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

Browse Source

- 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

...

This commit is contained in:

Claude

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

parent 393ca7117f

commit 23ab522445

4 changed files with 61 additions and 16 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

results/ledger.sqlite

BIN

Binary file not shown.