- Enhanced error handling in summary generation by using fallback messages for missing assistant messages.
- Updated the `buildSummaryPrompt` function to streamline the retrieval of the last assistant message.
- Improved the `extractLastMessage` function to log errors when transcript files are missing or empty, and to ensure proper handling of messages without content.
- Added checks to ensure that messages of the specified role are found in the transcript, with appropriate logging for missing messages.
- Refactored the logging mechanism to provide clearer insights into processing failures and successes.
- Added a new line after the command to run for restarting the worker in the error message.
- Included an additional instruction to restart Claude Code after running the worker restart command.
* Enhance error logging in hooks
- Added detailed error logging in context-hook, new-hook, save-hook, and summary-hook to capture status, project, port, and relevant session information on failures.
- Improved error messages thrown in save-hook and summary-hook to include specific context about the failure.
* Refactor migration logging to use console.log instead of console.error
- Updated SessionSearch and SessionStore classes to replace console.error with console.log for migration-related messages.
- Added notes in the documentation to clarify the use of console.log for migration messages due to the unavailability of the structured logger during constructor execution.
* Refactor SDKAgent and silent-debug utility to simplify error handling
- Updated SDKAgent to use direct defaults instead of happy_path_error__with_fallback for non-critical fields such as last_user_message, last_assistant_message, title, filesRead, filesModified, concepts, and summary.request.
- Enhanced silent-debug documentation to clarify appropriate use cases for happy_path_error__with_fallback, emphasizing its role in handling unexpected null/undefined values while discouraging its use for nullable fields with valid defaults.
* fix: correct happy_path_error__with_fallback usage to prevent false errors
Fixes false "Missing cwd" and "Missing transcript_path" errors that were
flooding silent.log even when values were present.
Root cause: happy_path_error__with_fallback was being called unconditionally
instead of only when the value was actually missing.
Pattern changed from:
value: happy_path_error__with_fallback('Missing', {}, value || '')
To correct usage:
value: value || happy_path_error__with_fallback('Missing', {}, '')
Fixed in:
- src/hooks/save-hook.ts (PostToolUse hook)
- src/hooks/summary-hook.ts (Stop hook)
- src/services/worker/http/routes/SessionRoutes.ts (2 instances)
Impact: Eliminates false error noise, making actual errors visible.
Addresses issue #260 - users were seeing "Missing cwd" errors despite
Claude Code correctly passing all required fields.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* Enhance error logging and handling across services
- Improved error messages in SessionStore to include project context when fetching boundary observations and timestamps.
- Updated ChromaSync error handling to provide more informative messages regarding client initialization failures, including the project context.
- Enhanced error logging in WorkerService to include the package path when reading version fails.
- Added detailed error logging in worker-utils to capture expected and running versions during health checks.
- Extended WorkerErrorMessageOptions to include actualError for more informative restart instructions.
* Refactor error handling in hooks to use standardized fetch error handler
- Introduced a new error handler `handleFetchError` in `shared/error-handler.ts` to standardize logging and user-facing error messages for fetch failures across hooks.
- Updated `context-hook.ts`, `new-hook.ts`, `save-hook.ts`, and `summary-hook.ts` to utilize the new error handler, improving consistency and maintainability.
- Removed redundant imports and error handling logic related to worker restart instructions from the hooks.
* feat: add comprehensive error handling tests for hooks and ChromaSync client
---------
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Fixes ENOENT error on first install when ~/.claude-mem/ directory
doesn't exist yet. The startWorker() function tried to write the
.pm2-migrated marker file without first creating the parent directory.
Fixes#259🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Removes bun-wrapper indirection. Hooks are compiled JavaScript that work perfectly with Node. Worker still uses Bun where performance matters. Fixes#264
- Updated multiple hooks (context-hook, new-hook, save-hook, summary-hook, user-message-hook) to throw errors using `getWorkerRestartInstructions` for improved user guidance on worker connection issues.
- Enhanced `handleWorkerError` function to utilize the new error message generator for consistent error reporting.
- Modified `ensureWorkerRunning` function to provide detailed instructions based on the worker's state, including port information.
- Introduced `getWorkerRestartInstructions` utility in `error-messages.ts` to generate platform-aware error messages for worker failures.
Updated built plugin files with latest changes including localhost
binding security improvements and enhanced runtime detection.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Critical improvement for seamless upgrades across all versions.
Changes:
1. Added /api/version endpoint to worker service
- Returns current worker version from package.json
2. Added version checking in worker-utils.ts
- getPluginVersion() - reads plugin's package.json version
- getWorkerVersion() - fetches version from worker API
- ensureWorkerVersionMatches() - compares and restarts if needed
3. Modified ensureWorkerRunning()
- Now calls ensureWorkerVersionMatches() after health check
- Automatically restarts worker when version mismatch detected
- Logs version mismatch for debugging
Impact:
- Users no longer need to manually restart worker after upgrades
- Eliminates connection errors from running old worker code
- Critical for v7.1.1 (Bun auto-install) and all future releases
- Fixes the issue where PR #236 changes weren't applied until manual restart
Testing:
- Version endpoint working: returns {"version":"7.1.0"}
- Worker health check: passing
- Auto-restart logic: triggers on version mismatch
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Previously skipped Windows PM2 cleanup based on assumption that PM2
wasn't used on Windows. However, this left potential orphaned processes.
Changes:
- Remove platform check (process.platform !== 'win32')
- Run PM2 cleanup on Mac/Linux/Windows consistently
- Create .pm2-migrated marker on all platforms
- Update documentation to reflect cross-platform behavior
Rationale:
- Quality migration should clean up ALL orphaned processes
- Error handling (try/catch) already makes this safe
- Even if PM2 had Windows issues, cleanup won't hurt
- Consistent behavior across platforms is better UX
Impact:
- Windows users will get PM2 cleanup on first hook trigger
- Marker file now created on Windows (prevents repeated attempts)
- No breaking changes (errors caught and ignored)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Implemented a method to check if Bun is available in the system PATH.
- Updated the startWithBun method to return an error if Bun is not found.
- Enhanced PID file parsing to validate required fields and their types.
- Cleaned up stale PID files if the process is no longer alive.
fix(SettingsRoutes): clear port cache after updating settings
- Added a call to clearPortCache after writing updated settings to ensure the application uses the latest configuration.
- Updated shebangs in user-message-hook.js, worker-cli.js, and worker-service.cjs to use Bun instead of Node.
- Modified build-hooks.js to generate Bun-compatible shebangs in built scripts.
- Enhanced sync-marketplace.cjs to trigger a worker restart after syncing files via an HTTP request.
- Improved worker-cli.ts to exit with appropriate status codes after executing commands.
- Added build-worker-binary.js to create a Windows executable for the worker service using Bun's compile feature.
- Replaced hardcoded migration port with dynamic port retrieval using `getWorkerPort()` in worker-cli.ts.
- Updated context generator to clarify error handling comments.
- Introduced timeout constants in ProcessManager for better maintainability.
- Configured SQLite settings using constants for mmap size and cache size in DatabaseManager.
- Added timeout constants for Git and NPM commands in BranchManager.
- Enhanced error logging in FormattingService and SearchManager to provide more context on failures.
- Removed deprecated silentDebug function and replaced its usage with logger.debug.
- Updated tests to use dynamic worker port retrieval instead of hardcoded values.
- Introduced `/api/admin/restart` and `/api/admin/shutdown` endpoints in WorkerService for restarting and shutting down the service.
- Updated error message in hook-error-handler to provide clearer instructions for restarting the worker.
- Refactored worker-utils to remove PM2 dependency and implement ProcessManager for starting the worker service.
- Cleaned up legacy PM2 references and provided new manual start instructions.
* 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>
- Enhanced logging functionality in user-message-hook.js to include better formatting and error handling.
- Updated worker-utils.ts to escape single quotes in PowerShell commands and added checks for global PM2 installation.
- Improved readability and maintainability of the code by restructuring and clarifying variable names.
**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.
- 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>
- 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.
* fix: Hide console window on Windows when spawning child processes
Add windowsHide: true to spawnSync and execSync calls to prevent
empty console windows from appearing on Windows when hooks execute.
Fixes two spawn points:
- worker-utils.ts: PM2 spawn when starting worker service
- user-message-hook.ts: Node spawn for context display
Reference: https://nodejs.org/api/child_process.html (windowsHide option)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: Add windowsHide to remaining execSync calls for complete Windows console window hiding
This completes the Windows console window fix by adding `windowsHide: true` to all remaining `execSync` calls:
- src/services/worker-service.ts:220 - pgrep command for orphaned process detection
- src/services/worker-service.ts:226 - pkill command for process cleanup
- src/services/worker/SDKAgent.ts:414 - where/which claude command for finding executable
These operations are less frequent than the user-prompt hook, but should still avoid spawning console windows on Windows for a complete fix.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Alex Newman <thedotmack@users.noreply.github.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Alex Newman <thedotmack@users.noreply.github.com>
* 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>
**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>
- Updated `new-hook.js` and `save-hook.js` to enhance logging functionality, including better error messages and structured logging.
- Improved the handling of worker startup in `summary-hook.js` and `worker-utils.ts`, ensuring proper directory context for PM2.
- Added checks for worker health and streamlined session management across hooks.
- 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>
* feat: Add discovery_tokens for ROI tracking in observations and session summaries
- Introduced `discovery_tokens` column in `observations` and `session_summaries` tables to track token costs associated with discovering and creating each observation and summary.
- Updated relevant services and hooks to calculate and display ROI metrics based on discovery tokens.
- Enhanced context economics reporting to include savings from reusing previous observations.
- Implemented migration to ensure the new column is added to existing tables.
- Adjusted data models and sync processes to accommodate the new `discovery_tokens` field.
* refactor: streamline context hook by removing unused functions and updating terminology
- Removed the estimateTokens and getObservations helper functions as they were not utilized.
- Updated the legend and output messages to replace "discovery" with "work" for clarity.
- Changed the emoji representation for different observation types to better reflect their purpose.
- Enhanced output formatting for improved readability and understanding of token usage.
* Refactor user-message-hook and context-hook for improved clarity and functionality
- Updated user-message-hook.js to enhance error messaging and improve variable naming for clarity.
- Modified context-hook.ts to include a new column key section, improved context index instructions, and added emoji icons for observation types.
- Adjusted footer messages in context-hook.ts to emphasize token savings and access to past research.
- Changed user-message-hook.ts to update the feedback and support message for clarity.
* fix: Critical ROI tracking fixes from PR review
Addresses critical findings from PR #111 review:
1. **Fixed incorrect discovery token calculation** (src/services/worker/SDKAgent.ts)
- Changed from passing cumulative total to per-response delta
- Now correctly tracks token cost for each observation/summary
- Captures token state before/after response processing
- Prevents all observations getting inflated cumulative values
2. **Fixed schema version mismatch** (src/services/sqlite/SessionStore.ts)
- Changed ensureDiscoveryTokensColumn() from version 11 to version 7
- Now matches migration007 definition in migrations.ts
- Ensures consistent version tracking across migration system
These fixes ensure ROI metrics accurately reflect token costs.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: Update search documentation to reflect hybrid ChromaDB architecture
The backend correctly implements ChromaDB-first semantic search with SQLite
temporal ordering and FTS5 fallback, but documentation incorrectly described
it as "FTS5 full-text search". This fix aligns all skill guides and tool
descriptions with the actual implementation.
Changes:
- Update SKILL.md to describe hybrid architecture with ChromaDB primary
- Update observations.md title and query parameter descriptions
- Update all three search tool descriptions in search-server.ts:
* search_observations
* search_sessions
* search_user_prompts
All tools now correctly document:
- ChromaDB semantic search (primary ranking)
- 90-day recency filter
- SQLite temporal ordering
- FTS5 fallback (when ChromaDB unavailable)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: Add discovery_tokens column to observations and session_summaries tables
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat: Add discovery_tokens for ROI tracking in observations and session summaries
- Introduced `discovery_tokens` column in `observations` and `session_summaries` tables to track token costs associated with discovering and creating each observation and summary.
- Updated relevant services and hooks to calculate and display ROI metrics based on discovery tokens.
- Enhanced context economics reporting to include savings from reusing previous observations.
- Implemented migration to ensure the new column is added to existing tables.
- Adjusted data models and sync processes to accommodate the new `discovery_tokens` field.
* refactor: streamline context hook by removing unused functions and updating terminology
- Removed the estimateTokens and getObservations helper functions as they were not utilized.
- Updated the legend and output messages to replace "discovery" with "work" for clarity.
- Changed the emoji representation for different observation types to better reflect their purpose.
- Enhanced output formatting for improved readability and understanding of token usage.
* Refactor user-message-hook and context-hook for improved clarity and functionality
- Updated user-message-hook.js to enhance error messaging and improve variable naming for clarity.
- Modified context-hook.ts to include a new column key section, improved context index instructions, and added emoji icons for observation types.
- Adjusted footer messages in context-hook.ts to emphasize token savings and access to past research.
- Changed user-message-hook.ts to update the feedback and support message for clarity.
* fix: Critical ROI tracking fixes from PR review
Addresses critical findings from PR #111 review:
1. **Fixed incorrect discovery token calculation** (src/services/worker/SDKAgent.ts)
- Changed from passing cumulative total to per-response delta
- Now correctly tracks token cost for each observation/summary
- Captures token state before/after response processing
- Prevents all observations getting inflated cumulative values
2. **Fixed schema version mismatch** (src/services/sqlite/SessionStore.ts)
- Changed ensureDiscoveryTokensColumn() from version 11 to version 7
- Now matches migration007 definition in migrations.ts
- Ensures consistent version tracking across migration system
These fixes ensure ROI metrics accurately reflect token costs.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
* refactor: Reduce continuation prompt token usage by 95 lines
Removed redundant instructions from continuation prompt that were originally
added to mitigate a session continuity issue. That issue has since been
resolved, making these detailed instructions unnecessary on every continuation.
Changes:
- Reduced continuation prompt from ~106 lines to ~11 lines (~95 line reduction)
- Changed "User's Goal:" to "Next Prompt in Session:" (more accurate framing)
- Removed redundant WHAT TO RECORD, WHEN TO SKIP, and OUTPUT FORMAT sections
- Kept concise reminder: "Continue generating observations and progress summaries..."
- Initial prompt still contains all detailed instructions
Impact:
- Significant token savings on every continuation prompt
- Faster context injection with no loss of functionality
- Instructions remain comprehensive in initial prompt
Files modified:
- src/sdk/prompts.ts (buildContinuationPrompt function)
- plugin/scripts/worker-service.cjs (compiled output)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: Enhance observation and summary prompts for clarity and token efficiency
* Enhance prompt clarity and instructions in prompts.ts
- Added a reminder to think about instructions before starting work.
- Simplified the continuation prompt instruction by removing "for this ongoing session."
* feat: Enhance settings.json with permissions and deny access to sensitive files
refactor: Remove PLAN-full-observation-display.md and PR_SUMMARY.md as they are no longer needed
chore: Delete SECURITY_SUMMARY.md since it is redundant after recent changes
fix: Update worker-service.cjs to streamline observation generation instructions
cleanup: Remove src-analysis.md and src-tree.md for a cleaner codebase
refactor: Modify prompts.ts to clarify instructions for memory processing
* refactor: Remove legacy worker service implementation
* feat: Enhance summary hook to extract last assistant message and improve logging
- Added function to extract the last assistant message from the transcript.
- Updated summary hook to include last assistant message in the summary request.
- Modified SDKSession interface to store last assistant message.
- Adjusted buildSummaryPrompt to utilize last assistant message for generating summaries.
- Updated worker service and session manager to handle last assistant message in summarize requests.
- Introduced silentDebug utility for improved logging and diagnostics throughout the summary process.
* docs: Add comprehensive implementation plan for ROI metrics feature
Added detailed implementation plan covering:
- Token usage capture from Agent SDK
- Database schema changes (migration #8)
- Discovery cost tracking per observation
- Context hook display with ROI metrics
- Testing and rollout strategy
Timeline: ~20 hours over 4 days
Goal: Empirical data for YC application amendment
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: Add transcript processing scripts for analysis and formatting
- Implemented `dump-transcript-readable.ts` to generate a readable markdown dump of transcripts, excluding certain entry types.
- Created `extract-rich-context-examples.ts` to extract and showcase rich context examples from transcripts, highlighting user requests and assistant reasoning.
- Developed `format-transcript-context.ts` to format transcript context into a structured markdown format for improved observation generation.
- Added `test-transcript-parser.ts` for validating data extraction from transcript JSONL files, including statistics and error reporting.
- Introduced `transcript-to-markdown.ts` for a complete representation of transcript data in markdown format, showing all context data.
- Enhanced type definitions in `transcript.ts` to support new features and ensure type safety.
- Built `transcript-parser.ts` to handle parsing of transcript JSONL files, including error handling and data extraction methods.
* Refactor hooks and SDKAgent for improved observation handling
- Updated `new-hook.ts` to clean user prompts by stripping leading slashes for better semantic clarity.
- Enhanced `save-hook.ts` to include additional tools in the SKIP_TOOLS set, preventing unnecessary observations from certain command invocations.
- Modified `prompts.ts` to change the structure of observation prompts, emphasizing the observational role and providing a detailed XML output format for observations.
- Adjusted `SDKAgent.ts` to enforce stricter tool usage restrictions, ensuring the memory agent operates solely as an observer without any tool access.
* feat: Enhance session initialization to accept user prompts and prompt numbers
- Updated `handleSessionInit` in `worker-service.ts` to extract `userPrompt` and `promptNumber` from the request body and pass them to `initializeSession`.
- Modified `initializeSession` in `SessionManager.ts` to handle optional `currentUserPrompt` and `promptNumber` parameters.
- Added logic to update the existing session's `userPrompt` and `lastPromptNumber` if a `currentUserPrompt` is provided.
- Implemented debug logging for session initialization and updates to track user prompts and prompt numbers.
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat: Enhance summary hook to include last user message from transcript
- Added functionality to extract the last user message from a JSONL transcript file in the summary hook.
- Updated the summary hook to send the last user message along with the summary request.
- Modified the SDKSession interface to include an optional last_user_message field.
- Updated the summary prompt to incorporate the last user message in the output format.
- Refactored worker service to handle the last user message in the summarize queue.
- Enhanced session manager to track and broadcast processing status based on active sessions and queue depth.
- Improved error handling and logging for better traceability during transcript reading and processing.
* feat(worker): enhance processing status broadcasting and session management
- Added immediate broadcasting of processing status when a prompt is received.
- Implemented logging for generator completion in multiple locations.
- Updated `broadcastProcessingStatus` to include queue depth and active session count in logs.
- Modified session iterator to stop yielding messages after a summary is yielded, with appropriate logging.
* Initial plan
* Initial analysis: Found root cause of double entries bug
Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>
* Fix double entries by assigning generatorPromise in handleSessionInit
Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>
* feat(logging): Enhance HTTP request logging and session management
- Added middleware for logging HTTP requests and responses, excluding static assets and health checks.
- Introduced a method to summarize request bodies for specific endpoints.
- Improved logging for user prompt synchronization with Chroma, including duration tracking.
- Enhanced session initialization logging to include additional session details.
- Updated observation and summary logging to provide more context and error handling during Chroma synchronization.
- Refactored tool name formatting for logging in the SessionManager.
- Expanded logger component types to include 'HTTP', 'SESSION', and 'CHROMA'.
* Refactor SDK prompts and logging for improved clarity and functionality
- Updated buildInitPrompt to clarify the observer's role and what to record.
- Enhanced buildSummaryPrompt with clearer instructions for summarizing ongoing sessions.
- Improved buildContinuationPrompt to emphasize the focus on deliverables and capabilities.
- Refactored WorkerService to utilize a centralized tool formatting function for logging.
- Added truncation for logged responses and observations to improve readability.
- Updated SessionManager to log the queuing of summarize actions with session details.
- Enhanced App and Sidebar components to support refreshing stats on sidebar open.
- Refactored useStats hook to allow manual refreshing of stats while maintaining automatic loading on mount.
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>
* feat: Enhance session and summary handling
- Update SQL query in SessionStore to exclude null or empty projects.
- Add 'investigated' field to Summary interface for better tracking.
- Modify App component to handle pagination more efficiently based on current filters.
- Update SummaryCard to display the 'investigated' field if present.
- Refactor usePagination hook to reset pagination state when filters change.
- Adjust mergeAndDeduplicateByProject function to ensure it only merges unfiltered data.
* refactor: address PR feedback - remove redundancies and fix dependency cycles
Fixes based on PR #70 review feedback:
Required:
- Fixed useEffect dependency cycle in App.tsx (removed handleLoadMore from deps)
Recommended:
- Removed redundant filter detection from App.tsx (usePagination handles this)
- Removed redundant stateRef update effect from usePagination.ts
- Simplified mergeAndDeduplicateByProject by removing defensive validation
- Removed unused imports (useRef, useEffect)
All changes follow CLAUDE.md principles: DRY, fail-fast, no defensive programming.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: Reset paginated data arrays when filter changes
Critical fix for data mixing bug identified in PR review follow-up.
Problem:
When filter changes, usePagination correctly resets its offset to 0, but
the paginated state arrays (observations, summaries, prompts) were NOT
being reset. This caused data from different projects to mix together
because setState appends to the existing array.
Example:
- User views Project A: [A1, A2, A3]
- User switches to Project B
- API fetches [B1, B2, B3]
- setState does: [...prev, ...new] = [A1, A2, A3, B1, B2, B3] ❌
Solution:
Added a separate useEffect that resets all three paginated arrays when
currentFilter changes. This happens BEFORE handleLoadMore fetches new
data, ensuring clean state for the new filter.
Files changed:
- src/ui/viewer/App.tsx: Added useEffect to reset arrays on filter change
- plugin/ui/viewer-bundle.js: Built UI bundle
Testing:
1. Select Project A, verify data loads
2. Switch to Project B
3. Verify ONLY Project B data is shown (no mixing)
4. Switch back to "All Projects"
5. Verify all data appears correctly
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: Combine filter change useEffect hooks for guaranteed order
Merged two separate useEffect hooks into one to:
1. Guarantee execution order (reset THEN load)
2. Reduce complexity (one hook instead of two)
3. Make intent clearer with single comment
Before:
- useEffect #1: handleLoadMore() on filter change
- useEffect #2: Reset arrays on filter change
- React could run these in any order
After:
- Single useEffect: Reset arrays THEN handleLoadMore()
- Execution order is now guaranteed
Files changed:
- src/ui/viewer/App.tsx: Combined useEffect hooks
- plugin/ui/viewer-bundle.js: Built UI bundle
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Introduced comprehensive API reference for the TypeScript Agent SDK.
- Documented installation instructions for the SDK.
- Detailed the main functions: `query()`, `tool()`, and `createSdkMcpServer()`.
- Defined various types including `Options`, `Query`, `AgentDefinition`, and more.
- Included message types and their structures, such as `SDKMessage`, `SDKAssistantMessage`, and `SDKUserMessage`.
- Explained hook types and their usage within the SDK.
- Provided detailed documentation for tool input and output types.
- Added sections on permission types and other relevant types for better clarity.
- Introduced WorkerService class to handle HTTP requests and manage sessions.
- Added endpoints for health check, session management, and data retrieval.
- Integrated ChromaSync for background data synchronization.
- Implemented SSE for real-time updates to connected clients.
- Added error handling and logging throughout the service.
- Cached Claude executable path for improved performance.
- Included settings management for user configuration.
- Established database interactions for session and observation management.
- Removed fragile PM2 string parsing and replaced with direct PM2 restart logic.
- Eliminated silent error handling in worker-utils.ts for better error visibility.
- Extracted duplicated session auto-creation logic into a new helper method getOrCreateSession() in worker-service.ts.
- Centralized configuration values and replaced magic numbers with named constants.
- Updated health check logic to ensure worker is restarted if unhealthy.
- Removed unnecessary getWorkerPort() wrapper function.
- Improved overall code quality and maintainability by applying DRY and YAGNI principles.
