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
+20 -23
View File
@@ -21,11 +21,11 @@ const (
// ObservationData contains data for a tool observation.
type ObservationData struct {
ToolName string
ToolInput interface{}
ToolResponse interface{}
PromptNumber int
ToolName string
CWD string
PromptNumber int
}
// SummarizeData contains data for a summarize request.
@@ -36,30 +36,28 @@ type SummarizeData struct {
// PendingMessage represents a message queued for SDK processing.
type PendingMessage struct {
Type MessageType
Observation *ObservationData
Summarize *SummarizeData
Type MessageType
}
// ActiveSession represents an in-memory active session being processed.
type ActiveSession struct {
SessionDBID int64
ClaudeSessionID string
SDKSessionID string
StartTime time.Time
ctx context.Context
cancel context.CancelFunc
notify chan struct{}
Project string
UserPrompt string
SDKSessionID string
ClaudeSessionID string
pendingMessages []PendingMessage
LastPromptNumber int
StartTime time.Time
CumulativeInputTokens int64
CumulativeOutputTokens int64
// Concurrency control
pendingMessages []PendingMessage
messageMu sync.Mutex
notify chan struct{}
ctx context.Context
cancel context.CancelFunc
generatorActive atomic.Bool
SessionDBID int64
messageMu sync.Mutex
generatorActive atomic.Bool
}
// SessionTimeout is how long an inactive session can exist before cleanup.
@@ -70,15 +68,14 @@ const CleanupInterval = 5 * time.Minute
// Manager manages active session lifecycles.
type Manager struct {
sessionStore *gorm.SessionStore
sessions map[int64]*ActiveSession
mu sync.RWMutex
onCreated func(int64)
onDeleted func(int64)
ctx context.Context
cancel context.CancelFunc
// Global notification channel for immediate processing
ctx context.Context
sessionStore *gorm.SessionStore
sessions map[int64]*ActiveSession
onCreated func(int64)
onDeleted func(int64)
cancel context.CancelFunc
ProcessNotify chan struct{}
mu sync.RWMutex
}
// NewManager creates a new session manager.
+7 -7
View File
@@ -669,16 +669,16 @@ func TestActiveSessionCWD(t *testing.T) {
// TestToolInputResponse tests various tool input/response types.
func TestToolInputResponse(t *testing.T) {
tests := []struct {
name string
input interface{}
response interface{}
name string
}{
{"nil_values", nil, nil},
{"string_values", "input string", "response string"},
{"map_values", map[string]string{"key": "value"}, map[string]interface{}{"result": true}},
{"slice_values", []string{"a", "b"}, []int{1, 2, 3}},
{"int_values", 42, 100},
{"bool_values", true, false},
{name: "nil_values", input: nil, response: nil},
{name: "string_values", input: "input string", response: "response string"},
{name: "map_values", input: map[string]string{"key": "value"}, response: map[string]interface{}{"result": true}},
{name: "slice_values", input: []string{"a", "b"}, response: []int{1, 2, 3}},
{name: "int_values", input: 42, response: 100},
{name: "bool_values", input: true, response: false},
}
for _, tt := range tests {