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

agent/hotpath_agent/loop.py

@@ -86,7 +86,9 @@ async def run_attempt(target: str, run_id: str, max_turns: int, repo_root: str)
         f"3. Read the relevant source with read_target_source — for large files pass "
         f"offset/limit and page through in windows (do NOT attempt any shell). State your "
         f"hypothesis, then propose_patch (unified diff, a/ b/ prefixes, paths relative to the "
-        f"target workspace root).\n"
+        f"target workspace root, trailing newline required). Each proposal is STANDALONE — "
+        f"the workspace resets to pristine before every apply, so always submit the complete "
+        f"patch, never an increment on a prior proposal.\n"
         f"4. run_verdict with run_id '{run_id}', the class number, and the hotspot string. "
         f"It launches a multi-minute pipeline and returns immediately.\n"
         f"5. Poll read_verdict('{run_id}') until it returns a verdict (not a 'running' status). "