v3.32.11
ruvnet/ruflov3.32.11Jul 26, 2026by ruvnet
AI Summary
Fixes `bridgeRecordFeedback` to call the correct API methods, enabling trajectory recording in the intelligence pipeline.
Key Highlights
- Fixed `bridgeRecordFeedback` to call `intelligence.recordTrajectory(steps, verdict)` instead of non-existent methods.
- Fixed `bridgeStoreEntry` to use the correct DB methods (INSERT ... ON CONFLICT).
- Enabled trajectory recording in `hooks intelligence stats` without mocks.
New Features
- intelligence.recordTrajectory integration
- LocalReasoningBank.store(pattern) integration
Full Release Notes
Follow-up patch closing the last remaining item flagged by the 2026-07-26 tracker-sweep agent — the sweep tagged it "architectural" but investigation showed a much smaller surgical fix was available.
## Fixed
- **#2786 fix-3** — `bridgeRecordFeedback` no longer silently swallows every call. The prior code called `learningSystem.recordFeedback`/`.record` and `reasoningBank.recordOutcome`/`.record`, but the registry actually wires the LOCAL intelligence classes (`LocalSonaCoordinator` / `LocalReasoningBank`) via `initializeIntelligence()` in `memory/intelligence.ts` — those classes never had those methods, and two `catch { /* API mismatch — skip */ }` blocks made the failure invisible. Fix: call the real public API `intelligence.recordTrajectory(steps, verdict)` — same call `hooks_post-command` already uses. Pattern-store branch also fixed to call `LocalReasoningBank.store(pattern)` (the one method that actually exists). No mocks, no silent catches on the happy path.
## E2E verification (no mocks)
Fresh scratch cwd, `memory init` + 3× `hooks post-task --task ... --store-results true`:
- Before: `hooks intelligence stats` → 0 trajectories
- After: **6 trajectories on disk + 3 pattern entries** (`~/.claude-flow/neural/stats.json`)
## Upgrade
```bash
npx ruflo@latest --version # → 3.32.11
```
Closes: #2786 (the last remaining fix from the 2026-07-26 sweep).