Claude 23ab522445 agent: propose_patch ergonomics from the phase2-comrak-004 audit ...

- Standalone-proposal semantics: workspace resets to pristine before
  every apply, so probe patches can't accumulate into a tested tree the
  ledger's patch field doesn't describe.
- Friendly errors: explicit trailing-newline check, and git apply's
  stderr relayed on refusal instead of a generic message.
- Tool docs + task prompt updated to match.
- phase2-comrak-004 audited: honest rejected-bench (median 1.0124,
  CI [1.0011, 1.0267] — real but under the 2% bar), Mutex pre-flagged
  for human review, cumulative-probe state disclosed in the hypothesis.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2

2026-07-10 05:32:08 +00:00

..

hotpath_agent

agent: propose_patch ergonomics from the phase2-comrak-004 audit

2026-07-10 05:32:08 +00:00

pyproject.toml

agent: unattended Phase 2 loop — profile to gated verdict, zero false accepts

2026-07-09 23:29:52 +00:00