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). "

agent/hotpath_agent/mcp_server.py

@@ -50,9 +50,12 @@ def read_target_source(target: str, path: str, offset: int = 0, limit: int = 400
 
 @mcp.tool()
 def propose_patch(target: str, diff: str, hypothesis: str) -> str:
-    """Submit a unified git diff (a/ b/ prefixes, paths relative to the target workspace)
-    plus the hypothesis it tests. The harness applies it only after a path-allowlist
-    check. Returns a patch_id, or an error string if refused."""
+    """Submit a unified git diff (a/ b/ prefixes, paths relative to the target
+    workspace, MUST end with a trailing newline) plus the hypothesis it tests.
+    Each proposal is STANDALONE: the workspace is reset to pristine before the
+    diff is applied, so always submit the complete patch — never an increment
+    on top of an earlier proposal. The harness applies it only after a
+    path-allowlist check. Returns a patch_id, or an error string if refused."""
     return harness.propose_patch(target, diff, hypothesis)
 
 

crates/harnessd/src/main.rs

@@ -222,6 +222,13 @@ fn handle(root: &Path, line: &str) -> Result<Value> {
             let diff = field(&req, "diff")?;
             let hypothesis = field(&req, "hypothesis")?;
             check_target(t)?;
+            // git rejects a diff without a final newline with an opaque
+            // "corrupt patch" — say it plainly (phase2-comrak-004 burned
+            // several turns rediscovering this).
+            ensure!(
+                diff.ends_with('\n'),
+                "diff must end with a trailing newline (git would report 'corrupt patch' at EOF)"
+            );
             // Allowlist: every path named by the diff must be a safe
             // relative path (the git -C below roots them in the target
             // workspace; nothing outside it is reachable).
@@ -238,18 +245,51 @@ fn handle(root: &Path, line: &str) -> Result<Value> {
                 );
             }
             let ws = root.join(format!("targets/{t}/workspace"));
-            let mut check = Command::new("git")
-                .args(["-C", ws.to_str().unwrap(), "apply", "--check", "-"])
+            // Every proposal stands alone: reset the workspace to HEAD
+            // first so probe/iteration patches cannot accumulate into a
+            // tested tree the ledger's patch field doesn't describe
+            // (phase2-comrak-004 audit finding).
+            ensure!(
+                Command::new("git")
+                    .args(["-C", ws.to_str().unwrap(), "checkout", "--", "."])
+                    .status()?
+                    .success(),
+                "workspace reset failed"
+            );
+            ensure!(
+                Command::new("git")
+                    .args(["-C", ws.to_str().unwrap(), "clean", "-fdq"])
+                    .status()?
+                    .success(),
+                "workspace clean failed"
+            );
+            let run_git_apply = |check: bool| -> Result<std::process::Output> {
+                let mut args = vec!["-C", ws.to_str().unwrap(), "apply"];
+                if check {
+                    args.push("--check");
+                }
+                args.push("-");
+                let mut child = Command::new("git")
+                    .args(&args)
                     .stdin(std::process::Stdio::piped())
+                    .stderr(std::process::Stdio::piped())
                     .spawn()?;
-            check.stdin.take().unwrap().write_all(diff.as_bytes())?;
-            ensure!(check.wait()?.success(), "diff does not apply cleanly");
-            let mut apply = Command::new("git")
-                .args(["-C", ws.to_str().unwrap(), "apply", "-"])
-                .stdin(std::process::Stdio::piped())
-                .spawn()?;
-            apply.stdin.take().unwrap().write_all(diff.as_bytes())?;
-            ensure!(apply.wait()?.success(), "git apply failed");
+                child.stdin.take().unwrap().write_all(diff.as_bytes())?;
+                Ok(child.wait_with_output()?)
+            };
+            let checked = run_git_apply(true)?;
+            ensure!(
+                checked.status.success(),
+                "diff does not apply cleanly against the pristine workspace \
+                 (proposals are standalone; prior proposals were reset): {}",
+                String::from_utf8_lossy(&checked.stderr).trim()
+            );
+            let applied = run_git_apply(false)?;
+            ensure!(
+                applied.status.success(),
+                "git apply failed: {}",
+                String::from_utf8_lossy(&applied.stderr).trim()
+            );
             let patch_id = format!("{:x}", Sha256::digest(diff.as_bytes()))[..12].to_string();
             let pending = root.join("results/pending");
             std::fs::create_dir_all(&pending)?;