Files
claude-mnemonic/pkg/hooks/response.go
T
lukaszraczylo 5c2685c7b6 feat(leann-phase2): implement hybrid vector storage and graph-based search (#20)
* 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.
2026-01-07 22:03:59 +00:00

181 lines
4.8 KiB
Go

// Package hooks provides hook utilities for claude-mnemonic.
package hooks
import (
"crypto/sha256"
"encoding/hex"
"encoding/json"
"fmt"
"io"
"os"
"path/filepath"
)
// HookResponse is the response sent back to Claude Code.
type HookResponse struct {
Continue bool `json:"continue"`
}
// ProjectIDWithName returns both the hash ID and the directory name for display.
// Format: "dirname_abc123" (name + truncated hash for human-readability)
func ProjectIDWithName(cwd string) string {
absPath, err := filepath.Abs(cwd)
if err != nil {
absPath = cwd
}
dirName := filepath.Base(absPath)
hash := sha256.Sum256([]byte(absPath))
shortHash := hex.EncodeToString(hash[:3]) // 6 chars
return fmt.Sprintf("%s_%s", dirName, shortHash)
}
// Exit codes for Claude Code hooks
const (
ExitSuccess = 0
ExitFailure = 1
ExitUserMessageOnly = 3 // Display stderr as user message
)
// WriteResponse writes a hook response to stdout.
func WriteResponse(hookName string, success bool) {
response := HookResponse{Continue: success}
data, _ := json.Marshal(response)
fmt.Println(string(data))
}
// WriteError writes an error message to stderr and exits.
func WriteError(hookName string, err error) {
fmt.Fprintf(os.Stderr, "[%s] Error: %v\n", hookName, err)
WriteResponse(hookName, false)
}
// BaseInput contains common fields shared by all hook inputs.
type BaseInput struct {
SessionID string `json:"session_id"`
CWD string `json:"cwd"`
PermissionMode string `json:"permission_mode"`
HookEventName string `json:"hook_event_name"`
}
// HookContext provides common context for hook handlers.
type HookContext struct {
HookName string
Project string
SessionID string
CWD string
RawInput []byte
Port int
}
// HookHandler is a function that handles hook-specific logic.
// It receives the context and returns an optional context string and error.
type HookHandler[T any] func(ctx *HookContext, input *T) (additionalContext string, err error)
// RunHook executes a hook with common boilerplate handling.
// It handles: internal call skip, stdin reading, JSON unmarshaling,
// worker startup, and project ID generation.
func RunHook[T any](hookName string, handler HookHandler[T]) {
// Skip if this is an internal call (from SDK processor)
if os.Getenv("CLAUDE_MNEMONIC_INTERNAL") == "1" {
WriteResponse(hookName, true)
return
}
// Read input from stdin
inputData, err := io.ReadAll(os.Stdin)
if err != nil {
WriteError(hookName, err)
os.Exit(1)
}
// Parse input
var input T
if err := json.Unmarshal(inputData, &input); err != nil {
WriteError(hookName, err)
os.Exit(1)
}
// Ensure worker is running
port, err := EnsureWorkerRunning()
if err != nil {
WriteError(hookName, err)
os.Exit(1)
}
// Extract base fields using interface assertion or reflection
var base BaseInput
_ = json.Unmarshal(inputData, &base)
// Generate project ID from CWD
project := ProjectIDWithName(base.CWD)
// Create context
ctx := &HookContext{
HookName: hookName,
Port: port,
Project: project,
SessionID: base.SessionID,
CWD: base.CWD,
RawInput: inputData,
}
// Run hook-specific handler
additionalContext, err := handler(ctx, &input)
if err != nil {
WriteError(hookName, err)
os.Exit(1)
}
// Output response
if additionalContext != "" {
response := map[string]interface{}{
"continue": true,
"hookSpecificOutput": map[string]interface{}{
"hookEventName": hookName,
"additionalContext": additionalContext,
},
}
_ = json.NewEncoder(os.Stdout).Encode(response)
os.Exit(0)
}
WriteResponse(hookName, true)
}
// StatuslineHandler is a function that handles statusline-specific logic.
// It receives input and port, returns formatted status string.
// No context injection or worker startup - just display.
type StatuslineHandler[T any] func(input *T, port int) string
// RunStatuslineHook executes a statusline hook with minimal overhead.
// Unlike RunHook, this:
// - Does NOT check CLAUDE_MNEMONIC_INTERNAL (statuslines always run)
// - Uses GetWorkerPort() instead of EnsureWorkerRunning() (no startup)
// - Prints output directly to stdout (no JSON wrapping)
// This keeps statusline fast (<100ms requirement).
func RunStatuslineHook[T any](handler StatuslineHandler[T]) {
// Read input from stdin
inputData, err := io.ReadAll(os.Stdin)
if err != nil {
// On error, handler receives nil and should return offline status
fmt.Println(handler(nil, 0))
return
}
// Parse input
var input T
if err := json.Unmarshal(inputData, &input); err != nil {
// On parse error, handler receives nil and should return offline status
fmt.Println(handler(nil, 0))
return
}
// Get worker port (does NOT start worker)
port := GetWorkerPort()
// Run handler and print result
fmt.Println(handler(&input, port))
}