* changeset version bump
* Updating CHANGELOG.md format
* changeset version bump
* Updating CHANGELOG.md format
* Eve manually updating the banner and the release version
* Manually update the changelog
* Fix GLM 5 model ID in banner
---------
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: cline-test <132302818+candieduniverse@users.noreply.github.com>
* docs: add subagents feature documentation
Add new documentation page covering the Subagents feature, including
how it works, enabling/configuring, auto-approve behavior, available
tools, and usage guidance. Register the page in docs.json sidebar nav.
* docs: remove hardcoded subagent limit from subagents page
Remove references to 'up to five' subagents, as the limit is no longer
fixed. Updates both the intro paragraph and the How It Works section.
* feat: checkpoint subagent tool workflow and approval UX
* feat: support subagent tool execution without native tool calls
* fix: expose use_subagents when native tool calling is disabled
* fix: stabilize subagent command UX and suppress nested command rows
* chore: tune subagent prompt guidance for context-heavy exploration
* fix: align subagent row spacing with chat row conventions
* fix: keep cancelled subagent state during immediate resume
* feat: implement subagent message rendering for approval prompts and progress updates
* feat: enhance SubagentRunner with tool use ID resolution and fallback handling
* fix: stabilize subagent cline requests with ulid and initial workspace metadata
* refactor: unify subagent chat row rendering
* feat: surface subagent costs in task metrics and status rows
* fix: refine cli subagent tree alignment and wrapping
* fix: refine subagent streaming rows in cli and webview
* fix: ensure unique act mode hint keys in CLI chat
* feat: add subagents settings toggle wiring across webview and cli
* fix(webview): stream subagent stats per prompt while constructing prompts
* fix: remove duplicate subagentsEnabled declaration after rebase
* chore: restore package lockfiles to main
* fix: harden task history usage parsing and clean prompt separators
* chore: refine subagent response formatting guidance
* feat: collapse subagent prompts with show more
* feat: show latest subagent tool call in status rows
* fix: fall back to non-native mode for subagents when native tools are unavailable
* fix: retry empty subagent responses before failing
* fix(subagents): require attempt_completion and dedupe tool result formatting
* feat(subagents): polish prompt guidance and webview status row
* fix(task): prevent duplicate partial text rows after completion
Avoid adding a new partial text message when the latest text row is already completed with the same content. This stops a presenter race from rendering duplicate streamed text lines for MiniMax-style timing.
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(task): cover duplicate partial text dedupe behavior
Add a Task.say unit test that reproduces the duplicate-partial-after-complete scenario and verifies we skip creating a second text row with identical content.
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(claude-code): add opus 4.6 1m model option
* fix(claude-code): support opus[1m] alias and align opus alias
* fix(claude-code): add sonnet[1m] model support
* add more shortcuts to help output
* Apply suggestions from code review
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
---------
Co-authored-by: Max Paulus 🥪 <max@cline.bot>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Add Bedrock to the list in isNextGenModelProvider()
* feat(bedrock): Remove testing script used to develop isNextGenModelProvider() change against
* refactor: extract shared isParallelToolCallingEnabled into model-utils
Consolidate duplicated parallel tool calling logic from ToolExecutor.ts
and task/index.ts into a single exported function in model-utils.ts.
Both callers now delegate to the shared function, eliminating the need
to maintain identical checks in two places.
Replaces inline --body with --body-file approach in the PR creation skill documentation. This avoids shell escaping issues, newline problems, and command-line flakiness when creating PRs with complex markdown content.
Related to #8785
* feat: enable sync-ed deletion for remote mcp servers from remote config to extension
* chore: add tests for syncing remote mcp server adding and removal
* address comments
* WIP - Render a Remote Config secttion and add an option to refresh
* Add the different remote config sections and test them
* fixes
* refactor
* Add proper wrapping
* Stack more values
* Properly report errors when prompt uploading fails
* Add a better error message for the otel test button
* clean
* Fix option rendering
* Render less options if they aren't configured
* fix: use vscode.env.asExternalUri for web OAuth callbacks
In VS Code Web (Codespaces, code serve-web), OAuth callbacks using
http://127.0.0.1:PORT break because the extension host runs remotely.
Changes:
- getCallbackUrl now accepts a path parameter
- Desktop: uses vscode://extension-id/path directly
- Web (UIKind.Web): uses vscode.env.asExternalUri() for web-reachable URL
- Updated all callers (/auth, /openrouter, /hicap, /requesty, MCP) to
pass path and use URL+searchParams for proper encoding
- Added regression test asserting web callback URL is not 127.0.0.1
- AuthHandler (localhost HTTP) now only used by CLI/standalone mode
* fix: use URL.searchParams for proper callback URL encoding
Callers were using template literal interpolation to embed callback URLs
into query strings, which breaks when the URL contains special characters
(e.g. from asExternalUri with query params). Use URL+searchParams.set()
which automatically encodes values.
* chore: revert unrelated whitespace change in account.proto
* revert: remove non-essential URL encoding changes in auth callers
Keep only the core fix (getCallbackUrl path parameter + asExternalUri for web).
Revert the URL+searchParams encoding improvement to minimize diff.
* fix: URL-encode callback_url in auth callers, add encoding test
In VS Code Web, callback URLs from asExternalUri can contain their own
query params (?tkn=...&extra=...). String-interpolating them into
callback_url= causes everything after the first & to be parsed as
top-level params, truncating the callback URL.
Use URL + searchParams.set() in openrouter, hicap, and requesty callers.
Replace tautology test with deterministic round-trip encoding assertions.
* feat(tools): add auto-approval support for attempt_completion commands
- Add auto-approval logic for bash commands in AttemptCompletionHandler
- Show commands as 'say' instead of 'ask' when auto-approved
- Display notification prompting user approval when manual approval needed
- Add 30-second timeout notification for long-running auto-approved commands
- Fix Logger import path from @/shared to @shared
* Send to cline provider
* feat(bedrock): Create agent implementation plan for supporting parallel tool calling.
* Add Bedrock tool calling support
* Improve Bedrock tool calling test guidance
* Add Bedrock CLI parallel tool calling test script
* fix: add ALLOW_AWS_DEFAULT_CHAIN support to live integration test script
* chore: add changeset for Bedrock parallel tool calling
* feat(bedrock): enable native parallel tool calling for Bedrock provider
- Add 'bedrock' to isNextGenModelProvider() so native tool calling is enabled
- Add 'bedrock' to getNativeConverter() to use Anthropic-format tool specs (input_schema)
- Fix empty tool description validation error in mapClineToolsToBedrockToolConfig
(Bedrock requires description length >= 1)
- Update CLI test to use Sonnet 4.5 (Haiku too small for native tool calling)
- Add <invoke> XML detection to CLI test to catch XML fallback
Verified: conversation history shows 3 native tool_use blocks in a single
assistant response with 3 matching tool_result blocks — true parallel
tool calling via Bedrock Converse API.
* docs: mark all phases complete in bedrock parallel tool calling implementation plan
* chore: switch test scripts default model to Haiku 4.5 (cheaper for testing)
* feat: enhance CLI verification suite with 3 test cases (single, parallel, round-trip)
* Remove bedrock parallel tool calling implementation plan doc.
* refactor: simplify to single CLI verification script for bedrock parallel tool calling
Remove the handler-level test script (test-bedrock-tool-calling.ts) and consolidate
into a single focused CLI test that proves parallel tool calling works end-to-end:
- Spawns Cline CLI with Bedrock config
- Asks it to read 3 files
- Verifies ≥2 parallel native tool calls (not XML fallback)
- Task completion proves tool result round-trip works
* refactor(bedrock): improve type safety and code quality for parallel tool calling
- Add typed interfaces (ToolUseStart, ToolUseDelta) for Bedrock stream
events instead of relying on `as any` casts
- Extend ContentBlockStart and ContentBlockDelta interfaces with toolUse
fields so stream parsing uses typed property access
- Remove dead `inputBuffer` field from activeToolCalls Map (was tracked
but never read — tool input deltas are yielded immediately)
- Add JSDoc to mapClineToolsToBedrockToolConfig explaining its purpose
and return semantics
- Document why createDeepseekMessage intentionally ignores the tools
parameter (DeepSeek R1 uses InvokeModel, not Converse API)
* refactor(scripts): improve test script readability and resource cleanup
- Add try/finally with cleanupDirs() to remove temp workspace and config
dirs after each run (previously accumulated in $TMPDIR)
- Extract named constants for CLI_TIMEOUT_SECONDS and HEARTBEAT_INTERVAL_MS
- Add CliResult interface for the runCli return type
- Rename cryptic variables: hb → heartbeatInterval, c → chunk, p/d → filePath/data
- Add JSDoc to parseReadFilePaths and hasXmlFallback
- Add explanatory comments to empty catch blocks
- Log stderr on non-zero exit code for easier debugging
- Extract createTestWorkspace() to separate workspace setup from main flow
- Add section separator comments for visual structure
* test(bedrock): add missing edge-case tests and remove dead describe block
- Add tests for mapClineToolsToBedrockToolConfig edge cases:
undefined/empty input returns undefined, tools without input_schema
are silently dropped
- Add test for formatMessagesForConverseAPI with array tool_result
content (multi-block text responses)
- Add test for tool_result is_error → status:'error' mapping
- Remove empty 'reasoning content handling (deprecated)' describe block
35 tests passing (was 31).
* test(bedrock): add integration-level tests covering E2E script gaps
Add 'native tool calling integration' test suite that validates the
concerns previously only covered by the live E2E CLI script:
- Bedrock + Claude 4 is recognized as native tool calling eligible
(catches silent regression if Bedrock is removed from
isNextGenModelProvider or Claude 4 from isNextGenModelFamily)
- Bedrock + Claude 3.x correctly does NOT qualify (pre-4.0 guard)
- Native tool calling disabled when user setting is off
- createAnthropicMessage passes toolConfig to ConverseStreamCommand
(catches the tool spec not reaching the API)
- Full multi-turn tool call round-trip formatting (tool_use in
assistant → tool_result in user → reformatted for next API call)
40 tests passing (was 35).
* Remove functional verification script before code review
The diff editor e2e test flakes consistently on Windows CI because the
40s test timeout is too tight. The test does signin, message send,
history verification, then a second message send before the diff
assertion -- on slow Windows runners this setup alone can eat most of
the budget. Bumping to 60s gives enough headroom.
Add Terminal-Bench-proven rules as items 5 and 6 in the double-check
re-verification checklist, so they're enforced at completion
verification time rather than in the system prompt.
* feat: add double-check completion experimental feature
When enabled, the first attempt_completion call in a task is rejected
with a tool error that instructs the model to re-verify its work
against the original task requirements. The rejection includes the
initial task text for context. The second call proceeds normally.
This is opt-in (default off) and available via:
- Settings > Features > Experimental > Double-Check Completion
- CLI flag: --double-check-completion
- CLI TUI settings panel toggle
Adds completionAttemptCount to TaskState, plumbs the setting through
TaskConfig/ToolExecutor following existing patterns, and includes
9 unit tests.
* chore: add cli:run script for quick CLI testing
* fix: increase task preview to 8000 chars, revert unintended regex change
* fix: preserve existing proto field numbers
The auto-generator renumbered open_ai_headers (175->177) and
openai_codex_oauth_credentials (46->48), and dropped the reserved 146
comment. Restore original field numbers to avoid breaking wire-format
compatibility.
* fix: remove partial completion_result message on double-check rejection
During streaming, handlePartialBlock shows the completion_result in
the chat view. When we reject the first attempt, we need to clean up
that partial message so the user doesn't see a stale completion that
was actually rejected.
* refactor: switch from counter to boolean toggle for double-check
Use a boolean pending flag instead of a counter so that every
attempt_completion gets double-checked, not just the first one in
a task. The flag toggles: reject (set pending), accept (clear pending),
so if the model does more work and tries to complete again later, it
gets double-checked again.
* fix(prompt): add output precision and threshold iteration rules
Two concise rules proven effective via Terminal-Bench testing:
1. Output precision: produce exactly what's specified, no extra columns/fields/debug output
2. Threshold iteration: verify results meet numerical criteria before completing
Tested on 6 targeted Terminal-Bench tasks (job 2026-02-07__16-15-00):
- log-summary-date-ranges: FAIL→PASS (output precision rule eliminated extra columns)
- dna-insert: FAIL→PASS (iterate rule helped agent meet Tm threshold)
A third rule (no-cleanup) was tested and deliberately excluded: it failed to
prevent self-sabotage on configure-git-webserver despite STRICTLY FORBIDDEN
language, and caused a side-effect on polyglot-c-py by preventing legitimate
build artifact cleanup. The cleanup behavior is too deeply trained to override
via prompt rules alone.
* test: update prompt snapshots for new rules
* fix(cli): route PostHog networking through shared fetch
* remove unnecessary `as RequestInit` casts from PostHog fetch wrappers
PostHogFetchOptions is a structural subset of RequestInit, so the cast
is unnecessary. Also removes a stale comment about shared client support
in PostHogErrorProvider.
The --thinking flag now accepts an optional number argument to set a
custom thinking budget instead of always using the 1024 default.
cline "prompt" --thinking # 1024 tokens (default)
cline "prompt" --thinking 8000 # 8000 tokens
Invalid values get a warning and fall back to 1024.
* feat: move reasoning effort to model config and update model selection UX
* refactor: dedupe reasoning effort handling and drop lockfile churn
* refactor: default reasoning effort to low
* refactor(cli): sync mode-scoped thinking and reasoning writes
* fix: centralize reasoning effort normalization and avoid implicit openai effort
* fix: restore proto field number for codex credentials and reserve removed fields
- Keep openai_codex_oauth_credentials at field 46 (was incorrectly
changed to 47)
- Add reserved 146 in Settings for removed openai_reasoning_effort
- Add reserved 15 in UpdateSettingsRequest for removed openai_reasoning_effort
- Remove stale openai_reasoning_effort field from UpdateSettingsRequest
* fix: map medium reasoning effort to LOW for Gemini models
Gemini API only accepts LOW and HIGH thinking levels. MEDIUM exists in
the SDK enum but is rejected at the API level. Map medium to LOW and
update the default fallback accordingly.
Introduces a mechanism to save system prompts and task metadata to disk for debugging and analysis purposes.
- Added `writePromptMetadataArtifacts` to the `Task` class.
- Feature is enabled via the `CLINE_WRITE_PROMPT_ARTIFACTS` environment variable.
- Artifacts are saved to `.cline-prompt-artifacts` or a custom path defined by `CLINE_PROMPT_ARTIFACT_DIR`.
- Writes both a JSON manifest (containing task ID, model info, and timestamp) and the raw system prompt for every API request.
* fix: use vscode.env.asExternalUri for auth callback URLs in VS Code Web
The OAuth callback redirect was broken in VS Code Web (code serve-web)
environments because the callback URL used a raw vscode:// URI scheme,
which the OS would route to the local desktop VS Code app instead of
the web instance.
This change wraps both getCallbackUrl() and getIdeRedirectUri() with
vscode.env.asExternalUri() which properly transforms URIs based on the
environment:
- Desktop VS Code: unchanged (vscode://...)
- VS Code Remote SSH: adds remote authority for proper routing
- VS Code Web: transforms to HTTPS URL that routes through the web server
Fixes#5109 (remaining callback redirect issue)
Related: #2152
* fix: use HTTP-based auth callback for VS Code Web mode
In VS Code Web (code serve-web), vscode:// URIs redirect to the desktop
app instead of staying in the browser. This change uses AuthHandler
(local HTTP server) for the auth callback in web mode, matching how
CLI/standalone already handles auth.
- getCallbackUrl: use AuthHandler when UIKind.Web
- getIdeRedirectUri: return empty in web mode to avoid vscode:// redirect
* fix: add fallback for openExternal RPC for JetBrains compatibility
The openExternal host bridge RPC is not implemented in the JetBrains
plugin, causing sign-in to fail silently. This adds a fallback to the
'open' npm package when the host RPC fails with UNIMPLEMENTED.
Fixes#9164, #9137, #9138
alex-lum