* fix: resolve Claude Code token counting inefficiency and enable caching (#5104)
- Remove 1.5x fudge factor from Claude Code token counting
- Enable prompt caching support for all Claude Code models
- Add comprehensive tests for token counting and caching
- Update existing tests to reflect accurate token counting
This fixes the extreme token inefficiency where simple messages would
jump from ~40k to over 60k tokens, causing API hangs when approaching
the artificial 120k limit. Claude Code now properly utilizes its full
200k context window with accurate token counting.
* fix: address PR review comments
- Extract IMAGE_TOKEN_ESTIMATE as a named constant for clarity
- Update token counting tests to use exact counts instead of ranges for deterministic testing
- Fix test expectations to match actual tokenizer output
* Remove token counting changes, keep only cache support
- Removed custom countTokens override from claude-code.ts
- Deleted claude-code-token-counting.spec.ts test file
- Kept cache token collection and reporting functionality
- Kept supportsPromptCache: true for all Claude Code models
- Kept claude-code-caching.spec.ts tests
This focuses the PR on enabling cache support without modifying token counting behavior.
* fix: update webview test to expect supportsPromptCache=true for Claude Code models
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* fix: resolve intermittent reasoning content not displayed for Claude Code provider (#5111)
- Modified fallback logic in stream parsing to handle all message types, not just assistant messages
- Added proper parsing attempts for partial data before yielding
- Improved error logging to help debug streaming issues
- Added debug logging (controlled by DEBUG_CLAUDE_CODE env var) to trace message types
This ensures reasoning/thinking content from Claude 3.5 Sonnet 4.0 is properly displayed in all cases.
* fix: disable reasoning budget UI controls for Claude Code provider (#5111)
- Set supportsReasoningBudget to false for all Claude Code models
- Claude Code CLI doesn't support thinking/reasoning parameters
- UI controls were misleading users since they had no effect
* fix: update Claude Code models configuration
- Add missing requiredReasoningBudget: false to claude-3-5-sonnet-20241022 and claude-3-5-haiku-20241022
- Revert run.ts changes as they are not needed for fixing the UI issue
- The UI issue is resolved by properly disabling reasoning budget support in model configuration
* feat: add reasoning effort support to Claude Code models and integrate into model selection
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
This PR adds filtering of git repository properties from telemetry data and includes git info in telemetry properties, with comprehensive tests.
Behavior:
PostHogTelemetryClient now filters out repositoryUrl, repositoryName, and defaultBranch from telemetry events.
ClineProvider includes git repository information in telemetry properties, filtered by clients.
Functions:
Added isPropertyCapturable() in BaseTelemetryClient to allow property filtering.
Implemented getGitRepositoryInfo() and getWorkspaceGitInfo() in git.ts to extract git info.
Tests:
Added tests for isPropertyCapturable() in PostHogTelemetryClient.test.ts.
Added tests for getGitRepositoryInfo() and getWorkspaceGitInfo() in git.spec.ts.
Co-authored-by: Bruno Bergher <me@brunobergher.comexport>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* Store the organization id in credentials
* Better organization logic
* Fix tests
* Update cloud settings defaults
* Fix organization_id handling in Clerk API calls
Address review feedback by properly handling 3 cases for organization_id:
1. Have an org id: send organization_id=THE_ORG_ID
2. Have a personal account: send organization_id= (empty string)
3. Don't know if you have an org id (old credentials): don't send organization_id param at all
Changes:
- Updated clerkCreateSessionToken() to check credentials.organizationId !== undefined
- Updated fetchUserInfo() to handle all 3 cases consistently
- Added fallback logic for old credentials without organization context
- Improved logging for better debugging of organization context
* DRY up organization loading code in AuthService
Extract common organization membership processing logic into reusable helper methods:
- findOrganizationMembership(): Find specific org membership by ID
- findPrimaryOrganizationMembership(): Get first/primary org membership
- setUserOrganizationInfo(): Set organization info on user object
This eliminates duplication between the two clerkGetOrganizationMemberships()
call sites that were doing very similar organization data processing.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
* Fixes#4882: Remove experimental setting for command execution in attempt_completion
- Remove DISABLE_COMPLETION_COMMAND from experiments system
- Permanently disable command execution in attempt_completion tool
- Update tool prompts to remove command parameter and examples
- Remove experimental UI toggle and localization entries (18+ languages)
- Update tests to reflect permanent behavior
- Remove experiment-specific test file
Command execution is now permanently disabled in attempt_completion.
Users must use execute_command tool separately before attempt_completion.
* refactor: simplify getAttemptCompletionDescription by removing unnecessary variables
* test: fix tests by regenerating snaps
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
* Add reasoning budget support to Bedrock models and update related components
- Introduced `supportsReasoningBudget` property in Bedrock models.
- Enhanced `AwsBedrockHandler` to handle reasoning budget in payloads.
- Updated `ThinkingBudget` component to dynamically set max tokens based on reasoning support.
- Modified `ApiOptions` and `Bedrock` components to conditionally render `ThinkingBudget`.
- Added tests for extended thinking functionality in `bedrock-reasoning.test.ts`.
* Add BedrockThinkingConfig interface and update payload structure
* fix: address PR review feedback (#4481)
- Simplify ThinkingBudget ternary logic since component only renders when reasoning budget supported
- Break down complex thinking enabled condition with clear documentation
- Replace 'as any' usage with proper TypeScript interfaces for AWS SDK events
- Add comprehensive documentation for multiple stream structures explaining AWS SDK compatibility
* feat: show ThinkingBudget component unconditionally
Remove selectedProviderModels.length check to display ThinkingBudget
for all providers, not just those with available models
---------
Co-authored-by: hannesrudolph <hrudolph@gmail.com>
* Add reasoning budget support to Bedrock models and update related components
- Introduced `supportsReasoningBudget` property in Bedrock models.
- Enhanced `AwsBedrockHandler` to handle reasoning budget in payloads.
- Updated `ThinkingBudget` component to dynamically set max tokens based on reasoning support.
- Modified `ApiOptions` and `Bedrock` components to conditionally render `ThinkingBudget`.
- Added tests for extended thinking functionality in `bedrock-reasoning.test.ts`.
* Add BedrockThinkingConfig interface and update payload structure
* fix: address PR review feedback (#4481)
- Simplify ThinkingBudget ternary logic since component only renders when reasoning budget supported
- Break down complex thinking enabled condition with clear documentation
- Replace 'as any' usage with proper TypeScript interfaces for AWS SDK events
- Add comprehensive documentation for multiple stream structures explaining AWS SDK compatibility
* feat: add BatchDiffApproval component for multi-file diff application
- Introduced a new component `BatchDiffApproval` to handle the approval of batch changes across multiple files.
- Integrated the `BatchDiffApproval` component into `ChatRow` to display batch diff requests.
- Updated experimental settings to include a toggle for multi-file apply diff functionality.
- Enhanced localization files to support new strings related to batch changes in multiple languages.
- Updated tests to cover the new multi-file apply diff feature.
* revert this
* fix: update applyDiff parameter type to accept string or DiffItem
* refactor: keep original file name for apply diff tool
* revert this
* Update src/core/webview/__tests__/ClineProvider.test.ts
* revert this
* fix: keep the original path if the experiment is disabled
* test: add dynamic strategy selection tests for MultiSearchReplaceDiffStrategy and MultiFileSearchReplaceDiffStrategy
* fix: mock applyDiffTool module and ensure legacy tool resolves successfully in tests
* remove this
* ellipsis suggestion
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* refactor: mirror concurrent file reads
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
Co-authored-by: Daniel <57051444+daniel-lxs@users.noreply.github.com>
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* feat: add MCP viewer and enhanced UI
- Add McpExecutionStatus type with discriminated union for execution states
- Implement McpExecution component with live status updates and collapsible output
- Replace inline MCP UI in ChatRow with dedicated McpExecution component
- Add comprehensive test coverage for useMcpToolTool
- Enhance CodeAccordian to support custom headers
- Improve combineCommandSequences to handle MCP execution flows
* refactor: merge loops in combineCommandSequences for better efficiency
- Reduced from 3 separate loops to 1 main processing loop
- Improved time complexity from O(n²) to O(n)
- Reduced total passes through array from 4 to 2
- Better memory access patterns and cache utilization
* feat: enhance JSON parsing and rendering in McpExecution component
* feat: add mock implementations for react-markdown and remark-gfm
* fix: remove unreachable return statement in ChatRowContent component
* feat(i18n): add execution status messages and error handling for invalid JSON arguments
* test: add parameter validation tests for missing server_name and tool_name
* Update McpExecution component to show server name in header and tool name in approval section
---------
Co-authored-by: Daniel Riccio <ricciodaniel98@gmail.com>
feat: Clicking the panel will always focus it
Adds a new `focusPanel` command and utility function to allow focusing the active webview panel (tab or sidebar). This command is now triggered when a user clicks on non-interactive content within the webview, improving user experience by automatically bringing the panel into focus.
This fixes an issue where sometimes the menu options do not appear because the panel is not in focus:
https://github.com/orgs/Kilo-Org/projects/4/views/1?pane=issue&itemId=113936749&issue=Kilo-Org%7Ckilocode%7C619
**Details**
- **New Command:** Introduced `focusPanel` command to programmatically focus the webview panel.
- **Utility Function:** Created `src/utils/focusPanel.ts` to encapsulate the logic for revealing tab panels or focusing sidebar panels.
- **Webview Integration:** Added a `focusPanelRequest` message type to `WebviewMessage` and implemented a handler in `webviewMessageHandler` to execute the new `focusPanel` command.
- **User Experience:** Implemented a `useAddNonInteractiveClickListener` hook in `webview-ui` that sends a `focusPanelRequest` message to the extension when a click occurs on non-interactive elements, ensuring the webview gains focus.
- **Refactor:** Modified the `focusInput` command to utilize the new `focusPanel` utility, reducing code duplication and centralizing panel focus logic.
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
