.Clients.GetRegistry()
registry := global.Instances.GetRegistry()
// If --default flag provided, set this instance as the default
if setDefault {
if err := registry.SetDefaultInstance(instance.Address); err != nil {
if err := registry.SetDefaultInstance(instance.CoreAddress); err != nil {
fmt.Printf("Warning: Failed to set as default: %v\n", err)
} else {
fmt.Printf(" Status: Set as default instance\n")
}
} else {
// Otherwise, check if EnsureDefaultInstance already set it as default
if registry.GetDefaultInstance() == instance.Address {
if registry.GetDefaultInstance() == instance.CoreAddress {
fmt.Printf(" Status: Default instance\n")
}
}
+72 -1
View File
@@ -348,7 +348,7 @@ func (m *InputModel) handleSubmit() (tea.Model, tea.Cmd) {
return ChangeInputTypeMsg{
InputType: InputTypeFeedback,
Title: "Your feedback",
Placeholder: "/plan or /act to switch modes\nctrl+e to open editor",
Placeholder: "/plan or /act to switch modes\nctrl+e to open editor\nctrl+c to exit",
}
}
}
@@ -547,3 +547,74 @@ func (m *InputModel) openEditor() tea.Cmd {
func (m *InputModel) SetSlashRegistry(registry *slash.Registry) {
m.completion.SetRegistry(registry)
}
// initialPromptWrapper wraps InputModel to capture the submit result for initial task prompts
type initialPromptWrapper struct {
model *InputModel
result string
cancelled bool
}
func (w *initialPromptWrapper) Init() tea.Cmd {
return w.model.Init()
}
func (w *initialPromptWrapper) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
switch msg := msg.(type) {
case InputSubmitMsg:
w.result = msg.Value
clearCodes := w.model.ClearScreen()
if clearCodes != "" {
fmt.Print(clearCodes)
}
return w, tea.Quit
case InputCancelMsg:
w.cancelled = true
clearCodes := w.model.ClearScreen()
if clearCodes != "" {
fmt.Print(clearCodes)
}
return w, tea.Quit
}
// Forward to wrapped model
_, cmd := w.model.Update(msg)
return w, cmd
}
func (w *initialPromptWrapper) View() string {
return w.model.View()
}
// ErrUserAborted is returned when the user cancels the input prompt
var ErrUserAborted = fmt.Errorf("user aborted")
// PromptForInitialTask displays an interactive prompt for the initial task with slash command autocomplete.
// Returns the entered text, or ErrUserAborted if cancelled.
func PromptForInitialTask(title, placeholder, mode string, registry *slash.Registry) (string, error) {
model := NewInputModelWithRegistry(
InputTypeMessage,
title,
placeholder,
mode,
registry,
)
wrapper := &initialPromptWrapper{
model: &model,
}
p := tea.NewProgram(wrapper)
_, err := p.Run()
if err != nil {
return "", fmt.Errorf("input prompt failed: %w", err)
}
if wrapper.cancelled {
return "", ErrUserAborted
}
return strings.TrimSpace(wrapper.result), nil
}
+39 -22
View File
@@ -2,10 +2,11 @@ package slash
import (
"context"
"fmt"
"strings"
"sync"
"github.com/cline/grpc-go/client"
"github.com/cline/cli/pkg/cli/global"
"github.com/cline/grpc-go/cline"
)
@@ -32,25 +33,31 @@ var cliLocalCommands = []Command{
}
// NewRegistry creates a new slash command registry
func NewRegistry() *Registry {
return &Registry{
commands: make([]Command, 0),
func NewRegistry(ctx context.Context) *Registry {
defaultCommands := append([]Command{}, cliLocalCommands...)
r := &Registry{
commands: defaultCommands,
}
r.FetchFromBackend(ctx)
return r
}
// FetchFromBackend fetches available commands from cline-core backend
func (r *Registry) FetchFromBackend(ctx context.Context, c *client.ClineClient) error {
resp, err := c.Slash.GetAvailableSlashCommands(ctx, &cline.EmptyRequest{})
if err != nil {
return err
func (r *Registry) FetchFromBackend(ctx context.Context) error {
grpcClient, err := global.GetDefaultClient(ctx)
if err != nil && global.Config.Verbose {
fmt.Printf("Warning: could not get gRPC client: %v\n", err)
return nil
}
resp, err := grpcClient.Slash.GetAvailableSlashCommands(ctx, &cline.EmptyRequest{})
if err != nil && global.Config.Verbose {
fmt.Printf("Warning: could not get gRPC client: %v\n", err)
return nil
}
r.mu.Lock()
defer r.mu.Unlock()
// Start with CLI-local commands
r.commands = append([]Command{}, cliLocalCommands...)
// Add backend commands (only CLI-compatible ones)
for _, cmd := range resp.Commands {
if cmd.CliCompatible {
@@ -66,17 +73,6 @@ func (r *Registry) FetchFromBackend(ctx context.Context, c *client.ClineClient)
return nil
}
// GetCommands returns all available commands
func (r *Registry) GetCommands() []Command {
r.mu.RLock()
defer r.mu.RUnlock()
// Return a copy to avoid race conditions
result := make([]Command, len(r.commands))
copy(result, r.commands)
return result
}
// GetMatching returns commands that start with the given prefix (case-insensitive)
func (r *Registry) GetMatching(prefix string) []Command {
r.mu.RLock()
@@ -123,3 +119,24 @@ func (r *Registry) HasCommands() bool {
defer r.mu.RUnlock()
return len(r.commands) > 0
}
// ParseModeSwitch checks if message starts with /act or /plan and extracts the mode and remaining message.
// Returns (mode, remainingMessage, isModeSwitch).
// This is a package-level function so it can be used both during initial task creation
// and during interactive input handling.
func ParseModeSwitch(message string) (string, string, bool) {
trimmed := strings.TrimSpace(message)
lower := strings.ToLower(trimmed)
if strings.HasPrefix(lower, "/plan") {
remaining := strings.TrimSpace(trimmed[5:])
return "plan", remaining, true
}
if strings.HasPrefix(lower, "/act") {
remaining := strings.TrimSpace(trimmed[4:])
return "act", remaining, true
}
return "", message, false
}
+7 -7
View File
@@ -19,20 +19,20 @@ import (
// Handles localhost/127.0.0.1 equivalence by returning both forms.
func normalizeAddressVariants(address string) []string {
variants := []string{address}
// Extract host and port
host, port, err := net.SplitHostPort(address)
if err != nil {
return variants
}
// Add the alternate form for localhost/127.0.0.1
if host == "localhost" {
variants = append(variants, net.JoinHostPort("127.0.0.1", port))
} else if host == "127.0.0.1" {
variants = append(variants, net.JoinHostPort("localhost", port))
}
return variants
}
@@ -182,7 +182,7 @@ func (lm *LockManager) GetInstanceInfo(address string) (*common.CoreInstanceInfo
query := common.SelectInstanceLockByHolderSQL
variants := normalizeAddressVariants(address)
var heldBy, lockTarget string
var lockedAt int64
var lastErr error
@@ -193,7 +193,7 @@ func (lm *LockManager) GetInstanceInfo(address string) (*common.CoreInstanceInfo
if err == nil {
// Found it!
return &common.CoreInstanceInfo{
Address: heldBy,
CoreAddress: heldBy,
HostServiceAddress: lockTarget,
Status: grpc_health_v1.HealthCheckResponse_UNKNOWN,
LastSeen: time.Unix(lockedAt/1000, 0),
@@ -204,7 +204,7 @@ func (lm *LockManager) GetInstanceInfo(address string) (*common.CoreInstanceInfo
lastErr = err
}
}
// None of the variants were found
if lastErr != nil {
return nil, fmt.Errorf("failed to query instance: %w", lastErr)
@@ -235,7 +235,7 @@ func (lm *LockManager) ListInstancesWithHealthCheck(ctx context.Context) ([]*com
}
info := &common.CoreInstanceInfo{
Address: lock.HeldBy,
CoreAddress: lock.HeldBy,
HostServiceAddress: lock.LockTarget,
Status: status,
LastSeen: time.Unix(lock.LockedAt/1000, 0),
+5 -10
View File
@@ -80,7 +80,7 @@ func ensureTaskManager(ctx context.Context, address string) error {
}
// Always set the instance we're using as the default
registry := global.Clients.GetRegistry()
registry := global.Instances.GetRegistry()
if err := registry.SetDefaultInstance(instanceAddress); err != nil {
// Log warning but don't fail - this is not critical
fmt.Printf("Warning: failed to set default instance: %v\n", err)
@@ -91,10 +91,10 @@ func ensureTaskManager(ctx context.Context, address string) error {
// ensureInstanceAtAddress ensures an instance exists at the given address
func ensureInstanceAtAddress(ctx context.Context, address string) error {
if global.Clients == nil {
if global.Instances == nil {
return fmt.Errorf("global clients not initialized")
}
return global.Clients.EnsureInstanceAtAddress(ctx, address)
return global.Instances.EnsureInstanceAtAddress(ctx, address)
}
func newTaskNewCommand() *cobra.Command {
@@ -117,7 +117,7 @@ func newTaskNewCommand() *cobra.Command {
ctx := cmd.Context()
// Check if an instance exists when no address specified
if address == "" && global.Clients.GetRegistry().GetDefaultInstance() == "" {
if address == "" && global.Instances.GetRegistry().GetDefaultInstance() == "" {
fmt.Println("No instances available for creating tasks")
return nil
}
@@ -230,7 +230,7 @@ func newTaskSendCommand() *cobra.Command {
ctx := cmd.Context()
// Check if an instance exists when no address specified
if address == "" && global.Clients.GetRegistry().GetDefaultInstance() == "" {
if address == "" && global.Instances.GetRegistry().GetDefaultInstance() == "" {
fmt.Println("No instances available for sending messages")
return nil
}
@@ -620,11 +620,6 @@ func CleanupTaskManager() {
}
}
// NewTaskManagerForAddress is an exported wrapper around task.NewManagerForAddress
func NewTaskManagerForAddress(ctx context.Context, address string) (*task.Manager, error) {
return task.NewManagerForAddress(ctx, address)
}
// CreateAndFollowTask creates a new task and immediately follows it in interactive mode
// This is used by the root command to provide a streamlined UX
func CreateAndFollowTask(ctx context.Context, prompt string, opts TaskOptions) error {
+29 -44
View File
@@ -13,38 +13,41 @@ import (
"github.com/charmbracelet/lipgloss"
"github.com/cline/cli/pkg/cli/global"
"github.com/cline/cli/pkg/cli/output"
"github.com/cline/cli/pkg/cli/slash"
"github.com/cline/cli/pkg/cli/types"
)
// InputHandler manages interactive user input during follow mode
type InputHandler struct {
manager *Manager
coordinator *StreamCoordinator
cancelFunc context.CancelFunc
mu sync.RWMutex
isRunning bool
pollTicker *time.Ticker
program *tea.Program
programRunning bool
programDoneChan chan struct{} // Signals when program actually exits
resultChan chan output.InputSubmitMsg
cancelChan chan struct{}
feedbackApproval bool // Track if we're in feedback after approval
feedbackApproved bool // Track the approval decision
approvalMessage *types.ClineMessage // Store the approval message for determining action
ctx context.Context // Context for restart callback
manager *Manager
coordinator *StreamCoordinator
cancelFunc context.CancelFunc
mu sync.RWMutex
isRunning bool
pollTicker *time.Ticker
program *tea.Program
programRunning bool
programDoneChan chan struct{} // Signals when program actually exits
resultChan chan output.InputSubmitMsg
cancelChan chan struct{}
feedbackApproval bool // Track if we're in feedback after approval
feedbackApproved bool // Track the approval decision
approvalMessage *types.ClineMessage // Store the approval message for determining action
slashCommandRegistry *slash.Registry // Slash command registry for autocomplete
ctx context.Context // Context for restart callback
}
// NewInputHandler creates a new input handler
func NewInputHandler(manager *Manager, coordinator *StreamCoordinator, cancelFunc context.CancelFunc) *InputHandler {
return &InputHandler{
manager: manager,
coordinator: coordinator,
cancelFunc: cancelFunc,
isRunning: false,
pollTicker: time.NewTicker(500 * time.Millisecond),
resultChan: make(chan output.InputSubmitMsg, 1),
cancelChan: make(chan struct{}, 1),
manager: manager,
coordinator: coordinator,
cancelFunc: cancelFunc,
isRunning: false,
pollTicker: time.NewTicker(500 * time.Millisecond),
resultChan: make(chan output.InputSubmitMsg, 1),
slashCommandRegistry: slash.NewRegistry(context.Background()),
cancelChan: make(chan struct{}, 1),
}
}
@@ -163,7 +166,7 @@ func (ih *InputHandler) Start(ctx context.Context, errChan chan error) {
if shouldSend {
// Check for mode switch commands first
newMode, remainingMessage, isModeSwitch := ih.parseModeSwitch(message)
newMode, remainingMessage, isModeSwitch := slash.ParseModeSwitch(message)
if isModeSwitch {
// Create styles for mode switch messages (respect global color profile)
actStyle := lipgloss.NewStyle().Foreground(lipgloss.Color("39")).Bold(true)
@@ -284,9 +287,9 @@ func (ih *InputHandler) promptForInput(ctx context.Context) (string, bool, error
model := output.NewInputModelWithRegistry(
output.InputTypeMessage,
"Cline is ready for your message...",
"/plan or /act to switch modes\nctrl+e to open editor\ntab to autocomplete commands",
"/plan or /act to switch modes\ntab to autocomplete commands\nctrl+e to open editor\nctrl+c to exit",
currentMode,
ih.manager.GetSlashRegistry(),
ih.slashCommandRegistry,
)
return ih.runInputProgram(ctx, model)
@@ -302,7 +305,7 @@ func (ih *InputHandler) promptForApproval(ctx context.Context, msg *types.ClineM
"Let Cline use this tool?",
"",
ih.manager.GetCurrentMode(),
ih.manager.GetSlashRegistry(), // Pass registry for feedback input after approval
ih.slashCommandRegistry,
)
message, shouldSend, err := ih.runInputProgram(ctx, model)
@@ -478,24 +481,6 @@ func (w *inputProgramWrapper) View() string {
return w.model.View()
}
// parseModeSwitch checks if message starts with /act or /plan and extracts the mode and remaining message
func (ih *InputHandler) parseModeSwitch(message string) (string, string, bool) {
trimmed := strings.TrimSpace(message)
lower := strings.ToLower(trimmed)
if strings.HasPrefix(lower, "/plan") {
remaining := strings.TrimSpace(trimmed[5:])
return "plan", remaining, true
}
if strings.HasPrefix(lower, "/act") {
remaining := strings.TrimSpace(trimmed[4:])
return "act", remaining, true
}
return "", message, false
}
// handleSpecialCommand processes special commands like /cancel, /exit
func (ih *InputHandler) handleSpecialCommand(ctx context.Context, message string) bool {
switch strings.ToLower(strings.TrimSpace(message)) {
+7 -34
View File
@@ -14,7 +14,6 @@ import (
"github.com/cline/cli/pkg/cli/display"
"github.com/cline/cli/pkg/cli/global"
"github.com/cline/cli/pkg/cli/handlers"
"github.com/cline/cli/pkg/cli/slash"
"github.com/cline/cli/pkg/cli/types"
"github.com/cline/grpc-go/client"
"github.com/cline/grpc-go/cline"
@@ -38,7 +37,6 @@ type Manager struct {
systemRenderer *display.SystemMessageRenderer
streamingDisplay *display.StreamingDisplay
handlerRegistry *handlers.HandlerRegistry
slashRegistry *slash.Registry
isStreamingMode bool
isInteractive bool
currentMode string // "plan" or "act"
@@ -68,7 +66,6 @@ func NewManager(client *client.ClineClient) *Manager {
systemRenderer: systemRenderer,
streamingDisplay: streamingDisplay,
handlerRegistry: registry,
slashRegistry: slash.NewRegistry(),
currentMode: "plan", // Default mode
}
}
@@ -83,9 +80,6 @@ func NewManagerForAddress(ctx context.Context, address string) (*Manager, error)
manager := NewManager(client)
manager.clientAddress = address
// Fetch slash commands from backend (non-blocking, errors are logged)
manager.fetchSlashCommands(ctx)
return manager, nil
}
@@ -99,29 +93,13 @@ func NewManagerForDefault(ctx context.Context) (*Manager, error) {
manager := NewManager(client)
// Get the default instance address
if global.Clients != nil {
manager.clientAddress = global.Clients.GetRegistry().GetDefaultInstance()
if global.Instances != nil {
manager.clientAddress = global.Instances.GetRegistry().GetDefaultInstance()
}
// Fetch slash commands from backend (non-blocking, errors are logged)
manager.fetchSlashCommands(ctx)
return manager, nil
}
// fetchSlashCommands fetches available slash commands from the backend
// This is non-blocking and errors are logged but don't prevent manager creation
func (m *Manager) fetchSlashCommands(ctx context.Context) {
if err := m.slashRegistry.FetchFromBackend(ctx, m.client); err != nil {
if global.Config.Verbose {
m.renderer.RenderDebug("Failed to fetch slash commands: %v", err)
}
// Non-fatal: CLI-local commands are still available
} else if global.Config.Verbose {
m.renderer.RenderDebug("Loaded %d slash commands", len(m.slashRegistry.GetCommands()))
}
}
// SwitchToInstance switches the manager to use a different Cline instance
func (m *Manager) SwitchToInstance(ctx context.Context, address string) error {
m.mu.Lock()
@@ -1206,11 +1184,11 @@ func (m *Manager) displayMessage(msg *types.ClineMessage, isLast, isPartial bool
m.mu.RUnlock()
dc := &handlers.DisplayContext{
State: m.state,
Renderer: m.renderer,
ToolRenderer: m.toolRenderer,
HookRenderer: m.hookRenderer,
SystemRenderer: m.systemRenderer,
State: m.state,
Renderer: m.renderer,
ToolRenderer: m.toolRenderer,
HookRenderer: m.hookRenderer,
SystemRenderer: m.systemRenderer,
IsLast: isLast,
IsPartial: isPartial,
Verbose: global.Config.Verbose,
@@ -1320,11 +1298,6 @@ func (m *Manager) GetCurrentMode() string {
return m.currentMode
}
// GetSlashRegistry returns the slash command registry
func (m *Manager) GetSlashRegistry() *slash.Registry {
return m.slashRegistry
}
// extractModeFromState extracts the current mode from state JSON
func (m *Manager) extractModeFromState(stateJson string) string {
var rawState map[string]interface{}
-6
View File
@@ -290,12 +290,6 @@ func setSimpleField(settings *cline.Settings, key, value string) error {
return err
}
settings.ActModeAwsBedrockCustomSelected = boolPtr(val)
case "hooks_enabled":
val, err := parseBool(value)
if err != nil {
return err
}
settings.HooksEnabled = boolPtr(val)
case "azure_identity":
val, err := parseBool(value)
if err != nil {
+2 -2
View File
@@ -10,7 +10,7 @@ import (
// This is the canonical definition used across all CLI packages
type CoreInstanceInfo struct {
// Full core address including port
Address string `json:"address"`
CoreAddress string `json:"address"`
// Host bridge service address that core holds (host is ALWAYS running on localhost FYI)
HostServiceAddress string `json:"host_port"`
Status grpc_health_v1.HealthCheckResponse_ServingStatus `json:"status"`
@@ -20,7 +20,7 @@ type CoreInstanceInfo struct {
}
func (c *CoreInstanceInfo) CorePort() int {
_, port, _ := ParseHostPort(c.Address)
_, port, _ := ParseHostPort(c.CoreAddress)
return port
}
-39
View File
@@ -1,39 +0,0 @@
package hostbridge
import (
"log"
"github.com/cline/grpc-go/host"
)
// WatchService implements the host.WatchServiceServer interface
type WatchService struct {
host.UnimplementedWatchServiceServer
coreAddress string
verbose bool
}
// NewWatchService creates a new WatchService
func NewWatchService(coreAddress string, verbose bool) *WatchService {
return &WatchService{
coreAddress: coreAddress,
verbose: verbose,
}
}
// SubscribeToFile subscribes to file change notifications
func (s *WatchService) SubscribeToFile(req *host.SubscribeToFileRequest, stream host.WatchService_SubscribeToFileServer) error {
if s.verbose {
log.Printf("SubscribeToFile called for path: %s", req.GetPath())
}
// For console implementation, we'll just log that we would watch the file
// In a real implementation, we'd use fsnotify or similar to watch file changes
log.Printf("[Cline] Would watch file: %s", req.GetPath())
// Keep the stream open but don't send any events for now
// In a real implementation, we'd send FileChangeEvent messages when files change
<-stream.Context().Done()
return nil
}
+6 -4
View File
@@ -5,6 +5,7 @@ import (
"log"
"os"
"github.com/cline/grpc-go/cline"
"github.com/cline/grpc-go/host"
)
@@ -43,24 +44,25 @@ func (s *WorkspaceService) GetWorkspacePaths(ctx context.Context, req *host.GetW
// SaveOpenDocumentIfDirty saves an open document if it has unsaved changes
func (s *WorkspaceService) SaveOpenDocumentIfDirty(ctx context.Context, req *host.SaveOpenDocumentIfDirtyRequest) (*host.SaveOpenDocumentIfDirtyResponse, error) {
if s.verbose {
log.Printf("SaveOpenDocumentIfDirty called for path: %s", req.GetPath())
log.Printf("SaveOpenDocumentIfDirty called for path: %v", req.FilePath)
}
// For console implementation, we'll assume the document is already saved
// In a real implementation, we'd check if the file has unsaved changes
f := false
return &host.SaveOpenDocumentIfDirtyResponse{
WasSaved: false, // Assume no changes to save
WasSaved: &f, // Assume no changes to save
}, nil
}
// GetDiagnostics returns diagnostic information for a file
func (s *WorkspaceService) GetDiagnostics(ctx context.Context, req *host.GetDiagnosticsRequest) (*host.GetDiagnosticsResponse, error) {
if s.verbose {
log.Printf("GetDiagnostics called for path: %s", req.GetPath())
log.Printf("GetDiagnostics called")
}
// For console implementation, return empty diagnostics
return &host.GetDiagnosticsResponse{
Diagnostics: []*host.Diagnostic{},
FileDiagnostics: []*cline.FileDiagnostics{},
}, nil
}
+7 -4
View File
@@ -104,14 +104,18 @@ func (s *EnvService) Shutdown(ctx context.Context, req *cline.EmptyRequest) (*cl
return &cline.Empty{}, nil
}
func (s *EnvService) isTelemetryEnabled() bool {
// In CLI mode, check the CLINE_TELEMETRY_DISABLED environment variable
return os.Getenv("CLINE_TELEMETRY_DISABLED") != "true"
}
// GetTelemetrySettings returns the telemetry settings for CLI mode
func (s *EnvService) GetTelemetrySettings(ctx context.Context, req *cline.EmptyRequest) (*host.GetTelemetrySettingsResponse, error) {
if s.verbose {
log.Printf("GetTelemetrySettings called")
}
// In CLI mode, check the POSTHOG_TELEMETRY_ENABLED environment variable
telemetryEnabled := os.Getenv("POSTHOG_TELEMETRY_ENABLED") == "true"
telemetryEnabled := s.isTelemetryEnabled()
var setting host.Setting
if telemetryEnabled {
@@ -133,8 +137,7 @@ func (s *EnvService) SubscribeToTelemetrySettings(req *cline.EmptyRequest, strea
log.Printf("SubscribeToTelemetrySettings called")
}
// Send initial telemetry state
telemetryEnabled := os.Getenv("POSTHOG_TELEMETRY_ENABLED") == "true"
telemetryEnabled := s.isTelemetryEnabled()
var setting host.Setting
if telemetryEnabled {
Binary file not shown.

After

Width:  |  Height:  |  Size: 8.9 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 6.2 MiB

+17 -1
View File
@@ -117,7 +117,13 @@
"features/auto-compact",
"features/background-edit",
"features/checkpoints",
"features/cline-rules",
{
"group": "Cline Rules",
"pages": [
"features/cline-rules/overview",
"features/cline-rules/conditional-rules"
]
},
{
"group": "Commands & Shortcuts",
"pages": [
@@ -148,6 +154,7 @@
"features/hooks/samples"
]
},
"features/jupyter-notebooks",
"features/multiroot-workspace",
"features/plan-and-act",
"features/skills",
@@ -198,6 +205,7 @@
"provider-config/anthropic",
"provider-config/claude-code",
"provider-config/openai",
"provider-config/openai-codex",
"provider-config/openrouter",
"provider-config/cerebras",
"provider-config/deepseek",
@@ -422,6 +430,14 @@
{
"source": "/enterprise-solutions/team-management/roles-and-permissions",
"destination": "/enterprise-solutions/team-management/managing-members"
},
{
"source": "/features/cline-rules",
"destination": "/features/cline-rules/overview"
},
{
"source": "/features/conditional-rules",
"destination": "/features/cline-rules/conditional-rules"
}
],
"search": {
-188
View File
@@ -1,188 +0,0 @@
Cline Rules allow you to provide Cline with system-level guidance. Think of them as a persistent way to include context and preferences for your projects or globally for every conversation.
## Creating a Rule
You can create a rule by clicking the `+` button in the Rules tab. This will open a new file in your IDE which you can use to write your rule.
<Frame>
<img src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-rules.png" alt="Create a Rule" />
</Frame>
Once you save the file:
- Your rule will be stored in the `.clinerules/` directory in your project (if it's a Workspace Rule)
- Or in the Global Rules directory (if it's a Global Rule):
### Global Rules Directory Location
The location of your Global Rules directory depends on your operating system:
| Operating System | Default Location | Notes |
|------------------|------------------|-------|
| **Windows** | `Documents\Cline\Rules` | Uses system Documents folder |
| **macOS** | `~/Documents/Cline/Rules` | Uses user Documents folder |
| **Linux/WSL** | `~/Documents/Cline/Rules` | May fall back to `~/Cline/Rules` on some systems |
> **Note for Linux/WSL users**: If you don't find your global rules in `~/Documents/Cline/Rules`, check `~/Cline/Rules` as the location may vary depending on your system configuration and whether the Documents directory exists.
You can also have Cline create a rule for you by using the [`/newrule` slash command](/features/slash-commands/new-rule) in the chat.
```markdown Example Cline Rule Structure [expandable]
# Project Guidelines
## Documentation Requirements
- Update relevant documentation in /docs when modifying features
- Keep README.md in sync with new capabilities
- Maintain changelog entries in CHANGELOG.md
## Architecture Decision Records
Create ADRs in /docs/adr for:
- Major dependency changes
- Architectural pattern changes
- New integration patterns
- Database schema changes
Follow template in /docs/adr/template.md
## Code Style & Patterns
- Generate API clients using OpenAPI Generator
- Use TypeScript axios template
- Place generated code in /src/generated
- Prefer composition over inheritance
- Use repository pattern for data access
- Follow error handling pattern in /src/utils/errors.ts
## Testing Standards
- Unit tests required for business logic
- Integration tests for API endpoints
- E2E tests for critical user flows
```
### Key Benefits
1. **Version Controlled**: The `.clinerules` file becomes part of your project's source code
2. **Team Consistency**: Ensures consistent behavior across all team members
3. **Project-Specific**: Rules and standards tailored to each project's needs
4. **Institutional Knowledge**: Maintains project standards and practices in code
Place the `.clinerules` file in your project's root directory:
```
your-project/
├── .clinerules
├── src/
├── docs/
└── ...
```
Cline's system prompt, on the other hand, is not user-editable ([here's where you can find it](https://github.com/cline/cline/blob/main/src/core/prompts/system.ts)). For a broader look at prompt engineering best practices, check out [this resource](https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview).
### AGENTS.md Standard Support
Cline also supports the [AGENTS.md](https://agents.md/) standard as a fallback
(in addition to Cline Rules) by automatically detecting `AGENTS.md` files in
your workspace root. This allows you to use the same rules file across different AI
coding tools.
```
your-project/
├── AGENTS.md
├── src/
└── ...
```
### Tips for Writing Effective Cline Rules
- Be Clear and Concise: Use simple language and avoid ambiguity.
- Focus on Desired Outcomes: Describe the results you want, not the specific steps.
- Test and Iterate: Experiment to find what works best for your workflow.
### .clinerules/ Folder System
```
your-project/
├── .clinerules/ # Folder containing active rules
│ ├── 01-coding.md # Core coding standards
│ ├── 02-documentation.md # Documentation requirements
│ └── current-sprint.md # Rules specific to current work
├── src/
└── ...
```
Cline automatically processes **all Markdown files** inside the `.clinerules/` directory, combining them into a unified set of rules. The numeric prefixes (optional) help organize files in a logical sequence.
#### Using a Rules Bank
For projects with multiple contexts or teams, maintain a rules bank directory:
```
your-project/
├── .clinerules/ # Active rules - automatically applied
│ ├── 01-coding.md
│ └── client-a.md
├── clinerules-bank/ # Repository of available but inactive rules
│ ├── clients/ # Client-specific rule sets
│ │ ├── client-a.md
│ │ └── client-b.md
│ ├── frameworks/ # Framework-specific rules
│ │ ├── react.md
│ │ └── vue.md
│ └── project-types/ # Project type standards
│ ├── api-service.md
│ └── frontend-app.md
└── ...
```
#### Benefits of the Folder Approach
1. **Contextual Activation**: Copy only relevant rules from the bank to the active folder
2. **Easier Maintenance**: Update individual rule files without affecting others
3. **Team Flexibility**: Different team members can activate rules specific to their current task
4. **Reduced Noise**: Keep the active ruleset focused and relevant
#### Usage Examples
Switch between client projects:
```bash
# Switch to Client B project
rm .clinerules/client-a.md
cp clinerules-bank/clients/client-b.md .clinerules/
```
Adapt to different tech stacks:
```bash
# Frontend React project
cp clinerules-bank/frameworks/react.md .clinerules/
```
#### Implementation Tips
- Keep individual rule files focused on specific concerns
- Use descriptive filenames that clearly indicate the rule's purpose
- Consider git-ignoring the active `.clinerules/` folder while tracking the `clinerules-bank/`
- Create team scripts to quickly activate common rule combinations
The folder system transforms your Cline rules from a static document into a dynamic knowledge system that adapts to your team's changing contexts and requirements.
### Managing Rules with the Toggleable Popover
To make managing both single `.clinerules` files and the folder system even easier, Cline v3.13 introduces a dedicated popover UI directly accessible from the chat interface.
Located conveniently under the chat input field, this popover allows you to:
- **Instantly See Active Rules:** View which global rules (from your user settings) and workspace rules (`.clinerules` file or folder contents) are currently active.
- **Quickly Toggle Rules:** Enable or disable specific rule files within your workspace `.clinerules/` folder with a single click. This is perfect for activating context-specific rules (like `react-rules.md` or `memory-bank.md`) only when needed.
- **Easily Add/Manage Rules:** Quickly create a workspace `.clinerules` file or folder if one doesn't exist, or add new rule files to an existing folder.
This UI significantly simplifies switching contexts and managing different sets of instructions without needing to manually edit files or configurations during a conversation.
<Frame>
<img src="https://storage.googleapis.com/cline_public_images/docs/assets/image%20(1).png" alt="Cline Logo" />
</Frame>
@@ -0,0 +1,267 @@
---
title: "Conditional Rules"
sidebarTitle: "Conditional Rules"
description: "Activate rules automatically based on which files you're working with"
---
Conditional rules let you scope rules to specific parts of your codebase. Rules activate only when you're working with matching files, keeping your context focused and relevant.
For an introduction to Cline Rules, see the [Overview](/features/cline-rules/overview).
- **Without conditionals**: every rule loads for every request.
- **With conditionals**, rules activate only when your current files match their defined scope.
For example, React component rules should appear when you're working with React components, not when you're editing Python or documentation.
## How It Works
Conditional rules use YAML frontmatter at the top of your rule files. When Cline processes a request, it gathers context from your current work (open files, visible tabs, mentioned paths, edited files), evaluates each rule's conditions, and activates matching rules.
<Note>
When a conditional rule activates, you'll see a notification: **"Conditional rules applied: workspace:frontend-rules.md"**
</Note>
## Writing Conditional Rules
Add YAML frontmatter to the top of any rule file in your `.clinerules/` directory:
```yaml
---
paths:
- "src/components/**"
- "src/hooks/**"
---
# React Component Guidelines
When creating or modifying React components:
- Use functional components with React hooks
- Extract reusable logic into custom React hooks
- Keep components focused on a single responsibility
```
The `---` markers delimit the frontmatter. Everything after the closing `---` is your rule content.
### The `paths` Conditional
Currently, `paths` is the supported conditional. It takes an array of glob patterns:
```yaml
---
paths:
- "src/**" # All files under src/
- "*.config.js" # Config files in root
- "packages/*/src/" # Monorepo package sources
---
```
**Glob pattern syntax:**
- `*` matches any characters except `/`
- `**` matches any characters including `/` (recursive)
- `?` matches a single character
- `[abc]` matches any character in the brackets
- `{a,b}` matches either pattern
**Examples:**
| Pattern | Matches |
|---------|---------|
| `src/**/*.ts` | All TypeScript files under `src/` |
| `*.md` | Markdown files in root only |
| `**/*.test.ts` | Test files anywhere in the project |
| `packages/{web,api}/**` | Files in web or api packages |
| `src/components/*.tsx` | TSX files directly in components (not nested) |
### Behavior Details
**Multiple patterns**: A rule activates if any pattern matches any file in your context.
```yaml
---
paths:
- "frontend/**"
- "mobile/**"
---
# Activates when working in frontend OR mobile
```
**No frontmatter**: Rules without frontmatter are always active.
**Empty paths array**: `paths: []` means the rule never activates. Use this to temporarily disable a rule.
**Invalid YAML**: If frontmatter can't be parsed, Cline fails open: the rule activates with raw content visible to help debugging.
## What Counts as "Current Context"
Cline evaluates rules based on:
1. **Your message**: File paths mentioned in your prompt (e.g., "update `src/App.tsx`")
2. **Open tabs**: Files currently open in your editor
3. **Visible files**: Files visible in your active editor panes
4. **Edited files**: Files Cline has created, modified, or deleted during the task
5. **Pending operations**: Files Cline is about to edit
Conditional rules can activate on your first message, when relevant files are open, or mid-task when Cline starts working with matching files.
<Tip>
Be explicit about file paths in your prompts. "Update `src/services/user.ts`" reliably triggers path-based rules; "update the user service" may not.
</Tip>
## Practical Examples
Copy these patterns and adapt them to your project structure.
### Frontend vs Backend Rules
Keep frontend and backend rules separate to avoid noise. Frontend rules only load when working with UI code, backend rules only load when working with API or service code.
```yaml
# .clinerules/frontend.md
---
paths:
- "src/components/**"
- "src/pages/**"
- "src/hooks/**"
---
# Frontend Guidelines
- Use Tailwind CSS for styling
- Prefer server components where possible
- Keep client components small and focused
```
```yaml
# .clinerules/backend.md
---
paths:
- "src/api/**"
- "src/services/**"
- "src/db/**"
---
# Backend Guidelines
- Use dependency injection for services
- All database queries go through repositories
- Return typed errors, not thrown exceptions
```
### Test File Rules
Enforce testing standards automatically. This rule activates only when you're writing or modifying tests, so testing guidance appears exactly when you need it.
```yaml
# .clinerules/testing.md
---
paths:
- "**/*.test.ts"
- "**/*.spec.ts"
- "**/__tests__/**"
---
# Testing Standards
- Use descriptive test names: "should [expected behavior] when [condition]"
- One assertion per test when possible
- Mock external dependencies, not internal modules
- Use factories for test data, not fixtures
```
### Documentation Rules
Apply documentation standards only when editing docs. Prevents style rules from cluttering your context when you're writing code.
```yaml
# .clinerules/docs.md
---
paths:
- "docs/**"
- "**/*.md"
- "**/*.mdx"
---
# Documentation Guidelines
- Use sentence case for headings
- Include code examples for all features
- Keep paragraphs short (3-4 sentences max)
- Link to related documentation
```
## Combining with Rule Toggles
Conditional rules work alongside the rule toggle UI. Toggle off a conditional rule to disable it entirely (it won't activate even if paths match). Toggle on to let it activate when conditions are met.
This provides two levels of control: manual toggles and automatic condition-based activation.
## Tips for Effective Conditional Rules
### Start Broad, Then Narrow
Begin with broader patterns and refine as you learn what works:
```yaml
# Start here
paths:
- "src/**"
# Then narrow down
paths:
- "src/features/auth/**"
```
### Use Descriptive Filenames
Name your rule files to indicate their scope:
```
.clinerules/
├── api-endpoints.md # Rules for API code
├── database-models.md # Rules for DB layer
├── react-components.md # Rules for React
└── universal.md # No frontmatter = always active
```
### Keep Universal Rules Separate
Put always-on rules (coding standards, project conventions) in files without frontmatter. Reserve conditional rules for context-specific guidance.
### Test Your Patterns
Not sure if a pattern matches? Create a simple test rule:
```yaml
---
paths:
- "your/pattern/here/**"
---
TEST: This rule should activate for your/pattern/here files.
```
Then work with a file in that path and check if you see the activation notification.
## Troubleshooting
**Rule not activating:**
- Check that file paths in your context match the glob pattern
- Verify the rule is toggled on in the rules panel
- Ensure YAML frontmatter has proper `---` delimiters
**Rule activating unexpectedly:**
- Review glob patterns: `**` is recursive and may match more than intended
- Check for open files that match the pattern
- File paths mentioned in your message also count as context
**Frontmatter showing in output:**
- YAML couldn't be parsed
- Check for syntax errors (unquoted special characters, improper indentation)
## Related
- [Cline Rules Overview](/features/cline-rules/overview) - Complete rules system guide
- [Skills](/features/skills) - Load instructions on demand with `/skill` command
- [Workflows](/features/slash-commands/workflows/index) - Define explicit task automation
- [@ Mentions](/features/at-mentions/overview) - Add files to context explicitly
- [Understanding Context Management](/prompting/understanding-context-management) - How Cline manages context window
+205
View File
@@ -0,0 +1,205 @@
---
title: "Cline Rules"
sidebarTitle: "Overview"
description: "Add persistent instructions and context to guide Cline's behavior"
---
Cline Rules provide system-level guidance for your projects. Rules persist across conversations, ensuring consistent behavior without repeating instructions in every chat.
## How It Works
Rules are loaded when Cline starts a task. Here's what happens:
**Loading order**: Cline checks for rules in this sequence:
1. `.clinerules/` folder (all `.md` files inside)
2. Single `.clinerules` file
3. `AGENTS.md` file
**Scope precedence**: Workspace rules override global rules when both define the same guidance.
**Multiple files**: When using a `.clinerules/` folder, all Markdown files are combined into one ruleset. Numeric prefixes (like `01-`, `02-`) control the order.
**Conditional activation**: Rules with YAML frontmatter activate only when you're working with matching files. See [Conditional Rules](/features/cline-rules/conditional-rules) for details.
## Supported Rule Files
Cline reads rules from multiple file formats in your workspace root, letting you share rules across different AI coding tools:
| File/Folder | Source | Notes |
|-------------|--------|-------|
| `.clinerules/` | Cline | Folder with `.md` files (recommended) |
| `.cursor/rules/` | Cursor | Folder with `.mdc` files |
| `.windsurf/rules` | Windsurf | Folder with multiple `md` files |
| `AGENTS.md` | Universal | Follows [agents.md](https://agents.md/) standard, searched recursively |
Cline prioritizes `.clinerules` when present. Other formats load only if no `.clinerules` exists (except `AGENTS.md`, which always searches subdirectories). All rules appear in the Rules popover where you can toggle them.
## Creating Rules
Click the `+` button in the Rules tab to create a new rule. This opens a file in your editor where you write your guidance.
<Frame>
<img src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-rules.png" alt="Create a Rule" />
</Frame>
When you save the file, it's stored in:
- **Workspace rules**: `.clinerules/` in your project root
- **Global rules**: Platform-specific location (see table below)
You can also use the [`/newrule` slash command](/features/slash-commands/new-rule) to have Cline generate a rule based on your description.
### Global Rules Location
| Operating System | Default Location |
|------------------|------------------|
| **Windows** | `Documents\Cline\Rules` |
| **macOS** | `~/Documents/Cline/Rules` |
| **Linux/WSL** | `~/Documents/Cline/Rules` or `~/Cline/Rules` |
<Note>
Linux/WSL users: Check both locations if you don't find global rules in `~/Documents/Cline/Rules`.
</Note>
## Managing Rules
The Rules popover (below the chat input) shows active rules and lets you toggle them on or off.
<Frame>
<img src="https://storage.googleapis.com/cline_public_images/docs/assets/image%20(1).png" alt="Rules Popover" />
</Frame>
The popover displays:
- **Global rules**: From your user-level Rules directory
- **Workspace rules**: From `.clinerules/` in your project
Toggle any rule to enable or disable it. Disabled rules won't load, even if they match conditions.
## When to Use Rules
Rules work best for persistent project context:
- **Code standards**: Formatting preferences, naming conventions, project-specific patterns
- **Documentation requirements**: Where to add docs, what format to follow
- **Architecture decisions**: Design patterns, dependency rules, module boundaries
- **Team conventions**: PR processes, branch naming, commit message format
- **Technology constraints**: Required libraries, banned APIs, version requirements
Rules are less effective for:
- One-time instructions (just say it in the chat)
- Complex multi-step workflows (use [Workflows](/features/slash-commands/workflows/index) instead)
- Dynamic decisions that depend on runtime context
## Example Rule
```markdown
# Backend API Guidelines
## Route Handlers
- Use async/await, not callbacks
- Validate request bodies with Zod schemas
- Return typed errors from `src/errors.ts`
- All routes require authentication unless in `publicRoutes` array
## Database Access
- All queries go through repository classes in `src/repositories/`
- Use transactions for multi-table updates
- Never expose raw database errors to clients
## Testing
- Unit tests for business logic in `src/services/`
- Integration tests for route handlers in `src/routes/`
- Mock external APIs, not internal modules
```
This rule provides clear, actionable guidance without explaining obvious concepts or using vague language.
## Using a Folder Structure
For projects with many rules, organize them in a `.clinerules/` folder:
```
your-project/
├── .clinerules/
│ ├── 01-coding-standards.md
│ ├── 02-documentation.md
│ └── 03-testing.md
├── src/
└── ...
```
Cline loads all Markdown files in `.clinerules/` automatically. The numeric prefixes help you control ordering, but they're optional.
### Organizing a Rules Bank
Maintain a separate folder for rules you might need but don't always want active:
```
your-project/
├── .clinerules/ # Active rules
│ ├── 01-coding.md
│ └── client-a.md
├── clinerules-bank/ # Available but inactive
│ ├── clients/
│ │ ├── client-a.md
│ │ └── client-b.md
│ └── frameworks/
│ ├── react.md
│ └── vue.md
└── ...
```
Copy files from the bank to `.clinerules/` when you need them. This keeps your active context lean while maintaining a library of reusable guidance.
Switch contexts with simple file operations:
```bash
# Switch to Client B
rm .clinerules/client-a.md
cp clinerules-bank/clients/client-b.md .clinerules/
```
<Tip>
Consider git-ignoring `.clinerules/` while tracking `clinerules-bank/` so team members can activate the rules relevant to their current work.
</Tip>
## Conditional Rules
Scope rules to specific file patterns using YAML frontmatter. This keeps React guidance out of Python code and backend rules away from frontend work.
```yaml
---
paths:
- "src/components/**"
- "src/hooks/**"
---
# React Guidelines
Use functional components with hooks. Extract reusable logic into custom hooks.
```
This rule activates only when working with files matching those patterns. Read the [Conditional Rules guide](/features/cline-rules/conditional-rules) for pattern syntax, behavior details, and more examples.
## Tips for Effective Rules
**Be specific**: "Use async/await for all database calls" beats "write good async code."
**Show patterns**: Include file paths and real examples. "Follow the error handling in `src/utils/errors.ts`" gives Cline a concrete reference.
**Focus on outcomes**: Describe what you want, not step-by-step instructions. Let Cline figure out how.
**Test and refine**: Start with core standards. Add rules when you find yourself repeating the same feedback.
**Use conditional rules**: Load guidance only when relevant. This keeps context efficient and reduces noise.
## Related
- [Conditional Rules](/features/cline-rules/conditional-rules) - Activate rules based on file patterns
- [Skills](/features/skills) - Load instructions on demand with `/skill` command
- [Workflows](/features/slash-commands/workflows/index) - Define explicit task automation
- [New Rule Slash Command](/features/slash-commands/new-rule) - Generate rules with AI assistance
- [Plan and Act Mode](/features/plan-and-act) - Use different rules for planning vs execution
+112
View File
@@ -0,0 +1,112 @@
---
title: "Jupyter Notebooks"
description: "AI-assisted editing of Jupyter notebooks with cell-level context awareness"
---
# Jupyter Notebooks
Cline provides comprehensive support for Jupyter notebooks (`.ipynb` files), enabling AI-assisted editing with full cell-level context awareness. This feature was developed in collaboration with Amazon to bring AI coding assistance to data science workflows.
## Getting started
Jupyter notebook support is a built-in feature of Cline. To use it, you just need to have the Jupyter notebook extension enabled in VS Code. Once you open any `.ipynb` file, you'll see AI-assisted buttons in your notebook interface.
## How to use
### Generate Cell
Click the sparkle icon (✨) in the notebook toolbar to generate new cells with AI assistance.
![Generate Cell demo](../assets/jupyter-generate-cell.gif)
**How it works:** The AI receives context from surrounding cells, so it understands the variables and imports already in scope. This means you can reference existing DataFrames, functions, and other objects without re-explaining them.
**Example prompt:** "Create a visualization showing the correlation matrix of numeric columns with a heatmap"
The cell is inserted with proper notebook JSON structure, preserving metadata and ready to execute.
### Explain Cell
Click the Explain button in any cell's title bar to get a detailed explanation of what the cell does.
This is useful for:
- Revisiting old notebooks
- Onboarding to a teammate's analysis
- Understanding complex transformations
**How it works:** Cline extracts the full cell context, including outputs, so explanations can reference actual results like column names, row counts, and computed values.
### Improve Cell
Click the Improve button in any cell's title bar to enhance existing cells with AI suggestions.
![Explain and Improve Cell demo](../assets/jupyter-explain-improve-cell.gif)
Use this to:
- Optimize slow pandas operations
- Add error handling
- Refactor for clarity
- Convert loops to vectorized operations
**How it works:** Cline suggests improvements while preserving the cell's position and metadata in the notebook structure. The AI explains what was changed and why.
## How cell context works
Unlike traditional file editing, Jupyter notebooks are JSON documents containing arrays of cells. Each cell has its own type, source content, metadata, execution count, and outputs.
When you use a Jupyter command, Cline extracts structured context that includes:
- **Cell type** (code, markdown, or raw)
- **Source content** as an array of lines
- **Cell metadata** and configuration
- **Execution count** for code cells
- **Outputs** including data, text, and error traces
This structured representation allows the AI to understand not just the code, but its context within the notebook and its actual output.
### JSON structure preservation
Cline is designed to work carefully with the cell JSON structure, aiming to:
- Keep cell boundaries intact
- Preserve execution counts
- Maintain cell metadata
- Keep outputs associated with their source cells
The AI is specifically prompted to preserve notebook structure, though you should always review changes to ensure your notebook format remains correct.
## Keyboard shortcuts
You can bind any of these commands to keyboard shortcuts for faster access:
1. Open VS Code keyboard shortcuts (Cmd/Ctrl + K, Cmd/Ctrl + S)
2. Search for `cline.jupyterGenerateCell`, `cline.jupyterExplainCell`, or `cline.jupyterImproveCell`
3. Assign your preferred key combinations
## Tips for best results
**For Generate Cell:**
- Be specific about what you want the cell to do
- Reference existing variables by name (the AI can see them)
- Mention preferred libraries if you have a preference (e.g., "use seaborn" or "use plotly")
**For Explain Cell:**
- Works best on cells that have been executed (outputs provide additional context)
- Good for complex chained operations like pandas groupby/merge sequences
**For Improve Cell:**
- Mention what aspect you want to improve (performance, readability, error handling)
- The AI will explain the changes it suggests
## Limitations
- Notebook support requires the Jupyter notebook extension to be enabled in VS Code
- Cell context extraction depends on VS Code's notebook API
- Very large notebooks may require more context than some models can handle efficiently
## Related
- [Cline Tools Guide](/exploring-clines-tools/cline-tools-guide) -- Overview of all Cline commands
- [Model Selection Guide](/core-features/model-selection-guide) -- Choosing the right model for your workflow
+19 -2
View File
@@ -25,11 +25,28 @@ The easiest way to get started is with **Cline** as your provider:
## Alternative: Use Another Provider
If you prefer to use your own API keys, you can select from providers like:
If you prefer to use your own accounts or API keys, you have several options:
### Sign in with OpenAI (Recommended)
The easiest way to use OpenAI models is with **OpenAI Codex**—no API keys needed:
1. Select **"OpenAI Codex"** from the API Provider dropdown
2. Click **"Sign in with OpenAI"**
3. Authorize Cline in your browser
4. Choose your model
<Card title="OpenAI Codex Setup Guide" icon="key" href="/provider-config/openai-codex">
See the full setup guide with screenshots and troubleshooting tips.
</Card>
### Other Providers
You can also use API keys with these providers:
- **OpenRouter** - Great value, multiple models
- **Anthropic** - Direct access to Claude models
- **OpenAI** - Access to GPT models
- **OpenAI** - Access to GPT models via API key
- **Google Gemini** - Google's AI models
- **Ollama** - Run models locally on your computer
+2 -2
View File
@@ -103,8 +103,8 @@ Master planning vs. execution for complex tasks
Set project-specific guidelines for consistent results
</Card>
<Card title="Worktrees" href="/features/worktrees" icon="git-branch">
Work on multiple branches simultaneously with parallel Cline sessions
<Card title="Prompting Guide" href="/prompting/prompt-engineering-guide" icon="wand-magic-sparkles">
Learn to write prompts that get the best results
</Card>
</CardGroup>
+1 -3
View File
@@ -99,9 +99,6 @@ Cline explores your codebase and works with you to create comprehensive plans be
<div>
<strong><a href="/features/dictation">Dictation</a></strong> • Speak naturally to Cline for rapid planning and complex requirements
</div>
<div>
<strong><a href="/features/worktrees">Worktrees</a></strong> • Work on multiple branches simultaneously with parallel Cline sessions
</div>
</div>
</Accordion>
@@ -147,3 +144,4 @@ Cline explores your codebase and works with you to create comprehensive plans be
See every file read, every decision considered, every token used. No black box, no surprises.
</Card>
</CardGroup>
-1
View File
@@ -18,7 +18,6 @@ Cerebras delivers the world's fastest AI inference through their revolutionary w
Cline supports the following Cerebras models:
- `zai-glm-4.6` - Fast general-purpose model on Cerebras (up to 1,000 tokens/s). To be deprecated soon.
- `zai-glm-4.7` - Highly capable general-purpose model on Cerebras (up to 1,000 tokens/s), competitive with leading proprietary models on coding tasks.
- `qwen-3-235b-a22b-instruct-2507` - Advanced instruction-following model
- `qwen-3-235b-a22b-thinking-2507` - Reasoning model with step-by-step thinking
+105
View File
@@ -0,0 +1,105 @@
---
title: "OpenAI Codex"
sidebarTitle: "OpenAI Codex"
description: "Connect your OpenAI account to Cline via OAuth for seamless access to OpenAI models."
---
OpenAI Codex lets you connect your OpenAI account directly to Cline using OAuth, meaning you don't need to manage API keys. Simply sign in with your OpenAI account through a one-click browser authentication, and you'll automatically have access to all the models available on your OpenAI plan. No additional configuration required.
<Tip>
If you prefer to use API keys instead, see the [OpenAI (API Key)](/provider-config/openai) provider configuration.
</Tip>
## Prerequisites
- An [OpenAI account](https://platform.openai.com/signup)
- An active OpenAI subscription or API access plan
<Note>
The models available to you depend on your OpenAI account's subscription tier. See [OpenAI's pricing page](https://openai.com/pricing) for details on what's included in each plan.
</Note>
## Connecting Your OpenAI Account
<Steps>
<Step title="Open Cline Settings">
Click the settings gear icon in the top-right corner of the Cline extension.
</Step>
<Step title="Select OpenAI Codex Provider">
Choose **"OpenAI Codex"** from the "API Provider" dropdown menu.
</Step>
<Step title="Sign In with OpenAI">
Click the **"Sign in with OpenAI"** button. This will open a browser window for authentication.
</Step>
<Step title="Authorize Cline">
In the browser window that opens:
1. Sign in to your OpenAI account (if not already signed in)
2. Review the permissions Cline is requesting
3. Click **"Authorize"** to grant access
</Step>
<Step title="Select Your Model">
Once authorized, you'll be returned to Cline. Choose your desired model from the **"Model"** dropdown.
</Step>
</Steps>
<Note>
If a model doesn't appear in your dropdown, it may not be available on your OpenAI subscription tier.
</Note>
For the most current list of available models and their capabilities, see the official [OpenAI Models documentation](https://platform.openai.com/docs/models).
## Managing Your Connection
### Disconnecting Your Account
To disconnect your OpenAI account from Cline:
1. Open Cline Settings
2. With OpenAI Codex selected as the provider, click **"Sign out"**
3. Confirm the disconnection
This removes the OAuth connection. You can reconnect at any time by signing in again.
### Token Refresh
OAuth tokens are automatically refreshed by Cline. If you encounter authentication errors:
1. Try disconnecting and reconnecting your account
2. Ensure your OpenAI account is in good standing
3. Check that your subscription is active
## Troubleshooting
### "Authentication failed" error
- Ensure you're signing in with the correct OpenAI account
- Check that your OpenAI subscription is active
- Try clearing your browser cache and signing in again
### Models not appearing
- The available models depend on your OpenAI subscription tier
- Some models may require specific plan upgrades
- Check [OpenAI's pricing page](https://openai.com/pricing) for model availability by plan
### OAuth window doesn't open
- Check if pop-ups are blocked in your browser
- Try using a different browser
- Ensure you have a stable internet connection
### Connection keeps expiring
- This is rare but can happen if your OpenAI account session expired
- Disconnect and reconnect to refresh your authentication
## Good to Know
Cline only requests the permissions necessary to make API calls on your behalf. Your OpenAI credentials are never stored by Cline.
When using OpenAI Codex, Cline accesses models through your OpenAI/ChatGPT subscription. There is no separate per-token API billing or consumption of OpenAI API credits for this provider; usage and limits are governed by your ChatGPT (or OpenAI account) subscription plan, not by Cline.
## Related Documentation
- [OpenAI (API Key)](/provider-config/openai): Alternative configuration using API keys
- [Model Selection Guide](/core-features/model-selection-guide): Help choosing the right model
-4
View File
@@ -144,10 +144,6 @@ if (process.env.ERROR_SERVICE_API_KEY) {
buildEnvVars["process.env.ERROR_SERVICE_API_KEY"] = JSON.stringify(process.env.ERROR_SERVICE_API_KEY)
}
if (process.env.POSTHOG_TELEMETRY_ENABLED) {
buildEnvVars["process.env.POSTHOG_TELEMETRY_ENABLED"] = JSON.stringify(process.env.POSTHOG_TELEMETRY_ENABLED)
}
// OpenTelemetry configuration (injected at build time from GitHub secrets)
// These provide production defaults that can be overridden at runtime via environment variables
if (process.env.OTEL_TELEMETRY_ENABLED) {
+48 -65
View File
@@ -1,12 +1,12 @@
{
"name": "claude-dev",
"version": "3.51.0",
"version": "3.55.0",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "claude-dev",
"version": "3.51.0",
"version": "3.55.0",
"license": "Apache-2.0",
"dependencies": {
"@anthropic-ai/sdk": "^0.37.0",
@@ -1184,6 +1184,7 @@
"integrity": "sha512-2BCOP7TN8M+gVDj7/ht3hsaO/B/n5oDbiAyyvnRlNOs+u1o+JWNYTQrmpuNp1/Wq2gcFrI01JAW+paEKDMx/CA==",
"dev": true,
"license": "MIT",
"peer": true,
"dependencies": {
"@babel/code-frame": "^7.27.1",
"@babel/generator": "^7.28.3",
@@ -2646,6 +2647,7 @@
"node_modules/@grpc/grpc-js": {
"version": "1.9.15",
"license": "Apache-2.0",
"peer": true,
"dependencies": {
"@grpc/proto-loader": "^0.7.8",
"@types/node": ">=12.12.47"
@@ -3229,6 +3231,7 @@
"resolved": "https://registry.npmjs.org/@modelcontextprotocol/sdk/-/sdk-1.25.1.tgz",
"integrity": "sha512-yO28oVFFC7EBoiKdAn+VqRm+plcfv4v0xp6osG/VsCB0NlPZWi87ajbCZZ8f/RvOFLEu7//rSRmuZZ7lMoe3gQ==",
"license": "MIT",
"peer": true,
"dependencies": {
"@hono/node-server": "^1.19.7",
"ajv": "^8.17.1",
@@ -3297,6 +3300,7 @@
"resolved": "https://registry.npmjs.org/@opentelemetry/api/-/api-1.9.0.tgz",
"integrity": "sha512-3giAOQvZiH5F9bMlMiv8+GSPMeqg0dbaeo58/0SlA9sxSqZhnUtxzX9/2FzyhS9sWQf5S0GJE0AKBrFqjpeYcg==",
"license": "Apache-2.0",
"peer": true,
"engines": {
"node": ">=8.0.0"
}
@@ -4912,8 +4916,7 @@
"optional": true,
"os": [
"android"
],
"peer": true
]
},
"node_modules/@rollup/rollup-android-arm64": {
"version": "4.52.4",
@@ -4926,8 +4929,7 @@
"optional": true,
"os": [
"android"
],
"peer": true
]
},
"node_modules/@rollup/rollup-darwin-arm64": {
"version": "4.52.4",
@@ -4940,8 +4942,7 @@
"optional": true,
"os": [
"darwin"
],
"peer": true
]
},
"node_modules/@rollup/rollup-darwin-x64": {
"version": "4.52.4",
@@ -4954,8 +4955,7 @@
"optional": true,
"os": [
"darwin"
],
"peer": true
]
},
"node_modules/@rollup/rollup-freebsd-arm64": {
"version": "4.52.4",
@@ -4968,8 +4968,7 @@
"optional": true,
"os": [
"freebsd"
],
"peer": true
]
},
"node_modules/@rollup/rollup-freebsd-x64": {
"version": "4.52.4",
@@ -4982,8 +4981,7 @@
"optional": true,
"os": [
"freebsd"
],
"peer": true
]
},
"node_modules/@rollup/rollup-linux-arm-gnueabihf": {
"version": "4.52.4",
@@ -4996,8 +4994,7 @@
"optional": true,
"os": [
"linux"
],
"peer": true
]
},
"node_modules/@rollup/rollup-linux-arm-musleabihf": {
"version": "4.52.4",
@@ -5010,8 +5007,7 @@
"optional": true,
"os": [
"linux"
],
"peer": true
]
},
"node_modules/@rollup/rollup-linux-arm64-gnu": {
"version": "4.52.4",
@@ -5024,8 +5020,7 @@
"optional": true,
"os": [
"linux"
],
"peer": true
]
},
"node_modules/@rollup/rollup-linux-arm64-musl": {
"version": "4.52.4",
@@ -5038,8 +5033,7 @@
"optional": true,
"os": [
"linux"
],
"peer": true
]
},
"node_modules/@rollup/rollup-linux-loong64-gnu": {
"version": "4.52.4",
@@ -5052,8 +5046,7 @@
"optional": true,
"os": [
"linux"
],
"peer": true
]
},
"node_modules/@rollup/rollup-linux-ppc64-gnu": {
"version": "4.52.4",
@@ -5066,8 +5059,7 @@
"optional": true,
"os": [
"linux"
],
"peer": true
]
},
"node_modules/@rollup/rollup-linux-riscv64-gnu": {
"version": "4.52.4",
@@ -5080,8 +5072,7 @@
"optional": true,
"os": [
"linux"
],
"peer": true
]
},
"node_modules/@rollup/rollup-linux-riscv64-musl": {
"version": "4.52.4",
@@ -5094,8 +5085,7 @@
"optional": true,
"os": [
"linux"
],
"peer": true
]
},
"node_modules/@rollup/rollup-linux-s390x-gnu": {
"version": "4.52.4",
@@ -5108,8 +5098,7 @@
"optional": true,
"os": [
"linux"
],
"peer": true
]
},
"node_modules/@rollup/rollup-linux-x64-gnu": {
"version": "4.52.4",
@@ -5122,8 +5111,7 @@
"optional": true,
"os": [
"linux"
],
"peer": true
]
},
"node_modules/@rollup/rollup-linux-x64-musl": {
"version": "4.52.4",
@@ -5136,8 +5124,7 @@
"optional": true,
"os": [
"linux"
],
"peer": true
]
},
"node_modules/@rollup/rollup-openharmony-arm64": {
"version": "4.52.4",
@@ -5150,8 +5137,7 @@
"optional": true,
"os": [
"openharmony"
],
"peer": true
]
},
"node_modules/@rollup/rollup-win32-arm64-msvc": {
"version": "4.52.4",
@@ -5164,8 +5150,7 @@
"optional": true,
"os": [
"win32"
],
"peer": true
]
},
"node_modules/@rollup/rollup-win32-ia32-msvc": {
"version": "4.52.4",
@@ -5178,8 +5163,7 @@
"optional": true,
"os": [
"win32"
],
"peer": true
]
},
"node_modules/@rollup/rollup-win32-x64-gnu": {
"version": "4.52.4",
@@ -5192,8 +5176,7 @@
"optional": true,
"os": [
"win32"
],
"peer": true
]
},
"node_modules/@rollup/rollup-win32-x64-msvc": {
"version": "4.52.4",
@@ -5206,8 +5189,7 @@
"optional": true,
"os": [
"win32"
],
"peer": true
]
},
"node_modules/@sap-ai-sdk/ai-api": {
"version": "2.1.0",
@@ -6770,8 +6752,7 @@
"version": "1.0.8",
"resolved": "https://registry.npmjs.org/@types/estree/-/estree-1.0.8.tgz",
"integrity": "sha512-dWHzHa2WqEXI/O1E9OjrocMTKJl2mSrEolh1Iomrv6U+JuNwaHXsXx9bLu5gG7BUWFIN0skIQJQ/L1rIex4X6w==",
"license": "MIT",
"peer": true
"license": "MIT"
},
"node_modules/@types/get-folder-size": {
"version": "3.0.4",
@@ -6803,6 +6784,7 @@
"resolved": "https://registry.npmjs.org/@types/node/-/node-20.19.21.tgz",
"integrity": "sha512-CsGG2P3I5y48RPMfprQGfy4JPRZ6csfC3ltBZSRItG3ngggmNY/qs2uZKp4p9VbrpqNNSMzUZNFZKzgOGnd/VA==",
"license": "MIT",
"peer": true,
"dependencies": {
"undici-types": "~6.21.0"
}
@@ -7519,6 +7501,7 @@
"resolved": "https://registry.npmjs.org/acorn/-/acorn-8.15.0.tgz",
"integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
"license": "MIT",
"peer": true,
"bin": {
"acorn": "bin/acorn"
},
@@ -8320,6 +8303,7 @@
}
],
"license": "MIT",
"peer": true,
"dependencies": {
"baseline-browser-mapping": "^2.8.3",
"caniuse-lite": "^1.0.30001741",
@@ -8654,9 +8638,9 @@
}
},
"node_modules/cheerio/node_modules/undici": {
"version": "6.22.0",
"resolved": "https://registry.npmjs.org/undici/-/undici-6.22.0.tgz",
"integrity": "sha512-hU/10obOIu62MGYjdskASR3CUAiYaFTtC9Pa6vHyf//mAipSvSQg6od2CnJswq7fvzNS3zJhxoRkgNVaHurWKw==",
"version": "6.23.0",
"resolved": "https://registry.npmjs.org/undici/-/undici-6.23.0.tgz",
"integrity": "sha512-VfQPToRA5FZs/qJxLIinmU59u0r7LXqoJkCzinq3ckNJp3vKEh7jTWN589YQ5+aoAC/TGRLyJLCPKcLQbM8r9g==",
"license": "MIT",
"engines": {
"node": ">=18.17"
@@ -9525,7 +9509,8 @@
},
"node_modules/devtools-protocol": {
"version": "0.0.1342118",
"license": "BSD-3-Clause"
"license": "BSD-3-Clause",
"peer": true
},
"node_modules/diff": {
"version": "5.2.0",
@@ -12476,6 +12461,7 @@
"resolved": "https://registry.npmjs.org/jiti/-/jiti-2.6.1.tgz",
"integrity": "sha512-ekilCSN1jwRvIbgeg/57YFh8qQDNbwDb9xT/qu2DAHbFFZUicIl4ygVaAvzveMhMVr3LnpSKTNnwt8PoOfmKhQ==",
"license": "MIT",
"peer": true,
"bin": {
"jiti": "lib/jiti-cli.mjs"
}
@@ -12709,6 +12695,7 @@
"resolved": "https://registry.npmjs.org/lightningcss/-/lightningcss-1.30.1.tgz",
"integrity": "sha512-xi6IyHML+c9+Q3W0S4fCQJOym42pyurFiJUHEcEyHS0CeKzia4yZDEsLlqOFykxOdHpNy0NmvVO31vcSqAxJCg==",
"license": "MPL-2.0",
"peer": true,
"dependencies": {
"detect-libc": "^2.0.3"
},
@@ -14860,9 +14847,9 @@
}
},
"node_modules/open-graph-scraper/node_modules/undici": {
"version": "6.22.0",
"resolved": "https://registry.npmjs.org/undici/-/undici-6.22.0.tgz",
"integrity": "sha512-hU/10obOIu62MGYjdskASR3CUAiYaFTtC9Pa6vHyf//mAipSvSQg6od2CnJswq7fvzNS3zJhxoRkgNVaHurWKw==",
"version": "6.23.0",
"resolved": "https://registry.npmjs.org/undici/-/undici-6.23.0.tgz",
"integrity": "sha512-VfQPToRA5FZs/qJxLIinmU59u0r7LXqoJkCzinq3ckNJp3vKEh7jTWN589YQ5+aoAC/TGRLyJLCPKcLQbM8r9g==",
"license": "MIT",
"engines": {
"node": ">=18.17"
@@ -15430,6 +15417,7 @@
"resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
"integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
"license": "MIT",
"peer": true,
"engines": {
"node": ">=12"
},
@@ -15611,7 +15599,6 @@
}
],
"license": "MIT",
"peer": true,
"dependencies": {
"nanoid": "^3.3.11",
"picocolors": "^1.1.1",
@@ -15632,7 +15619,6 @@
}
],
"license": "MIT",
"peer": true,
"bin": {
"nanoid": "bin/nanoid.cjs"
},
@@ -16322,7 +16308,6 @@
"resolved": "https://registry.npmjs.org/rollup/-/rollup-4.52.4.tgz",
"integrity": "sha512-CLEVl+MnPAiKh5pl4dEWSyMTpuflgNQiLGhMv8ezD5W/qP8AKvmYpCOKRRNOh7oRKnauBZ4SyeYkMS+1VSyKwQ==",
"license": "MIT",
"peer": true,
"dependencies": {
"@types/estree": "1.0.8"
},
@@ -17800,7 +17785,6 @@
"resolved": "https://registry.npmjs.org/tinyglobby/-/tinyglobby-0.2.15.tgz",
"integrity": "sha512-j2Zq4NyQYG5XMST4cbs02Ak8iJUdxRM0XI5QyxXuZOzKOINmWurp3smXu3y5wDcJrptwpSjgXHzIQxR0omXljQ==",
"license": "MIT",
"peer": true,
"dependencies": {
"fdir": "^6.5.0",
"picomatch": "^4.0.3"
@@ -17817,7 +17801,6 @@
"resolved": "https://registry.npmjs.org/fdir/-/fdir-6.5.0.tgz",
"integrity": "sha512-tIbYtZbucOs0BRGqPJkshJUYdL+SDH7dVM8gjy+ERp3WAUjLEFJE+02kanyHtwjWOnwrKYBiwAmM0p4kLJAnXg==",
"license": "MIT",
"peer": true,
"engines": {
"node": ">=12.0.0"
},
@@ -18178,6 +18161,7 @@
"version": "5.5.3",
"dev": true,
"license": "Apache-2.0",
"peer": true,
"bin": {
"tsc": "bin/tsc",
"tsserver": "bin/tsserver"
@@ -18250,9 +18234,9 @@
"license": "MIT"
},
"node_modules/undici": {
"version": "7.16.0",
"resolved": "https://registry.npmjs.org/undici/-/undici-7.16.0.tgz",
"integrity": "sha512-QEg3HPMll0o3t2ourKwOeUAZ159Kn9mx5pnzHRQO8+Wixmh88YdZRiIwat0iNzNNXn0yoEtXJqFpyW7eM8BV7g==",
"version": "7.19.0",
"resolved": "https://registry.npmjs.org/undici/-/undici-7.19.0.tgz",
"integrity": "sha512-Heho1hJD81YChi+uS2RkSjcVO+EQLmLSyUlHyp7Y/wFbxQaGb4WXVKD073JytrjXJVkSZVzoE2MCSOKugFGtOQ==",
"license": "MIT",
"engines": {
"node": ">=20.18.1"
@@ -18430,7 +18414,6 @@
"resolved": "https://registry.npmjs.org/vite/-/vite-7.2.2.tgz",
"integrity": "sha512-BxAKBWmIbrDgrokdGZH1IgkIk/5mMHDreLDmCJ0qpyJaAteP8NvMhkwr/ZCQNqNH97bw/dANTE9PDzqwJghfMQ==",
"license": "MIT",
"peer": true,
"dependencies": {
"esbuild": "^0.25.0",
"fdir": "^6.5.0",
@@ -18505,7 +18488,6 @@
"resolved": "https://registry.npmjs.org/fdir/-/fdir-6.5.0.tgz",
"integrity": "sha512-tIbYtZbucOs0BRGqPJkshJUYdL+SDH7dVM8gjy+ERp3WAUjLEFJE+02kanyHtwjWOnwrKYBiwAmM0p4kLJAnXg==",
"license": "MIT",
"peer": true,
"engines": {
"node": ">=12.0.0"
},
@@ -19193,6 +19175,7 @@
"node_modules/zod": {
"version": "3.25.76",
"license": "MIT",
"peer": true,
"funding": {
"url": "https://github.com/sponsors/colinhacks"
}
+1 -1
View File
@@ -2,7 +2,7 @@
"name": "claude-dev",
"displayName": "Cline",
"description": "Autonomous coding agent right in your IDE, capable of creating/editing files, running commands, using the browser, and more with your permission every step of the way.",
"version": "3.51.0",
"version": "3.55.0",
"icon": "assets/icons/icon.png",
"engines": {
"vscode": "^1.84.0"
+14
View File
@@ -75,6 +75,19 @@ message McpResourceTemplate {
optional string description = 4;
}
message McpPromptArgument {
string name = 1;
optional string description = 2;
optional bool required = 3;
}
message McpPrompt {
string name = 1;
optional string title = 2;
optional string description = 3;
repeated McpPromptArgument arguments = 4;
}
enum McpServerStatus {
// Protobuf enums (in proto3) must have a zero value defined, which serves as the default if the field isn't explicitly set.
// To align with the required nature of the TypeScript type and avoid an unnecessary UNSPECIFIED state, we map one of the existing statuses to this zero value.
@@ -95,6 +108,7 @@ message McpServer {
optional int32 timeout = 9;
optional bool oauth_required = 10;
optional string oauth_auth_status = 11;
repeated McpPrompt prompts = 12;
}
message McpServers {
+3 -3
View File
@@ -108,7 +108,6 @@ message Secrets {
message Settings {
optional string lite_llm_base_url = 1;
optional bool lite_llm_use_prompt_cache = 2;
map<string, string> open_ai_headers = 3;
optional string anthropic_base_url = 4;
optional string open_router_provider_sorting = 5;
optional string aws_region = 6;
@@ -257,7 +256,6 @@ message Settings {
optional FocusChainSettings focus_chain_settings = 149;
optional string custom_prompt = 150;
optional double auto_condense_threshold = 151;
optional bool hooks_enabled = 152;
optional bool subagents_enabled = 153;
optional bool enable_parallel_tool_calling = 154;
optional bool background_edit_enabled = 155;
@@ -278,6 +276,7 @@ message Settings {
optional int32 open_telemetry_log_batch_timeout = 170;
optional int32 open_telemetry_log_max_queue_size = 171;
optional bool worktrees_enabled = 172;
map<string, string> open_ai_headers = 173;
}
message DictationSettings {
@@ -384,6 +383,8 @@ message UpdateTaskSettingsRequest {
// Message for updating settings
message UpdateSettingsRequest {
reserved 26; // was hooks_enabled (removed - now always enabled on macOS/Linux)
Metadata metadata = 1;
optional ModelsApiConfiguration api_configuration = 2;
optional string telemetry_setting = 3;
@@ -408,7 +409,6 @@ message UpdateSettingsRequest {
optional DictationSettings dictation_settings = 23;
optional double auto_condense_threshold = 24;
optional bool multi_root_enabled = 25;
optional bool hooks_enabled = 26;
optional string vscode_terminal_execution_mode = 27;
optional int32 max_consecutive_mistakes = 28;
optional bool subagents_enabled = 29;
+1
View File
@@ -70,6 +70,7 @@ enum ClineSay {
HOOK_STATUS = 30;
HOOK_OUTPUT_STREAM = 31;
COMMAND_PERMISSION_DENIED = 32;
CONDITIONAL_RULES_APPLIED = 33;
}
// Enum for ClineSayTool tool types
+3
View File
@@ -33,6 +33,9 @@ service EnvService {
// Initiates a graceful shutdown of the host bridge service.
rpc shutdown(cline.EmptyRequest) returns (cline.Empty);
// Logs a debug message to the host environment's log/output console.
rpc debugLog(cline.StringRequest) returns (cline.Empty);
}
message GetHostVersionResponse {
+1 -1
View File
@@ -105,7 +105,7 @@ async function main(): Promise<void> {
console.log("Extracting standalone.zip to extensions directory...")
try {
if (!fs.existsSync(extensionsDir)) {
execSync(`unzip -q "${standaloneZipPath}" -d "${extensionsDir}"`, { stdio: "inherit" })
execSync(`unzip -o -q "${standaloneZipPath}" -d "${extensionsDir}"`, { stdio: "inherit" })
}
console.log(`Successfully extracted standalone.zip to: ${extensionsDir}`)
} catch (error) {
+542
View File
@@ -0,0 +1,542 @@
import { afterEach, beforeEach, describe, it } from "mocha"
import "should"
import fs from "fs/promises"
import os from "os"
import path from "path"
import sinon from "sinon"
import { ClineConfigurationError, ClineEndpoint, ClineEnv, Environment } from "../config"
describe("ClineEndpoint configuration", () => {
let sandbox: sinon.SinonSandbox
let tempDir: string
let originalHomedir: typeof os.homedir
beforeEach(async () => {
sandbox = sinon.createSandbox()
tempDir = path.join(os.tmpdir(), `config-test-${Date.now()}-${Math.random().toString(36).slice(2)}`)
await fs.mkdir(tempDir, { recursive: true })
// Create .cline directory
await fs.mkdir(path.join(tempDir, ".cline"), { recursive: true })
// Stub os.homedir to return our temp directory
originalHomedir = os.homedir
sandbox
.stub(os, "homedir")
.returns(tempDir)
// Reset the singleton state using internal method
;(ClineEndpoint as any)._instance = null
;(ClineEndpoint as any)._initialized = false
})
afterEach(async () => {
sandbox.restore()
// Reset singleton state
;(ClineEndpoint as any)._instance = null
;(ClineEndpoint as any)._initialized = false
try {
await fs.rm(tempDir, { recursive: true, force: true })
} catch {
// Ignore cleanup errors
}
})
describe("valid config parsing", () => {
it("should parse valid endpoints.json with all required fields", async () => {
const validConfig = {
appBaseUrl: "https://app.enterprise.com",
apiBaseUrl: "https://api.enterprise.com",
mcpBaseUrl: "https://mcp.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(validConfig), "utf8")
await ClineEndpoint.initialize()
const config = ClineEndpoint.config
config.appBaseUrl.should.equal("https://app.enterprise.com")
config.apiBaseUrl.should.equal("https://api.enterprise.com")
config.mcpBaseUrl.should.equal("https://mcp.enterprise.com")
config.environment.should.equal(Environment.selfHosted)
})
it("should work without endpoints.json (standard mode)", async () => {
// No endpoints.json file exists
await ClineEndpoint.initialize()
const config = ClineEndpoint.config
config.environment.should.not.equal(Environment.selfHosted)
// Should use production defaults
config.appBaseUrl.should.equal("https://app.cline.bot")
config.apiBaseUrl.should.equal("https://api.cline.bot")
})
it("should accept URLs with ports", async () => {
const validConfig = {
appBaseUrl: "http://localhost:3000",
apiBaseUrl: "http://localhost:7777",
mcpBaseUrl: "http://localhost:8080/mcp",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(validConfig), "utf8")
await ClineEndpoint.initialize()
const config = ClineEndpoint.config
config.appBaseUrl.should.equal("http://localhost:3000")
config.apiBaseUrl.should.equal("http://localhost:7777")
config.mcpBaseUrl.should.equal("http://localhost:8080/mcp")
})
it("should accept URLs with paths", async () => {
const validConfig = {
appBaseUrl: "https://proxy.enterprise.com/cline/app",
apiBaseUrl: "https://proxy.enterprise.com/cline/api",
mcpBaseUrl: "https://proxy.enterprise.com/cline/mcp",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(validConfig), "utf8")
await ClineEndpoint.initialize()
const config = ClineEndpoint.config
config.appBaseUrl.should.equal("https://proxy.enterprise.com/cline/app")
})
})
describe("invalid JSON handling", () => {
it("should throw ClineConfigurationError for invalid JSON syntax", async () => {
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), "{ invalid json }", "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql("Invalid JSON")
}
})
it("should throw ClineConfigurationError for truncated JSON", async () => {
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), '{"appBaseUrl": "https://test.com"', "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql("Invalid JSON")
}
})
it("should throw ClineConfigurationError for empty file", async () => {
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), "", "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
}
})
it("should throw ClineConfigurationError for non-object JSON", async () => {
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), '"just a string"', "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql("must contain a JSON object")
}
})
it("should throw ClineConfigurationError for array JSON", async () => {
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), "[]", "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
// Arrays pass the object check but fail on required fields
error.message.should.containEql("Missing required field")
}
})
it("should throw ClineConfigurationError for null JSON", async () => {
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), "null", "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql("must contain a JSON object")
}
})
})
describe("missing required fields", () => {
it("should throw ClineConfigurationError when appBaseUrl is missing", async () => {
const config = {
apiBaseUrl: "https://api.enterprise.com",
mcpBaseUrl: "https://mcp.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(config), "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql('Missing required field "appBaseUrl"')
}
})
it("should throw ClineConfigurationError when apiBaseUrl is missing", async () => {
const config = {
appBaseUrl: "https://app.enterprise.com",
mcpBaseUrl: "https://mcp.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(config), "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql('Missing required field "apiBaseUrl"')
}
})
it("should throw ClineConfigurationError when mcpBaseUrl is missing", async () => {
const config = {
appBaseUrl: "https://app.enterprise.com",
apiBaseUrl: "https://api.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(config), "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql('Missing required field "mcpBaseUrl"')
}
})
it("should throw ClineConfigurationError when all fields are missing", async () => {
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), "{}", "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql("Missing required field")
}
})
it("should throw ClineConfigurationError when field is null", async () => {
const config = {
appBaseUrl: null,
apiBaseUrl: "https://api.enterprise.com",
mcpBaseUrl: "https://mcp.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(config), "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql('Missing required field "appBaseUrl"')
}
})
it("should throw ClineConfigurationError when field is empty string", async () => {
const config = {
appBaseUrl: "",
apiBaseUrl: "https://api.enterprise.com",
mcpBaseUrl: "https://mcp.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(config), "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql("cannot be empty")
}
})
it("should throw ClineConfigurationError when field is whitespace only", async () => {
const config = {
appBaseUrl: " ",
apiBaseUrl: "https://api.enterprise.com",
mcpBaseUrl: "https://mcp.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(config), "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql("cannot be empty")
}
})
it("should throw ClineConfigurationError when field is non-string", async () => {
const config = {
appBaseUrl: 12345,
apiBaseUrl: "https://api.enterprise.com",
mcpBaseUrl: "https://mcp.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(config), "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql("must be a string")
}
})
})
describe("invalid URL detection", () => {
it("should throw ClineConfigurationError for invalid URL format", async () => {
const config = {
appBaseUrl: "not-a-valid-url",
apiBaseUrl: "https://api.enterprise.com",
mcpBaseUrl: "https://mcp.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(config), "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql("must be a valid URL")
}
})
it("should throw ClineConfigurationError for URL without protocol", async () => {
const config = {
appBaseUrl: "app.enterprise.com",
apiBaseUrl: "https://api.enterprise.com",
mcpBaseUrl: "https://mcp.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(config), "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql("must be a valid URL")
}
})
it("should throw ClineConfigurationError for malformed URL", async () => {
const config = {
appBaseUrl: "https://",
apiBaseUrl: "https://api.enterprise.com",
mcpBaseUrl: "https://mcp.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(config), "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql("must be a valid URL")
}
})
it("should include the invalid URL value in error message", async () => {
const invalidUrl = "definitely-not-a-url"
const config = {
appBaseUrl: invalidUrl,
apiBaseUrl: "https://api.enterprise.com",
mcpBaseUrl: "https://mcp.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(config), "utf8")
try {
await ClineEndpoint.initialize()
throw new Error("Should have thrown")
} catch (error: any) {
error.should.be.instanceof(ClineConfigurationError)
error.message.should.containEql(invalidUrl)
}
})
})
describe("environment switching blocked in self-hosted mode", () => {
it("should throw error when trying to change environment in self-hosted mode", async () => {
const config = {
appBaseUrl: "https://app.enterprise.com",
apiBaseUrl: "https://api.enterprise.com",
mcpBaseUrl: "https://mcp.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(config), "utf8")
await ClineEndpoint.initialize()
// Verify we're in self-hosted mode
ClineEndpoint.config.environment.should.equal(Environment.selfHosted)
// Try to change environment - should throw
try {
ClineEnv.setEnvironment("staging")
throw new Error("Should have thrown")
} catch (error: any) {
error.message.should.containEql("Cannot change environment in on-premise mode")
}
})
it("should throw error for all environment values in self-hosted mode", async () => {
const config = {
appBaseUrl: "https://app.enterprise.com",
apiBaseUrl: "https://api.enterprise.com",
mcpBaseUrl: "https://mcp.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(config), "utf8")
await ClineEndpoint.initialize()
const environments = ["staging", "local", "production", "anything"]
for (const env of environments) {
try {
ClineEnv.setEnvironment(env)
throw new Error(`Should have thrown for environment: ${env}`)
} catch (error: any) {
error.message.should.containEql("Cannot change environment in on-premise mode")
}
}
})
it("should allow environment switching in standard mode", async () => {
// No endpoints.json file - standard mode
await ClineEndpoint.initialize()
// Verify we're NOT in self-hosted mode
ClineEndpoint.config.environment.should.not.equal(Environment.selfHosted)
// Should be able to change environment
ClineEnv.setEnvironment("staging")
ClineEnv.getEnvironment().environment.should.equal("staging")
ClineEnv.setEnvironment("local")
ClineEnv.getEnvironment().environment.should.equal("local")
ClineEnv.setEnvironment("production")
ClineEnv.getEnvironment().environment.should.equal("production")
})
})
describe("self-hosted mode behavior", () => {
it("should report selfHosted environment in self-hosted mode", async () => {
const config = {
appBaseUrl: "https://app.enterprise.com",
apiBaseUrl: "https://api.enterprise.com",
mcpBaseUrl: "https://mcp.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(config), "utf8")
await ClineEndpoint.initialize()
const envConfig = ClineEndpoint.config
envConfig.environment.should.equal(Environment.selfHosted)
})
it("should use custom endpoints from file", async () => {
const customConfig = {
appBaseUrl: "https://custom-app.internal",
apiBaseUrl: "https://custom-api.internal",
mcpBaseUrl: "https://custom-mcp.internal/v1",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(customConfig), "utf8")
await ClineEndpoint.initialize()
const config = ClineEndpoint.config
config.appBaseUrl.should.equal("https://custom-app.internal")
config.apiBaseUrl.should.equal("https://custom-api.internal")
config.mcpBaseUrl.should.equal("https://custom-mcp.internal/v1")
})
})
describe("initialization behavior", () => {
it("should only initialize once", async () => {
await ClineEndpoint.initialize()
ClineEndpoint.isInitialized().should.be.true()
// Second initialize should be a no-op
await ClineEndpoint.initialize()
ClineEndpoint.isInitialized().should.be.true()
})
it("should throw error when accessing config before initialization", async () => {
// Already reset in beforeEach, so accessing should throw
try {
const _ = ClineEndpoint.config
throw new Error("Should have thrown")
} catch (error: any) {
error.message.should.containEql("not initialized")
}
})
})
describe("isSelfHosted() method", () => {
it("should return true when not initialized (safety fallback)", async () => {
// Reset singleton state - already done in beforeEach, not initialized
ClineEndpoint.isInitialized().should.be.false()
ClineEndpoint.isSelfHosted().should.be.true()
})
it("should return true when in self-hosted mode", async () => {
const config = {
appBaseUrl: "https://app.enterprise.com",
apiBaseUrl: "https://api.enterprise.com",
mcpBaseUrl: "https://mcp.enterprise.com",
}
await fs.writeFile(path.join(tempDir, ".cline", "endpoints.json"), JSON.stringify(config), "utf8")
await ClineEndpoint.initialize()
ClineEndpoint.isSelfHosted().should.be.true()
})
it("should return false when in normal mode (no endpoints.json)", async () => {
// No endpoints.json file exists
await ClineEndpoint.initialize()
ClineEndpoint.isSelfHosted().should.be.false()
})
})
})
+20 -10
View File
@@ -2,18 +2,18 @@ import * as vscode from "vscode"
import {
cleanupMcpMarketplaceCatalogFromGlobalState,
migrateCustomInstructionsToGlobalRules,
migrateHooksEnabledToBoolean,
migrateTaskHistoryToFile,
migrateWelcomeViewCompleted,
migrateWorkspaceToGlobalStorage,
} from "./core/storage/state-migrations"
import { WebviewProvider } from "./core/webview"
import { Logger } from "./services/logging/Logger"
import "./utils/path" // necessary to have access to String.prototype.toPosix
import { HostProvider } from "@/hosts/host-provider"
import { Logger } from "@/shared/services/Logger"
import { FileContextTracker } from "./core/context/context-tracking/FileContextTracker"
import { StateManager } from "./core/storage/StateManager"
import { openAiCodexOAuthManager } from "./integrations/openai-codex/oauth"
import { ExtensionRegistryInfo } from "./registry"
import { BannerService } from "./services/banner/BannerService"
import { audioRecordingService } from "./services/dictation/AudioRecordingService"
@@ -26,19 +26,30 @@ import { ShowMessageType } from "./shared/proto/host/window"
import { syncWorker } from "./shared/services/worker/sync"
import { getBlobStoreSettingsFromEnv } from "./shared/services/worker/worker"
import { getLatestAnnouncementId } from "./utils/announcements"
import { openAiCodexOAuthManager } from "./integrations/openai-codex/oauth"
import { arePathsEqual } from "./utils/path"
/**
* Performs intialization for Cline that is common to all platforms.
*
* @param context
* @returns The webview provider
* @throws ClineConfigurationError if endpoints.json exists but is invalid
*/
export async function initialize(context: vscode.ExtensionContext): Promise<WebviewProvider> {
// Configure the shared Logging class to use HostProvider's output channels and debug logger
Logger.subscribe((msg: string) => HostProvider.get().logToChannel(msg)) // File system logging
Logger.subscribe((msg: string) => HostProvider.env.debugLog({ value: msg })) // Host debug logging
// Initialize ClineEndpoint configuration first (reads ~/.cline/endpoints.json if present)
// This must be done before any other code that calls ClineEnv.config()
// Throws ClineConfigurationError if config file exists but is invalid
const { ClineEndpoint } = await import("./config")
await ClineEndpoint.initialize()
try {
await StateManager.initialize(context)
} catch (error) {
console.error("[Controller] CRITICAL: Failed to initialize StateManager - extension may not function properly:", error)
Logger.error("[Controller] CRITICAL: Failed to initialize StateManager - extension may not function properly:", error)
HostProvider.window.showMessage({
type: ShowMessageType.ERROR,
message: "Failed to initialize Cline's application state. Please restart the extension.",
@@ -51,8 +62,10 @@ export async function initialize(context: vscode.ExtensionContext): Promise<Webv
// Set the distinct ID for logging and telemetry
await initializeDistinctId(context)
// Initialize PostHog client provider
PostHogClientProvider.getInstance()
// Initialize PostHog client provider (skip in self-hosted mode)
if (!ClineEndpoint.isSelfHosted()) {
PostHogClientProvider.getInstance()
}
// Setup the external services
await ErrorService.initialize()
@@ -70,9 +83,6 @@ export async function initialize(context: vscode.ExtensionContext): Promise<Webv
// Ensure taskHistory.json exists and migrate legacy state (runs once)
await migrateTaskHistoryToFile(context)
// Migrate hooksEnabled from ClineFeatureSetting to boolean (one-time cleanup)
await migrateHooksEnabledToBoolean(context)
// Clean up MCP marketplace catalog from global state (moved to disk cache)
await cleanupMcpMarketplaceCatalogFromGlobalState(context)
@@ -127,7 +137,7 @@ async function showVersionUpdateAnnouncement(context: vscode.ExtensionContext) {
}
} catch (error) {
const errorMessage = error instanceof Error ? error.message : String(error)
console.error(`Error during post-update actions: ${errorMessage}, Stack trace: ${error.stack}`)
Logger.error(`Error during post-update actions: ${errorMessage}, Stack trace: ${error.stack}`)
}
}
+227 -14
View File
@@ -1,22 +1,38 @@
export enum Environment {
production = "production",
staging = "staging",
local = "local",
}
import * as fs from "fs/promises"
import * as os from "os"
import * as path from "path"
import { Environment, type EnvironmentConfig } from "./shared/config-types"
import { Logger } from "./shared/services/Logger"
export interface EnvironmentConfig {
environment: Environment
export { Environment, type EnvironmentConfig }
/**
* Schema for the endpoints.json configuration file used in on-premise deployments.
* All fields are required and must be valid URLs.
*/
interface EndpointsFileSchema {
appBaseUrl: string
apiBaseUrl: string
mcpBaseUrl: string
}
class ClineEndpoint {
public static instance = new ClineEndpoint()
public static get config() {
return ClineEndpoint.instance.config()
/**
* Error thrown when the Cline configuration file exists but is invalid.
* This error prevents Cline from starting to avoid misconfiguration in enterprise environments.
*/
export class ClineConfigurationError extends Error {
constructor(message: string) {
super(message)
this.name = "ClineConfigurationError"
}
}
class ClineEndpoint {
private static _instance: ClineEndpoint | null = null
private static _initialized = false
// On-premise config loaded from file (null if not on-premise)
private onPremiseConfig: EndpointsFileSchema | null = null
private environment: Environment = Environment.production
private constructor() {
@@ -24,15 +40,189 @@ class ClineEndpoint {
const _env = process?.env?.CLINE_ENVIRONMENT_OVERRIDE || process?.env?.CLINE_ENVIRONMENT
if (_env && Object.values(Environment).includes(_env as Environment)) {
this.environment = _env as Environment
return
}
}
/**
* Initializes the ClineEndpoint singleton.
* Must be called before any other methods.
* Reads the endpoints.json file if it exists and validates its schema.
*
* @throws ClineConfigurationError if the endpoints.json file exists but is invalid
*/
public static async initialize(): Promise<void> {
if (ClineEndpoint._initialized) {
return
}
ClineEndpoint._instance = new ClineEndpoint()
// Try to load on-premise config from file
const endpointsConfig = await ClineEndpoint.loadEndpointsFile()
if (endpointsConfig) {
ClineEndpoint._instance.onPremiseConfig = endpointsConfig
Logger.log("Cline running in self-hosted mode with custom endpoints")
}
ClineEndpoint._initialized = true
}
/**
* Returns true if the ClineEndpoint has been initialized.
*/
public static isInitialized(): boolean {
return ClineEndpoint._initialized
}
/**
* Checks if Cline is running in self-hosted/on-premise mode.
* @returns true if in selfHosted mode, or true if not initialized (safety fallback to prevent accidental external calls)
*/
public static isSelfHosted(): boolean {
// Safety fallback: if not initialized, treat as selfHosted
// to prevent accidental external service calls before configuration is loaded
if (!ClineEndpoint._initialized) {
return true
}
return ClineEndpoint.config.environment === Environment.selfHosted
}
/**
* Returns the singleton instance.
* @throws Error if not initialized
*/
public static get instance(): ClineEndpoint {
if (!ClineEndpoint._initialized || !ClineEndpoint._instance) {
throw new Error("ClineEndpoint not initialized. Call ClineEndpoint.initialize() first.")
}
return ClineEndpoint._instance
}
/**
* Static getter for convenient access to the current configuration.
* @throws Error if not initialized
*/
public static get config(): EnvironmentConfig {
return ClineEndpoint.instance.config()
}
/**
* Returns the path to the endpoints.json configuration file.
* Located at ~/.cline/endpoints.json
*/
private static getEndpointsFilePath(): string {
return path.join(os.homedir(), ".cline", "endpoints.json")
}
/**
* Loads and validates the endpoints.json file.
* @returns The validated endpoints config, or null if the file doesn't exist
* @throws ClineConfigurationError if the file exists but is invalid
*/
private static async loadEndpointsFile(): Promise<EndpointsFileSchema | null> {
const filePath = ClineEndpoint.getEndpointsFilePath()
try {
await fs.access(filePath)
} catch {
// File doesn't exist - not on-premise mode
return null
}
// File exists, must be valid or we fail
try {
const fileContent = await fs.readFile(filePath, "utf8")
let data: unknown
try {
data = JSON.parse(fileContent)
} catch (parseError) {
throw new ClineConfigurationError(
`Invalid JSON in endpoints configuration file (${filePath}): ${parseError instanceof Error ? parseError.message : String(parseError)}`,
)
}
return ClineEndpoint.validateEndpointsSchema(data, filePath)
} catch (error) {
if (error instanceof ClineConfigurationError) {
throw error
}
throw new ClineConfigurationError(
`Failed to read endpoints configuration file (${filePath}): ${error instanceof Error ? error.message : String(error)}`,
)
}
}
/**
* Validates that the provided data matches the EndpointsFileSchema.
* All fields must be present and be valid URLs.
*
* @param data The parsed JSON data to validate
* @param filePath The path to the file (for error messages)
* @returns The validated EndpointsFileSchema
* @throws ClineConfigurationError if validation fails
*/
private static validateEndpointsSchema(data: unknown, filePath: string): EndpointsFileSchema {
if (typeof data !== "object" || data === null) {
throw new ClineConfigurationError(`Endpoints configuration file (${filePath}) must contain a JSON object`)
}
const obj = data as Record<string, unknown>
const requiredFields = ["appBaseUrl", "apiBaseUrl", "mcpBaseUrl"] as const
const result: Partial<EndpointsFileSchema> = {}
for (const field of requiredFields) {
const value = obj[field]
if (value === undefined || value === null) {
throw new ClineConfigurationError(
`Missing required field "${field}" in endpoints configuration file (${filePath})`,
)
}
if (typeof value !== "string") {
throw new ClineConfigurationError(
`Field "${field}" in endpoints configuration file (${filePath}) must be a string`,
)
}
if (!value.trim()) {
throw new ClineConfigurationError(
`Field "${field}" in endpoints configuration file (${filePath}) cannot be empty`,
)
}
// Validate URL format
try {
new URL(value)
} catch {
throw new ClineConfigurationError(
`Field "${field}" in endpoints configuration file (${filePath}) must be a valid URL. Got: "${value}"`,
)
}
result[field] = value
}
return result as EndpointsFileSchema
}
/**
* Returns the current environment configuration.
*/
public config(): EnvironmentConfig {
return this.getEnvironment()
}
/**
* Sets the current environment.
* @throws Error if in on-premise mode (environment switching is disabled)
*/
public setEnvironment(env: string) {
if (this.onPremiseConfig) {
throw new Error("Cannot change environment in on-premise mode. Endpoints are configured via ~/.cline/endpoints.json")
}
switch (env.toLowerCase()) {
case "staging":
this.environment = Environment.staging
@@ -44,10 +234,24 @@ class ClineEndpoint {
this.environment = Environment.production
break
}
console.info("Cline environment updated: ", this.environment)
}
/**
* Returns the current environment configuration.
* If running in on-premise mode, returns the custom endpoints.
*/
public getEnvironment(): EnvironmentConfig {
// On-premise mode: use custom endpoints from file
if (this.onPremiseConfig) {
return {
environment: Environment.selfHosted,
appBaseUrl: this.onPremiseConfig.appBaseUrl,
apiBaseUrl: this.onPremiseConfig.apiBaseUrl,
mcpBaseUrl: this.onPremiseConfig.mcpBaseUrl,
}
}
// Standard mode: use built-in environment URLs
switch (this.environment) {
case Environment.staging:
return {
@@ -79,5 +283,14 @@ class ClineEndpoint {
* Usage:
* - ClineEnv.config() to get the current config.
* - ClineEnv.setEnvironment(Environment.local) to change the environment.
*
* IMPORTANT: ClineEndpoint.initialize() must be called before using ClineEnv.
*/
export const ClineEnv = ClineEndpoint.instance
export const ClineEnv = {
config: () => ClineEndpoint.config,
setEnvironment: (env: string) => ClineEndpoint.instance.setEnvironment(env),
getEnvironment: () => ClineEndpoint.instance.getEnvironment(),
}
// Export the class for initialization
export { ClineEndpoint }
+2 -1
View File
@@ -1,6 +1,7 @@
import { ApiConfiguration, ModelInfo, QwenApiRegions } from "@shared/api"
import { Mode } from "@shared/storage/types"
import { ClineStorageMessage } from "@/shared/messages/content"
import { Logger } from "@/shared/services/Logger"
import { ClineTool } from "@/shared/tools"
import { AIhubmixHandler } from "./providers/aihubmix"
import { AnthropicHandler } from "./providers/anthropic"
@@ -480,7 +481,7 @@ export function buildApiHandler(configuration: ApiConfiguration, mode: Mode): Ap
}
}
} catch (error) {
console.error("buildApiHandler error:", error)
Logger.error("buildApiHandler error:", error)
}
return createHandlerForProvider(apiProvider, options, mode)
+4 -3
View File
@@ -1,6 +1,7 @@
import { AskSageModelId, askSageDefaultModelId, askSageDefaultURL, askSageModels, ModelInfo } from "@shared/api"
import { ClineStorageMessage } from "@/shared/messages/content"
import { fetch } from "@/shared/net"
import { Logger } from "@/shared/services/Logger"
import { ApiHandler, CommonApiHandlerOptions } from ".."
import { withRetry } from "../retry"
import { ApiStream } from "../transform/stream"
@@ -58,7 +59,7 @@ export class AskSageHandler implements ApiHandler {
private apiKey: string
constructor(options: AskSageHandlerOptions) {
console.log("init api url", options.asksageApiUrl, askSageDefaultURL)
Logger.log("init api url", options.asksageApiUrl, askSageDefaultURL)
this.options = options
this.apiKey = options.asksageApiKey || ""
this.apiUrl = options.asksageApiUrl || askSageDefaultURL
@@ -164,7 +165,7 @@ export class AskSageHandler implements ApiHandler {
})
if (!response.ok) {
console.error("Failed to fetch AskSage usage", await response.text())
Logger.error("Failed to fetch AskSage usage", await response.text())
return undefined
}
@@ -177,7 +178,7 @@ export class AskSageHandler implements ApiHandler {
outputTokens: 0,
}
} catch (error) {
console.error("Error fetching AskSage usage:", error)
Logger.error("Error fetching AskSage usage:", error)
return undefined
}
}
+13 -8
View File
@@ -12,6 +12,7 @@ import { BedrockModelId, bedrockDefaultModelId, bedrockModels, CLAUDE_SONNET_1M_
import { calculateApiCostOpenAI, calculateApiCostQwen } from "@utils/cost"
import { ExtensionRegistryInfo } from "@/registry"
import { ClineStorageMessage } from "@/shared/messages/content"
import { Logger } from "@/shared/services/Logger"
import { ApiHandler, CommonApiHandlerOptions } from "../"
import { withRetry } from "../retry"
import { convertToR1Format } from "../transform/r1-format"
@@ -109,9 +110,13 @@ interface ProviderChainOptions {
profile?: string
}
// a special jp inference profile was created for sonnet 4.5
// a special jp inference profile was created for sonnet 4.5 & haiku 4.5
// https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html
const JP_SUPPORTED_CRIS_MODELS = ["anthropic.claude-sonnet-4-5-20250929-v1:0", "anthropic.claude-sonnet-4-5-20250929-v1:0:1m"]
const JP_SUPPORTED_CRIS_MODELS = [
"anthropic.claude-sonnet-4-5-20250929-v1:0",
"anthropic.claude-sonnet-4-5-20250929-v1:0:1m",
"anthropic.claude-haiku-4-5-20251001-v1:0",
]
// https://docs.anthropic.com/en/api/claude-on-amazon-bedrock
export class AwsBedrockHandler implements ApiHandler {
@@ -449,7 +454,7 @@ export class AwsBedrockHandler implements ApiHandler {
}
}
} catch (error) {
console.error("Error parsing Deepseek response chunk:", error)
Logger.error("Error parsing Deepseek response chunk:", error)
// Propagate the error by yielding a text response with error information
yield {
type: "text",
@@ -550,7 +555,7 @@ export class AwsBedrockHandler implements ApiHandler {
for await (const chunk of response.stream) {
// Debug logging to see actual response structure
// console.log("Bedrock chunk:", JSON.stringify(chunk, null, 2))
// Logger.log("Bedrock chunk:", JSON.stringify(chunk, null, 2))
// Handle thinking response in additionalModelResponseFields (LangChain format)
const metadata = chunk.metadata as ExtendedMetadata | undefined
@@ -854,7 +859,7 @@ export class AwsBedrockHandler implements ApiHandler {
}
// Log unsupported content types for debugging
console.warn(`Unsupported content type: ${(item as ContentItem).type}`)
Logger.warn(`Unsupported content type: ${(item as ContentItem).type}`)
return null
})
.filter((item): item is ContentBlock => item !== null)
@@ -912,7 +917,7 @@ export class AwsBedrockHandler implements ApiHandler {
},
}
} catch (error) {
console.error("Failed to process image content:", error)
Logger.error("Failed to process image content:", error)
// Return a text content indicating the error instead of null
// This ensures users are aware of the issue
return {
@@ -1111,7 +1116,7 @@ export class AwsBedrockHandler implements ApiHandler {
}
}
} catch (error) {
console.error("Error with OpenAI model via Converse API:", error)
Logger.error("Error with OpenAI model via Converse API:", error)
// Try to extract more detailed error information
let errorMessage = "Failed to process OpenAI model request"
@@ -1246,7 +1251,7 @@ export class AwsBedrockHandler implements ApiHandler {
}
}
} catch (error) {
console.error("Error with Qwen model via Converse API:", error)
Logger.error("Error with Qwen model via Converse API:", error)
// Try to extract more detailed error information
let errorMessage = "Failed to process Qwen model request"
+3 -2
View File
@@ -112,10 +112,11 @@ export class CerebrasHandler implements ApiHandler {
}
try {
const model = this.getModel()
const stream = await client.chat.completions.create({
model: this.getModel().id,
model: model.id,
messages: cerebrasMessages,
temperature: 0,
temperature: model.info.temperature ?? 0,
stream: true,
max_tokens: CEREBRAS_DEFAULT_MAX_TOKENS,
})
+11 -8
View File
@@ -7,10 +7,10 @@ import { ClineEnv } from "@/config"
import { ClineAccountService } from "@/services/account/ClineAccountService"
import { AuthService } from "@/services/auth/AuthService"
import { buildClineExtraHeaders } from "@/services/EnvUtils"
import { Logger } from "@/services/logging/Logger"
import { CLINE_ACCOUNT_AUTH_ERROR_MESSAGE } from "@/shared/ClineAccount"
import { ClineStorageMessage } from "@/shared/messages/content"
import { fetch, getAxiosSettings } from "@/shared/net"
import { Logger } from "@/shared/services/Logger"
import { ApiHandler, CommonApiHandlerOptions } from "../"
import { withRetry } from "../retry"
import { createOpenRouterStream } from "../transform/openrouter-stream"
@@ -35,10 +35,13 @@ export class ClineHandler implements ApiHandler {
private clineAccountService = ClineAccountService.getInstance()
private _authService: AuthService
private client: OpenAI | undefined
private readonly _baseUrl = ClineEnv.config().apiBaseUrl
lastGenerationId?: string
private lastRequestId?: string
private get _baseUrl(): string {
return ClineEnv.config().apiBaseUrl
}
constructor(options: ClineHandlerOptions) {
this.options = options
this._authService = AuthService.getInstance()
@@ -126,7 +129,7 @@ export class ClineHandler implements ApiHandler {
// openrouter returns an error object instead of the openai sdk throwing an error
if ("error" in chunk) {
const error = chunk.error as OpenRouterErrorResponse["error"]
console.error(`Cline API Error: ${error?.code} - ${error?.message}`)
Logger.error(`Cline API Error: ${error?.code} - ${error?.message}`)
// Include metadata in the error message if available
const metadataStr = error.metadata ? `\nMetadata: ${JSON.stringify(error.metadata, null, 2)}` : ""
throw new Error(`Cline API Error ${error.code}: ${error.message}${metadataStr}`)
@@ -143,7 +146,7 @@ export class ClineHandler implements ApiHandler {
const choiceWithError = choice as any
if (choiceWithError.error) {
const error = choiceWithError.error
console.error(`Cline Mid-Stream Error: ${error.code || error.type || "Unknown"} - ${error.message}`)
Logger.error(`Cline Mid-Stream Error: ${error.code || error.type || "Unknown"} - ${error.message}`)
throw new Error(`Cline Mid-Stream Error: ${error.code || error.type || "Unknown"} - ${error.message}`)
} else {
throw new Error(
@@ -199,7 +202,7 @@ export class ClineHandler implements ApiHandler {
// @ts-ignore-next-line
let totalCost = (chunk.usage.cost || 0) + (chunk.usage.cost_details?.upstream_inference_cost || 0)
if (["x-ai/grok-code-fast-1", "kwaipilot/kat-coder-pro"].includes(this.getModel().id)) {
if (["kwaipilot/kat-coder-pro"].includes(this.getModel().id)) {
totalCost = 0
}
@@ -217,14 +220,14 @@ export class ClineHandler implements ApiHandler {
// Fallback to generation endpoint if usage chunk not returned
if (!didOutputUsage) {
console.warn("Cline API did not return usage chunk, fetching from generation endpoint")
Logger.warn("Cline API did not return usage chunk, fetching from generation endpoint")
const apiStreamUsage = await this.getApiStreamUsage()
if (apiStreamUsage) {
yield apiStreamUsage
}
}
} catch (error) {
console.error("Cline API Error:", error)
Logger.error("Cline API Error:", error)
throw error
}
}
@@ -260,7 +263,7 @@ export class ClineHandler implements ApiHandler {
}
} catch (error) {
// ignore if fails
console.error("Error fetching cline generation details:", error)
Logger.error("Error fetching cline generation details:", error)
}
}
return undefined
+5 -9
View File
@@ -7,7 +7,7 @@ import { fetch } from "@/shared/net"
import { ApiHandler, CommonApiHandlerOptions } from "../"
import { withRetry } from "../retry"
import { convertToOpenAiMessages } from "../transform/openai-format"
import { convertToR1Format } from "../transform/r1-format"
import { addReasoningContent } from "../transform/r1-format"
import { ApiStream } from "../transform/stream"
import { getOpenAIToolParams, ToolCallProcessor } from "../transform/tool-call-processor"
@@ -81,14 +81,10 @@ export class DeepSeekHandler implements ApiHandler {
const isDeepseekReasoner = model.id.includes("deepseek-reasoner")
let openAiMessages: OpenAI.Chat.ChatCompletionMessageParam[] = [
{ role: "system", content: systemPrompt },
...convertToOpenAiMessages(messages),
]
if (isDeepseekReasoner) {
openAiMessages = convertToR1Format([{ role: "user", content: systemPrompt }, ...messages])
}
const convertedMessages = convertToOpenAiMessages(messages)
const openAiMessages: OpenAI.Chat.ChatCompletionMessageParam[] = isDeepseekReasoner
? [{ role: "system", content: systemPrompt }, ...addReasoningContent(convertedMessages, messages)]
: [{ role: "system", content: systemPrompt }, ...convertedMessages]
const stream = await client.chat.completions.create({
model: model.id,
+38 -37
View File
@@ -1,5 +1,6 @@
import { ClineStorageMessage } from "@/shared/messages/content"
import { fetch } from "@/shared/net"
import { Logger } from "@/shared/services/Logger"
import { ModelInfo } from "../../../shared/api"
import { ApiHandler } from "../index"
import { ApiStream } from "../transform/stream"
@@ -84,7 +85,7 @@ export class DifyHandler implements ApiHandler {
this.apiKey = options.difyApiKey || ""
this.baseUrl = options.difyBaseUrl || ""
console.log("[DIFY DEBUG] Constructor called with:", {
Logger.log("[DIFY DEBUG] Constructor called with:", {
hasApiKey: !!this.apiKey,
baseUrl: this.baseUrl,
})
@@ -98,7 +99,7 @@ export class DifyHandler implements ApiHandler {
}
async *createMessage(systemPrompt: string, messages: ClineStorageMessage[]): ApiStream {
console.log("[DIFY DEBUG] createMessage called with:", {
Logger.log("[DIFY DEBUG] createMessage called with:", {
systemPromptLength: systemPrompt?.length || 0,
messagesCount: messages?.length || 0,
})
@@ -115,8 +116,8 @@ export class DifyHandler implements ApiHandler {
}
const fullUrl = `${this.baseUrl}/chat-messages`
console.log("[DIFY DEBUG] Making request to:", fullUrl)
console.log("[DIFY DEBUG] Request body:", JSON.stringify(requestBody, null, 2))
Logger.log("[DIFY DEBUG] Making request to:", fullUrl)
Logger.log("[DIFY DEBUG] Request body:", JSON.stringify(requestBody, null, 2))
let response: Response
try {
@@ -129,21 +130,21 @@ export class DifyHandler implements ApiHandler {
body: JSON.stringify(requestBody),
})
} catch (error: any) {
console.error("[DIFY DEBUG] Network error during fetch:", error)
Logger.error("[DIFY DEBUG] Network error during fetch:", error)
const cause = error.cause ? ` | Cause: ${error.cause}` : ""
throw new Error(`Dify API network error: ${error.message}${cause}`)
}
console.log("[DIFY DEBUG] Response status:", response.status)
Logger.log("[DIFY DEBUG] Response status:", response.status)
const headersObj: Record<string, string> = {}
response.headers.forEach((value, key) => {
headersObj[key] = value
})
console.log("[DIFY DEBUG] Response headers:", headersObj)
Logger.log("[DIFY DEBUG] Response headers:", headersObj)
if (!response.ok) {
const errorText = await response.text()
console.error("[DIFY DEBUG] Error response:", errorText)
Logger.error("[DIFY DEBUG] Error response:", errorText)
throw new Error(`Dify API error: ${response.status} ${response.statusText} - ${errorText}`)
}
@@ -159,14 +160,14 @@ export class DifyHandler implements ApiHandler {
const processedEvents: string[] = []
let lastEventTime = Date.now()
console.log("[DIFY DEBUG] Starting to read streaming response...")
Logger.log("[DIFY DEBUG] Starting to read streaming response...")
try {
while (true) {
const { done, value } = await reader.read()
if (done) {
console.log("[DIFY DEBUG] Stream ended naturally")
console.log(
Logger.log("[DIFY DEBUG] Stream ended naturally")
Logger.log(
"[DIFY DEBUG] Final state - hasYieldedContent:",
hasYieldedContent,
"fullText length:",
@@ -178,7 +179,7 @@ export class DifyHandler implements ApiHandler {
}
const chunk = decoder.decode(value, { stream: true })
console.log("[DIFY DEBUG] Raw chunk received:", JSON.stringify(chunk))
Logger.log("[DIFY DEBUG] Raw chunk received:", JSON.stringify(chunk))
buffer += chunk
const lines = buffer.split("\n")
@@ -187,41 +188,41 @@ export class DifyHandler implements ApiHandler {
buffer = lines.pop() || ""
for (const line of lines) {
console.log("[DIFY DEBUG] Processing line:", JSON.stringify(line))
Logger.log("[DIFY DEBUG] Processing line:", JSON.stringify(line))
if (line.startsWith("data: ")) {
const data = line.slice(6).trim()
console.log("[DIFY DEBUG] Extracted data:", JSON.stringify(data))
Logger.log("[DIFY DEBUG] Extracted data:", JSON.stringify(data))
if (data === "[DONE]") {
console.log("[DIFY DEBUG] Received [DONE] signal")
Logger.log("[DIFY DEBUG] Received [DONE] signal")
break
}
if (data === "") {
console.log("[DIFY DEBUG] Empty data line, skipping")
Logger.log("[DIFY DEBUG] Empty data line, skipping")
continue
}
try {
const parsed = JSON.parse(data)
console.log("[DIFY DEBUG] Parsed JSON:", parsed)
Logger.log("[DIFY DEBUG] Parsed JSON:", parsed)
processedEvents.push(parsed.event || "unknown")
lastEventTime = Date.now()
// Capture conversation_id as soon as it's available
if (parsed.conversation_id && !this.conversationId) {
this.conversationId = parsed.conversation_id
console.log("[DIFY DEBUG] Captured conversation_id:", this.conversationId)
Logger.log("[DIFY DEBUG] Captured conversation_id:", this.conversationId)
}
// Handle different Dify event types based on actual Dify API
if (parsed.event === "message") {
console.log("[DIFY DEBUG] Message event, answer:", parsed.answer)
Logger.log("[DIFY DEBUG] Message event, answer:", parsed.answer)
// Dify sends the full text in each "answer" chunk, so we replace.
if (typeof parsed.answer === "string") {
fullText = parsed.answer
console.log("[DIFY DEBUG] Updated fullText length:", fullText.length)
Logger.log("[DIFY DEBUG] Updated fullText length:", fullText.length)
yield {
type: "text",
text: fullText,
@@ -229,10 +230,10 @@ export class DifyHandler implements ApiHandler {
hasYieldedContent = true
}
} else if (parsed.event === "message_replace") {
console.log("[DIFY DEBUG] Replace message event:", parsed)
Logger.log("[DIFY DEBUG] Replace message event:", parsed)
if (parsed.answer) {
fullText = parsed.answer // Replace instead of append
console.log("[DIFY DEBUG] Replaced fullText length:", fullText.length)
Logger.log("[DIFY DEBUG] Replaced fullText length:", fullText.length)
yield {
type: "text",
text: fullText,
@@ -240,7 +241,7 @@ export class DifyHandler implements ApiHandler {
hasYieldedContent = true
}
} else if (parsed.event === "message_end") {
console.log("[DIFY DEBUG] Message end event", parsed)
Logger.log("[DIFY DEBUG] Message end event", parsed)
// Message completed. Yield final text if we have any.
if (fullText) {
yield {
@@ -260,19 +261,19 @@ export class DifyHandler implements ApiHandler {
}
return // End of stream
} else if (parsed.event === "error") {
console.error("[DIFY DEBUG] Error event:", parsed)
Logger.error("[DIFY DEBUG] Error event:", parsed)
throw new Error(`Dify API error: ${parsed.message || "Unknown error"}`)
} else if (parsed.event === "workflow_started" || parsed.event === "workflow_finished") {
console.log("[DIFY DEBUG] Workflow event:", parsed.event)
Logger.log("[DIFY DEBUG] Workflow event:", parsed.event)
// These are informational events, continue processing
} else if (parsed.event === "node_started" || parsed.event === "node_finished") {
console.log("[DIFY DEBUG] Node event:", parsed.event, parsed.data)
Logger.log("[DIFY DEBUG] Node event:", parsed.event, parsed.data)
// These are informational events, continue processing
} else if (parsed.event === "ping") {
console.log("[DIFY DEBUG] Ping event received, keeping connection alive.")
Logger.log("[DIFY DEBUG] Ping event received, keeping connection alive.")
// Ping event, do nothing
} else {
console.log("[DIFY DEBUG] Unknown event type:", parsed.event, "Full object:", parsed)
Logger.log("[DIFY DEBUG] Unknown event type:", parsed.event, "Full object:", parsed)
// Try to extract text from other possible fields
if (parsed.text) {
fullText += parsed.text
@@ -299,17 +300,17 @@ export class DifyHandler implements ApiHandler {
}
}
} catch (e) {
console.warn("[DIFY DEBUG] Failed to parse JSON:", data, "Error:", e)
Logger.warn("[DIFY DEBUG] Failed to parse JSON:", data, "Error:", e)
}
} else if (line.trim() !== "") {
console.log(
Logger.log(
"[DIFY DEBUG] Non-data line (not starting with 'data:'), trying to parse as direct JSON:",
JSON.stringify(line),
)
// Try to parse as direct JSON (fallback for non-SSE responses, though Dify uses SSE)
try {
const parsed = JSON.parse(line.trim())
console.log("[DIFY DEBUG] Parsed direct JSON:", parsed)
Logger.log("[DIFY DEBUG] Parsed direct JSON:", parsed)
processedEvents.push(parsed.event || "direct-json")
// Handle the same event types as above
@@ -330,7 +331,7 @@ export class DifyHandler implements ApiHandler {
}
return
} else if (parsed.event === "error") {
console.error("[DIFY DEBUG] Direct JSON Error event:", parsed)
Logger.error("[DIFY DEBUG] Direct JSON Error event:", parsed)
throw new Error(`Dify API error: ${parsed.message || "Unknown error"}`)
} else if (parsed.answer || parsed.text || parsed.content) {
// Fallback for any content in direct JSON
@@ -344,7 +345,7 @@ export class DifyHandler implements ApiHandler {
}
} catch (e) {
// Not JSON, continue
console.log("[DIFY DEBUG] Line is not direct JSON, continuing")
Logger.log("[DIFY DEBUG] Line is not direct JSON, continuing")
}
}
}
@@ -359,11 +360,11 @@ export class DifyHandler implements ApiHandler {
streamDuration: Date.now() - lastEventTime,
conversationId: this.conversationId,
}
console.error("[DIFY DEBUG] No content was yielded! Diagnostic info:", diagnosticInfo)
Logger.error("[DIFY DEBUG] No content was yielded! Diagnostic info:", diagnosticInfo)
// If we have any accumulated text at all, yield it as a fallback
if (fullText.trim()) {
console.log("[DIFY DEBUG] Yielding accumulated text as fallback:", fullText)
Logger.log("[DIFY DEBUG] Yielding accumulated text as fallback:", fullText)
yield {
type: "text",
text: fullText,
@@ -380,7 +381,7 @@ export class DifyHandler implements ApiHandler {
}
} finally {
reader.releaseLock()
console.log("[DIFY DEBUG] Stream reader released")
Logger.log("[DIFY DEBUG] Stream reader released")
}
}
@@ -399,7 +400,7 @@ export class DifyHandler implements ApiHandler {
// Only prepend the system prompt if it's the very first message of a new conversation.
if (!this.conversationId && systemPrompt) {
console.log("[DIFY DEBUG] Prepending system prompt for new conversation.")
Logger.log("[DIFY DEBUG] Prepending system prompt for new conversation.")
return `${systemPrompt}\n\n---\n\n${userQuery}`
}
+6 -5
View File
@@ -11,6 +11,7 @@ import {
import { GeminiModelId, geminiDefaultModelId, geminiModels, ModelInfo } from "@shared/api"
import { telemetryService } from "@/services/telemetry"
import { ClineStorageMessage } from "@/shared/messages/content"
import { Logger } from "@/shared/services/Logger"
import { ApiHandler, CommonApiHandlerOptions } from "../"
import { RetriableError, withRetry } from "../retry"
import { convertAnthropicMessageToGemini } from "../transform/gemini-format"
@@ -332,7 +333,7 @@ export class GeminiHandler implements ApiHandler {
throughputTokensPerSec: throughputTokensPerSecSdk,
})
} else {
console.warn("GeminiHandler: ulid not available for telemetry in createMessage.")
Logger.warn("GeminiHandler: ulid not available for telemetry in createMessage.")
}
}
}
@@ -408,7 +409,7 @@ export class GeminiHandler implements ApiHandler {
trace.cacheRead = { price: cacheReadsPrice, tokens: cacheReadTokens ?? 0, cost: cacheReadCost }
}
// console.log(`[GeminiHandler] calculateCost -> ${totalCost}`, trace)
// Logger.log(`[GeminiHandler] calculateCost -> ${totalCost}`, trace)
return totalCost
}
@@ -450,13 +451,13 @@ export class GeminiHandler implements ApiHandler {
})
if (response.totalTokens === undefined) {
console.warn("Gemini token counting returned undefined, using fallback")
Logger.warn("Gemini token counting returned undefined, using fallback")
return this.estimateTokens(content)
}
return response.totalTokens
} catch (error) {
console.warn("Gemini token counting failed, using fallback", error)
Logger.warn("Gemini token counting failed, using fallback", error)
return this.estimateTokens(content)
}
}
@@ -475,7 +476,7 @@ export class GeminiHandler implements ApiHandler {
const jsonStr = JSON.stringify(block)
return total + jsonStr.length
} catch (e) {
console.warn("Failed to stringify block for token estimation", e)
Logger.warn("Failed to stringify block for token estimation", e)
return total
}
}
+6 -5
View File
@@ -4,6 +4,7 @@ import OpenAI from "openai"
import { StateManager } from "@/core/storage/StateManager"
import { ClineStorageMessage } from "@/shared/messages/content"
import { fetch } from "@/shared/net"
import { Logger } from "@/shared/services/Logger"
import { isAnthropicModelId } from "@/utils/model-utils"
import { ApiHandler, CommonApiHandlerOptions } from ".."
import { withRetry } from "../retry"
@@ -70,7 +71,7 @@ export async function fetchLiteLlmModelsInfo(baseUrl: string, apiKey: string): P
const data: LiteLlmModelInfoResponse = await response.json()
return data
} else {
console.error("Failed to fetch LiteLLM model info:", response.statusText)
Logger.error("Failed to fetch LiteLLM model info:", response.statusText)
// Try with Authorization header instead
const retryResponse = await fetch(url, {
method: "GET",
@@ -84,12 +85,12 @@ export async function fetchLiteLlmModelsInfo(baseUrl: string, apiKey: string): P
const data: LiteLlmModelInfoResponse = await retryResponse.json()
return data
} else {
console.error("Failed to fetch LiteLLM model info with Authorization header:", retryResponse.statusText)
Logger.error("Failed to fetch LiteLLM model info with Authorization header:", retryResponse.statusText)
throw new Error(`Failed to fetch LiteLLM model info: ${retryResponse.statusText}`)
}
}
} catch (error) {
console.error("Error fetching LiteLLM model info:", error)
Logger.error("Error fetching LiteLLM model info:", error)
throw error
}
}
@@ -169,7 +170,7 @@ export class LiteLlmHandler implements ApiHandler {
}
}
} catch (error) {
console.warn("Error getting LiteLLM model cost info:", error)
Logger.warn("Error getting LiteLLM model cost info:", error)
}
// Fallback to zero costs if we can't get the information
@@ -200,7 +201,7 @@ export class LiteLlmHandler implements ApiHandler {
return totalCost
} catch (error) {
console.error("Error calculating spend:", error)
Logger.error("Error calculating spend:", error)
return undefined
}
}
+4 -4
View File
@@ -8,11 +8,11 @@ import {
OCI_HEADER_OPC_REQUEST_ID,
} from "@/services/auth/oca/utils/constants"
import { createOcaHeaders } from "@/services/auth/oca/utils/utils"
import { Logger } from "@/services/logging/Logger"
import { OcaModelInfo } from "@/shared/api"
import { ClineStorageMessage } from "@/shared/messages/content"
import { fetch } from "@/shared/net"
import { ApiFormat } from "@/shared/proto/index.cline"
import { Logger } from "@/shared/services/Logger"
import { ApiHandler, type CommonApiHandlerOptions } from ".."
import { withRetry } from "../retry"
import { convertToOpenAiMessages } from "../transform/openai-format"
@@ -134,11 +134,11 @@ export class OcaHandler implements ApiHandler {
const data: { cost: number } = await response.json()
return data.cost
} else {
console.error("Error calculating spend:", response.statusText)
Logger.error("Error calculating spend:", response.statusText)
return undefined
}
} catch (error) {
console.error("Error calculating spend:", error)
Logger.error("Error calculating spend:", error)
return undefined
}
}
@@ -313,7 +313,7 @@ export class OcaHandler implements ApiHandler {
// Convert ChatCompletion tools to Responses API format if provided
const responseTools = tools
?.filter((tool) => tool.type === "function")
?.filter((tool) => tool?.type === "function")
.map((tool: any) => ({
type: "function" as const,
name: tool.function.name,
+35 -8
View File
@@ -1,11 +1,14 @@
import { type ModelInfo, openAiModelInfoSaneDefaults } from "@shared/api"
import { type Config, type Message, Ollama } from "ollama"
import type { ChatCompletionTool } from "openai/resources/chat/completions"
import { ClineStorageMessage } from "@/shared/messages/content"
import { fetch } from "@/shared/net"
import { Logger } from "@/shared/services/Logger"
import type { ApiHandler, CommonApiHandlerOptions } from "../"
import { withRetry } from "../retry"
import { convertToOllamaMessages } from "../transform/ollama-format"
import type { ApiStream } from "../transform/stream"
import { ToolCallProcessor } from "../transform/tool-call-processor"
interface OllamaHandlerOptions extends CommonApiHandlerOptions {
ollamaBaseUrl?: string
@@ -50,7 +53,7 @@ export class OllamaHandler implements ApiHandler {
}
@withRetry({ retryAllErrors: true })
async *createMessage(systemPrompt: string, messages: ClineStorageMessage[]): ApiStream {
async *createMessage(systemPrompt: string, messages: ClineStorageMessage[], tools?: ChatCompletionTool[]): ApiStream {
const client = this.ensureClient()
const ollamaMessages: Message[] = [{ role: "system", content: systemPrompt }, ...convertToOllamaMessages(messages)]
@@ -69,20 +72,44 @@ export class OllamaHandler implements ApiHandler {
options: {
num_ctx: Number(this.options.ollamaApiOptionsCtxNum),
},
tools: tools as any,
})
const toolCallProcessor = new ToolCallProcessor()
// Race the API request against the timeout
const stream = (await Promise.race([apiPromise, timeoutPromise])) as Awaited<typeof apiPromise>
try {
for await (const chunk of stream) {
if (typeof chunk.message.content === "string") {
yield {
type: "text",
text: chunk.message.content,
}
Logger.debug("[OllamaHandler] Message Chunk" + JSON.stringify(chunk))
const delta = chunk.message
if (delta?.tool_calls) {
Logger.debug(`[OllamaHandler] Tool Calls Detected: ${JSON.stringify(delta.tool_calls)}`)
yield* toolCallProcessor.processToolCallDeltas(
delta.tool_calls?.map((tc, inx) => ({
index: inx,
id: `ollama-tool-${inx}`,
function: {
name: tc.function.name,
arguments:
typeof tc.function.arguments === "string"
? tc.function.arguments
: JSON.stringify(tc.function.arguments),
},
type: "function",
})),
)
}
if (typeof delta.content === "string") {
yield {
type: "text",
text: delta.content,
}
}
// Handle token usage if available
if (chunk.eval_count !== undefined || chunk.prompt_eval_count !== undefined) {
yield {
@@ -93,7 +120,7 @@ export class OllamaHandler implements ApiHandler {
}
}
} catch (streamError: any) {
console.error("Error processing Ollama stream:", streamError)
Logger.error("Error processing Ollama stream:", streamError)
throw new Error(`Ollama stream processing error: ${streamError.message || "Unknown error"}`)
}
} catch (error) {
@@ -107,7 +134,7 @@ export class OllamaHandler implements ApiHandler {
const statusCode = error.status || error.statusCode
const errorMessage = error.message || "Unknown error"
console.error(`Ollama API error (${statusCode || "unknown"}): ${errorMessage}`)
Logger.error(`Ollama API error (${statusCode || "unknown"}): ${errorMessage}`)
throw error
}
}
+18 -42
View File
@@ -1,16 +1,11 @@
import * as os from "os"
import { v7 as uuidv7 } from "uuid"
import { ModelInfo, OpenAiCodexModelId, openAiCodexDefaultModelId, openAiCodexModels } from "@shared/api"
import OpenAI from "openai"
import type { ChatCompletionTool } from "openai/resources/chat/completions"
import {
ModelInfo,
OpenAiCodexModelId,
openAiCodexDefaultModelId,
openAiCodexModels,
} from "@shared/api"
import * as os from "os"
import { v7 as uuidv7 } from "uuid"
import { openAiCodexOAuthManager } from "@/integrations/openai-codex/oauth"
import { ClineStorageMessage } from "@/shared/messages/content"
import { fetch } from "@/shared/net"
import { openAiCodexOAuthManager } from "@/integrations/openai-codex/oauth"
import { ApiHandler, CommonApiHandlerOptions } from "../"
import { convertToOpenAIResponsesInput } from "../transform/openai-response-format"
import { ApiStream, ApiStreamUsageChunk } from "../transform/stream"
@@ -53,7 +48,9 @@ export class OpenAiCodexHandler implements ApiHandler {
}
private normalizeUsage(usage: any, model: { id: string; info: ModelInfo }): ApiStreamUsageChunk | undefined {
if (!usage) return undefined
if (!usage) {
return undefined
}
const inputDetails = usage.input_tokens_details ?? usage.prompt_tokens_details
@@ -90,11 +87,7 @@ export class OpenAiCodexHandler implements ApiHandler {
return out
}
async *createMessage(
systemPrompt: string,
messages: ClineStorageMessage[],
tools?: ChatCompletionTool[],
): ApiStream {
async *createMessage(systemPrompt: string, messages: ClineStorageMessage[], tools?: ChatCompletionTool[]): ApiStream {
const model = this.getModel()
// Reset state for this request
@@ -104,9 +97,7 @@ export class OpenAiCodexHandler implements ApiHandler {
// Get access token from OAuth manager
let accessToken = await openAiCodexOAuthManager.getAccessToken()
if (!accessToken) {
throw new Error(
"Not authenticated with OpenAI Codex. Please sign in using the OpenAI Codex OAuth flow in settings.",
)
throw new Error("Not authenticated with OpenAI Codex. Please sign in using the OpenAI Codex OAuth flow in settings.")
}
// Format conversation for Responses API
@@ -166,7 +157,7 @@ export class OpenAiCodexHandler implements ApiHandler {
// Pass through strict value from tool (MCP/custom tools have strict: false, built-in tools default to true)
if (tools && tools.length > 0) {
body.tools = tools
.filter((tool: any) => tool.type === "function")
.filter((tool: any) => tool?.type === "function")
.map((tool: any) => ({
type: "function",
name: tool.function.name,
@@ -179,11 +170,7 @@ export class OpenAiCodexHandler implements ApiHandler {
return body
}
private async *executeRequest(
requestBody: any,
model: { id: string; info: ModelInfo },
accessToken: string,
): ApiStream {
private async *executeRequest(requestBody: any, model: { id: string; info: ModelInfo }, accessToken: string): ApiStream {
// Create AbortController for cancellation
this.abortController = new AbortController()
@@ -237,11 +224,7 @@ export class OpenAiCodexHandler implements ApiHandler {
}
}
private async *makeCodexRequest(
requestBody: any,
model: { id: string; info: ModelInfo },
accessToken: string,
): ApiStream {
private async *makeCodexRequest(requestBody: any, model: { id: string; info: ModelInfo }, accessToken: string): ApiStream {
const url = `${CODEX_API_BASE_URL}/responses`
// Get ChatGPT account ID for organization subscriptions
@@ -302,10 +285,7 @@ export class OpenAiCodexHandler implements ApiHandler {
}
}
private async *handleStreamResponse(
body: ReadableStream<Uint8Array>,
model: { id: string; info: ModelInfo },
): ApiStream {
private async *handleStreamResponse(body: ReadableStream<Uint8Array>, model: { id: string; info: ModelInfo }): ApiStream {
const reader = body.getReader()
const decoder = new TextDecoder()
let buffer = ""
@@ -317,7 +297,9 @@ export class OpenAiCodexHandler implements ApiHandler {
}
const { done, value } = await reader.read()
if (done) break
if (done) {
break
}
buffer += decoder.decode(value, { stream: true })
const lines = buffer.split("\n")
@@ -380,10 +362,7 @@ export class OpenAiCodexHandler implements ApiHandler {
}
// Handle tool/function call deltas
if (
event?.type === "response.tool_call_arguments.delta" ||
event?.type === "response.function_call_arguments.delta"
) {
if (event?.type === "response.tool_call_arguments.delta" || event?.type === "response.function_call_arguments.delta") {
const callId = event.call_id || event.tool_call_id || event.id || this.pendingToolCallId
const name = event.name || event.function_name || this.pendingToolCallName
const args = event.delta || event.arguments
@@ -484,10 +463,7 @@ export class OpenAiCodexHandler implements ApiHandler {
getModel(): { id: OpenAiCodexModelId; info: ModelInfo } {
const modelId = this.options.apiModelId
const id =
modelId && modelId in openAiCodexModels
? (modelId as OpenAiCodexModelId)
: openAiCodexDefaultModelId
const id = modelId && modelId in openAiCodexModels ? (modelId as OpenAiCodexModelId) : openAiCodexDefaultModelId
const info: ModelInfo = openAiCodexModels[id]
+6 -6
View File
@@ -8,10 +8,10 @@ import {
import { calculateApiCostOpenAI } from "@utils/cost"
import OpenAI from "openai"
import type { ChatCompletionReasoningEffort, ChatCompletionTool } from "openai/resources/chat/completions"
import { Logger } from "@/services/logging/Logger"
import { ClineStorageMessage } from "@/shared/messages/content"
import { fetch } from "@/shared/net"
import { ApiFormat } from "@/shared/proto/cline/models"
import { Logger } from "@/shared/services/Logger"
import { isGPT5ModelFamily } from "@/utils/model-utils"
import { ApiHandler, CommonApiHandlerOptions } from "../"
import { withRetry } from "../retry"
@@ -135,7 +135,7 @@ export class OpenAiNativeHandler implements ApiHandler {
try {
yield* toolCallProcessor.processToolCallDeltas(delta.tool_calls)
} catch (error) {
console.error("Error processing tool call delta:", error, delta.tool_calls)
Logger.error("Error processing tool call delta:", error, delta.tool_calls)
}
}
@@ -159,7 +159,7 @@ export class OpenAiNativeHandler implements ApiHandler {
// Convert ChatCompletion tools to Responses API format if provided
const responseTools = tools
?.filter((tool) => tool.type === "function")
?.filter((tool) => tool?.type === "function")
.map((tool: any) => ({
type: "function" as const,
name: tool.function.name,
@@ -316,11 +316,11 @@ export class OpenAiNativeHandler implements ApiHandler {
chunk.response?.status === "incomplete" &&
chunk.response?.incomplete_details?.reason === "max_output_tokens"
) {
console.log("Ran out of tokens")
Logger.log("Ran out of tokens")
if (chunk.response?.output_text?.length > 0) {
console.log("Partial output:", chunk.response.output_text)
Logger.log("Partial output:", chunk.response.output_text)
} else {
console.log("Ran out of tokens during reasoning")
Logger.log("Ran out of tokens during reasoning")
}
}
+7 -6
View File
@@ -7,6 +7,7 @@ import OpenAI from "openai"
import type { ChatCompletionTool as OpenAITool } from "openai/resources/chat/completions"
import { ClineStorageMessage } from "@/shared/messages/content"
import { fetch, getAxiosSettings } from "@/shared/net"
import { Logger } from "@/shared/services/Logger"
import { ApiHandler, CommonApiHandlerOptions } from "../"
import { withRetry } from "../retry"
import { createOpenRouterStream } from "../transform/openrouter-stream"
@@ -80,7 +81,7 @@ export class OpenRouterHandler implements ApiHandler {
// Check for error field directly on chunk
if ("error" in chunk) {
const error = chunk.error as OpenRouterErrorResponse["error"]
console.error(`OpenRouter API Error: ${error?.code} - ${error?.message}`)
Logger.error(`OpenRouter API Error: ${error?.code} - ${error?.message}`)
// Include metadata in the error message if available
const metadataStr = error.metadata ? `\nMetadata: ${JSON.stringify(error.metadata, null, 2)}` : ""
throw new Error(`OpenRouter API Error ${error.code}: ${error.message}${metadataStr}`)
@@ -95,7 +96,7 @@ export class OpenRouterHandler implements ApiHandler {
const choiceWithError = choice as any
if (choiceWithError.error) {
const error = choiceWithError.error
console.error(
Logger.error(
`OpenRouter Mid-Stream Error: ${error?.code || "Unknown"} - ${error?.message || "Unknown error"}`,
)
// Format error details
@@ -179,7 +180,7 @@ export class OpenRouterHandler implements ApiHandler {
try {
const generationIterator = this.fetchGenerationDetails(this.lastGenerationId)
const generation = (await generationIterator.next()).value
// console.log("OpenRouter generation details:", generation)
// Logger.log("OpenRouter generation details:", generation)
return {
type: "usage",
cacheWriteTokens: 0,
@@ -191,7 +192,7 @@ export class OpenRouterHandler implements ApiHandler {
}
} catch (error) {
// ignore if fails
console.error("Error fetching OpenRouter generation details:", error)
Logger.error("Error fetching OpenRouter generation details:", error)
}
}
return undefined
@@ -199,7 +200,7 @@ export class OpenRouterHandler implements ApiHandler {
@withRetry({ maxRetries: 4, baseDelay: 250, maxDelay: 1000, retryAllErrors: true })
async *fetchGenerationDetails(genId: string) {
// console.log("Fetching generation details for:", genId)
// Logger.log("Fetching generation details for:", genId)
try {
const response = await axios.get(`https://openrouter.ai/api/v1/generation?id=${genId}`, {
headers: {
@@ -211,7 +212,7 @@ export class OpenRouterHandler implements ApiHandler {
yield response.data?.data
} catch (error) {
// ignore if fails
console.error("Error fetching OpenRouter generation details:", error)
Logger.error("Error fetching OpenRouter generation details:", error)
throw error
}
}
+2 -1
View File
@@ -6,6 +6,7 @@ import * as os from "os"
import * as path from "path"
import { ClineStorageMessage } from "@/shared/messages/content"
import { fetch } from "@/shared/net"
import { Logger } from "@/shared/services/Logger"
import { ApiHandler, CommonApiHandlerOptions } from "../"
import { withRetry } from "../retry"
import { convertToOpenAiMessages } from "../transform/openai-format"
@@ -76,7 +77,7 @@ export class QwenCodeHandler implements ApiHandler {
const credsStr = await fs.readFile(keyFile, "utf-8")
return JSON.parse(credsStr)
} catch (error) {
console.error(
Logger.error(
`Error reading or parsing credentials file at ${getQwenCachedCredentialPath(this.options.qwenCodeOauthPath)}`,
)
throw new Error(`Failed to load Qwen OAuth credentials: ${error}`)
+2 -1
View File
@@ -12,6 +12,7 @@ import OpenAI from "openai"
import type { ChatCompletionTool as OpenAITool } from "openai/resources/chat/completions"
import { ClineStorageMessage } from "@/shared/messages/content"
import { fetch } from "@/shared/net"
import { Logger } from "@/shared/services/Logger"
import { ApiHandler, CommonApiHandlerOptions } from "../"
import { withRetry } from "../retry"
import { convertToOpenAiMessages } from "../transform/openai-format"
@@ -134,7 +135,7 @@ export class QwenHandler implements ApiHandler {
try {
yield* toolCallProcessor.processToolCallDeltas(delta.tool_calls)
} catch (error) {
console.error("Error processing tool call delta:", error, delta.tool_calls)
Logger.error("Error processing tool call delta:", error, delta.tool_calls)
}
}
+22 -21
View File
@@ -12,6 +12,7 @@ import JSON5 from "json5"
import OpenAI from "openai"
import { ClineStorageMessage } from "@/shared/messages/content"
import { getAxiosSettings } from "@/shared/net"
import { Logger } from "@/shared/services/Logger"
import { ApiHandler, CommonApiHandlerOptions } from "../"
import { withRetry } from "../retry"
import { convertToOpenAiMessages } from "../transform/openai-format"
@@ -144,7 +145,7 @@ namespace Bedrock {
}
// Log unsupported content types for debugging
console.warn(`Unsupported content type: ${(item as ContentItem).type}`)
Logger.warn(`Unsupported content type: ${(item as ContentItem).type}`)
return null
})
.filter((item): item is BedrockContentBlock => item !== null)
@@ -213,7 +214,7 @@ namespace Bedrock {
},
}
} catch (error) {
console.error("Failed to process image content:", error)
Logger.error("Failed to process image content:", error)
// Return a text content indicating the error instead of null
// This ensures users are aware of the issue
return {
@@ -412,7 +413,7 @@ export class SapAiCoreHandler implements ApiHandler {
url: destination.url || this.options.sapAiCoreBaseUrl!,
}
} catch (error) {
console.error("Failed to create AI Core destination:", error)
Logger.error("Failed to create AI Core destination:", error)
throw new Error(`Unable to create AI Core destination: ${error instanceof Error ? error.message : String(error)}`)
}
}
@@ -473,7 +474,7 @@ export class SapAiCoreHandler implements ApiHandler {
})
.filter((deployment: any) => deployment !== null)
} catch (error) {
console.error("Error fetching deployments:", error)
Logger.error("Error fetching deployments:", error)
throw new Error("Failed to fetch deployments")
}
}
@@ -577,7 +578,7 @@ export class SapAiCoreHandler implements ApiHandler {
}
}
} catch (error) {
console.error("Error in SAP orchestration mode:", error)
Logger.error("Error in SAP orchestration mode:", error)
throw error
}
}
@@ -596,7 +597,7 @@ export class SapAiCoreHandler implements ApiHandler {
if (!deploymentId) {
// Fallback to runtime deployment id fetching for users who haven't opened the SAP provider UI
console.log(`No pre-configured deployment ID found for model ${model.id}, falling back to runtime fetching`)
Logger.log(`No pre-configured deployment ID found for model ${model.id}, falling back to runtime fetching`)
deploymentId = await this.getDeploymentForModel(model.id)
}
@@ -800,8 +801,8 @@ export class SapAiCoreHandler implements ApiHandler {
if (error.response) {
// The request was made and the server responded with a status code
// that falls out of the range of 2xx
console.error("Error status:", error.response.status)
console.error("Error headers:", error.response.headers)
Logger.error("Error status:", error.response.status)
Logger.error("Error headers:", error.response.headers)
// Handle error data - need to read stream if responseType was 'stream'
let errorMessage = "Unknown error"
@@ -830,10 +831,10 @@ export class SapAiCoreHandler implements ApiHandler {
} else if (typeof error.response.data === "object") {
errorMessage = JSON.stringify(error.response.data, null, 2)
}
console.error("Error data:", errorMessage)
Logger.error("Error data:", errorMessage)
} catch (e) {
console.error("Failed to read error data:", e)
console.error("Raw error data:", error.response.data)
Logger.error("Failed to read error data:", e)
Logger.error("Raw error data:", error.response.data)
}
}
@@ -846,11 +847,11 @@ export class SapAiCoreHandler implements ApiHandler {
throw new Error(`HTTP ${error.response.status}: ${errorMessage}`)
} else if (error.request) {
// The request was made but no response was received
console.error("Error request:", error.request)
Logger.error("Error request:", error.request)
throw new Error("No response received from server")
} else {
// Something happened in setting up the request that triggered an Error
console.error("Error message:", error.message)
Logger.error("Error message:", error.message)
throw new Error(`Error setting up request: ${error.message}`)
}
}
@@ -898,13 +899,13 @@ export class SapAiCoreHandler implements ApiHandler {
}
}
} catch (error) {
console.error("Failed to parse JSON data:", error)
Logger.error("Failed to parse JSON data:", error)
}
}
}
}
} catch (error) {
console.error("Error streaming completion:", error)
Logger.error("Error streaming completion:", error)
throw error
}
}
@@ -965,7 +966,7 @@ export class SapAiCoreHandler implements ApiHandler {
}
}
} catch (error) {
console.error("Failed to parse JSON data:", error)
Logger.error("Failed to parse JSON data:", error)
yield {
type: "text",
text: `[ERROR] Failed to parse response data: ${error instanceof Error ? error.message : String(error)}`,
@@ -975,7 +976,7 @@ export class SapAiCoreHandler implements ApiHandler {
}
}
} catch (error) {
console.error("Error streaming completion:", error)
Logger.error("Error streaming completion:", error)
yield {
type: "text",
text: `[ERROR] Failed to process stream: ${error instanceof Error ? error.message : String(error)}`,
@@ -1044,13 +1045,13 @@ export class SapAiCoreHandler implements ApiHandler {
}
}
} catch (error) {
console.error("Failed to parse GPT JSON data:", error)
Logger.error("Failed to parse GPT JSON data:", error)
}
}
}
}
} catch (error) {
console.error("Error streaming GPT completion:", error)
Logger.error("Error streaming GPT completion:", error)
throw error
}
}
@@ -1109,13 +1110,13 @@ export class SapAiCoreHandler implements ApiHandler {
}
}
} catch (error) {
console.error("Failed to parse Gemini JSON data:", error)
Logger.error("Failed to parse Gemini JSON data:", error)
}
}
}
}
} catch (error) {
console.error("Error streaming Gemini completion:", error)
Logger.error("Error streaming Gemini completion:", error)
throw error
}
}
+4 -3
View File
@@ -4,6 +4,7 @@ import OpenAI from "openai"
import type { ChatCompletionTool as OpenAITool } from "openai/resources/chat/completions"
import { ClineStorageMessage } from "@/shared/messages/content"
import { fetch } from "@/shared/net"
import { Logger } from "@/shared/services/Logger"
import { ApiHandler, CommonApiHandlerOptions } from "../index"
import { withRetry } from "../retry"
import { ApiStream } from "../transform/stream"
@@ -125,11 +126,11 @@ export class VercelAIGatewayHandler implements ApiHandler {
}
if (!didOutputUsage) {
console.warn("Vercel AI Gateway did not provide usage information in stream")
Logger.warn("Vercel AI Gateway did not provide usage information in stream")
}
} catch (error: any) {
console.error("Vercel AI Gateway error details:", error)
console.error("Error stack:", error.stack)
Logger.error("Vercel AI Gateway error details:", error)
Logger.error("Error stack:", error.stack)
throw new Error(`Vercel AI Gateway error: ${error.message}`)
}
}
+18 -17
View File
@@ -3,6 +3,7 @@ import { SELECTOR_SEPARATOR, stringifyVsCodeLmModelSelector } from "@shared/vsCo
import { calculateApiCostAnthropic } from "@utils/cost"
import * as vscode from "vscode"
import { ClineStorageMessage } from "@/shared/messages/content"
import { Logger } from "@/shared/services/Logger"
import { ApiHandler, CommonApiHandlerOptions, SingleCompletionHandler } from "../"
import { withRetry } from "../retry"
import { ApiStream } from "../transform/stream"
@@ -123,7 +124,7 @@ declare module "vscode" {
* const systemPrompt = "You are a helpful assistant";
* const messages = [{ role: "user", content: "Hello!" }];
* for await (const chunk of handler.createMessage(systemPrompt, messages)) {
* console.log(chunk);
* Logger.log(chunk);
* }
* ```
*/
@@ -147,7 +148,7 @@ export class VsCodeLmHandler implements ApiHandler, SingleCompletionHandler {
this.client = null
this.ensureCleanState()
} catch (error) {
console.error("Error during configuration change cleanup:", error)
Logger.error("Error during configuration change cleanup:", error)
}
}
})
@@ -279,7 +280,7 @@ export class VsCodeLmHandler implements ApiHandler, SingleCompletionHandler {
private async getClient(): Promise<vscode.LanguageModelChat> {
if (!this.client) {
console.debug("Cline <Language Model API>: Getting client with options:", {
Logger.debug("Cline <Language Model API>: Getting client with options:", {
vsCodeLmModelSelector: this.options.vsCodeLmModelSelector,
hasOptions: !!this.options,
selectorKeys: this.options.vsCodeLmModelSelector ? Object.keys(this.options.vsCodeLmModelSelector) : [],
@@ -288,11 +289,11 @@ export class VsCodeLmHandler implements ApiHandler, SingleCompletionHandler {
try {
// Use default empty selector if none provided to get all available models
const selector = this.options?.vsCodeLmModelSelector || {}
console.debug("Cline <Language Model API>: Creating client with selector:", selector)
Logger.debug("Cline <Language Model API>: Creating client with selector:", selector)
this.client = await this.createClient(selector)
} catch (error) {
const message = error instanceof Error ? error.message : "Unknown error"
console.error("Cline <Language Model API>: Client creation failed:", message)
Logger.error("Cline <Language Model API>: Client creation failed:", message)
throw new Error(`Cline <Language Model API>: Failed to create client: ${message}`)
}
}
@@ -413,7 +414,7 @@ export class VsCodeLmHandler implements ApiHandler, SingleCompletionHandler {
if (chunk instanceof vscode.LanguageModelTextPart) {
// Validate text part value
if (typeof chunk.value !== "string") {
console.warn("Cline <Language Model API>: Invalid text part value received:", chunk.value)
Logger.warn("Cline <Language Model API>: Invalid text part value received:", chunk.value)
continue
}
@@ -426,18 +427,18 @@ export class VsCodeLmHandler implements ApiHandler, SingleCompletionHandler {
try {
// Validate tool call parameters
if (!chunk.name || typeof chunk.name !== "string") {
console.warn("Cline <Language Model API>: Invalid tool name received:", chunk.name)
Logger.warn("Cline <Language Model API>: Invalid tool name received:", chunk.name)
continue
}
if (!chunk.callId || typeof chunk.callId !== "string") {
console.warn("Cline <Language Model API>: Invalid tool callId received:", chunk.callId)
Logger.warn("Cline <Language Model API>: Invalid tool callId received:", chunk.callId)
continue
}
// Ensure input is a valid object
if (!chunk.input || typeof chunk.input !== "object") {
console.warn("Cline <Language Model API>: Invalid tool input received:", chunk.input)
Logger.warn("Cline <Language Model API>: Invalid tool input received:", chunk.input)
continue
}
@@ -453,7 +454,7 @@ export class VsCodeLmHandler implements ApiHandler, SingleCompletionHandler {
accumulatedText += toolCallText
// Log tool call for debugging
console.debug("Cline <Language Model API>: Processing tool call:", {
Logger.debug("Cline <Language Model API>: Processing tool call:", {
name: chunk.name,
callId: chunk.callId,
inputSize: JSON.stringify(chunk.input).length,
@@ -464,10 +465,10 @@ export class VsCodeLmHandler implements ApiHandler, SingleCompletionHandler {
text: toolCallText,
}
} catch (error) {
console.error("Cline <Language Model API>: Failed to process tool call:", error)
Logger.error("Cline <Language Model API>: Failed to process tool call:", error)
}
} else {
console.warn("Cline <Language Model API>: Unknown chunk type received:", chunk)
Logger.warn("Cline <Language Model API>: Unknown chunk type received:", chunk)
}
}
@@ -489,7 +490,7 @@ export class VsCodeLmHandler implements ApiHandler, SingleCompletionHandler {
}
if (error instanceof Error) {
console.error("Cline <Language Model API>: Stream error details:", {
Logger.error("Cline <Language Model API>: Stream error details:", {
message: error.message,
stack: error.stack,
name: error.name,
@@ -500,12 +501,12 @@ export class VsCodeLmHandler implements ApiHandler, SingleCompletionHandler {
} else if (typeof error === "object" && error !== null) {
// Handle error-like objects
const errorDetails = JSON.stringify(error, null, 2)
console.error("Cline <Language Model API>: Stream error object:", errorDetails)
Logger.error("Cline <Language Model API>: Stream error object:", errorDetails)
throw new Error(`Cline <Language Model API>: Response stream error: ${errorDetails}`)
} else {
// Fallback for unknown error types
const errorMessage = String(error)
console.error("Cline <Language Model API>: Unknown stream error:", errorMessage)
Logger.error("Cline <Language Model API>: Unknown stream error:", errorMessage)
throw new Error(`Cline <Language Model API>: Response stream error: ${errorMessage}`)
}
}
@@ -526,7 +527,7 @@ export class VsCodeLmHandler implements ApiHandler, SingleCompletionHandler {
// Log any missing properties for debugging
for (const [prop, value] of Object.entries(requiredProps)) {
if (!value && value !== 0) {
console.warn(`Cline <Language Model API>: Client missing ${prop} property`)
Logger.warn(`Cline <Language Model API>: Client missing ${prop} property`)
}
}
@@ -557,7 +558,7 @@ export class VsCodeLmHandler implements ApiHandler, SingleCompletionHandler {
? stringifyVsCodeLmModelSelector(this.options.vsCodeLmModelSelector)
: "vscode-lm"
console.debug("Cline <Language Model API>: No client available, using fallback model info")
Logger.debug("Cline <Language Model API>: No client available, using fallback model info")
return {
id: fallbackId,
+3 -1
View File
@@ -1,3 +1,5 @@
import { Logger } from "@/shared/services/Logger"
interface RetryOptions {
maxRetries?: number
baseDelay?: number
@@ -72,7 +74,7 @@ export function withRetry(options: RetryOptions = {}) {
try {
await handlerInstance.options.onRetryAttempt(attempt + 1, maxRetries, delay, error)
} catch (e) {
console.error("Error in onRetryAttempt callback:", e)
Logger.error("Error in onRetryAttempt callback:", e)
}
}

Some files were not shown because too many files have changed in this diff Show More