* 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.
* 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>
* 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>
- Implemented `findClaudePath` function to determine the path of the Claude executable using environment variables or system commands (`which` for Unix/Mac and `where` for Windows).
- Integrated the `findClaudePath` function into the SDK worker and worker service to ensure the correct executable path is used when running the SDK agent.
- Enhanced error handling and logging for better debugging and user feedback regarding the executable path.
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>
- Removed validation for required fields in parseSummary function.
- Added a note emphasizing the importance of saving the summary even if some fields are missing.
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>
- Changed the title of the summary prompt to "THIS REQUEST'S SUMMARY" for better context.
- Revised instructions to focus on summarizing what was built/fixed/deployed/configured, rather than the observation process.
- Clarified when not to summarize, emphasizing conversational requests and trivial inquiries.
- Updated examples to better illustrate good summary practices.
Added "WHEN NOT TO SUMMARIZE" section to buildSummaryPrompt that instructs the SDK to skip creating summaries for:
- Work already covered in previous prompts (prevents duplicates)
- Conversational banter with no deliverables
- Trivial requests (questions, status checks)
- Meta-discussions about memory system without shipped changes
Implementation:
- src/sdk/prompts.ts: Added WHEN NOT TO SUMMARIZE section with <skip_summary> output format
- src/sdk/parser.ts: Added skip_summary detection before parsing full summary XML
- src/sdk/parser.ts: Fixed observation type validation to include all 6 types (bugfix, feature, refactor, change, discovery, decision)
This should eliminate the duplicate summaries like the three "restore 6 types" summaries we saw for session d9137878.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Restored full type system: bugfix, feature, refactor, change, discovery, decision.
This enables more precise search queries like "show all bugfixes in auth" vs generic "show all changes".
Also updated README to reflect current behavior (10 summaries with three-tier verbosity).
Changes:
- prompts.ts: Expanded type field from 3 to 6 types with clear definitions
- CLAUDE.md: Fixed context hook description (3 → 10 summaries)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Updated SDK prompts to distinguish between deliverables (what was built/shipped) vs meta-operations (what the memory system is doing). This prevents self-referential pollution like "Process tool executions" instead of actual coding tasks like "Fix authentication bug".
Changes:
- buildInitPrompt: Added deliverable-focused framing with contrastive examples
- buildSummaryPrompt: Injected user's original prompt + explicit examples
- Added verb guidance (implemented/fixed/deployed vs analyzed/tracked/stored)
- Added "NOW DOES" present-tense capability framing
Works across all project types: dev, DevOps, docs, infrastructure, research, config.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Filter out observation type from concepts array in parseObservations function to ensure types and concepts are treated as separate dimensions. Added logging for removed types.
- Update prompts documentation to clarify that the observation type must not be included in the concepts array.
- Modify search-server to provide clearer guidance on result limits, emphasizing starting with smaller limits to avoid exceeding token limits.
- Refactor SessionSearch methods to accept options for limit, offset, and orderBy parameters, improving flexibility in querying observations by concept and type.
Changed summary prompts to generate discrete per-request summaries instead of cumulative session summaries. This provides better chronological memory where each summary is a clean unit representing one request/response cycle.
Changes:
- Renamed buildFinalizePrompt() to buildSummaryPrompt() in src/sdk/prompts.ts
- Updated prompt text to focus on "THIS REQUEST" rather than "this session"
- Updated all import and function call sites in worker-service.ts and worker.ts
- Added IMPORTANT warning to emphasize request-level scope
Expected behavior: Each summary will now describe only what happened during that specific request, eliminating cumulative recaps.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added search functionality for observations and sessions using full-text search.
- Implemented formatting functions for search results with citations.
- Created multiple tools for searching by various criteria including concept, file, type, and advanced search.
- Integrated structured filters and pagination options for search queries.
- Established error handling for search operations and server initialization.
- Added SDK session, observation, and summary types to types.ts.
- Refactored worker-service to use SessionStore for session management.
- Created SessionSearch class for FTS5 full-text search and structured queries.
- Implemented SessionStore for CRUD operations on SDK sessions, observations, and summaries.
- Added migrations for database schema updates, including new columns and constraints.
- Enhanced search capabilities with filters for projects, types, concepts, and date ranges.
- Updated `summary-hook.js` to improve logging and session handling.
- Modified `context.ts` to fetch recent sessions with status and summary info, enhancing output formatting.
- Added new methods in `HooksDatabase.ts` for retrieving recent sessions and their summaries.
- Improved observation retrieval logic in `context.ts` to display relevant information for active sessions.
- Enhanced prompt documentation in `prompts.ts` to clarify output expectations.
- Refactored logger methods in `logger.ts` to instance methods for better encapsulation.
- Introduced a new Logger utility to standardize logging with correlation IDs and structured context.
- Replaced console.error and console.log statements with logger methods in various modules including save.ts, summary.ts, parser.ts, HooksDatabase.ts, and worker-service.ts.
- Enhanced error handling and logging for better traceability of observations and summaries.
- Made observations.text nullable in the database schema to support structured fields.
- Added correlation IDs for tracking observations through the processing pipeline.
- Updated observation schema to include hierarchical fields: title, subtitle, facts, narrative, concepts, files_read, and files_modified.
- Modified the save-hook and summary-hook scripts to accommodate the new observation structure.
- Added migration logic to the HooksDatabase for adding new fields to the observations table.
- Refactored the parser to extract new fields from XML formatted observations.
- Adjusted prompt generation to reflect the new observation format and requirements.
- Updated worker service to handle new observation and summary structures.
- Added final finalize prompt for session summary generation with required XML fields.
- Introduced recommended prompt flow with structured observation format and hierarchical storage principles.
- Created final init prompt for processing tool executions with clear guidelines on when to store observations.
- Developed final observation prompt for analyzing tool outputs and generating structured observations.
- Migrated old prompt flow to a new system with improved clarity and structured data handling.
- Updated parser and storage mechanisms to accommodate new observation formats and fields.
- Enhanced documentation for new prompts and their usage in memory processing 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.
- Implemented a simple server using the net module.
- The server listens on a specified socket path.
- Added error handling for server errors.
- Included checks to verify the existence of the socket file.
- Removed `path-discovery.ts` service and replaced its usage with a new `paths.ts` module.
- Updated all commands and services to utilize the new path constants and helper functions.
- Ensured all necessary directories are created using the new utility functions.
- Improved code readability and maintainability by centralizing path configurations.
- Added background agent architecture for processing tool observations and generating session summaries.
- Created SDK Prompts Module for generating prompts for the Claude Agent SDK.
- Developed XML Parser Module for parsing observation and summary XML blocks from SDK responses.
- Implemented SDK Worker Process to handle observation processing and session management.
- Updated newHook implementation to spawn the SDK worker as a detached process with path resolution for development and production.
- Created comprehensive test suite for SDK prompts, XML parsing, and HooksDatabase integration, ensuring all tests pass.
- Documented Phase 2 implementation details, architecture validation, and success criteria in PHASE2-COMPLETE.md.
Alex Newman