fix: bound SQLite WAL growth and prevent worker hangs (#49)

The worker's SQLite WAL could grow unbounded (observed 19MB) and wedge the
DB, hanging Claude Code on every prompt. No checkpoint ever truncated the
WAL (only PASSIVE auto-checkpoint, which cannot reclaim the file), the
connection-scoped pragmas were set via a single Exec so only one pooled
connection received them (e.g. busy_timeout=0 on the rest), and the
maintenance service that would optimize/checkpoint was never wired up.

- Register a sqlite3 ConnectHook driver so all pragmas (busy_timeout,
  journal_mode, synchronous, cache_size, foreign_keys, journal_size_limit)
  apply to every pooled connection; enable safe connection recycling.
- Add Store.Checkpoint (TRUNCATE), checkpoint-on-Close, and a periodic
  size-gated checkpoint loop with configurable interval/threshold.
- Wire up the previously-dead maintenance service; make trigger_maintenance
  actually run DB maintenance instead of only recalculating scores.
- Harden the user-prompt hook to honor its deadline and fail open so a
  slow worker can never stall a prompt.
- Add regression tests for WAL truncation, checkpoint-on-close, and
  per-connection pragmas.
This commit is contained in:
2026-06-01 16:40:27 +01:00
parent f78370a531
commit b7b82ce22f
10 changed files with 957 additions and 93 deletions
+67
View File
@@ -564,6 +564,44 @@ func POSTWithContext(ctx context.Context, port int, path string, body interface{
return nil
}
// POSTWithContextResult sends a POST request using the provided context and
// decodes the JSON response body, mirroring POST but honoring ctx for
// cancellation/deadline. Used on the prompt critical path so a wedged worker
// aborts at the hook deadline instead of blocking for the full client timeout.
// A non-JSON body is returned as (nil, nil), matching POST's behavior.
func POSTWithContextResult(ctx context.Context, port int, path string, body interface{}) (map[string]interface{}, error) {
jsonBody, err := json.Marshal(body)
if err != nil {
return nil, err
}
req, err := http.NewRequestWithContext(ctx, http.MethodPost,
fmt.Sprintf("http://127.0.0.1:%d%s", port, path),
bytes.NewReader(jsonBody))
if err != nil {
return nil, err
}
req.Header.Set("Content-Type", "application/json")
resp, err := hookClient.Do(req)
if err != nil {
return nil, err
}
defer func() { _ = resp.Body.Close() }()
if resp.StatusCode >= 400 {
return nil, fmt.Errorf("request failed: %s", resp.Status)
}
var result map[string]interface{}
if err := json.NewDecoder(resp.Body).Decode(&result); err != nil {
// Not all endpoints return JSON
return nil, nil
}
return result, nil
}
// GET sends a GET request to the worker.
func GET(port int, path string) (map[string]interface{}, error) {
resp, err := hookClient.Get(fmt.Sprintf("http://127.0.0.1:%d%s", port, path))
@@ -584,6 +622,35 @@ func GET(port int, path string) (map[string]interface{}, error) {
return result, nil
}
// GETWithContext sends a GET request using the provided context and decodes the
// JSON response body, mirroring GET but honoring ctx for cancellation/deadline.
// Used on the prompt critical path so a wedged worker aborts at the hook
// deadline instead of blocking for the full client timeout.
func GETWithContext(ctx context.Context, port int, path string) (map[string]interface{}, error) {
req, err := http.NewRequestWithContext(ctx, http.MethodGet,
fmt.Sprintf("http://127.0.0.1:%d%s", port, path), nil)
if err != nil {
return nil, err
}
resp, err := hookClient.Do(req)
if err != nil {
return nil, err
}
defer func() { _ = resp.Body.Close() }()
if resp.StatusCode >= 400 {
return nil, fmt.Errorf("request failed: %s", resp.Status)
}
var result map[string]interface{}
if err := json.NewDecoder(resp.Body).Decode(&result); err != nil {
return nil, err
}
return result, nil
}
// versionsCompatible checks if two versions are compatible for dev builds.
// Returns true if both versions share the same base version (ignoring -dirty, -dev, commit suffixes).
// This prevents unnecessary restarts during development.