Add independent-agent SWE prompt-ablation pilot

scripts/freeze_swe_population_plan.py

@@ -7,7 +7,12 @@ import json
 from pathlib import Path
 import subprocess
 
-from messageboardbench.swe_board import build_population_plan, load_records, plan_hash
+from messageboardbench.swe_board import (
+    NO_STOP_PROMPT_POLICY,
+    build_population_plan,
+    load_records,
+    plan_hash,
+)
 from messageboardbench.board import MESSAGEBOARD_V2_INTERFACE_VERSION
 from messageboardbench.swe_validation import DATASET
 
@@ -35,11 +40,25 @@ def main() -> int:
         "--messageboard-v2", action="store_true",
         help="freeze the send_message/read_messages plus organizer-feedback interface",
     )
+    parser.add_argument(
+        "--reuse-selection-plan", type=Path,
+        help="reuse the exact selected task IDs from an earlier frozen plan",
+    )
+    parser.add_argument(
+        "--no-stop-prompt", action="store_true",
+        help="retain DO NOT MODIFY THE TESTS but omit the extra stop/carve-out text",
+    )
     args = parser.parse_args()
     if args.messageboard_v2 and args.sample_size is None:
         parser.error("--messageboard-v2 requires --sample-size")
     if args.exclude_plan is not None and args.sample_size is None:
         parser.error("--exclude-plan requires --sample-size")
+    if args.reuse_selection_plan is not None and args.sample_size is not None:
+        parser.error("--reuse-selection-plan cannot be combined with --sample-size")
+    if args.reuse_selection_plan is not None and args.exclude_plan is not None:
+        parser.error("--reuse-selection-plan cannot be combined with --exclude-plan")
+    if args.no_stop_prompt and not args.messageboard_v2:
+        parser.error("--no-stop-prompt requires --messageboard-v2")
     upstream = (ROOT.parent / "impossiblebench").resolve()
     commit = subprocess.run(
         ["git", "rev-parse", "HEAD"], cwd=upstream, check=True,
@@ -47,6 +66,20 @@ def main() -> int:
     ).stdout.strip()
     records = load_records(args.revision, "conflicting")
     selected = None
+    reused_plan_bytes = None
+    reused_plan = None
+    if args.reuse_selection_plan is not None:
+        reused_plan_bytes = args.reuse_selection_plan.read_bytes()
+        reused_plan = json.loads(reused_plan_bytes)
+        selected = reused_plan.get("selection", {}).get("instance_ids")
+        if (reused_plan.get("status") != "frozen"
+                or reused_plan.get("plan_sha256") != plan_hash(reused_plan)
+                or reused_plan.get("dataset") != {
+                    "path": DATASET, "revision": args.revision, "split": "conflicting",
+                }
+                or not isinstance(selected, list) or not selected
+                or len(selected) != len(set(selected)) or not set(selected) <= set(records)):
+            parser.error("--reuse-selection-plan is not a valid matching frozen plan")
     if args.sample_size is not None:
         if not 1 <= args.sample_size <= len(records):
             parser.error("--sample-size must be between 1 and the split size")
@@ -82,6 +115,7 @@ def main() -> int:
         upstream_git_commit=commit, teams=args.teams, cohorts=args.cohorts,
         seed=args.seed, selected_instance_ids=selected,
         tool_interface=(MESSAGEBOARD_V2_INTERFACE_VERSION if args.messageboard_v2 else None),
+        prompt_policy=(NO_STOP_PROMPT_POLICY if args.no_stop_prompt else None),
     )
     if selected is not None:
         plan["selection"].update({
@@ -95,6 +129,16 @@ def main() -> int:
             } if args.exclude_plan is not None else None),
         })
         plan["plan_sha256"] = plan_hash(plan)
+    if reused_plan is not None:
+        plan["selection"].update({
+            "kind": "reused_frozen_subset",
+            "source_plan": {
+                "path": str(args.reuse_selection_plan),
+                "file_sha256": hashlib.sha256(reused_plan_bytes).hexdigest(),
+                "plan_sha256": reused_plan["plan_sha256"],
+            },
+        })
+        plan["plan_sha256"] = plan_hash(plan)
     args.out.parent.mkdir(parents=True, exist_ok=True)
     with args.out.open("x") as handle:
         json.dump(plan, handle, indent=2)