feat(leann-phase2): implement hybrid vector storage and graph-based search

- [x] Add AST-aware code chunking for Go, Python, and TypeScript using tree-sitter
- [x] Implement LEANN-inspired hybrid vector storage with hub detection and selective embedding storage (60-80% savings)
- [x] Add observation relationship graph with CSR format and edge detection (file overlap, semantic similarity, temporal, concept)
- [x] Implement graph-aware search with two-level traversal and relationship-based ranking
- [x] Add auto-tuning system for dynamic hub threshold adjustment based on query performance
- [x] Add comprehensive metrics tracking for vector storage, queries, latency, and graph traversals
- [x] Update configuration system with graph and hybrid storage settings
- [x] Add graph stats and vector metrics endpoints to worker service
- [x] Enhance UI sidebar with advanced metrics display and graph visualization
- [x] Optimize struct field alignment throughout codebase for memory efficiency
- [x] Update documentation with LEANN Phase 2 features and performance benefits
- [x] Add tree-sitter dependency for AST parsing
This commit is contained in:
2026-01-07 20:43:10 +00:00
parent 7ab4b07cf2
commit 74ae8ed4c1
83 changed files with 5190 additions and 603 deletions
+3 -4
View File
@@ -31,15 +31,14 @@ type SyncSummaryFunc func(summary *models.SessionSummary)
// Processor handles SDK agent processing of observations and summaries using Claude Code CLI.
type Processor struct {
claudePath string
model string
observationStore *gorm.ObservationStore
summaryStore *gorm.SummaryStore
broadcastFunc BroadcastFunc
syncObservationFunc SyncObservationFunc
syncSummaryFunc SyncSummaryFunc
// Semaphore to limit concurrent Claude CLI calls (prevents API overload)
sem chan struct{}
sem chan struct{}
claudePath string
model string
}
// SetBroadcastFunc sets the broadcast callback for SSE events.