mirror of
https://github.com/lukaszraczylo/claude-mnemonic.git
synced 2026-06-09 23:59:40 +00:00
5c2685c7b6
* 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
* fix: add fts5 build tag to CI workflow
Pass build-tags: "fts5" to shared workflow to properly compile
sqlite-vec-go-bindings with SQLite FTS5 support.
This fixes test failures in hybrid vector storage tests that require
CGO and FTS5 build tags.
Requires shared-actions@8f7f235 or later.
* docs: add testing documentation and macOS ARM64 known issue
Document the macOS ARM64 CGO linking issue with sqlite-vec-go-bindings
that prevents hybrid package tests from compiling locally.
Added:
- .github/TESTING.md: Comprehensive testing guide with platform-specific
issues, workarounds, and CI configuration details
- internal/vector/hybrid/README.md: Package-specific documentation
explaining the macOS limitation
- .github/CI_FIX_SUMMARY.md: Technical details of the CI fix
Key points:
- 41 out of 42 packages test successfully on all platforms
- hybrid package tests fail only on macOS ARM64 (local dev issue)
- Linux CI tests pass with proper build-tags: "fts5" configuration
- Production builds and runtime functionality unaffected
This is a known limitation of sqlite-vec-go-bindings on macOS ARM64
and does not impact CI/CD or production deployments.
* fix: add SQLite busy_timeout to prevent database locked errors
Set PRAGMA busy_timeout=5000 (5 seconds) to allow SQLite to retry
when the database is locked instead of failing immediately.
This fixes race conditions when multiple goroutines try to write
simultaneously, particularly in tests where StoreObservation spawns
async cleanup goroutines.
Root cause:
- StoreObservation launches goroutine -> CleanupOldObservations
- Multiple concurrent cleanups caused "database is locked" errors
- Without busy_timeout, SQLite fails immediately on lock contention
Solution:
- Add 5-second busy timeout for automatic retry on lock
- Standard practice for concurrent SQLite usage
- Works with existing WAL mode configuration
Fixes TestObservationStore_CleanupOldObservations in CI.
* docs: complete summary of all CI test fixes
Comprehensive documentation of all fixes applied:
1. Missing build tags (fts5)
2. Database locked errors (busy_timeout)
All 41/42 packages now pass tests. The hybrid package has a known
macOS ARM64 limitation that doesn't affect CI or production.
No functionality was removed - all fixes are additive only.
* fix: add SQLite driver import to hybrid tests for CGO linking
Add blank import of mattn/go-sqlite3 to hybrid test files to ensure
the SQLite driver is linked into the test binary. This provides the
SQLite symbols that sqlite-vec-go-bindings requires.
Root cause:
- hybrid package imports sqlitevec (transitively depends on sqlite-vec CGO)
- Test binary needs SQLite symbols for linking
- sqlitevec tests already had this import, but hybrid tests didn't
- Without the driver import, linker fails with "undefined symbols"
This fix enables hybrid tests to run with -race flag on all platforms.
Before: 41/42 packages pass (hybrid failed to link)
After: 42/42 packages pass ✅
Fixes hybrid test compilation on macOS ARM64, Linux, and Windows.
* docs: remove outdated macOS limitation documentation
The hybrid test linking issue has been fixed by adding the SQLite
driver import. All tests now pass on all platforms including macOS.
Removed:
- internal/vector/hybrid/README.md (documented workaround no longer needed)
- .github/TESTING.md (macOS limitation section obsolete)
All 42/42 packages now test successfully with -race flag.
* docs: final comprehensive summary of all CI fixes
All three issues now resolved:
1. Missing fts5 build tags
2. Database busy_timeout for concurrent writes
3. Missing SQLite driver import in hybrid tests
Result: 42/42 packages pass with -race on all platforms.
Credit to reviewer for identifying the race detector concern.
312 lines
8.8 KiB
Go
312 lines
8.8 KiB
Go
// Package search provides unified search capabilities for claude-mnemonic.
|
|
package search
|
|
|
|
import (
|
|
"context"
|
|
"strings"
|
|
|
|
"github.com/lukaszraczylo/claude-mnemonic/internal/db/gorm"
|
|
"github.com/lukaszraczylo/claude-mnemonic/internal/vector/sqlitevec"
|
|
"github.com/lukaszraczylo/claude-mnemonic/pkg/models"
|
|
)
|
|
|
|
// Manager provides unified search across SQLite and sqlite-vec.
|
|
type Manager struct {
|
|
observationStore *gorm.ObservationStore
|
|
summaryStore *gorm.SummaryStore
|
|
promptStore *gorm.PromptStore
|
|
vectorClient *sqlitevec.Client
|
|
}
|
|
|
|
// NewManager creates a new search manager.
|
|
func NewManager(
|
|
observationStore *gorm.ObservationStore,
|
|
summaryStore *gorm.SummaryStore,
|
|
promptStore *gorm.PromptStore,
|
|
vectorClient *sqlitevec.Client,
|
|
) *Manager {
|
|
return &Manager{
|
|
observationStore: observationStore,
|
|
summaryStore: summaryStore,
|
|
promptStore: promptStore,
|
|
vectorClient: vectorClient,
|
|
}
|
|
}
|
|
|
|
// SearchParams contains parameters for unified search.
|
|
type SearchParams struct {
|
|
Format string
|
|
Type string
|
|
Project string
|
|
ObsType string
|
|
Concepts string
|
|
Files string
|
|
Query string
|
|
Scope string
|
|
OrderBy string
|
|
DateStart int64
|
|
Offset int
|
|
Limit int
|
|
DateEnd int64
|
|
IncludeGlobal bool
|
|
ExcludeSuperseded bool
|
|
}
|
|
|
|
// SearchResult represents a unified search result.
|
|
type SearchResult struct {
|
|
Metadata map[string]interface{} `json:"metadata,omitempty"`
|
|
Type string `json:"type"`
|
|
Title string `json:"title,omitempty"`
|
|
Content string `json:"content,omitempty"`
|
|
Project string `json:"project"`
|
|
Scope string `json:"scope,omitempty"`
|
|
ID int64 `json:"id"`
|
|
CreatedAt int64 `json:"created_at_epoch"`
|
|
Score float64 `json:"score,omitempty"`
|
|
}
|
|
|
|
// UnifiedSearchResult contains the combined search results.
|
|
type UnifiedSearchResult struct {
|
|
Query string `json:"query,omitempty"`
|
|
Results []SearchResult `json:"results"`
|
|
TotalCount int `json:"total_count"`
|
|
}
|
|
|
|
// UnifiedSearch performs a unified search across all document types.
|
|
func (m *Manager) UnifiedSearch(ctx context.Context, params SearchParams) (*UnifiedSearchResult, error) {
|
|
if params.Limit <= 0 {
|
|
params.Limit = 20
|
|
}
|
|
if params.Limit > 100 {
|
|
params.Limit = 100
|
|
}
|
|
if params.OrderBy == "" {
|
|
params.OrderBy = "date_desc"
|
|
}
|
|
|
|
// If query is provided and vector client is available, use vector search
|
|
if params.Query != "" && m.vectorClient != nil && m.vectorClient.IsConnected() {
|
|
return m.vectorSearch(ctx, params)
|
|
}
|
|
|
|
// Otherwise fall back to structured filter search
|
|
return m.filterSearch(ctx, params)
|
|
}
|
|
|
|
// vectorSearch performs semantic search via sqlite-vec.
|
|
func (m *Manager) vectorSearch(ctx context.Context, params SearchParams) (*UnifiedSearchResult, error) {
|
|
// Build where filter based on search type
|
|
var docType sqlitevec.DocType
|
|
switch params.Type {
|
|
case "observations":
|
|
docType = sqlitevec.DocTypeObservation
|
|
case "sessions":
|
|
docType = sqlitevec.DocTypeSessionSummary
|
|
case "prompts":
|
|
docType = sqlitevec.DocTypeUserPrompt
|
|
}
|
|
where := sqlitevec.BuildWhereFilter(docType, params.Project)
|
|
|
|
// Query sqlite-vec
|
|
vectorResults, err := m.vectorClient.Query(ctx, params.Query, params.Limit*2, where)
|
|
if err != nil {
|
|
// Fall back to filter search on error
|
|
return m.filterSearch(ctx, params)
|
|
}
|
|
|
|
// Extract IDs grouped by document type using shared helper
|
|
extracted := sqlitevec.ExtractIDsByDocType(vectorResults)
|
|
obsIDs := extracted.ObservationIDs
|
|
summaryIDs := extracted.SummaryIDs
|
|
promptIDs := extracted.PromptIDs
|
|
|
|
// Fetch full records from SQLite
|
|
var results []SearchResult
|
|
|
|
if len(obsIDs) > 0 && (params.Type == "" || params.Type == "observations") {
|
|
obs, err := m.observationStore.GetObservationsByIDs(ctx, obsIDs, params.OrderBy, 0)
|
|
if err == nil {
|
|
for _, o := range obs {
|
|
// Skip superseded observations when requested
|
|
if params.ExcludeSuperseded && o.IsSuperseded {
|
|
continue
|
|
}
|
|
results = append(results, m.observationToResult(o, params.Format))
|
|
}
|
|
}
|
|
}
|
|
|
|
if len(summaryIDs) > 0 && (params.Type == "" || params.Type == "sessions") {
|
|
summaries, err := m.summaryStore.GetSummariesByIDs(ctx, summaryIDs, params.OrderBy, 0)
|
|
if err == nil {
|
|
for _, s := range summaries {
|
|
results = append(results, m.summaryToResult(s, params.Format))
|
|
}
|
|
}
|
|
}
|
|
|
|
if len(promptIDs) > 0 && (params.Type == "" || params.Type == "prompts") {
|
|
prompts, err := m.promptStore.GetPromptsByIDs(ctx, promptIDs, params.OrderBy, 0)
|
|
if err == nil {
|
|
for _, p := range prompts {
|
|
results = append(results, m.promptToResult(p, params.Format))
|
|
}
|
|
}
|
|
}
|
|
|
|
// Apply limit
|
|
if len(results) > params.Limit {
|
|
results = results[:params.Limit]
|
|
}
|
|
|
|
return &UnifiedSearchResult{
|
|
Results: results,
|
|
TotalCount: len(results),
|
|
Query: params.Query,
|
|
}, nil
|
|
}
|
|
|
|
// filterSearch performs structured filter search via SQLite.
|
|
func (m *Manager) filterSearch(ctx context.Context, params SearchParams) (*UnifiedSearchResult, error) {
|
|
var results []SearchResult
|
|
|
|
// Search observations
|
|
if params.Type == "" || params.Type == "observations" {
|
|
var obs []*models.Observation
|
|
var err error
|
|
|
|
// Use active observations (excluding superseded) when requested
|
|
if params.ExcludeSuperseded {
|
|
obs, err = m.observationStore.GetActiveObservations(ctx, params.Project, params.Limit)
|
|
} else {
|
|
obs, err = m.observationStore.GetRecentObservations(ctx, params.Project, params.Limit)
|
|
}
|
|
|
|
if err == nil {
|
|
for _, o := range obs {
|
|
results = append(results, m.observationToResult(o, params.Format))
|
|
}
|
|
}
|
|
}
|
|
|
|
// Search summaries
|
|
if params.Type == "" || params.Type == "sessions" {
|
|
summaries, err := m.summaryStore.GetRecentSummaries(ctx, params.Project, params.Limit)
|
|
if err == nil {
|
|
for _, s := range summaries {
|
|
results = append(results, m.summaryToResult(s, params.Format))
|
|
}
|
|
}
|
|
}
|
|
|
|
// Apply limit
|
|
if len(results) > params.Limit {
|
|
results = results[:params.Limit]
|
|
}
|
|
|
|
return &UnifiedSearchResult{
|
|
Results: results,
|
|
TotalCount: len(results),
|
|
}, nil
|
|
}
|
|
|
|
// Decisions performs a semantic search optimized for finding decisions.
|
|
func (m *Manager) Decisions(ctx context.Context, params SearchParams) (*UnifiedSearchResult, error) {
|
|
// Boost query with decision-related keywords
|
|
if params.Query != "" {
|
|
params.Query = params.Query + " decision chose architecture"
|
|
}
|
|
params.Type = "observations"
|
|
return m.UnifiedSearch(ctx, params)
|
|
}
|
|
|
|
// Changes performs a semantic search optimized for finding code changes.
|
|
func (m *Manager) Changes(ctx context.Context, params SearchParams) (*UnifiedSearchResult, error) {
|
|
// Boost query with change-related keywords
|
|
if params.Query != "" {
|
|
params.Query = params.Query + " changed modified refactored"
|
|
}
|
|
params.Type = "observations"
|
|
return m.UnifiedSearch(ctx, params)
|
|
}
|
|
|
|
// HowItWorks performs a semantic search optimized for understanding architecture.
|
|
func (m *Manager) HowItWorks(ctx context.Context, params SearchParams) (*UnifiedSearchResult, error) {
|
|
// Boost query with architecture-related keywords
|
|
if params.Query != "" {
|
|
params.Query = params.Query + " architecture design pattern implements"
|
|
}
|
|
params.Type = "observations"
|
|
return m.UnifiedSearch(ctx, params)
|
|
}
|
|
|
|
// Helper methods
|
|
|
|
func (m *Manager) observationToResult(obs *models.Observation, format string) SearchResult {
|
|
result := SearchResult{
|
|
Type: "observation",
|
|
ID: obs.ID,
|
|
Project: obs.Project,
|
|
Scope: string(obs.Scope),
|
|
CreatedAt: obs.CreatedAtEpoch,
|
|
Metadata: map[string]interface{}{
|
|
"obs_type": string(obs.Type),
|
|
"scope": string(obs.Scope),
|
|
},
|
|
}
|
|
|
|
if obs.Title.Valid {
|
|
result.Title = obs.Title.String
|
|
}
|
|
|
|
if format == "full" && obs.Narrative.Valid {
|
|
result.Content = obs.Narrative.String
|
|
}
|
|
|
|
return result
|
|
}
|
|
|
|
func (m *Manager) summaryToResult(summary *models.SessionSummary, format string) SearchResult {
|
|
result := SearchResult{
|
|
Type: "session",
|
|
ID: summary.ID,
|
|
Project: summary.Project,
|
|
CreatedAt: summary.CreatedAtEpoch,
|
|
}
|
|
|
|
if summary.Request.Valid {
|
|
result.Title = truncate(summary.Request.String, 100)
|
|
}
|
|
|
|
if format == "full" && summary.Learned.Valid {
|
|
result.Content = summary.Learned.String
|
|
}
|
|
|
|
return result
|
|
}
|
|
|
|
func (m *Manager) promptToResult(prompt *models.UserPromptWithSession, format string) SearchResult {
|
|
result := SearchResult{
|
|
Type: "prompt",
|
|
ID: prompt.ID,
|
|
Project: prompt.Project,
|
|
CreatedAt: prompt.CreatedAtEpoch,
|
|
}
|
|
|
|
result.Title = truncate(prompt.PromptText, 100)
|
|
|
|
if format == "full" {
|
|
result.Content = prompt.PromptText
|
|
}
|
|
|
|
return result
|
|
}
|
|
|
|
func truncate(s string, maxLen int) string {
|
|
s = strings.TrimSpace(s)
|
|
if len(s) <= maxLen {
|
|
return s
|
|
}
|
|
return s[:maxLen] + "..."
|
|
}
|