This is a backup of all work done by the 3 Phase 1 agents:
Agent A - Command Injection Fix (Issue #354):
- Fixed command injection in BranchManager.ts
- Fixed unnecessary shell usage in bun-path.ts
- Added comprehensive security test suite
- Created SECURITY.md and SECURITY_AUDIT_REPORT.md
Agent B - Observation Persistence Fix (Issue #353):
- Added PendingMessageStore from PR #335
- Integrated persistent queue into SessionManager
- Modified SDKAgent to mark messages complete
- Updated SessionStore with pending_messages migration
- Updated worker-types.ts with new interfaces
Agent C - Batch Endpoint Verification (Issue #348):
- Created batch-observations.test.ts
- Updated worker-service.mdx documentation
Also includes:
- Documentation context files (biomimetic, windows struggles)
- Build artifacts from agent testing
This work will be re-evaluated after v7.3.0 release.
- Delete separate desktop-skill/ directory (was outdated)
- Generate mem-search.zip during build from plugin/skills/mem-search/
- Update docs with correct MCP tool list and new download path
- Single source of truth for Claude Desktop skill
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: Add batch fetching for observations and update documentation
- Implemented a new endpoint for fetching multiple observations by IDs in a single request.
- Updated the DataRoutes to include a POST /api/observations/batch endpoint.
- Enhanced SKILL.md documentation to reflect changes in the search process and batch fetching capabilities.
- Increased the default limit for search results from 5 to 40 for better usability.
* feat!: Fix timeline parameter passing with SearchManager alignment
BREAKING CHANGE: Timeline MCP tools now use standardized parameter names
- anchor_id → anchor
- before → depth_before
- after → depth_after
- obs_type → type (timeline tool only)
Fixes timeline endpoint failures caused by parameter name mismatch between
MCP layer and SearchManager. Adds new SessionStore methods for fetching
prompts and session summaries by ID.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* docs: reframe timeline parameter fix as bug fix, not breaking change
The timeline tools were completely broken due to parameter name mismatch.
There's nothing to migrate from since the old parameters never worked.
Co-authored-by: Alex Newman <thedotmack@users.noreply.github.com>
* Refactor mem-search documentation and optimize API tool definitions
- Updated SKILL.md to emphasize batch fetching for observations, clarifying usage and efficiency.
- Removed deprecated tools from mcp-server.ts and streamlined tool definitions for clarity.
- Enhanced formatting in FormattingService.ts for better output readability.
- Adjusted SearchManager.ts to improve result headers and removed unnecessary search tips from combined text.
* Refactor FormattingService and SearchManager for table-based output
- Updated FormattingService to format search results as tables, including methods for formatting observations, sessions, and user prompts.
- Removed JSON format handling from SearchManager and streamlined result formatting to consistently use table format.
- Enhanced readability and consistency in search tips and formatting logic.
- Introduced token estimation for observations and improved time formatting.
* refactor: update documentation and API references for version bump and search functionalities
* Refactor code structure for improved readability and maintainability
* chore: change default model from haiku to sonnet
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: unify timeline formatting across search and context services
Extract shared timeline formatting utilities into reusable module to align
MCP search output format with context-generator's date/file-grouped format.
Changes:
- Create src/shared/timeline-formatting.ts with reusable utilities
(parseJsonArray, formatDateTime, formatTime, formatDate, toRelativePath,
extractFirstFile, groupByDate)
- Refactor context-generator.ts to use shared utilities
- Update SearchManager.search() to use date/file grouping
- Add search-specific row formatters to FormattingService
- Fix timeline methods to extract actual file paths from metadata
instead of hardcoding 'General'
- Remove Work column from search output (kept in context output)
Result: Consistent date/file-grouped markdown formatting across both
systems while maintaining their different column requirements.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* refactor: remove redundant legend from search output
Remove legend from search/timeline results since it's already shown
in SessionStart context. Saves ~30 tokens per search result.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* Refactor session summary rendering to remove links
- Removed link generation for session summaries in context generation and search manager.
- Updated output formatting to exclude links while maintaining the session summary structure.
- Adjusted related components in TimelineService to ensure consistency across the application.
* fix: move skillPath declaration outside try block to fix scoping bug
The skillPath variable was declared inside the try block but referenced
in the catch block for error logging. Since const is block-scoped, this
would cause a ReferenceError when the error handler executes.
Moved skillPath declaration before the try block so it's accessible in
both try and catch scopes.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix: address PR #317 code review feedback
**Critical Fixes:**
- Replace happy_path_error__with_fallback debug calls with proper logger methods in mcp-server.ts
- All HTTP API calls now use logger.debug/error for consistent logging
**Code Quality Improvements:**
- Extract 90-day recency window magic numbers to named constants
- Added RECENCY_WINDOW_DAYS and RECENCY_WINDOW_MS constants in SearchManager
**Documentation:**
- Document model cost implications of Haiku → Sonnet upgrade in CHANGELOG
- Provide clear migration path for users who want to revert to Haiku
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* refactor: simplify CHANGELOG - remove cost documentation
Removed model cost comparison documentation per user feedback.
Kept only the technical code quality improvements.
🤖 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>
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Alex Newman <thedotmack@users.noreply.github.com>
* 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>
Add comprehensive technical documentation explaining the v7.1.0 migration from PM2 to Bun-based process management and better-sqlite3 to bun:sqlite database driver.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Major architectural migration from PM2 to native Bun process management,
and better-sqlite3 to bun:sqlite database driver.
Key changes:
- Replace PM2 with custom Bun-based ProcessManager
- Migrate from better-sqlite3 npm to bun:sqlite runtime
- Auto-install Bun and uv (Python) on first run
- Automatic legacy PM2 process cleanup on all platforms
- Complete documentation in docs/PM2-TO-BUN-MIGRATION.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 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 README.md to include responsive badges that adapt to the user's color scheme preference.
- Added new SVG files for dark and light theme badges to enhance visual consistency.
- Delete BinaryManager.ts - no longer needed
- Simplify ProcessManager.ts - single Bun spawn path for all platforms
- Update smart-install.js - auto-install Bun if missing (Windows/Unix)
- Update documentation to reflect Bun requirement
This simplifies the codebase by:
- Using Bun consistently across all platforms (hooks + worker)
- Eliminating binary download/hosting complexity
- Zero native dependencies with bun:sqlite
- Auto-installing Bun on first run if not present
Co-authored-by: Claude <noreply@anthropic.com>
Critical bug fix:
- Pass project filter to getSessionSummariesByIds() and getUserPromptsByIds() in SearchManager
- Previously only observations were filtered by project, sessions and prompts leaked from other projects
Documentation improvements:
- Update "FTS5 search" to "hybrid search" (accurate terminology)
- Add privacy warning about sensitive data in exports
- Document --project parameter for filtered exports
- Add "Export by Project" examples to advanced usage
Verified with test export using --project=claude-mem filter.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* Initial plan
* Update all references from claude-opus-4 to claude-opus-4-5
Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>
* Use shorthand model names (haiku, sonnet, opus) throughout codebase
Updated model references to use shorthand names that automatically forward to latest versions:
- UI components (Sidebar, ContextSettingsModal)
- Documentation (configuration.mdx, worker-service.mdx)
- Build artifacts (viewer-bundle.js)
Shorthand names provide forward compatibility without requiring version-specific updates.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>
Co-authored-by: Alex Newman <thedotmack@gmail.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
* 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>
- 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.
- 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.
- 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 comprehensive documentation for integrating claude-mem into VSCode extensions, IDE plugins, and CLI tools.
- Detailed worker service basics, including environment variables and build commands.
- Provided an overview of worker architecture and request flow.
- Documented API reference for session lifecycle, data retrieval, search operations, and settings configuration.
- Included integration patterns, error handling strategies, and development workflow guidelines.
- Added critical implementation notes and additional resources for developers.
Rewrote architecture/hooks.mdx with complete technical reference including:
- 5-stage lifecycle overview with ASCII architecture diagram
- Detailed input/output specs for each hook
- Processing steps with TypeScript code examples
- Data flow diagram showing complete request lifecycle
- Session ID threading explanation
- Privacy tag stripping pipeline
- SDK agent processing details
- Implementation checklist for other platforms
- Common pitfalls and solutions table
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Decorative Product Hunt announcement in terminal with rocket borders
- Product Hunt badge in viewer header with theme-aware switching
- Badge uses separate tracking URL for analytics
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Comprehensive documentation update with current features:
- Updated "What's New" section to highlight v6.4.x features
- Added privacy tags and context configuration to key features
- Fixed default model (claude-haiku-4-5)
- Clarified lifecycle hook count (5 events, 6 scripts)
- Removed outdated MCP server references
- Updated version numbers across all docs
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.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>
* fix(context-hook): update savings message to reference mem-search skill
Changed "Use claude-mem search" to "Use the mem-search skill" for clarity.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* chore: delete outdated docs, experiments, and test results
Removed:
- docs/context/ (moved to private/)
- experiment/ (obsolete)
- test-results/ (stale)
- tests/ (outdated)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(user-message-hook): update support link to Discord community
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Updated the 'decisions' tool to accept an optional 'query' parameter for semantic filtering.
- Implemented logic to handle semantic search using Chroma when a query is provided.
- Preserved ranking order of results based on Chroma's output.
- Added fallback to metadata-first search when no query is present.
* 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>
- Updated version badge in README.md to 6.0.0
- Updated 'What's New' sections in README.md and introduction.mdx
- Highlighted major session management and transcript processing improvements
- Removed restrictive permissions from .claude/settings.json
🤖 Generated with [Claude Code](https://claude.com/claude-code)
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: add mem-search skill with progressive disclosure architecture
Add comprehensive mem-search skill for accessing claude-mem's persistent
cross-session memory database. Implements progressive disclosure workflow
and token-efficient search patterns.
Features:
- 12 search operations (observations, sessions, prompts, by-type, by-concept, by-file, timelines, etc.)
- Progressive disclosure principles to minimize token usage
- Anti-patterns documentation to guide LLM behavior
- HTTP API integration for all search functionality
- Common workflows with composition examples
Structure:
- SKILL.md: Entry point with temporal trigger patterns
- principles/: Progressive disclosure + anti-patterns
- operations/: 12 search operation files
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* docs: add CHANGELOG entry for mem-search skill
Document mem-search skill addition in Unreleased section with:
- 100% effectiveness compliance metrics
- Comparison to previous search skill implementation
- Progressive disclosure architecture details
- Reference to audit report documentation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* docs: add mem-search skill audit report
Add comprehensive audit report validating mem-search skill against
Anthropic's official skill-creator documentation.
Report includes:
- Effectiveness metrics comparison (search vs mem-search)
- Critical issues analysis for production readiness
- Compliance validation across 6 key dimensions
- Reference implementation guidance
Result: mem-search achieves 100% compliance vs search's 67%
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: Add comprehensive search architecture analysis document
- Document current state of dual search architectures (HTTP API and MCP)
- Analyze HTTP endpoints and MCP search server architectures
- Identify DRY violations across search implementations
- Evaluate the use of curl as the optimal approach for search
- Provide architectural recommendations for immediate and long-term improvements
- Outline action plan for cleanup, feature parity, DRY refactoring
* refactor: Remove deprecated search skill documentation and operations
* refactor: Reorganize documentation into public and context directories
Changes:
- Created docs/public/ for Mintlify documentation (.mdx files)
- Created docs/context/ for internal planning and implementation docs
- Moved all .mdx files and assets to docs/public/
- Moved all internal .md files to docs/context/
- Added CLAUDE.md to both directories explaining their purpose
- Updated docs.json paths to work with new structure
Benefits:
- Clear separation between user-facing and internal documentation
- Easier to maintain Mintlify docs in dedicated directory
- Internal context files organized separately
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Enhance session management and continuity in hooks
- Updated new-hook.ts to clarify session_id threading and idempotent session creation.
- Modified prompts.ts to require claudeSessionId for continuation prompts, ensuring session context is maintained.
- Improved SessionStore.ts documentation on createSDKSession to emphasize idempotent behavior and session connection.
- Refined SDKAgent.ts to detail continuation prompt logic and its reliance on session.claudeSessionId for unified session handling.
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Alex Newman <thedotmack@gmail.com>
- Implemented a new skill-based search approach, replacing MCP search tools to reduce session start context from ~2,500 tokens to ~250 tokens.
- Added 10 new HTTP API endpoints to the worker service for various search functionalities.
- Created a new search skill with detailed instructions and examples for users.
- Removed MCP search server references and updated documentation to reflect the new skill-based approach.
- Enhanced context handling in the context hook to conditionally display the most recent summary based on observations.
- Introduced comprehensive documentation for Agent Skills, including creation, management, and best practices.
Alex Newman