- Improved session handling by implementing ensureSession to load sessions from disk if not in memory, reducing "session not found" errors.
- Enhanced error messages for non-existent sessions, providing clearer diagnostics.
- Updated CodexProvider and OpencodeProvider to improve error handling and messaging.
- Refactored various routes to use async/await for better readability and error handling.
- Added event emission for merge and stash operations in the MergeService and StashService.
- Cleaned up error messages in AgentExecutor to remove redundant prefixes and ANSI codes for better clarity.
- Extract merge logic from pipeline-orchestrator to merge-service.ts to avoid HTTP self-call
- Make agent-executor error handling provider-agnostic using shared isAuthenticationError utility
- Fix cross-platform path handling in tests using path.normalize/path.resolve helpers
- Add catch handlers in plan-approval-service tests to prevent unhandled promise rejection warnings
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- agent-executor: move executeQuery into try block for proper heartbeat cleanup,
re-parse tasks when edited plan is approved
- auto-loop-coordinator: handle feature execution failures with proper logging
and failure tracking, support backward-compatible method signatures
- facade: delegate getActiveAutoLoopProjects/Worktrees to coordinator,
always create own AutoLoopCoordinator (not shared), pass projectPath
to approval methods and branchName to failure tracking
- global-service: document shared autoLoopCoordinator is for monitoring only
- execution-types: fix ExecuteFeatureFn type to match implementation
- feature-state-manager: use readJsonWithRecovery for loadFeature
- pipeline-orchestrator: add defensive null check and try/catch for
merge response parsing
- plan-approval-service: use project-scoped keys to prevent cross-project
collisions, maintain backward compatibility for featureId-only lookups
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Delete the 2705-line auto-mode-service.ts monolith
- Create AutoModeServiceCompat as compatibility layer for routes
- Create GlobalAutoModeService for cross-project operations
- Update all routes to use AutoModeServiceCompat type
- Add SharedServices interface for state sharing across facades
- Add getActiveProjects/getActiveWorktrees to AutoLoopCoordinator
- Delete obsolete monolith test files
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add 29 unit tests for crash recovery functionality
- Test execution state persistence (save/load/clear)
- Test context detection (agent-output.md exists check)
- Test feature resumption flow (pipeline vs non-pipeline)
- Test interrupted feature batch resumption
- Test idempotent behavior and error handling
- Add 45 unit tests for execution lifecycle coordination
- Test constructor, executeFeature, stopFeature, buildFeaturePrompt
- Test approved plan handling, error handling, worktree resolution
- Test auto-mode integration, planning mode, summary extraction
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add AutoModeService integration tests for delegation verification
- Test executePipeline delegation with context fields
- Test detectPipelineStatus delegation for pipeline/non-pipeline status
- Test resumePipeline delegation with autoLoadClaudeMd and useWorktrees
- Add edge case tests for abort signals, missing context, deleted steps
- Tests for executePipeline: step sequence, events, status updates
- Tests for buildPipelineStepPrompt: context inclusion, previous work
- Tests for detectPipelineStatus: pipeline status detection and parsing
- Tests for resumePipeline/resumeFromStep: excluded steps, slot management
- Tests for executeTestStep: 5-attempt fix loop, failure events
- Tests for attemptMerge: merge endpoint, conflict detection
- Tests for buildTestFailureSummary: output parsing
37 tests covering all core functionality
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add 11 new test cases for execute() behavior
- Test callback invocation (progress events, tool events)
- Test error handling (API errors, auth failures)
- Test result structure and response accumulation
- Test abort signal propagation
- Test branchName propagation in event payloads
Test file: 388 -> 935 lines (+547 lines)
- Test constructor injection with all dependencies
- Test interface exports (AgentExecutionOptions, AgentExecutionResult)
- Test callback type signatures (WaitForApprovalFn, SaveFeatureSummaryFn, etc.)
- Test dependency injection patterns with custom implementations
- Verify execute method signature
Note: Full integration tests for streaming/marker detection require
complex mocking of @automaker/utils module which has hoisting issues.
Integration testing covered in E2E and auto-mode-service tests.
- Extract parseTasksFromSpec for parsing tasks from spec content
- Extract marker detection functions (task start/complete, phase complete)
- Extract detectSpecFallback for non-Claude model support
- Extract extractSummary with multi-format support and last-match behavior
- Add 65 unit tests covering all functions and edge cases
- Add WorktreeResolver and FeatureStateManager as constructor parameters
- Remove top-level getCurrentBranch function (now in WorktreeResolver)
- Delegate loadFeature, updateFeatureStatus to FeatureStateManager
- Delegate markFeatureInterrupted, resetStuckFeatures to FeatureStateManager
- Delegate updateFeaturePlanSpec, saveFeatureSummary, updateTaskStatus
- Replace findExistingWorktreeForBranch calls with worktreeResolver
- Update tests to mock featureStateManager instead of internal methods
- All 89 tests passing across 3 service files
- Create FeatureStateManager class for feature status updates
- Extract updateFeatureStatus, markFeatureInterrupted, resetStuckFeatures
- Extract updateFeaturePlanSpec, saveFeatureSummary, updateTaskStatus
- Persist BEFORE emit pattern for data integrity (Pitfall 2)
- Handle corrupted JSON with readJsonWithRecovery backup support
- Preserve pipeline_* statuses in markFeatureInterrupted
- Fix bug: version increment now checks old content before applying updates
- Add 33 unit tests covering all state management operations
- Add TypedEventBus as wrapper around EventEmitter
- Implement emitAutoModeEvent method for auto-mode event format
- Add emit, subscribe, getUnderlyingEmitter methods
- Create comprehensive test suite (20 tests)
- Verify exact event format for frontend compatibility
- AutoModeService now delegates to ConcurrencyManager for all running feature tracking
- Constructor accepts optional ConcurrencyManager for dependency injection
- Remove local RunningFeature interface (imported from ConcurrencyManager)
- Migrate all this.runningFeatures usages to concurrencyManager methods
- Update tests to use concurrencyManager.acquire() instead of direct Map access
- ConcurrencyManager accepts getCurrentBranch function for testability
BREAKING: AutoModeService no longer exposes runningFeatures Map directly.
Tests must use concurrencyManager.acquire() to add running features.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Test lease counting basics (acquire/release semantics)
- Test running count queries (project and worktree level)
- Test feature state queries (isRunning, getRunningFeature, getAllRunning)
- Test edge cases (multiple features, multiple worktrees)
- 36 test cases documenting expected behavior
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Changed model identifier from `claude-opus-4-5-20251101` to `claude-opus-4-6` across various files, including documentation and code references.
- Updated the SDK to support adaptive thinking for Opus 4.6, allowing the model to determine its own reasoning depth.
- Enhanced the thinking level options to include 'adaptive' and adjusted related components to reflect this change.
- Updated tests to ensure compatibility with the new model and its features.
These changes improve the model's capabilities and user experience by leveraging adaptive reasoning.
Fix#684: Prevent Windows reserved filename creation
- Add sanitizeFilename() utility to detect and prefix Windows reserved names
(NUL, CON, PRN, AUX, COM1-9, LPT1-9)
- Apply sanitization to save-image route to prevent "nul" file creation
- Add 23 comprehensive tests for filename sanitization edge cases
Fix#576: Detect actual dev server port from output
- Parse stdout/stderr for real server URLs (Vite, Next.js, generic formats)
- Update server URL when detected instead of using allocated PORT
- Emit dev-server:url-detected event for frontend updates
- Add 6 tests for URL detection patterns
Fix#193: Commit only feature-specific changes
- Change from 'git add -A' to branch-aware file staging
- Use git diff to find files changed on feature branch only
- Prevent committing unrelated changes from other features
- Maintain backward compatibility with main branch workflow
All fixes include comprehensive tests and maintain backward compatibility.
Test results: 1,968 tests passed (547 package + 1,421 server tests)
Git initialization now explicitly specifies --initial-branch=main to match
GitHub's default branch standard (since October 2020). This prevents the
branch name mismatch that caused features to disappear from the UI when
pushing to GitHub.
Fixes#734🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Dev server test was failing on non-localhost hostnames (e.g., 'fedora')
because it expected 'localhost' in the URL. Now sets HOSTNAME env var
in test setup and restores it in teardown for consistent test behavior
across all environments.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Resolved conflict in auto-mode-service.ts by keeping the v0.14.0rc version
which uses isFeatureRunning() method and has more informative logging.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Simplified the graceful shutdown process by removing redundant error handling for marking features as interrupted, as it is now managed internally.
- Updated orphan detection logging to streamline the process and enhance clarity.
- Added logic to preserve specific pipeline statuses when marking features as interrupted, ensuring correct resumption of features after a server restart.
- Enhanced unit tests to cover new behavior for preserving pipeline statuses and handling various feature states.
- Add graceful shutdown handler that marks running features as 'interrupted'
before server exit (SIGTERM/SIGINT)
- Add 30-second shutdown timeout to prevent hanging on exit
- Add orphan detection to identify features with missing branches
- Add isFeatureRunning() for idempotent resume checks
- Improve resumeInterruptedFeatures() to handle features without saved context
- Add 'interrupted' status to FeatureStatusWithPipeline type
- Replace console.log with proper logger in auto-mode-service
- Add comprehensive unit tests for all new functionality (15 new tests)
Fixes#696🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Resolved conflict in apps/ui/src/hooks/use-query-invalidation.ts by:
- Keeping the refactored structure from v0.14.0rc (using constants and hasFeatureId() type guard)
- Adding the additional event types from the feature branch (auto_mode_task_status, auto_mode_summary) to SINGLE_FEATURE_INVALIDATION_EVENTS constant
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Closes#671 (Complete fix for the plan mode system inside automaker)
Related: #619, #627, #531, #660
## Issues Fixed
### 1. Non-Claude Provider Support
- Removed Claude model restriction from planning mode UI selectors
- Added `detectSpecFallback()` function to detect specs without `[SPEC_GENERATED]` marker
- All providers (OpenAI, Gemini, Cursor, etc.) can now use spec and full planning modes
- Fallback detection looks for structural elements: tasks block, acceptance criteria,
problem statement, implementation plan, etc.
### 2. Crash/Restart Recovery
- Added `resetStuckFeatures()` to clean up transient states on auto-mode start
- Features stuck in `in_progress` are reset to `ready` or `backlog`
- Tasks stuck in `in_progress` are reset to `pending`
- Plan generation stuck in `generating` is reset to `pending`
- `loadPendingFeatures()` now includes recovery cases for interrupted executions
- Persisted task status in `planSpec.tasks` array allows resuming from last completed task
### 3. Spec Todo List UI Updates
- Added `ParsedTask` and `PlanSpec` types to `@automaker/types` for consistent typing
- New `auto_mode_task_status` event emitted when task status changes
- New `auto_mode_summary` event emitted when summary is extracted
- Query invalidation triggers on task status updates for real-time UI refresh
- Task markers (`[TASK_START]`, `[TASK_COMPLETE]`, `[PHASE_COMPLETE]`) are detected
and persisted to planSpec.tasks for UI display
### 4. Summary Extraction
- Added `extractSummary()` function to parse summaries from multiple formats:
- `<summary>` tags (explicit)
- `## Summary` sections (markdown)
- `**Goal**:` sections (lite mode)
- `**Problem**:` sections (spec/full modes)
- `**Solution**:` sections (fallback)
- Summary is saved to `feature.summary` field after execution
- Summary is extracted from plan content during spec generation
### 5. Worktree Mode Support (#619)
- Recovery logic properly handles branchName filtering
- Features in worktrees maintain correct association during recovery
## Files Changed
- libs/types/src/feature.ts - Added ParsedTask and PlanSpec interfaces
- libs/types/src/index.ts - Export new types
- apps/server/src/services/auto-mode-service.ts - Core fixes for all issues
- apps/server/tests/unit/services/auto-mode-task-parsing.test.ts - New tests
- apps/ui/src/store/app-store.ts - Import types from @automaker/types
- apps/ui/src/hooks/use-auto-mode.ts - Handle new events
- apps/ui/src/hooks/use-query-invalidation.ts - Invalidate on task updates
- apps/ui/src/types/electron.d.ts - New event type definitions
- apps/ui/src/components/views/board-view/dialogs/*.tsx - Enable planning for all models
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add GitHub Copilot SDK provider integration
Adds comprehensive GitHub Copilot SDK provider support including:
- CopilotProvider class with CLI detection and OAuth authentication check
- Copilot models definition with GPT-4o, Claude, and o1/o3 series models
- Settings UI integration with provider tab, model configuration, and navigation
- Onboarding flow integration with Copilot setup step
- Model selector integration for all phase-specific model dropdowns
- Persistence of enabled models and default model settings via API sync
- Server route for Copilot CLI status endpoint
https://claude.ai/code/session_01D26w7ZyEzP4H6Dor3ttk9d
* chore: update package-lock.json
https://claude.ai/code/session_01D26w7ZyEzP4H6Dor3ttk9d
* refactor: rename Copilot SDK to Copilot CLI and use GitHub icon
- Update all references from "GitHub Copilot SDK" to "GitHub Copilot CLI"
- Change install command from @github/copilot-sdk to @github/copilot
- Update CopilotIcon to use official GitHub Octocat logo
- Update error codes and comments throughout codebase
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: update Copilot model definitions and add dynamic model discovery
- Update COPILOT_MODEL_MAP with correct models from CLI (claude-sonnet-4.5,
claude-haiku-4.5, claude-opus-4.5, claude-sonnet-4, gpt-5.x series, gpt-4.1,
gemini-3-pro-preview)
- Change default Copilot model to copilot-claude-sonnet-4.5
- Add model caching methods to CopilotProvider (hasCachedModels,
clearModelCache, refreshModels)
- Add API routes for dynamic model discovery:
- GET /api/setup/copilot/models
- POST /api/setup/copilot/models/refresh
- POST /api/setup/copilot/cache/clear
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: use @github/copilot-sdk instead of direct CLI calls
- Install @github/copilot-sdk package for proper SDK integration
- Rewrite CopilotProvider to use SDK's CopilotClient API
- Use client.createSession() for session management
- Handle SDK events (assistant.message, tool.execution_*, session.idle)
- Auto-approve permissions for autonomous agent operation
- Remove incorrect CLI flags (--mode, --output-format)
- Update default model to claude-sonnet-4.5
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: add Copilot and Gemini model support to model resolver
- Import isCopilotModel and isGeminiModel from types
- Add explicit checks for copilot- and gemini- prefixed models
- Pass through Copilot/Gemini models unchanged to their providers
- Update resolver documentation to list all supported providers
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: pass working directory to Copilot SDK and reduce event noise
- Create CopilotClient per execution with correct cwd from options.cwd
- This ensures the CLI operates in the correct project directory, not the
server's current directory
- Skip assistant.message_delta events (they create excessive noise)
- Only yield the final assistant.message event which has complete content
- Clean up client on completion and error paths
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: simplify Copilot SDK execution with sendAndWait
- Use sendAndWait() instead of manual event polling for more reliable
execution
- Disable streaming (streaming: false) to simplify response handling
- Increase timeout to 10 minutes for agentic operations
- Still capture tool execution events for UI display
- Add more debug logging for troubleshooting
- This should fix the "invalid_request_body" error on subsequent calls
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: allow Copilot model IDs with claude-, gemini-, gpt- prefixes
Copilot's bare model IDs legitimately contain prefixes like claude-,
gemini-, gpt- because those are the actual model names from the
Copilot CLI (e.g., claude-sonnet-4.5, gemini-3-pro-preview, gpt-5.1).
The generic validateBareModelId function was incorrectly rejecting
these valid model IDs. Now we only check that the copilot- prefix
has been stripped by the ProviderFactory.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: enable real-time streaming of tool events for Copilot
- Switch back to streaming mode (streaming: true) for real-time events
- Use async queue pattern to bridge SDK callbacks to async generator
- Events are now yielded as they happen, not batched at the end
- Tool calls (Read, Write, Edit, Bash, TodoWrite, etc.) show in real-time
- Better progress visibility during agentic operations
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: expand Copilot tool name and input normalization
Tool name mapping additions:
- view → Read (Copilot's file viewing tool)
- create_file → Write
- replace, patch → Edit
- run_shell_command, terminal → Bash
- search_file_content → Grep
- list_directory → Ls
- google_web_search → WebSearch
- report_intent → ReportIntent (Copilot-specific planning)
- think, plan → Think, Plan
Input normalization improvements:
- Read/Write/Edit: Map file, filename, filePath → file_path
- Bash: Map cmd, script → command
- Grep: Map query, search, regex → pattern
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: convert git+ssh to git+https in package-lock.json
The @electron/node-gyp dependency was resolved with a git+ssh URL
which fails in CI environments without SSH keys. Convert to HTTPS.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: address code review feedback for Copilot SDK provider
- Add guard for non-text prompts (vision not yet supported)
- Clear runtime model cache on fetch failure
- Fix race condition in async queue error handling
- Import CopilotAuthStatus from shared types
- Fix comment mismatch for default model constant
- Add auth-copilot and deauth-copilot routes
- Extract shared tool normalization utilities
- Create base model configuration UI component
- Add comprehensive unit tests for CopilotProvider
- Replace magic strings with constants
- Add debug logging for cleanup errors
* fix: address CodeRabbit review nitpicks
- Fix test mocks to include --version check for CLI detection
- Add aria-label for accessibility on refresh button
- Ensure default model checkbox always appears checked/enabled
* fix: address CodeRabbit review feedback
- Fix test mocks by creating fresh provider instances after mock setup
- Extract COPILOT_DISCONNECTED_MARKER_FILE constant to common.ts
- Add AUTONOMOUS MODE comment explaining auto-approval of permissions
- Improve tool-normalization with union types and null guards
- Handle 'canceled' (American spelling) status in todo normalization
* refactor: extract copilot connection logic to service and fix test mocks
- Create copilot-connection-service.ts with connect/disconnect logic
- Update auth-copilot and deauth-copilot routes to use service
- Fix test mocks for CLI detection:
- Mock fs.existsSync for CLI path validation
- Mock which/where command for CLI path detection
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add Gemini CLI provider for AI model execution
- Add GeminiProvider class extending CliProvider for Gemini CLI integration
- Add Gemini models (Gemini 3 Pro/Flash Preview, 2.5 Pro/Flash/Flash-Lite)
- Add gemini-models.ts with model definitions and types
- Update ModelProvider type to include 'gemini'
- Add isGeminiModel() to provider-utils.ts for model detection
- Register Gemini provider in provider-factory with priority 4
- Add Gemini setup detection routes (status, auth, deauth)
- Add GeminiCliStatus to setup store for UI state management
- Add Gemini to PROVIDER_ICON_COMPONENTS for UI icon display
- Add GEMINI_MODELS to model-display for dropdown population
- Support thinking levels: off, low, medium, high
Based on https://github.com/google-gemini/gemini-cli
* chore: update package-lock.json
* feat(ui): add Gemini provider to settings and setup wizard
- Add GeminiCliStatus component for CLI detection display
- Add GeminiSettingsTab component for global settings
- Update provider-tabs.tsx to include Gemini as 5th tab
- Update providers-setup-step.tsx with Gemini provider detection
- Add useGeminiCliStatus hook for querying CLI status
- Add getGeminiStatus, authGemini, deauthGemini to HTTP API client
- Add gemini query key for React Query
- Fix GeminiModelId type to not double-prefix model IDs
* feat(ui): add Gemini to settings sidebar navigation
- Add 'gemini-provider' to SettingsViewId type
- Add GeminiIcon and gemini-provider to navigation config
- Add gemini-provider to NAV_ID_TO_PROVIDER mapping
- Add gemini-provider case in settings-view switch
- Export GeminiSettingsTab from providers index
This fixes the missing Gemini entry in the AI Providers sidebar menu.
* feat(ui): add Gemini model configuration in settings
- Create GeminiModelConfiguration component for model selection
- Add enabledGeminiModels and geminiDefaultModel state to app-store
- Add setEnabledGeminiModels, setGeminiDefaultModel, toggleGeminiModel actions
- Update GeminiSettingsTab to show model configuration when CLI is installed
- Import GeminiModelId and getAllGeminiModelIds from types
This adds the ability to configure which Gemini models are available
in the feature modal, similar to other providers like Codex and OpenCode.
* feat(ui): add Gemini models to all model dropdowns
- Add GEMINI_MODELS to model-constants.ts for UI dropdowns
- Add Gemini to ALL_MODELS array used throughout the app
- Add GeminiIcon to PROFILE_ICONS mapping
- Fix GEMINI_MODELS in model-display.ts to use correct model IDs
- Update getModelDisplayName to handle Gemini models correctly
Gemini models now appear in all model selection dropdowns including
Model Defaults, Feature Defaults, and feature card settings.
* fix(gemini): fix CLI integration and event handling
- Fix model ID prefix handling: strip gemini- prefix in agent-service,
add it back in buildCliArgs for CLI invocation
- Fix event normalization to match actual Gemini CLI output format:
- type: 'init' (not 'system')
- type: 'message' with role (not 'assistant')
- tool_name/tool_id/parameters/output field names
- Add --sandbox false and --approval-mode yolo for faster execution
- Remove thinking level selector from UI (Gemini CLI doesn't support it)
- Update auth status to show errors properly
* test: update provider-factory tests for Gemini provider
- Add GeminiProvider import and spy mock
- Update expected provider count from 4 to 5
- Add test for GeminiProvider inclusion
- Add gemini key to checkAllProviders test
* fix(gemini): address PR review feedback
- Fix npm package name from @anthropic-ai/gemini-cli to @google/gemini-cli
- Fix comments in gemini-provider.ts to match actual CLI output format
- Convert sync fs operations to async using fs/promises
* fix(settings): add Gemini and Codex settings to sync
Add enabledGeminiModels, geminiDefaultModel, enabledCodexModels, and
codexDefaultModel to SETTINGS_FIELDS_TO_SYNC for persistence across sessions.
* fix(gemini): address additional PR review feedback
- Use 'Speed' badge for non-thinking Gemini models (consistency)
- Fix installCommand mapping in gemini-settings-tab.tsx
- Add hasEnvApiKey to GeminiCliStatus interface for API parity
- Clarify GeminiThinkingLevel comment (CLI doesn't support --thinking-level)
* fix(settings): restore Codex and Gemini settings from server
Add sanitization and restoration logic for enabledCodexModels,
codexDefaultModel, enabledGeminiModels, and geminiDefaultModel
in refreshSettingsFromServer() to match the fields in SETTINGS_FIELDS_TO_SYNC.
* feat(gemini): normalize tool names and fix workspace restrictions
- Add tool name mapping to normalize Gemini CLI tool names to standard
names (e.g., write_todos -> TodoWrite, read_file -> Read)
- Add normalizeGeminiToolInput to convert write_todos format to TodoWrite
format (description -> content, handle cancelled status)
- Pass --include-directories with cwd to fix workspace restriction errors
when Gemini CLI has a different cached workspace from previous sessions
---------
Co-authored-by: Claude <noreply@anthropic.com>
