Sync upstream Cline 0419#69
Open
little-croissant wants to merge 1336 commits into
Open
Conversation
* only doc changes * merge * fix installtion page redirects * fix redirect, remove unused parts * rm irrelevant info * clean up terminal guides * docs: add home page and reorganize navigation * chore: remove 71 unused docs files not referenced in navigation Remove .mdx files that are no longer referenced in docs.json navigation and only existed as stale content from previous documentation restructuring. These files were either completely orphaned or only served as redirect source pages (Mintlify handles redirects at the routing level without needing the source file to exist). Updated docs.json redirects that previously pointed to archive/ pages to point to current equivalents instead: - /archive/understanding-context-management → /model-config/context-windows - /archive/prompt-engineering-guide → /customization/cline-rules - /archive/telemetry → /enterprise-solutions/monitoring/telemetry Deleted files by category: Archive (entire directory removed): - archive/prompt-engineering-guide.mdx - archive/telemetry.mdx - archive/understanding-context-management.mdx Cline CLI: - cline-cli/cli-reference-deprecated.mdx Enterprise Solutions (16 files): - enterprise-solutions/bundled-endpoints.mdx - enterprise-solutions/configuration/overview.mdx - enterprise-solutions/configuration/choosing-your-deployment.mdx - enterprise-solutions/configuration/infrastructure-configuration/overview.mdx - enterprise-solutions/configuration/infrastructure-configuration/rules.mdx - enterprise-solutions/configuration/infrastructure-configuration/workflows.mdx - enterprise-solutions/configuration/infrastructure-configuration/control-other-cline-features/overview.mdx - enterprise-solutions/configuration/infrastructure-configuration/mcp/overview.mdx - enterprise-solutions/configuration/infrastructure-configuration/mcp/mcp-marketplace.mdx - enterprise-solutions/configuration/infrastructure-configuration/mcp/remote-mcp-servers.mdx - enterprise-solutions/configuration/infrastructure-configuration/providers/overview.mdx - enterprise-solutions/configuration/infrastructure-configuration/providers/custom.mdx - enterprise-solutions/configuration/infrastructure-configuration/providers/aws-bedrock/overview.mdx - enterprise-solutions/configuration/infrastructure-configuration/providers/google-vertex/overview.mdx - enterprise-solutions/configuration/infrastructure-configuration/providers/litellm/overview.mdx - enterprise-solutions/monitoring/opentelemetry_override.mdx Exploring Cline's Tools (entire directory removed): - exploring-clines-tools/cline-tools-guide.mdx - exploring-clines-tools/new-task-tool.mdx - exploring-clines-tools/remote-browser-support.mdx Features — old pages consolidated into core-workflows/ and customization/ (37 files): - features/checkpoints.mdx - features/drag-and-drop.mdx - features/editing-messages.mdx - features/explain-changes.mdx - features/skills.mdx - features/yolo-mode.mdx - features/at-mentions/ (7 files — all consolidated into core-workflows/working-with-files) - features/cline-rules/ (2 files — consolidated into customization/cline-rules) - features/commands-and-shortcuts/ (5 files — consolidated into core-workflows/using-commands) - features/customization/ (2 files) - features/hooks/ (3 files — consolidated into customization/hooks) - features/slash-commands/ (7 files) - features/slash-commands/workflows/ (3 files — consolidated into customization/workflows) - features/tasks/ (2 files — consolidated into core-workflows/task-management) Introduction (entire directory removed): - introduction/overview.mdx - introduction/welcome.mdx MCP: - mcp/adding-mcp-servers-from-github.mdx - mcp/configuring-mcp-servers.mdx More Info (entire directory removed): - more-info/telemetry.mdx Prompting (entire directory removed): - prompting/cline-memory-bank.mdx - prompting/prompt-engineering-guide.mdx - prompting/understanding-context-management.mdx Provider Config: - provider-config/fireworks-ai.mdx - provider-config/ollama.mdx Getting Started: - getting-started/selecting-your-model.mdx Total: 71 files deleted, 12,344 lines removed. * docs: update and add documentation pages * revert unintended formatting changes to src files * new first project docs --------- Co-authored-by: Juan Pablo Flores <juan@cline.bot>
* fix(chat): restore reasoning traces and polish thinking UX * chore(changeset): add patch note for reasoning trace UX fixes
… (#9334) * fix(chat): prevent partial text flicker during native tool streaming * fix(chat): revert act mode partial dedupe change
* fix(chat): keep reasoning visible before low-stakes tool groups * chore(changeset): add patch note for tool-group reasoning visibility * fix(chat): keep thinking loader visibility aligned with waiting states * fix(chat): avoid clipping descenders in thinking label
* docs: enrich Quick Start guide with more context for new users * docs: add Antigravity to full installation guide
* feat: add z-ai/glm-5 to free models list Include Z.AI's GLM 5 in the free model whitelist for zero-cost usage and update the model picker UI to display the free label. * Adding thinking * Adding thinking * Adding thinking
* fix(telemetry): refresh OTEL user/org attributes on every identify * fix(telemetry): refresh OTEL user/org attributes on every identify * test(telemetry): cover OTEL identifyUser org refresh scenarios * refactor(telemetry): rename member_roles to member_role (singular) * Apply suggestion from @BarreiroT simpler commenting Co-authored-by: Tomás Barreiro <52393857+BarreiroT@users.noreply.github.com> * removing verbose comments /** * Helper to build a ClineAccountUserInfo with an active organization. */ * removing verbose comments * removing unnecessary logger * assert -> chai expect --------- Co-authored-by: Tomás Barreiro <52393857+BarreiroT@users.noreply.github.com>
Updating CHANGELOG.md format update changelog update banner and bump version Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* feat: add Sonnet 5 support and make it default across surfaces * feat: surface Sonnet 5 as free while keeping Sonnet 4.5 defaults * fix: rename Sonnet 5 support to Sonnet 4.6 across providers and UI * fix: allow duplicate onboarding model ids across free and frontier * chore: update Sonnet 4.6 banner to limited-time free messaging * fix: align Bedrock Sonnet 4.6 model ids with AWS format * feat: update whats new promo to Sonnet 4.6 free offer * chore: update Sonnet 4.6 promo copy and timing
* docs: remove stale Claude 5 wording from auto compact docs * Remove stale Claude 5 mention from docs
* fix: remove expired MiniMax free promo surfaces * fix: remove MiniMax M2.5 from recommended models * chore: update GLM 5 whats-new promo wording
Co-authored-by: Arafatkatze <arafat.da.khan@gmail.com>
* fix: smarter retry for write_to_file missing content parameter (#7998) Replace generic 'missing parameter' error with progressive guidance when write_to_file fails due to empty content parameter. This breaks the infinite retry loop where the model repeatedly attempts the same write_to_file call that exceeds output token limits. Changes: - Add writeToFileMissingContentError() to formatResponse with 3 tiers: 1st failure: suggestions (use skeleton + replace_in_file) 2nd failure: strong directive (stop retrying write_to_file) 3rd+ failure: CRITICAL stop, forces alternative strategies - Add context window awareness: warns model when >50% context used - Add getContextUsagePercent() helper to WriteToFileToolHandler - Add 22 unit tests covering progressive escalation and context awareness Fixes #7998 * add changeset for write_to_file retry fix * refactor: simplify write_to_file error handling per review - Simplify writeToFileMissingContentError to single-tier error following existing diffError pattern (no progressive escalation) - Use shared getLastApiReqTotalTokens() for context window awareness - Remove private getContextUsagePercent() method from handler - Add proactive skeleton + replace_in_file guidance to write_to_file tool description for all variants - Simplify tests to match new API (11 tests) * test: update system prompt snapshots * chore: revert write_to_file prompt guidance * feat: restore progressive 3-tier guidance for write_to_file missing content Restore the progressive escalation that was removed in dd3c12d4e: - Tier 1 (1st failure): Gentle suggestions (skeleton + replace_in_file) - Tier 2 (2nd failure): Strong directive, 'Do NOT attempt full write again' - Tier 3 (3rd+ failure): CRITICAL stop, forces alternative strategies - Context window warning when >50% full - Dynamic UI message: 'Retrying...' vs 'multiple times — different approach' - 21 tests covering all tiers and context awareness * nit: extract context window warning threshold to named constant Also replace emoji with plain text in warning message for consistency. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Robin Newhouse <robin@cline.bot> Co-authored-by: Cursor <cursoragent@cursor.com>
…t (#9348) * fix: disable click-to-set auto-condense threshold and hardcode default Clicking anywhere on the context window progress bar silently set autoCondenseThreshold to a value based on click position (e.g. 0.05), persisting in globalState. This caused compaction to fire at ~10K tokens instead of the intended ~150K, resulting in ~20 context resets per task. - Comment out click and keyboard handlers on progress bar (keep components for future release with proper UX) - Hardcode threshold to 0.75 default, ignoring corrupted stored values Co-authored-by: Cursor <cursoragent@cursor.com> * test: add shouldCompactContextWindow unit tests Cover threshold math including the accidental low-threshold bug case, undefined/zero fallbacks, cache token inclusion, and maxAllowedSize cap. Co-authored-by: Cursor <cursoragent@cursor.com> * fix: hardcode autoCondenseThreshold in all remaining callsites Address Greptile review: SubagentRunner.ts, task/index.ts display logic, and controller/index.ts webview state all still read the corrupted value from globalState. Hardcode 0.75 everywhere. Co-authored-by: Cursor <cursoragent@cursor.com> * style: remove unnecessary union type on hardcoded threshold Drop `number | undefined` annotation from the hardcoded 0.75 literal in SubagentRunner.ts per Greptile review feedback. Co-authored-by: Cursor <cursoragent@cursor.com> * refactor: use SETTINGS_DEFAULTS constant, remove commented-out code, clarify test - Replace hardcoded 0.75 with SETTINGS_DEFAULTS.autoCondenseThreshold across all 4 callsites for a single source of truth - Delete commented-out click/keyboard handlers in ContextWindow.tsx, replace with TODO referencing PR #9348 - Make bug-case test self-documenting by deriving token values from the threshold calculation Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(cli): add /skills slash command for managing skills - Add /skills to CLI_ONLY_COMMANDS in slashCommands.ts - Create SkillsPanelContent component with: - Display global and workspace skills with toggle indicators - Enter to use skill (inserts @path into input) - Space to toggle skill enabled/disabled - Selectable marketplace link to skills.sh - Keyboard navigation with arrow keys and vim keys - Wire up panel in ChatView.tsx - Add comprehensive tests for keyboard interactions * refactor(cli): use static skill controller imports * fix(cli): add React import to skills panel test * fix(cli): suppress required React import lint in skills test * fix(cli): harden /skills panel interactions Revert optimistic skill toggle state when persistence fails, and surface a fallback URL when opening the marketplace fails. Also tighten and extend tests to verify exact marketplace URL handling and rollback behavior. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Cursor <cursoragent@cursor.com>
… (#9345) * feat(cerebras): remove deprecated llama-3.3-70b and qwen-3-32b models These models have been deprecated from the Cerebras inference platform. - Remove llama-3.3-70b and qwen-3-32b from cerebrasModels in api.ts - Update supported models documentation in cerebras.mdx - Add changeset for the deprecation * fix: remove stale llama-3.3-70b and qwen-3-32b references from rate limits Remove dead switch cases in getRateLimits() that referenced deprecated models no longer present in cerebrasModels.
…379) * Fix the featured models key * Add changeset
* Add MiniMax M2.5 to the MiniMax provider * Add changeset * Update default model
* fix(models): keep Sonnet 4.5 as default * chore(changeset): add release note for Sonnet 4.5 default * fix(models): remove Sonnet 4.6 from curated model lists * fix(models): restore Sonnet 4.6 in web recommended list
* changeset version bump * Updating CHANGELOG.md format * update package versions --------- 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>
- Remove `auto_condense_threshold` from `Settings` and `UpdateSettingsRequest` in `state.proto`. - Remove `autoCondenseThreshold` from `ApiProviderInfo` interface. - Update `generate-state-proto.mjs` to remove double field handling and improve integer parsing. - Add error handling to `ContextManager` when parsing previous request JSON to prevent crashes on malformed data.
* feat: add welcome banner support from backend * make DB banner format conform with existing banners * add support for welcome banner actions * remove debugging helper that bypass dismissal, dismissal should work again * undo changes to make welcome banner always appear during debugging * remove console logs for debugging * clean up bannerservice * clean up welcomesection.tsx * add new tests for ide type filtering * add welcome banner own feature flag and conditionally display between hard coded welcome banner and DB backed ones * turn on welcome banner flag locally by default * close welcome banners when clicking on actions * apply bot review suggestion, fix memory leak * address feedback: use p without span * split welcome banners into a seperate component to keep whatsnewmodal clean * get action through api schema instead of extractin it from rules_json * use only bannerWaitTimeoutRef, remove waitingForBannersRef * resolve new merge conflict * linter * cerebra
…onfigs (#10155) * Complete documentation for environment variable-based OpenTelemetry configuration * Address PR review comments - Add Values column to OTLP Configuration table for consistency - Fix New Relic endpoint to include required port 4318 - Add note about Datadog region-specific endpoints
…ion (#10161)
The previous copy ("Cline is moving out of the terminal", "old CLI")
gave the impression that the terminal TUI was being deprecated. Updated
to frame Kanban as the new default while making clear the TUI is still
fully available.
#10161 updated the component copy but missed updating the test assertions. This breaks CI on main and any branch based on it.
…0207) * feat(chat): add SpendLimitError UI for SPEND_LIMIT_EXCEEDED (429) When the Cline backend returns a 429 with code SPEND_LIMIT_EXCEEDED (org budget cap hit), the chat error flow now shows a dedicated SpendLimitError component instead of falling through to the generic rate-limit message. Changes: - proto/cline/account.proto: add submitLimitIncreaseRequest RPC + SubmitLimitIncreaseResponse message - src/services/error/ClineError.ts: add SpendLimit error type; detect SPEND_LIMIT_EXCEEDED before the generic rate-limit pattern check - src/services/account/ClineAccountService.ts: add submitLimitIncreaseRequestRPC() calling POST /api/v1/users/me/budget/request - src/core/controller/account/submitLimitIncreaseRequest.ts: new gRPC handler wired automatically by npm run protos - webview-ui/src/components/chat/SpendLimitError.tsx: new card component mirroring CreditLimitError; shows spent/limit amounts, resets_at, org attribution, and a Request Increase button with 5-min localSto When the Cline backend returns a 429 with code SPEND_LIMIT_EXCEEDED (org budgetrors to SpendLbudget cap hit), the chat budget_period,limit_usd,spent_usd,resets_at} - component instead of falling through to the generic rate-limnd Limit Reac Changes: - proto/cline/account.p * Update webview-ui/src/components/chat/SpendLimitError.tsx Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * chore: shorten spend limit error message verbiage * fix(storybook): align spend limit story messages with component output --------- Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* Update changelog files for release * Version bump for release * Update cli/CHANGELOG.md Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> --------- Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* Remove old evals tool * remove script
* Add support for Azure Blob Storage * fix comment
…… (#10200) * fix(prompts): add use_subagents to GLM, Hermes, and XS TOOL_USE_SECTION overrides These variants use hardcoded TOOL_USE_SECTION templates that bypass the auto-generated tool descriptions. When use_subagents was added as a new tool, it was registered in each variant's .tools() config but was never added to the hardcoded override templates — so models using these variants never saw use_subagents in their system prompt and could not call it. This adds the use_subagents description block to the TOOL_USE_SECTION override templates for glm, hermes, and xs variants, and updates the corresponding test snapshots. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(prompts): gate use_subagents on subagentsEnabled and isSubagentRun context The previous commit added use_subagents to the GLM, Hermes, and XS TOOL_USE_SECTION override templates unconditionally. This was incorrect — the canonical tool spec gates use_subagents with: context.subagentsEnabled === true && !context.isSubagentRun Without this guard, models would advertise use_subagents even when subagents are disabled by the user, and subagent runs could recursively spawn further subagents. This commit: - Wraps the use_subagents block in all three templates with the same subagentsEnabled && !isSubagentRun conditional - Converts HERMES_TOOL_USE_TEMPLATE from a plain string constant to a function so it can access context (matching the pattern used by GLM and XS templates) - Updates snapshots accordingly Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(prompts): align use_subagents rendering guard with tool context requirements --------- Co-authored-by: sunghyun <jjinjukks1227@gmail.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
…269) * fix: unblock pending command_output ask on terminal completion * test: cover timeout and idempotent command_output ask release * refactor: simplify pending command_output ask release guard
* docs: add Kanban remote access documentation Add comprehensive documentation for accessing Kanban remotely: - Local network access (--host flag and KANBAN_RUNTIME_HOST env var) - Tailscale for secure remote access - Docker deployment - SSH tunneling - Ngrok for public URLs - Cloudflare Tunnels with AWS CDK example * Update docs/kanban/remote-access.mdx Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * Update docs/kanban/remote-access.mdx Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> --------- Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Update the Cline Enterprise License link in enterprise onboarding prerequisites from https://cline.bot/enterprise to https://cline.bot/contact-sales
…056) Replace the old client-side per-org scan for remote config with a single discovery call to GET /api/v1/users/me/remote-config. Reuse the inline config value when possible, falling back to the org-level endpoint only when inline parse fails. Key changes: - Single discovery call replaces N org-level requests - Resolve config before switching org to avoid stranding the user - Transient errors preserve existing config (log-only, no clearing) - authenticatedRequest() strict null vs undefined validation - Auth precheck in fetchUserRemoteConfig() with token pass-through
* docs: add CI flakiness stabilization plan * test: harden global hook cwd timeout on windows * test: stabilize CLI skills panel interactions * ci: harden vscode test runtime setup * test: stabilize BannerService timer behavior * refactor: ignore CLI skills input while loading * docs: update stabilization plan status * docs: drop temporary stabilization plan * Update cli/src/components/SkillsPanelContent.tsx Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * Update .vscode-test.mjs Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * test: expose banner service drain hook * fix: stabilize CLI skills panel input state * Change polling interval --------- Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* feat(models): prepare Claude Opus 4.7 provider support * remove deprecated params for opus 4.7 - opus 4.7 doesn't accept params like temperature, top_p, top_k anymore. This commit removes those params only for opus 4.7 * Agent hill climb fixes * Anthropic adaptive thinking * Removing 1m context switcher * Removing 1m models fully * Restore Anthropic 1M variants and context switchers * Adding 1m * remove changeset * fix Opus 4.5 adaptive thinking detection --------- Co-authored-by: Max Paulus 🥪 <max@cline.bot> Co-authored-by: Arafatkatze <arafat.da.khan@gmail.com>
* v3.79.0 Release Notes Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com> 🔮 View transcript: https://agentlogs.beatrixwoo.workers.dev/s/i90f8jfxjc88hit3bs8v2e2k * chore(cli): bump CLI to v2.15.0 Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com> 🔮 View transcript: https://agentlogs.beatrixwoo.workers.dev/s/i90f8jfxjc88hit3bs8v2e2k * remove changeset * remove changeset
…l fixes [ENG-1774] (#10283)
* feat: wire up globalSkills consumption from remote config
The remote config schema already includes globalSkills (merged in #10236).
The dashboard can save skills to remote config. This PR wires up the
extension to read and use them.
## Changes
### State storage (Layer 1)
- Add remoteGlobalSkills to REMOTE_CONFIG_EXTRA_FIELDS
- Add remoteSkillsToggles to GLOBAL_STATE_FIELDS
### Remote config transform/apply/clear (Layer 2)
- Map globalSkills → remoteGlobalSkills in transformRemoteConfigToStateShape
- Sync remoteSkillsToggles in applyRemoteConfig using frontmatter.name
as the identity key (not entry.name)
- Clear remoteSkillsToggles in clearRemoteConfig
### Skill discovery (Layer 3)
- discoverSkills accepts optional remoteSkillEntries parameter (pure
utility, no StateManager coupling)
- getSkillContent accepts optional remoteSkillEntries parameter for
remote content loading without disk I/O
- Precedence: remote (enterprise) > disk-global (user) > project
### refreshSkills (Layer 3b)
- Reads remote entries from controller.stateManager, parses frontmatter,
builds SkillInfo entries with alwaysEnabled field
### UseSkillToolHandler (Layer 4)
- Toggle filter checks remoteSkillsToggles for remote: prefixed skills
- Directory note omitted for remote skills
- Passes remoteSkillEntries to both discoverSkills and getSkillContent
### toggleSkill
- Routes remote: prefixed paths to remoteSkillsToggles keyed by name
### Proto + webview
- Added always_enabled field to SkillInfo proto message
- Modal passes isRemote + alwaysEnabled to RuleRow for remote skills
- Uses skill.name as display label for remote skills
## Design decisions
- frontmatter.name is the sole identity for remote skills (entry.name
is ignored). This matches how local skills work.
- remote: path prefix distinguishes remote from disk skills in toggle
stores and content loading.
- skills.ts remains a pure utility module with zero StateManager coupling.
Callers inject remote entries as parameters.
- 42 unit tests covering discovery, precedence, content loading, toggle
sync, and frontmatter parsing.
* fix: enforce alwaysEnabled in toggle sync to prevent stale false overrides
When applyRemoteConfig syncs skill toggles, synchronizeRemoteRuleToggles
preserves existing toggle values — including false. If an admin later
sets alwaysEnabled: true on a skill that a user had previously disabled,
the stale false toggle would survive the sync. The UI would show the
skill as locked-on (via the alwaysEnabled check in refreshSkills), but
UseSkillToolHandler's filter would see false in the toggle store and
exclude it, causing a 'Skill not found' error for a skill the user can
see is active.
Fix: after synchronizeRemoteRuleToggles, force any alwaysEnabled entry
with a false toggle back to true. This makes the toggle store the single
source of truth — both UI and handler now agree.
Adds 4 tests covering the alwaysEnabled enforcement edge cases.
* fix: deduplicate remote skill parsing, add drift validation, and fix architectural gaps
1. Extract shared parseRemoteSkillEntries utility (skills.ts)
- Single validation point for remote skill entries, replacing duplicated
frontmatter parsing in skills.ts, refreshSkills.ts, and remote-config/utils.ts
- Enforces entry.name === frontmatter.name to catch drift between the
dashboard and SKILL.md content (rejects with warning on mismatch)
2. Eliminate redundant frontmatter re-parsing in getSkillContent
- Was re-parsing every entry's frontmatter to find a match by name
- Now uses entry.name for lookup since drift validation guarantees equality
3. Enforce alwaysEnabled in UseSkillToolHandler
- The toggle filter was missing the alwaysEnabled check, so a stale false
toggle could hide an admin-locked skill from the model
- Now matches the logic in refreshSkills.ts
4. Add remote_skills_toggles to SkillsToggles proto
- toggleSkill now returns remoteSkillsToggles in the response, matching
how remote rules/workflows already work
5. Separate Enterprise Skills section in UI
- Remote skills now render under their own "Enterprise Skills" header,
consistent with how rules and workflows display remote entries
6. Update tests for new validation behavior
- Tests now use entry.name matching frontmatter.name (was deliberately
mismatched before); added drift rejection tests
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: enable viewing remote skills and fix tooltip text in RuleRow
- openRemoteFile now handles remote://skill/{name} URIs (was only
rule and workflow), looking up content from remoteGlobalSkills
- RuleRow's handleEditClick builds the correct URI type for skills
(was falling through to "rule")
- Tooltip text now uses ruleType ("View skill file") instead of
hardcoded "View rule file" for all remote entries
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: soften drift validation to warn-not-reject, fix content lookup fallback
The strict entry.name !== frontmatter.name rejection was silently hiding
org-configured skills when the dashboard's entry.name didn't match the
SKILL.md frontmatter name.
- parseRemoteSkillEntries now warns on drift but uses frontmatter.name as
the canonical identity instead of rejecting the entry
- getSkillContent falls back to frontmatter match when entry.name lookup
misses (handles drift for content loading)
- openRemoteFile falls back to frontmatter match for skill view (same
reason)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: include remote skills in system prompt and fix remote config race
The system prompt generation called discoverSkills() without passing
remoteSkillEntries, so the model never learned about remote skills and
never invoked use_skill for them. This was the actual cause of remote
skills being invisible to the model despite showing in the UI.
Also fixes a race condition in applyRemoteConfig where clearRemoteConfig()
wiped the in-memory cache before repopulating it field-by-field. Any
concurrent reader (e.g., UseSkillToolHandler) during that window would
see an empty cache. Replaced with atomic replaceRemoteConfig() that
builds the new cache and swaps it in a single assignment.
- task/index.ts: pass remoteSkillEntries to discoverSkills, add
remoteSkillsToggles + alwaysEnabled filtering (matching handler)
- StateManager: add replaceRemoteConfig() for atomic cache swap
- remote-config/utils.ts: use replaceRemoteConfig instead of
clearRemoteConfig + setRemoteConfigField loop
- Remove debug logging from parseRemoteSkillEntries and handler
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: include remote skills in subagent path
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Update root package.json axios from 1.13.6 to 1.15.0 - Update evals/package.json axios from 1.13.6 to 1.15.0 - Update docs/package.json axios override from 1.13.5 to 1.15.0 - Regenerate all package-lock.json files
* docs: update Anthropic docs for Claude Opus 4.7 release - Add claude-opus-4-7 and claude-opus-4-7:1m to Anthropic supported models - Document adaptive thinking replacing classic extended thinking on Opus 4.7 - Document sampling parameter restrictions (temperature, top_p, top_k) on Opus 4.7 - Add claude-opus-4-7 to Claude Code supported models * Update docs/provider-config/anthropic.mdx Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * unblocker --------- Co-authored-by: Ara <arafat.da.khan@gmail.com> Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
…10195) * docs: add prompt storage schema and OpenTelemetry events reference - Add comprehensive prompt storage documentation (DEVREL-142) - Complete enterpriseTelemetry.promptUploading schema - Setup guides for AWS S3 and Cloudflare R2 - Storage architecture and sync worker behavior - IAM policies and troubleshooting - Add OpenTelemetry events catalog (DEVREL-143) - Document 80+ events across 8 categories - Example payloads and analytics query patterns - Integration examples for Datadog, Grafana, New Relic - Event schema reference and best practices - Update monitoring documentation - Add cross-references between related pages - Update navigation in docs.json - Integrate new pages into Enterprise > Monitoring section * fix: update broken link in telemetry.mdx to point to OTel events page * docs: address PR review comments - Fix file contents exclusion claim in prompt-storage.mdx - Remove misleading claim about file contents not being stored - Add warning that tool inputs (like write_to_file content) are included - Standardize attribute naming in opentelemetry-events.mdx - Change model_id to model in event tables for consistency - Match actual emitted event schema shown in example payloads - Add SQL syntax note in opentelemetry-events.mdx - Clarify that attribute access syntax is platform-specific - Provide examples for BigQuery and ClickHouse * adjustments
Made-with: Cursor
added 2 commits
April 19, 2026 18:02
…n forks
- Bump esbuild to ^0.27.0 in root + cli devDeps and add esbuild override
to force a single version across the tree. Resolves npm ci postinstall
failure ("Expected 0.27.7 but got 0.25.12") caused by vite 7.3.1
pulling a nested esbuild that conflicted with the top-level one.
- Regenerate package-lock.json so npm ci is clean.
- Fix Promise<Boolean> -> Promise<boolean> in ACPDiffViewProvider so cli
typecheck passes under TS 5.9.
- Gate cline-evals-regression.yml (Smoke Tests) on cline/cline so the
workflow stops failing on forks that lack the CLINE_API_KEY secret.
Made-with: Cursor
… tests on forks" This reverts commit eda78e7.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
20 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.