Commit Graph

5 Commits

Author SHA1 Message Date
Alex Newman 5d64df2ba5 docs: Update all documentation to reflect v5.4.0 skill-based search
Documentation Updates:
- README.md: Updated version badge, What's New, and search section
- docs/usage/search-tools.mdx: Rewrote for skill-based natural language approach
- docs/architecture/mcp-search.mdx → search-architecture.mdx: Complete rewrite
- docs/architecture/overview.mdx: Updated components and search pipeline
- docs/usage/getting-started.mdx: Added skill-based search section
- docs/configuration.mdx: Updated search configuration for v5.4.0
- docs/introduction.mdx: Updated key features
- docs/docs.json: Updated navigation to search-architecture

Key Changes:
- Emphasized ~2,250 token savings per session start
- Converted all examples to natural language queries
- Documented 10 HTTP API endpoints
- Explained progressive disclosure pattern
- Added migration notes (transparent, no user action required)
- Removed outdated MCP references

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-09 19:14:05 -05:00
Alex Newman 0475a57fb1 feat: Migrate to Skill-Based Search and enhance context handling
- 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.
2025-11-09 17:34:00 -05:00
copilot-swe-agent[bot] 192adf5cbc Fix: /clear DOES inject context via SessionStart hook
Corrected incorrect documentation that claimed /clear doesn't inject context.
The SessionStart hook fires with source: "clear" when /clear is used, which
re-injects context from recent sessions. Updated docs to accurately reflect
that /clear both clears conversation AND re-injects fresh context.

Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>
2025-10-31 21:28:54 +00:00
copilot-swe-agent[bot] 140a5f3469 Clarify Stop hook behavior and /clear vs exit in docs
- Changed "Stop Claude" to "Claude finishes responding" to clarify that the Stop hook fires automatically
- Explained Stop hook triggers summary generation automatically, not as a user action
- Added detailed section explaining /clear behavior vs completely exiting Claude Code
- Clarified when new context is injected (new session start, not after /clear)
- Fixed session count: changed "last 3 sessions" to "last 10 sessions" (matches implementation)

Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>
2025-10-31 21:06:59 +00:00
Alex Newman 8b4c962e62 Add initial documentation for Claude-Mem plugin
- Created docs structure including introduction, installation, troubleshooting, and usage guides.
- Added detailed installation instructions with quick start and advanced options.
- Documented the automatic operation of Claude-Mem and its session management features.
- Introduced MCP search tools with usage examples and query strategies.
- Provided troubleshooting steps for common issues related to worker service, hooks, database, and search tools.
- Included system requirements and upgrade notes for transitioning from v3.x to v4.0.0.
2025-10-24 18:04:03 -04:00