Tags give the ability to mark specific points in history as being important
-
v0.8.2
protected270635c5 · ·release: v0.8.2 - injection effectiveness tracking and workspace auto-init - Injection effectiveness analysis module for tracking context impact - Auto-register workspace on boot context (implicit workspace initialization) - Relevance filtering with MIN_RELEVANCE_THRESHOLD (0.35) - Heuristic and LLM-based reanalysis for injection quality
-
v0.8.1
protected38e19008 · ·release: v0.8.1 - injection effectiveness tracking - Injection effectiveness analysis module for tracking context impact - Auto-register workspace on boot context (implicit workspace initialization) - Relevance filtering with MIN_RELEVANCE_THRESHOLD (0.35) - Heuristic and LLM-based reanalysis for injection quality
-
v0.6.1
protectedf8e07cfe · ·v0.6.1 - Documentation alignment and fixes - Documentation alignment: 17 fixes across all docs - Updated BOOTSTRAP.md for auto-injection vs manual workflow - Added HTTP endpoints section to ARCHITECTURE.md - Added missing tool tables (Reminders, Knowledge Graph, Code Indexing, GitLab Spider, Analytics) - Documented unified context_events table migration - Updated tool count from 25+ to 45+ - Various doc fixes for Python version, memory age format, SKIP_BOOTSTRAP env var See v0.6.0 for the main feature release.
-
v0.6.0
protected4402501b · ·v0.6.0 - Unified Session Tracking and Boot Context Auto-Injection Features: - Plugin auto-injects boot context on first message of each session - Boot gates cascade by directory hierarchy (project → parent dir → global) - Session registration tracks boot context IDs for de-duplication - Enhanced memory usage instructions embedded in boot context - Include conversation_summary in date-range queries for session history Changes: - Setup script offers to clean up legacy AGENTS.md (no longer needed) - README updated to reflect auto-injection behavior - Add _memory_ids_shown and _token_estimate to boot context response
-
v0.3.0
protected7dbed6cc · ·v0.3.0 - Knowledge Graph and 3-Process Architecture Major release with: - Knowledge graph with entity relationships and traversal - Code structure indexing via tree-sitter AST parsing - LLM-based concept extraction - 3-process architecture (server, daemon, worker) - Automatic migration from old enrichment worker See CHANGELOG.md for details.