Addressed all 6 bugs identified in code reviews:
CRITICAL FIXES:
1. SessionStore.ts: Fixed concepts filter bug - removed empty params.push()
that was breaking SQL parameter alignment (line 849)
2. import-memories.ts: Removed worker_port and prompt_counter fields from
sdk_sessions insert to fix schema mismatch with fresh databases
3. export-memories.ts: Fixed hardcoded port - now reads from settings via
SettingsDefaultsManager.loadFromFile()
HIGH PRIORITY:
4. export-memories.ts: Added database existence check with clear error
message before opening database connection
5. export-memories.ts: Fixed variable shadowing - renamed local 'query'
variable to 'sessionQuery' (line 90)
MEDIUM PRIORITY:
6. export-memories.ts: Improved type safety - added ObservationRecord,
SdkSessionRecord, SessionSummaryRecord, UserPromptRecord interfaces
All fixes tested and verified:
- Export script successfully exports with project filtering
- Import script works on existing database with duplicate prevention
- Port configuration read from settings.json
- Type safety improvements prevent compile-time errors
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* Fix critical session persistence bug in new-hook
Restores the second POST call to /sessions/:sessionDbId/init that was
incorrectly removed as "duplicate" in the hooks refactor.
The two POST calls serve different purposes:
- POST /api/sessions/init: Creates DB session, saves prompt (no SDK agent)
- POST /sessions/:sessionDbId/init: Starts the SDK agent session
Without the second call, the SDK agent never started, causing:
- First prompts saved to DB but never processed
- Subsequent prompts queued but no agent running to consume them
- Each new prompt creating orphaned sessions instead of continuing
This fix restores proper session continuation across multiple prompts.
Fixes conversation fragmentation reported in production.
* updated agent-sdk
* Skip meta-observations for session-memory file operations
Added a check to skip meta-observations when file operations (Edit, Write, Read, NotebookEdit) are performed on session-memory files. If the file path includes 'session-memory', a debug log is generated and the response indicates that the observation was skipped.
* refactor: Clean up hook-response and new-hook files
- Removed 'PreCompact' hook type and associated logic from hook-response.ts for improved type safety.
- Deleted extensive architecture comments in new-hook.ts to streamline code readability.
- Simplified debug logging in new-hook.ts to reduce verbosity.
- Enhanced ensureWorkerRunning function in worker-utils.ts with a final health check before throwing errors.
- Added a new documentation file outlining the hooks cleanup process and future improvements.
* Refactor cleanup and user message hooks
- Updated cleanup-hook.js to improve error handling and remove unnecessary input checks.
- Simplified user-message-hook.js by removing time-sensitive announcements and streamlining output.
- Enhanced logging functionality in both hooks for better debugging and clarity.
* Refactor error handling in hooks to use centralized error handler
- Introduced `handleWorkerError` function in `src/shared/hook-error-handler.ts` to manage worker-related errors.
- Updated `context-hook.ts`, `new-hook.ts`, `save-hook.ts`, and `summary-hook.ts` to utilize the new error handler, simplifying error management and improving code readability.
- Removed repetitive error handling logic from individual hooks, ensuring consistent user-friendly messages for connection issues.
* Refactor user-message and summary hooks to utilize shared transcript parser; introduce hook exit codes
- Moved user message extraction logic to a new shared module `transcript-parser.ts` for better code reuse.
- Updated `summary-hook.ts` to use the new `extractLastMessage` function for retrieving user and assistant messages.
- Replaced direct exit code usage in `user-message-hook.ts` with constants from `hook-constants.ts` for improved readability and maintainability.
- Added `HOOK_EXIT_CODES` to `hook-constants.ts` to standardize exit codes across hooks.
* Refactor hook input interfaces to enforce required fields
- Updated `SessionStartInput`, `UserPromptSubmitInput`, `PostToolUseInput`, and `StopInput` interfaces to require `session_id`, `transcript_path`, and `cwd` fields, ensuring better type safety and clarity in hook inputs.
- Removed optional index signatures from these interfaces to prevent unintended properties and improve code maintainability.
- Adjusted related hook implementations to align with the new interface definitions.
* Refactor save-hook to remove tool skipping logic; enhance summary-hook to handle spinner stopping with error logging; update SessionRoutes to load skip tools from settings; add CLAUDE_MEM_SKIP_TOOLS to SettingsDefaultsManager for configurable tool exclusion.
* Document CLAUDE_MEM_SKIP_TOOLS setting in public docs
Added documentation for the new CLAUDE_MEM_SKIP_TOOLS configuration
setting in response to PR review feedback. Users can now discover and
customize which tools are excluded from observations.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
**Problem:**
Worker service crashed on startup with:
TypeError: Cannot read properties of undefined (reading 'get')
at new Wd (.../worker-service.cjs:52:131469)
**Root Cause:**
Circular dependency between SettingsDefaultsManager and logger:
1. SettingsDefaultsManager imports logger
2. logger imports SettingsDefaultsManager
3. logger constructor calls SettingsDefaultsManager.get() at init time
4. When CommonJS resolves the cycle, SettingsDefaultsManager is undefined
**Solution:**
Break the circular dependency by making logger lazy-load its configuration:
- Change logger.level from initialized in constructor to lazy-loaded
- Add getLevel() method that loads on first access
- Update all level checks to use getLevel()
This allows SettingsDefaultsManager to import logger without triggering
the circular dependency, since logger no longer accesses SettingsDefaultsManager
during module initialization.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Moved SettingsDefaultsManager from worker/settings to shared directory.
- Updated all import paths across the codebase to reflect the new location.
- Removed early-settings.ts as its functionality is now handled by SettingsDefaultsManager.
- Adjusted logger and paths to utilize SettingsDefaultsManager for configuration values.
- Replaced instances of silentDebug with happy_path_error__with_fallback across multiple files to improve error logging and handling.
- Updated the utility function to provide clearer semantics for error handling when expected values are missing.
- Introduced a script to find potential silent failures in the codebase that may need to be addressed with the new error handling approach.
- Introduced a new module `hook-constants.ts` to define timeout constants for various hooks.
- Updated `cleanup-hook.ts`, `context-hook.ts`, `save-hook.ts`, and `summary-hook.ts` to utilize the new `HOOK_TIMEOUTS.DEFAULT` for fetch timeouts instead of hardcoded values.
- Adjusted worker utility timeouts in `worker-utils.ts` to use constants from `hook-constants.ts`, improving maintainability and consistency across the codebase.
- Added silent debugging for settings file loading failures in early-settings.ts.
- Improved error logging in worker-utils.ts for health check and worker startup failures, including detailed error information and context.
- Removed direct database operations in new-hook.ts and replaced them with an HTTP call to initialize sessions.
- Added error handling for HTTP requests and improved logging for session initialization.
- Updated SessionRoutes to handle new session initialization and privacy checks.
- Enhanced privacy tag stripping logic to prevent saving fully private prompts.
- Improved overall error handling and debugging messages throughout the session management process.
- Updated paths in troubleshooting documentation to reflect new settings file location.
- Modified diagnostics and reference files to read from ~/.claude-mem/settings.json.
- Introduced getWorkerPort utility for cleaner worker port retrieval.
- Enhanced ChromaSync and SDKAgent to load Python version and Claude path from settings.
- Updated SettingsRoutes to validate new settings: CLAUDE_MEM_LOG_LEVEL and CLAUDE_MEM_PYTHON_VERSION.
- Added early-settings module to load settings for logger and other early-stage modules.
- Adjusted logger to use early-loaded log level setting.
- Refactored paths to utilize early-loaded data directory setting.
This PR addresses issue #193 affecting Windows installations of claude-mem.
## Bug 1: Missing ecosystem.config.cjs in packaged plugin
**Problem**: The ecosystem.config.cjs file was not included in the plugin
package, causing PM2 to fail when trying to start the worker from cache.
**Fix**: Added `plugin/ecosystem.config.cjs` with correct path for packaged
structure (`./scripts/worker-service.cjs` instead of `./plugin/scripts/`).
## Bug 2: Incorrect MCP Server Path (src/services/worker-service.ts)
**Problem**: Path `__dirname, '..', '..', 'plugin', 'scripts', 'mcp-server.cjs'`
only worked in dev structure, failed in packaged plugin.
**Error produced**:
```
Error: Cannot find module 'C:\Users\...\claude-mem\plugin\scripts\mcp-server.cjs'
[ERROR] [SYSTEM] Background initialization failed MCP error -32000: Connection closed
```
**Fix**: Changed to `path.join(__dirname, 'mcp-server.cjs')` since mcp-server.cjs
is in the same directory as worker-service.cjs after bundling.
## Bug 3: Missing smart-install.js in plugin package
**Problem**: smart-install.js was referenced in hooks.json but not included
in the plugin/ directory for cache deployment.
**Fix**: Added `plugin/scripts/smart-install.js` that uses `createRequire()`
to resolve modules from MARKETPLACE_ROOT.
## Bug 4: hooks.json incorrect path
**Problem**: Referenced `/../scripts/smart-install.js` but CLAUDE_PLUGIN_ROOT
points to the plugin/ directory.
**Fix**: Changed to `/scripts/smart-install.js`.
## Bug 5: Windows Worker Startup - Visible Console Windows
**Problem**: PM2 ignores windowsHide option on Windows, opening visible
console windows when starting the worker service.
**Fix**: Use PowerShell `Start-Process -WindowStyle Hidden` on Windows while
keeping PM2 for Unix systems (src/shared/worker-utils.ts).
## Additional Improvements
- Increased worker startup timeouts for Windows (500ms health check, 1000ms
wait between retries, 15 retries = 15s total vs previous 5s)
- Added `windowsHide: true` to root ecosystem.config.cjs for PM2
## Note on Assertion Failure
The Windows libuv assertion failure `!(handle->flags & UV_HANDLE_CLOSING)`
at `src\win\async.c:76` is a known upstream issue in Claude Code (Issue #7579),
triggered by fetch() calls on Windows. This is NOT caused by worker spawning
and cannot be fixed in claude-mem.
Tested on Windows 11 with Node.js v24.
Fixes#193🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Updated all documentation references from search-server to mcp-server
- Removed legacy search-server.cjs file
- Updated debug log messages to use [mcp-server] prefix
- Updated build output references in docs
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Introduced PrivacyCheckValidator class to encapsulate logic for checking if user prompts are private.
- Updated SessionRoutes to utilize PrivacyCheckValidator for determining prompt privacy during observation and summarization operations.
- Removed duplicate privacy check logic from SessionRoutes, improving code maintainability and readability.
- Added SessionEventBroadcaster to handle broadcasting of session lifecycle events, consolidating SSE broadcasting and processing status updates.
- Refactored SessionRoutes to utilize SessionEventBroadcaster for broadcasting events related to new prompts, session starts, and completions.
- Created SessionCompletionHandler to centralize session completion logic, reducing duplication across multiple endpoints.
- Updated WorkerService to initialize SessionEventBroadcaster and pass it to SessionRoutes.
- Introduced SettingsDefaultsManager to centralize default settings and loading logic.
- Updated context-generator, SDKAgent, SettingsRoutes, and worker-utils to utilize the new manager for loading settings.
- Removed redundant code for reading settings from files and environment variables.
- Ensured fallback to default values when settings file is missing or invalid.
- Introduced BaseRouteHandler class to centralize error handling and response management.
- Updated SettingsRoutes to use wrapHandler for automatic error logging and response.
- Refactored ViewerRoutes to extend BaseRouteHandler and utilize wrapHandler for health check and UI serving.
- Enhanced error handling in SettingsRoutes and ViewerRoutes for better maintainability and readability.
Remove cleanupOrphanedProcesses() method that was solving an old problem and is no longer needed. This method was platform-specific (crashes on Windows) and adds unnecessary complexity.
Changes:
- Delete cleanupOrphanedProcesses() method (28 lines)
- Remove call from initializeBackground()
- Worker starts cleanly without attempting process cleanup
Benefits:
- Simpler startup sequence
- Cross-platform compatibility (no pgrep/pkill)
- Reduced code complexity (YAGNI principle)
- No functional impact (orphaned processes indicate separate issues)
Phase 4 of Worker Service Quality Improvements Plan
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Extracted SQL query from handleSessionInit route handler into SessionStore.getLatestUserPrompt()
method to fix abstraction leak and improve type safety.
Changes:
- Added getLatestUserPrompt() method to SessionStore with proper return type
- Replaced raw SQL query in SessionRoutes with type-safe method call
- Removed direct database access through dbManager.getSessionStore().db
- Improved separation of concerns (data layer vs HTTP layer)
Benefits:
- Type safety: Explicit return type instead of 'as any' cast
- Maintainability: SQL query logic belongs in data layer
- Testability: Can test query logic independently from HTTP layer
- Consistency: Follows existing pattern of query methods in SessionStore
Phase 3 Complete: SQL abstraction leak fixed in session init endpoint.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Extracted duplicated generator auto-start logic (44 lines × 4 occurrences) into
single private method ensureGeneratorRunning() that accepts source parameter.
Benefits:
- Reduced code duplication from 72 lines to 24 lines (net -48 lines)
- Single source of truth for generator lifecycle management
- Improved maintainability - changes only needed in one place
- Better logging with parameterized source tracking
Phase 2 Complete: All 4 handler methods now use shared method:
- handleObservations (legacy endpoint)
- handleSummarize (legacy endpoint)
- handleObservationsByClaudeId (new endpoint)
- handleSummarizeByClaudeId (new endpoint)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Changed searchRoutes property to be of type SearchRoutes | null.
- Initialized searchRoutes to null instead of using a temporary type assertion.
- Removed conditional setup for searchRoutes in setupRoutes method, as it will be handled after database initialization.
- Added optional chaining and nullish coalescing to handle potential undefined values in Chroma results and timeline items.
- Updated logging statements to provide clearer information when no results are found.
- Refactored destructuring of parameters in findByConcept and findByFile methods for consistency.
- Introduced SearchManager to handle search operations directly instead of proxying to MCP server.
- Updated WorkerService to initialize SearchManager after database setup.
- Modified SearchRoutes to call SearchManager methods for search operations.
- Adjusted SearchManager to manage timeline and formatting services.
- Enhanced error handling and logging for search operations.
- Extracted timeline-related functionality from mcp-server.ts to a dedicated TimelineService class.
- Added methods to build, filter, and format timeline items based on observations, sessions, and prompts.
- Introduced interfaces for TimelineItem and TimelineData to standardize data structures.
- Implemented sorting and grouping of timeline items by date, with markdown formatting for output.
- Included utility methods for date and time formatting, as well as token estimation.
- Updated logging in `search-server.ts` to use `silentDebug` for non-critical messages, reducing console noise.
- Added a health check endpoint in `worker-service.ts` to improve service monitoring.
- Modified the worker service startup process to start the HTTP server immediately and perform slow initialization in the background.
- Refactored database initialization in `Database.ts` to use the correct `Database` class.
- Implemented a port availability check in `context-hook.ts` to ensure the worker service is ready before making requests.
Major architectural improvements to the worker service:
- Extracted monolithic WorkerService (~1900 lines) into organized route classes
- New HTTP layer with dedicated route handlers:
- SessionRoutes: Session lifecycle operations
- DataRoutes: Data retrieval endpoints
- SearchRoutes: Search/MCP proxy operations
- SettingsRoutes: Settings and configuration
- ViewerRoutes: Health, UI, and SSE streaming
- Added comprehensive README documenting worker architecture
- Improved build script to handle worker service compilation
- Added context-generator for hook context operations
This is Phase 1 of worker refactoring - pure code reorganization with zero
functional changes. All existing behavior preserved while improving
maintainability and code organization.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: Add Context Injection Settings modal with terminal preview
Adds a new settings modal accessible from the viewer UI header that allows users to configure context injection parameters with a live terminal preview showing how observations will appear.
Changes:
- New ContextSettingsModal component with auto-saving settings
- TerminalPreview component for live context visualization
- useContextPreview hook for fetching preview data
- Modal positioned to left of color mode button
- Settings sync with backend via worker service API
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: Add demo data and modify contextHook for cm_demo_content project
- Introduced DEMO_OBSERVATIONS and DEMO_SUMMARIES for the cm_demo_content project to provide mock data for testing and demonstration purposes.
- Updated contextHook to utilize demo data when the project is cm_demo_content, filtering observations based on configured types and concepts.
- Adjusted the worker service to use the contextHook with demo data, ensuring ANSI rendering for terminal output.
- Enhanced error handling and ensured proper closure of database connections.
* feat: add GitHub stars button with dynamic star count
- Implemented a new GitHubStarsButton component that fetches and displays the star count for a specified GitHub repository.
- Added useGitHubStars hook to handle API requests and state management for star count.
- Created formatStarCount utility function to format the star count into compact notation (k/M suffixes).
- Styled the GitHub stars button to match existing UI components, including hover and active states.
- Updated Header component to include the new GitHubStarsButton, replacing the static GitHub link.
- Added responsive styles to hide the GitHub stars button on mobile devices.
* feat: add API endpoint to fetch distinct projects and update context settings modal
- Implemented a new API endpoint `/api/projects` in `worker-service.ts` to retrieve a list of distinct projects from the observations.
- Modified `ContextSettingsModal.tsx` to replace the current project display with a dropdown for selecting projects, utilizing the fetched project list.
- Updated `useContextPreview.ts` to fetch projects on mount and manage the selected project state.
- Removed the `currentProject` prop from `ContextSettingsModal` and `App` components as it is now managed internally within the modal.
* Enhance Context Settings Modal and Terminal Preview
- Updated the styling of the Context Settings Modal for a modern clean design, including improved backdrop, header, and body layout.
- Introduced responsive design adjustments for smaller screens.
- Added custom scrollbar styles for better user experience.
- Refactored the TerminalPreview component to utilize `ansi-to-html` for rendering ANSI content, improving text display.
- Implemented new font variables for terminal styling across the application.
- Enhanced checkbox and input styles in the settings panel for better usability and aesthetics.
- Improved the layout and structure of settings groups and chips for a more organized appearance.
* Refactor UI components for compact design and enhance MCP toggle functionality
- Updated grid layout in viewer.html and viewer-template.html for better space utilization.
- Reduced padding and font sizes in settings groups, filter chips, and form controls for a more compact appearance.
- Implemented MCP toggle state management in ContextSettingsModal with API integration for status fetching and toggling.
- Reorganized settings groups for clarity, renaming and consolidating sections for improved user experience.
- Added feedback mechanism for MCP toggle status to inform users of changes and errors.
* feat: add collapsible sections, chip groups, form fields with tooltips, and toggle switches in settings modal
- Implemented collapsible sections for better organization of settings.
- Added chip groups with select all/none functionality for observation types and concepts.
- Enhanced form fields with optional tooltips for better user guidance.
- Introduced toggle switches for various settings, improving user interaction.
- Updated styles for new components to ensure consistency and responsiveness.
- Refactored ContextSettingsModal to utilize new components and improve readability.
- Improved TerminalPreview component styling for better layout and usability.
* Refactor modal header and preview selector styles; enhance terminal preview functionality
- Updated modal header padding and added gap for better spacing.
- Introduced a new header-controls section to include a project preview selector.
- Enhanced the preview selector styles for improved usability and aesthetics.
- Adjusted the preview column styles for a cleaner look.
- Implemented word wrap toggle functionality in the TerminalPreview component, allowing users to switch between wrapped and scrollable text.
- Improved scroll position handling in TerminalPreview to maintain user experience during content updates.
* feat: enhance modal settings with new icon links and update header controls
- Added new modal icon links for documentation and social media in ContextSettingsModal.
- Updated the header to remove sidebar toggle functionality and replaced it with context preview toggle.
- Refactored styles for modal icon links to improve UI/UX.
- Removed sidebar component from App and adjusted related state management.
* chore: remove abandoned cm_demo_content demo data approach
The demo data feature was prototyped but didn't work out. Removes:
- DEMO_OBSERVATIONS and DEMO_SUMMARIES arrays
- Conditional logic that bypassed DB for demo project
- Demo mode check in prior message extraction
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Updated context configuration loading path from ~/.claude/settings.json to ~/.claude-mem/settings.json.
- Modified the extractPriorMessages function to focus on retrieving the last assistant message only, removing user message extraction.
- Enhanced output formatting for displaying prior assistant messages in the context hook.
- Added new settings related to token economics and observation filtering in the useSettings hook.
- Introduced `observation-metadata.ts` to define valid observation types and concepts, along with their corresponding emoji mappings.
- Updated `context-hook.ts` to utilize new constants for observation types and concepts, enhancing maintainability.
- Refactored `worker-service.ts` to validate observation types and concepts against the new centralized constants.
- Consolidated settings management in `Sidebar.tsx` to streamline state handling for context settings.
- Improved error handling and logging for context loading failures.
- Added ContextConfig interface and loadContextConfig function to manage context settings.
- Implemented validation for context settings in WorkerService.
- Updated Sidebar component to include new context settings for token economics, observation filtering, display configuration, and feature toggles.
- Introduced default settings for new context features.
- Adjusted types to accommodate new settings in the application state.
* feat: Add dual-tag system for meta-observation control
Implements <private> and <claude-mem-context> tag stripping at hook layer
to give users fine-grained control over what gets persisted in observations
and enable future real-time context injection without recursive storage.
**Features:**
- stripMemoryTags() function in save-hook.ts
- Strips both <private> and <claude-mem-context> tags before sending to worker
- Always active (no configuration needed)
- Comprehensive test suite (19 tests, all passing)
- User documentation for <private> tag
- Technical architecture documentation
**Architecture:**
- Edge processing pattern (filter at hook, not worker)
- Defensive type handling with silentDebug
- Supports multiline, nested, and multiple tags
- Enables strategic orchestration for internal tools
**User-Facing:**
- <private> tag for manual privacy control (documented)
- Prevents sensitive data from persisting in observations
**Infrastructure:**
- <claude-mem-context> tag ready for real-time context feature
- Prevents recursive storage when context injection ships
**Files:**
- src/hooks/save-hook.ts: Core implementation
- tests/strip-memory-tags.test.ts: Test suite (19/19 passing)
- docs/public/usage/private-tags.mdx: User guide
- docs/public/docs.json: Navigation update
- docs/context/dual-tag-system-architecture.md: Technical docs
- plugin/scripts/save-hook.js: Built hook
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: Strip private tags from user prompts and skip memory ops for fully private prompts
Fixes critical privacy bug where <private> tags were not being stripped from
user prompts before storage in user_prompts table, making private content
searchable via mem-search.
Changes:
1. new-hook.ts: Skip memory operations for fully private prompts
- If cleaned prompt is empty after stripping tags, skip saveUserPrompt
- Skip worker init to avoid wasting resources on empty prompts
- Logs: "(fully private - skipped)"
2. save-hook.ts: Skip observations for fully private prompts
- Check if user prompt was entirely private before creating observations
- Respects user intent: fully private prompt = no observations at all
- Prevents "thoughts pop up" issue where private prompts create public observations
3. SessionStore.ts: Add getUserPrompt() method
- Retrieves prompt text by session_id and prompt_number
- Used by save-hook to check if prompt was private
4. Tests: Added 4 new tests for fully private prompt detection (16 total, all passing)
5. Docs: Updated private-tags.mdx to reflect correct behavior
- User prompts ARE now filtered before storage
- Private content never reaches database or search indices
Privacy Protection:
- Fully private prompts: No user_prompt saved, no worker init, no observations
- Partially private prompts: Tags stripped, content sanitized before storage
- Zero leaks: Private content never indexed or searchable
Addresses reviewer feedback on PR #153 about user prompt filtering.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: Enhance memory tag handling and indexing in user prompts
- Added a new index `idx_user_prompts_lookup` on `user_prompts` for improved query performance based on `claude_session_id` and `prompt_number`.
- Refactored memory tag stripping functionality into dedicated utility functions: `stripMemoryTagsFromJson` and `stripMemoryTagsFromPrompt` for better separation of concerns and reusability.
- Updated hooks (`new-hook.ts` and `save-hook.ts`) to utilize the new tag stripping functions, ensuring private content is not stored or searchable.
- Removed redundant inline tag stripping functions from hooks to streamline code.
- Added tests for the new tag stripping utilities to ensure functionality and prevent regressions.
---------
Co-authored-by: Claude <noreply@anthropic.com>
Adds Version Channel section to Settings sidebar allowing users to:
- See current branch (main or beta/7.0) and stability status
- Switch to beta branch to access Endless Mode features
- Switch back to stable for production use
- Pull updates for current branch
Implementation:
- BranchManager.ts: Git operations for branch detection/switching
- worker-service.ts: /api/branch/* endpoints (status, switch, update)
- Sidebar.tsx: Version Channel UI with branch state and handlers
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
**Problem:**
- Summaries created with empty project names even after database fix
- 13 summaries had empty project, couldn't appear in context-hook
- In-memory sessions cached stale empty project value
**Root Cause:**
SessionManager caches ActiveSession objects in memory. When reusing
an existing session, it never refreshed the project field from the
database. Even though createSDKSession() now updates the DB with the
correct project, the in-memory session.project remained empty, causing
summaries to be stored with empty project.
**Flow:**
1. Session created with empty project (cached in memory)
2. new-hook UPDATE fixes project in database
3. SessionManager reuses cached session (stale project="")
4. Summary stored with session.project (empty)
5. Context-hook can't find summary (WHERE project = 'claude-mem')
**Solution:**
When SessionManager.initializeSession() reuses an existing session,
refresh the project field from the database. This ensures summaries
and observations always use the latest project value.
**Impact:**
- Future summaries will have correct project name
- Backfilled 13 historical summaries with project='claude-mem'
- Context injection will now show recent summaries
- Both observations AND summaries fixed
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
**Problem:**
- Sessions created with empty project names couldn't be updated
- INSERT OR IGNORE skipped updates when session already existed
- Context-hook couldn't find observations (WHERE project = 'claude-mem')
- 364 observations had empty project names
**Root Cause:**
createSDKSession() used INSERT OR IGNORE for idempotency, but never
updated project/prompt fields when session already existed. If SAVE hook
created session first (with empty project), NEW hook couldn't fix it.
**Solution:**
When INSERT is ignored (session exists), UPDATE project and user_prompt
if we have non-empty values. This ensures project name gets set even
when session was created by SAVE hook or with incomplete data.
**Impact:**
- New sessions will always have correct project name
- Backfilled 364 historical observations with project='claude-mem'
- Context injection will now work (finds observations by project)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Refactor code structure for improved readability and maintainability
* Add test results for search API and related functionalities
- Created test result files for various search-related functionalities, including:
- test-11-search-server-changes.json
- test-12-context-hook-changes.json
- test-13-worker-service-changes.json
- test-14-patterns.json
- test-15-gotchas.json
- test-16-discoveries.json
- test-17-all-bugfixes.json
- test-18-all-features.json
- test-19-all-decisions.json
- test-20-session-search.json
- test-21-prompt-search.json
- test-22-decisions-endpoint.json
- test-23-changes-endpoint.json
- test-24-how-it-works-endpoint.json
- test-25-contextualize-endpoint.json
- test-26-timeline-around-observation.json
- test-27-multi-param-combo.json
- test-28-file-type-combo.json
- Each test result file captures specific search failures or outcomes, including issues with undefined properties and successful execution of search queries.
- Enhanced documentation of search architecture and testing strategies, ensuring compliance with established guidelines and improving overall search functionality.
* feat: Enhance unified search API with catch-all parameters and backward compatibility
- Implemented a unified search API at /api/search that accepts catch-all parameters for filtering by type, observation type, concepts, and files.
- Maintained backward compatibility by keeping granular endpoints functional while routing through the same infrastructure.
- Completed comprehensive testing of search capabilities with real-world query scenarios.
fix: Address missing debug output in search API query tests
- Flushed PM2 logs and executed search queries to verify functionality.
- Diagnosed absence of "Raw Chroma" debug messages in worker logs, indicating potential issues with logging or query processing.
refactor: Improve build and deployment pipeline for claude-mem plugin
- Successfully built and synced all hooks and services to the marketplace directory.
- Ensured all dependencies are installed and up-to-date in the deployment location.
feat: Implement hybrid search filters with 90-day recency window
- Enhanced search server to apply a 90-day recency filter to Chroma results before categorizing by document type.
fix: Correct parameter handling in searchUserPrompts method
- Added support for filter-only queries and improved dual-path logic for clarity.
refactor: Rename FTS5 method to clarify fallback status
- Renamed escapeFTS5 to escapeFTS5_fallback_when_chroma_unavailable to indicate its temporary usage.
feat: Introduce contextualize tool for comprehensive project overview
- Added a new tool to fetch recent observations, sessions, and user prompts, providing a quick project overview.
feat: Add semantic shortcut tools for common search patterns
- Implemented 'decisions', 'changes', and 'how_it_works' tools for convenient access to frequently searched observation categories.
feat: Unified timeline tool supports anchor and query modes
- Combined get_context_timeline and get_timeline_by_query into a single interface for timeline exploration.
feat: Unified search tool added to MCP server
- New tool queries all memory types simultaneously, providing combined chronological results for improved search efficiency.
* Refactor search functionality to clarify FTS5 fallback usage
- Updated `worker-service.cjs` to replace FTS5 fallback function with a more descriptive name and improved error handling.
- Enhanced documentation in `SKILL.md` to specify the unified API endpoint and clarify the behavior of the search engine, including the conditions under which FTS5 is used.
- Modified `search-server.ts` to provide clearer logging and descriptions regarding the fallback to FTS5 when UVX/Python is unavailable.
- Renamed and updated the `SessionSearch.ts` methods to reflect the conditions for using FTS5, emphasizing the lack of semantic understanding in fallback scenarios.
* feat: Add ID-based fetch endpoints and simplify mem-search skill
**Problem:**
- Search returns IDs but no way to fetch by ID
- Skill documentation was bloated with too many options
- Claude wasn't using IDs because we didn't tell it how
**Solution:**
1. Added three new HTTP endpoints:
- GET /api/observation/:id
- GET /api/session/:id
- GET /api/prompt/:id
2. Completely rewrote SKILL.md:
- Stripped complexity down to essentials
- Clear 3-step prescriptive workflow: Search → Review IDs → Fetch by ID
- Emphasized ID usage: "The IDs are there for a reason - USE THEM"
- Removed confusing multi-endpoint documentation
- Kept only unified search with filters
**Impact:**
- Token efficiency: Claude can now fetch full details only for relevant IDs
- Clarity: One clear workflow instead of 10+ options to choose from
- Usability: IDs are no longer wasted context - they're actionable
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* chore: Move internal docs to private directory
Moved POSTMORTEM and planning docs to ./private to exclude from PR reviews.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: Remove experimental contextualize endpoint
- Removed contextualize MCP tool from search-server (saves ~4KB)
- Disabled FTS5 fallback paths in SessionSearch (now vector-first)
- Cleaned up CLAUDE.md documentation
- Removed contextualize-rewrite-plan.md doc
Rationale:
- Contextualize is better suited as a skill (LLM-powered) than an endpoint
- Search API already provides vector search with configurable limits
- Created issue #132 to track future contextualize skill implementation
Changes:
- src/servers/search-server.ts: Removed contextualize tool definition
- src/services/sqlite/SessionSearch.ts: Disabled FTS5 fallback, added deprecation warnings
- CLAUDE.md: Cleaned up outdated skill documentation
- docs/: Removed contextualize plan document
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: Complete FTS5 cleanup - remove all deprecated search code
This completes the FTS5 cleanup work by removing all commented-out
FTS5 search code while preserving database tables for backward compatibility.
Changes:
- Removed 200+ lines of commented FTS5 search code from SessionSearch.ts
- Removed deprecated degraded_search_query__when_uvx_unavailable method
- Updated all method documentation to clarify vector-first architecture
- Updated class documentation to reflect filter-only query support
- Updated CLAUDE.md to remove FTS5 search references
- Clarified that FTS5 tables exist for backward compatibility only
- Updated "Why SQLite FTS5" section to "Why Vector-First Search"
Database impact: NONE - FTS5 tables remain intact for existing installations
Search architecture:
- ChromaDB: All text-based vector search queries
- SQLite: Filter-only queries (date ranges, metadata, no query text)
- FTS5 tables: Maintained but unused (backward compatibility)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: Remove all FTS5 fallback execution code from search-server
Completes the FTS5 cleanup by removing all fallback execution paths
that attempted to use FTS5 when ChromaDB was unavailable.
Changes:
- Removed all FTS5 fallback code execution paths
- When ChromaDB fails or is unavailable, return empty results with helpful error messages
- Updated all deprecated tool descriptions (search_observations, search_sessions, search_user_prompts)
- Changed error messages to indicate FTS5 fallback has been removed
- Added installation instructions for UVX/Python when vector search is unavailable
- Updated comments from "hybrid search" to "vector-first search"
- Removed ~100 lines of dead FTS5 fallback code
Database impact: NONE - FTS5 tables remain intact (backward compatibility)
Search behavior when ChromaDB unavailable:
- Text queries: Return empty results with error explaining ChromaDB is required
- Filter-only queries (no text): Continue to work via direct SQLite
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: Address PR 133 review feedback
Critical fixes:
- Remove contextualize endpoint from worker-service (route + handler)
- Fix build script logging to show correct .cjs extension (was .mjs)
Documentation improvements:
- Add comprehensive FTS5 retention rationale documentation
- Include v7.0.0 removal TODO for future cleanup
Testing:
- Build succeeds with correct output logging
- Worker restarts successfully (30th restart)
- Contextualize endpoint properly removed (404 response)
- Search endpoint verified working
This addresses all critical review feedback from PR 133.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Implements a visual badge that displays the count of active work items (queued + currently processing) in the worker service. The badge appears next to the claude-mem logo and updates in real-time via SSE.
Features:
- Shows count of pending messages + active SDK generators
- Only displays when queueDepth > 0
- Subtle pulse animation for visual feedback
- Theme-aware styling
Backend changes:
- Added getTotalActiveWork() method to SessionManager
- Updated worker-service to broadcast queueDepth via SSE
- Enhanced processing status API endpoint
Frontend changes:
- Updated Header component to display queue bubble
- Enhanced useSSE hook to track queueDepth state
- Added CSS styling with pulse animation
Closes#122Closes#96Closes#97🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added a new script to simulate token savings from Endless Mode using real observation data.
- Introduced functions to calculate token costs with and without Endless Mode, showcasing the differences in context handling.
- Enhanced output to display detailed token usage statistics and potential savings at scale.
- Integrated assumptions for user activity to estimate weekly and annual token savings.
- Updated worker-utils to automatically start the worker using PM2 if not running, improving service reliability.
Root cause: The ensureDiscoveryTokensColumn migration was using version 7,
which was already taken by removeSessionSummariesUniqueConstraint. This
duplicate version number caused migration tracking issues in some databases.
Changes:
- Updated migration version from 7 to 11 (next available)
- Added schema_versions check to prevent unnecessary re-runs
- Updated comments to clarify the version number conflict
- Added error propagation (already present, but now more reliable)
This resolves issue #121 where users were seeing "no such column: discovery_tokens"
errors after upgrading to v6.0.6.
Affected users can manually add the columns:
ALTER TABLE observations ADD COLUMN discovery_tokens INTEGER DEFAULT 0;
ALTER TABLE session_summaries ADD COLUMN discovery_tokens INTEGER DEFAULT 0;
Or wait for v6.0.7 release which includes this fix.
Fixes#121🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Implemented a new method `cleanupOrphanedProcesses` to identify and terminate orphaned `uvx` processes from previous sessions.
- Integrated the cleanup method into the `start` process of the WorkerService to ensure a clean environment at startup.
- Added logging for process cleanup actions and handled potential errors gracefully without failing the service startup.
