tegwick
d0261ebb52
Per Bernd's call: the guardrails prevent security harm but not LLM content errors, so the worker should triage + draft, not auto-send, until reply quality is proven (matches the build-stage/recoverability posture). run_conservative triages NEW messages into a reviewed digest (state_dir/worker-digest.md) with drafted replies, posts ONE progress note, tracks seen message ids (schedule-safe dedup), and sends NOTHING to other agents / marks nothing read. `warden worker run --execute` now runs this conservative tier; `--full-auto` opts into the auto-send path. Live-verified with the LLM brain on the real inbox: produced a high-quality draft reply to a secrets-engine coordination message and correctly flagged the llm-connect custody request as NEEDS YOU. Conservative mode is safe to schedule (T4). 244 tests, lint clean. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| routing | ||
| scripts | ||
| __init__.py | ||
| access.py | ||
| ca.py | ||
| cli.py | ||
| config.py | ||
| doubles.py | ||
| inventory.py | ||
| models.py | ||
| policy.py | ||
| posture.py | ||
| proxy.py | ||
| scorecard.py | ||
| vault.py | ||
| worker.py | ||