* 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>
* 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>
- 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.
- Updated `save-hook.js`, `summary-hook.js`, `context-hook.ts`, `new-hook.ts`, and `save-hook.ts` to include a call to `ensureWorkerRunning()` at the beginning of their main functions. This ensures that the worker is active before any operations are performed.
- Cleaned up import statements in the affected files to include the new utility function from `worker-utils.js`.
- Minor adjustments to logging and error handling to improve robustness and clarity.
- Removed ensureWorkerRunning calls from multiple hooks (cleanup, context, new, save, summary) to streamline code and avoid unnecessary checks.
- Introduced fixed port usage for worker communication across hooks.
- Enhanced error handling in newHook, saveHook, and summaryHook to provide clearer messages for worker connection issues.
- Updated worker service to start without health checks, relying on PM2 for management.
- Cached Claude executable path to optimize repeated calls.
- Improved logging for better traceability of worker actions and errors.
- Removed bin/hooks/ wrapper layer
- Moved all hook logic into consolidated hooks/*-hook.ts files
- Each hook now handles its own stdin/stdout/JSON wrapping
- Removed ALL try-catch blocks from context-hook (let errors surface)
- Updated build script to reference new src/hooks/ paths
- Reduced from 12+ files to 6 hook files
This simplifies the architecture and makes debugging actually possible.
Alex Newman