Fixes
- Tightened live loop detection so short successful tool results no longer trigger
Possible retry loopwarnings. - Retry-churn warnings now require concrete failure signals and repeated failures from the same tool family.
- Added conservative guards for benign outputs such as
0 failedand normal search-styleexit code 1results.
Version sync
- Bumped Claude Code plugin metadata from
5.6.3to5.6.4. - Confirmed no
id-manifest.jsonis present in this marketplace tree.
OpenClaw check
- Checked the OpenClaw implementation: this exact live short-result detector is deferred/not present there, and the existing retry-churn detector is session-level and failure-outcome based.
- Synced OpenClaw patch metadata to
2.4.1and fixed stale README/CLI version strings.
Verification
python3 -m py_compile skills/token-optimizer/scripts/measure.py- Focused loop-detection regression checks
npm run buildinopenclaw/python3 -m pytest tests(141 passed)