Ajax Davis 1bf7879c1e feat: implement BM25 search with context from last 3 user messages ... - Implement proper BM25 scoring algorithm in /api/tools/search - Term frequency with saturation (k1 = 1.5) - Length normalization (b = 0.75) - Inverse document frequency (IDF) - Accept recent messages via 'messages' query param for better context - Update search-registry tool to: - Use /api/tools/search endpoint (not /api/tools) - Pass last 3 user messages for contextual search - Include recentMessages in tool input schema - Update chat API to extract and pass last 3 user messages to search BM25 formula: Σ IDF(qi) * (tf * (k1 + 1)) / (tf + k1 * (1 - b + b * |D| / avgdl)) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>		2025-12-04 13:59:22 +10:00
..
playground	feat: implement BM25 search with context from last 3 user messages	2025-12-04 13:59:22 +10:00
railway-executor	fix: use deployed /api/tools endpoint with client-side filtering and streamline git hooks	2025-12-04 13:43:19 +10:00
web	feat: implement BM25 search with context from last 3 user messages	2025-12-04 13:59:22 +10:00