K variants for training (free text, EPOD tool names), second attempt only for failed tasks, docs/epod-syntax-hint.md

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

harness/trajectories.py

@@ -47,6 +47,15 @@ def done_keys():
     return {(r["task"], r["attempt"]) for r in map(json.loads, open(path))}
 
 
+def failed_first_attempts(min_score):
+    """Tasks whose attempt 0 did not give an acceptable run (score, end reason, harness error)."""
+    path = os.path.join(OUT, "summary.jsonl")
+    rows = [json.loads(l) for l in open(path)] if os.path.exists(path) else []
+    return sorted(r["task"] for r in rows if r["attempt"] == 0 and (
+        r.get("harness_error") or r.get("setup_failed") or r.get("end_reason") != "report"
+        or (r.get("score") or 0) < min_score))
+
+
 def append(name, row):
     with LOCK, open(os.path.join(OUT, name), "a") as f:
         f.write(json.dumps(row) + "\n")
@@ -91,7 +100,10 @@ def main():
     ap = argparse.ArgumentParser()
     ap.add_argument("cmd", choices=["run", "list"])
     ap.add_argument("--workers", type=int, default=6)
-    ap.add_argument("--attempts", type=int, default=1)
+    ap.add_argument("--attempts", type=int, default=1,
+                    help="1 = one attempt per task; with --retry-failed: the second attempt only for failed tasks")
+    ap.add_argument("--retry-failed", action="store_true")
+    ap.add_argument("--min-score", type=float, default=80)
     ap.add_argument("--limit", type=int, help="maximum number of runs in this call")
     ap.add_argument("--tasks", nargs="*")
     a = ap.parse_args()
@@ -99,6 +111,8 @@ def main():
     tasks = a.tasks or accepted_tasks()
     done = done_keys()
     todo = [(t, k) for k in range(a.attempts) for t in tasks if (t, k) not in done]
+    if a.retry_failed:  # attempt 1 only for tasks whose attempt 0 failed
+        todo = [(t, 1) for t in failed_first_attempts(a.min_score) if t in tasks and (t, 1) not in done]
     if a.limit:
         todo = todo[:a.limit]
     print(len(tasks), "accepted tasks,", len(todo), "runs to do, spent", spent(), flush=True)