Changes:
- Updated legend to show only observation types (bugfix, feature, refactor, change, discovery, decision)
- Mapped each type to a color dot emoji (🔴 bugfix, 🟢 feature, 🔵 refactor, ⚪ change, 🟡 discovery, 🟤 decision)
- Removed concept-based filtering and icon selection
- Simplified progressive disclosure instructions to reference types instead of concepts
- All observations now shown in timeline (no concept filtering)
Technical details:
- Modified: src/hooks/context-hook.ts:203-207 (legend)
- Modified: src/hooks/context-hook.ts:210-223 (progressive disclosure text)
- Modified: src/hooks/context-hook.ts:344-369 (icon mapping switched from concepts to types)
- Modified: src/hooks/context-hook.ts:168-173 (removed concept filtering)
- Rebuilt: plugin/scripts/context-hook.js
Rationale: Types are mutually exclusive and core to categorization, while concepts are multi-select metadata better accessed through MCP search tools. This simplifies the display and reduces visual noise.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Features:
- New UsageLogger utility that writes usage metrics to daily JSONL files
- Captures token counts, costs, timing, and cache metrics from SDK result messages
- Usage logs stored in ~/.claude-mem/usage-logs/ (one file per day)
- Added analyze-usage.js script for analyzing usage patterns
Usage data captured:
- Token counts (input, output, cache creation, cache read)
- Total cost in USD per API call
- Duration metrics (total and API time)
- Number of turns per session
- Session and project attribution
Analysis script features:
- Aggregates totals by project and model
- Shows cache hit rates and savings
- Displays cost breakdowns and averages
- npm scripts: usage:analyze and usage:today
Files:
- src/utils/usage-logger.ts (new)
- src/services/worker-service.ts (modified - captures SDK result messages)
- scripts/analyze-usage.js (new)
- package.json (added usage:* npm scripts)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Fixes:
- Fixed SessionStart hooks running on session resume
- Added matcher configuration to only run hooks on startup, clear, or compact events
- Prevents unnecessary hook execution and improves performance
Technical changes:
- Modified plugin/hooks/hooks.json (added matcher)
- Updated version to 4.3.4 in all metadata files
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Updated package.json version to 4.3.1
- Updated marketplace.json version to 4.3.1
- Added v4.3.1 entry to CLAUDE.md version history
- Documented SessionStart hook context injection fix
- Documented hooks architecture consolidation
- Rebuilt all executables with updated version
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Critical bugfix release.
Problem:
- NOT NULL constraint violations prevented all observations/summaries from being stored
- Worker service could not store any data in database
- System was completely non-functional for new sessions
Root Cause:
- SessionStore.getSessionById() missing claude_session_id in SELECT query
- Worker received undefined for claude_session_id
- Caused database INSERT failures
Fix:
- Added claude_session_id to getSessionById SQL query
- Updated return type to include claude_session_id field
- Session ID now flows correctly: hook → database → worker → SDK
Impact:
- All observation and summary storage now works correctly
- System maintains session consistency throughout lifecycle
- Critical for proper functioning of memory compression
Version Changes:
- package.json: 4.2.7 → 4.2.8
- marketplace.json: 4.2.6 → 4.2.8
- CLAUDE.md: Updated version and added v4.2.8 changelog
Files Changed:
- package.json (version bump)
- .claude-plugin/marketplace.json (version bump)
- CLAUDE.md (version and changelog)
- src/services/sqlite/SessionStore.ts (bugfix)
- plugin/scripts/* (rebuilt with fix)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Improvements:
- Enhanced null handling for empty/whitespace fields
- Ensures clean null values in database instead of empty strings
- Improves query efficiency and data consistency
Testing:
- Added comprehensive regression test suite (49 tests)
- Tests v4.2.5 summary fixes and v4.2.6 observation fixes
- Tests edge cases: missing fields, empty fields, whitespace
- New test script: npm run test:parser
- All tests passing with 100% coverage
Code Quality:
- Removed unused extractFileArray() function
- Improved function documentation
- TypeScript diagnostics clean
Technical Details:
- Updated src/sdk/parser.ts extractField function
- Created src/sdk/parser.test.ts regression test suite
- Updated package.json to v4.2.7
- Updated CLAUDE.md with version history
- All changes backward compatible
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Critical Bugfix:
- Fixed overly defensive observation validation blocking observations from being saved
- Parser now NEVER skips observations - always saves them
- Invalid or missing type defaults to "change" (generic catch-all type)
- Removed validation requiring title, subtitle, and narrative fields
- Prevents critical data loss - partial observations better than no observations
Impact:
- Before: Missing title, subtitle, OR narrative caused entire observation to be discarded
- After: ALL observations preserved regardless of field completeness
- Even partial observations contain valuable data: concepts, files_read, files_modified, facts
- LLMs make mistakes - system must be resilient and save everything
- Consistent with v4.2.5 summary fix
Technical changes:
- Updated src/sdk/parser.ts:52-67 to never skip observations
- Uses "change" as fallback type for invalid/missing types (no schema change)
- Updated ParsedObservation interface to allow null for title, subtitle, narrative
- Updated SessionStore.storeObservation signature to accept nullable fields
- Updated built worker-service.cjs
- Bumped version to 4.2.6 in all metadata files
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Critical Bugfix:
- Fixed overly defensive summary validation blocking summaries from being saved
- Removed validation that returned null when any required fields were missing
- Summaries now always saved when <summary> tags present, even if incomplete
- Prevents critical data loss - partial summaries better than no summaries
Impact:
- Before: Missing single field caused entire summary to be discarded
- After: All summaries preserved, maintaining session context when incomplete
- Ensures continuity of memory compression system
Technical changes:
- Updated src/sdk/parser.ts:137-147 to remove blocking validation
- Parser returns ParsedSummary with whatever fields are available
- Updated built worker-service.cjs
- Bumped version to 4.2.5 in all metadata files
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Improvements:
- Removed optional skip_summary functionality (summaries now always generated)
- Clarified that summaries are mid-session checkpoints, not session endings
- Improved request field instructions to better form descriptive titles
- Changed wording from "discovered" to "learned" for consistency
Technical changes:
- Updated src/sdk/prompts.ts summary prompt
- Removed "WHEN NOT TO SUMMARIZE" section
- Added clarifying footer text about ongoing sessions
- Updated built worker-service.cjs
- Bumped version to 4.2.4 in all metadata files
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Patch release confirming the effectiveness of prompt engineering changes that prevent meta-referential observations.
Key Improvements (from v4.2.0 prompt work):
- Observations now focus on deliverables shipped, not memory system operations
- Clear distinction between "what was built" vs "what the memory tool processed"
- Contrastive examples prevent pollution like "Processed tool executions"
- Smart handling of edge cases when working ON the memory system itself
Evidence:
Recent context shows progression from meta-referential garbage (10/21 10:48 PM) to excellent deliverable-focused observations (10/21 11:46 PM).
No code changes in this release - just version bump to mark the successful prompt improvements as stable.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added functionality to automatically create a session record in the database if it does not exist when storing observations or session summaries.
- Updated `storeObservation` and `storeSummary` methods to include checks for existing session records and insert new records as needed.
- Added logging for auto-created session records for better traceability.
Version bump to 4.1.1 with critical bug fixes and API simplification.
Removed:
- Redundant advanced_search MCP tool (no unique functionality)
- advancedSearch method from SessionSearch class
Fixed:
- findByConcept, findByType, findByFile now respect limit/offset
- Parser validation prevents observation types in concepts array
- Added token limit warnings to tool descriptions
Changed:
- Simplified MCP API from 7 to 6 tools
- Enhanced SDK prompts to prevent AI data contamination
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
### Changed
- Graceful session cleanup: Cleanup hook now marks sessions as completed instead of sending DELETE requests to worker
- Natural worker shutdown: Workers now finish pending operations (like summary generation) before terminating
- Restored MCP search server: Re-enabled full-text search capabilities from backup
### Fixed
- Session summaries no longer interrupted by aggressive cleanup during session end
- Workers can now complete final operations before shutdown
### Dependencies
- Updated @anthropic-ai/claude-agent-sdk to ^0.1.23
- Added @modelcontextprotocol/sdk ^1.20.1
- Added zod-to-json-schema ^3.24.6
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Changed all hook entry points to use dynamic imports after bootstrap runs. This ensures that better-sqlite3 is installed before Node.js attempts to resolve the import.
Changes:
- Modified src/bin/hooks/*.ts to call ensureDependencies() before dynamic import
- Moved from static `import { hook } from '...'` to `const { hook } = await import('...')`
- This delays module resolution until after npm install completes
- Bumped version to 4.0.6
The previous approach failed because static imports are resolved at module link time, before any runtime code (including ensureDependencies) executes.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Fixed better-sqlite3 distribution by implementing self-bootstrapping hooks
that auto-install dependencies on first run. This eliminates the need for
users to have native compilation tools or manually install dependencies.
## Solution
Instead of bundling 25MB of better-sqlite3 binaries in git or requiring
manual npm install, hooks now bootstrap themselves on first execution:
1. Created `src/shared/bootstrap.ts` with `ensureDependencies()` function
2. Added bootstrap calls to all hook entry points (context, new, save, summary, cleanup)
3. Created `plugin/scripts/package.json` declaring better-sqlite3 dependency
4. Bootstrap checks if `node_modules` exists, runs `npm install` if missing
5. npm automatically downloads prebuilt better-sqlite3 binary for user's platform
## Changes
**Core Bootstrap System:**
- Added src/shared/bootstrap.ts: Auto-install dependencies using npm
- Modified all hooks (context, new, save, summary, cleanup) to call ensureDependencies()
- Created plugin/scripts/package.json with better-sqlite3 dependency
**Build & Distribution:**
- Removed node_modules copying logic from build script
- Build output is now compact (hooks + package.json, no binaries)
- Updated marketplace.json to point to GitHub for direct installation
**Documentation:**
- Updated README: GitHub Marketplace installation is now recommended method
- Installation instructions emphasize no compilation needed
- Version bumped to 4.0.5 throughout
## Benefits
- ✅ No git bloat (repo stays small, no 25MB binaries committed)
- ✅ No compilation needed (npm downloads prebuilt binaries)
- ✅ Works on all platforms (npm handles platform-specific binaries)
- ✅ Zero manual steps (hooks bootstrap themselves automatically)
- ✅ Idempotent (skips install if dependencies already exist)
Installation now works via simple:
```
/plugin marketplace add https://github.com/thedotmack/claude-mem
/plugin install claude-mem
```
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Reverted from GitHub-hosted marketplace to local marketplace file installation method. This allows us to resolve issues with better-sqlite3 native module builds before enabling GitHub marketplace distribution.
Changes:
- Simplified .claude-plugin/marketplace.json (removed metadata, version fields)
- Updated README installation instructions to use local .claude-plugin/marketplace.json
- Bumped version to 4.0.4
Installation now requires cloning the repo and using:
/plugin marketplace add .claude-plugin/marketplace.json
Will restore GitHub marketplace method once native module issues are resolved.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Updated `new-hook.js` to streamline logging and session management.
- Enhanced database schema initialization and migration processes.
- Improved error handling for worker startup in `worker-utils.ts`, ensuring PM2 binary and ecosystem config existence before spawning.
- Added detailed error messages for missing dependencies and spawn failures.
- Removed try-catch blocks in new-hook, save-hook, and summary-hook for cleaner flow.
- Enhanced error handling in save and summary hooks to throw errors instead of logging and returning.
- Introduced ensureWorkerRunning utility to manage worker service lifecycle and health checks.
- Replaced dynamic port allocation with a fixed port for the worker service.
- Simplified path management and removed unused port allocator utility.
- Added database schema initialization for fresh installations and improved migration handling.
BREAKING CHANGES:
- Data directory moved from ~/.claude-mem/ to ${CLAUDE_PLUGIN_ROOT}/data/
- Fresh start required - no migration from v3.x databases
- Worker service now auto-starts on SessionStart hook
New Features:
- MCP Search Server with 6 specialized search tools
- FTS5 full-text search across observations and sessions
- Auto-starting worker service in SessionStart hook
- Citation support for search results (claude-mem:// URIs)
Changes:
- Updated paths.ts to use CLAUDE_PLUGIN_ROOT for data directory
- Added worker auto-start logic to context hook
- Updated worker service to write port file to plugin data dir
- Bumped version to 4.0.0 in package.json and plugin.json
- Created comprehensive CHANGELOG.md documenting v4.0.0 changes
- Updated README.md with v4.0.0 breaking changes and features
- Rebuilt all hooks and worker service
Technical Improvements:
- Improved error handling and graceful degradation
- Structured logging across all components
- Enhanced plugin integration with Claude Code
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added prompt_number to observations and session summaries for better tracking.
- Implemented prompt counter in SDK sessions to manage user prompts effectively.
- Updated database schema to include prompt tracking columns and removed unique constraints on session summaries.
- Modified hooks to utilize prompt_number in observations and summaries.
- Changed worker service to handle summarize requests instead of finalize, keeping the SDK agent active.
- Improved logging for better debugging and tracking of prompt numbers across sessions.
- Added WorkerService to handle long-running HTTP service with session management.
- Implemented endpoints for initializing, observing, finalizing, checking status, and deleting sessions.
- Integrated with Claude SDK for processing observations and generating responses.
- Added port allocator utility to dynamically find available ports for the service.
- Configured TypeScript settings for the project.
- Introduced a new `hook-response.ts` module to create standardized hook responses.
- Updated `context-hook.ts`, `new.ts`, `save.ts`, and `summary.ts` to utilize the new response format.
- Enhanced error handling in `context-hook.ts` to check for input from stdin.
- Refactored database interaction in hooks to ensure consistent session management.
- Improved readability and maintainability of hook implementations by restructuring code.
- Updated database queries to use consistent variable naming and formatting.
- Modified the handling of socket connections in `save.ts` and `summary.ts` to ensure proper response on close and error events.
- Deleted the install.ts command file, removing the installation logic for the Claude Memory System.
- Removed logs.ts command file, eliminating the log viewing functionality.
- Deleted restore.ts command file, which handled restoring files from trash.
- Removed status.ts command file, which provided system status checks.
- Deleted trash-empty.ts and trash-view.ts command files, removing trash management features.
- Removed trash.ts command file, which handled moving files to trash.
- Deleted uninstall.ts command file, eliminating the uninstallation process for the memory system.
- Updated new.ts hook to enforce plugin mode for Claude Code integration.
- Cleaned up config.ts by removing unused export for CLI_NAME.
- Implemented context-hook.ts for handling session start events.
- Created new-hook.ts for user prompt submission events.
- Developed save-hook.ts for post tool use events.
- Added summary-hook.ts for handling stop events.
- Introduced worker.ts as a standalone background process for the SDK agent.
- Each hook reads input from stdin, processes it, and handles errors gracefully.
- Updated the published package contents to exclude `hook-templates`.
- Removed references to the hooks directory and related scripts in the installation and uninstallation processes.
- Simplified the status command by eliminating checks for runtime hook scripts.
- Adjusted the path discovery service to remove methods related to hook templates.
- Updated the installation logic to directly configure hooks using CLI commands.
- Cleaned up the uninstall process to remove claude-mem hooks from settings.
- Deleted hook-prompt-renderer.js and hook-prompts.config.js as they are no longer needed.
- Removed path-resolver.js, stop.js, and user-prompt-submit.js for streamlining the codebase.
- Updated package.json scripts to point to new build and publish scripts.
- Adjusted test imports to reflect new directory structure after removing unnecessary files.
- Updated import statements across multiple files to use bun:sqlite.
- Changed database query methods from `prepare` to `query` for consistency.
- Removed dependency on better-sqlite3 from package.json and adjusted package.json to specify bun as the engine.
- Modified hook installation process to eliminate unnecessary dependency installation.
- Updated migration scripts to align with bun:sqlite's API.
- Implemented a CLI tool for version bumping, building, and publishing to npm.
- Added checks for uncommitted changes and current version retrieval.
- Included options for patch, minor, major, and custom version bumps.
- Integrated git commit and tagging after version update.
- Added npm publish functionality and git push after successful publish.
- Implemented error handling and user confirmations throughout the process.
Alex Newman