Extend oracle gap P06 bracket

scripts/oracle_gap/run_frontier.py

@@ -20,6 +20,7 @@ from analyze import CONFIGS, PHASES, atomic_json, score_trial, summarize_trials
 
 
 SCHEMA = 1
+AMENDMENT = "A-OG-1"
 REMOTE_ROOT = Path("/home/admin/cpfs/wjh/oracle-gap-20260713")
 RUN_ROOT = REMOTE_ROOT / "runs"
 STATE = RUN_ROOT / "controller-state.json"
@@ -56,7 +57,10 @@ BASE_RATES = {
     "P01": (32.0, 26.0, 36.0, 28.0, 34.0, 30.0),
     "P06": (1.7, 1.4, 2.0, 1.5, 1.9, 1.6, 1.8),
 }
-UP_EXTENSIONS = {"P01": (38.0, 40.0, 42.0), "P06": (2.1, 2.2, 2.3)}
+UP_EXTENSIONS = {
+    "P01": (38.0, 40.0, 42.0),
+    "P06": (2.1, 2.2, 2.3, 2.4, 2.5, 2.6, 2.8, 3.0),
+}
 DOWN_EXTENSIONS = {"P01": (24.0, 22.0, 20.0), "P06": (1.3, 1.2, 1.1)}
 TIMELINE = {
     "P01": {"warmup": 60, "clean": 60, "drain": 120},
@@ -207,6 +211,9 @@ def fingerprint() -> dict[str, Any]:
     return {
         "controller_sha256": sha256_file(Path(__file__).resolve()),
         "analyzer_sha256": sha256_file(Path(__file__).with_name("analyze.py")),
+        "protocol_sha256": sha256_file(
+            REPO / "docs/opprof/oracle-gap-protocol.md"
+        ),
         "p5_client_sha256": sha256_file(P5_CLIENT),
         "p3_client_sha256": sha256_file(P3_CLIENT_DIR / "opprof_phase3_client.py"),
         "repo_commit": run_text(["git", "-C", str(REPO), "rev-parse", "HEAD"]).strip(),
@@ -220,9 +227,27 @@ def fingerprint() -> dict[str, Any]:
         "driver": run_text(["nvidia-smi", "--query-gpu=driver_version", "--format=csv,noheader"]).splitlines()[0],
         "config_details": CONFIG_DETAILS,
         "base_rates": {key: list(value) for key, value in BASE_RATES.items()},
+        "up_extensions": {
+            key: list(value) for key, value in UP_EXTENSIONS.items()
+        },
     }
 
 
+def resume_compatible(old: dict[str, Any], current: dict[str, Any]) -> bool:
+    immutable = (
+        "p5_client_sha256",
+        "p3_client_sha256",
+        "vllm_commit",
+        "model",
+        "manifests",
+        "runtime",
+        "driver",
+        "config_details",
+        "base_rates",
+    )
+    return all(old.get(key) == current.get(key) for key in immutable)
+
+
 def ensure_provenance(current: dict[str, Any]) -> None:
     destination = RUN_ROOT / "provenance"
     destination.mkdir(parents=True, exist_ok=True)
@@ -235,10 +260,18 @@ def ensure_provenance(current: dict[str, Any]) -> None:
     ):
         target = destination / source.name
         if target.exists() and sha256_file(target) != sha256_file(source):
-            raise RuntimeError(f"provenance file changed: {target}")
+            digest = sha256_file(source)
+            target = destination / f"{source.stem}.{digest[:12]}{source.suffix}"
+        if target.exists() and sha256_file(target) != sha256_file(source):
+            raise RuntimeError(f"content-addressed provenance mismatch: {target}")
         if not target.exists():
             shutil.copy2(source, target)
-    atomic_json(destination / "fingerprint.json", current)
+    fingerprint_path = (
+        destination / f"fingerprint.{current['repo_commit'][:8]}.json"
+    )
+    atomic_json(fingerprint_path, current)
+    if not (destination / "fingerprint.json").exists():
+        atomic_json(destination / "fingerprint.json", current)
     atomic_json(destination / "host-before.json", gpu_snapshot())
     (destination / "nvidia-smi-q.txt").write_text(run_text(["nvidia-smi", "-q"]))
 
@@ -607,7 +640,28 @@ def execute(resume: bool) -> None:
     assert_idle()
     current = fingerprint()
     if state["fingerprint"] and state["fingerprint"] != current:
-        raise RuntimeError("resume fingerprint changed")
+        if not (
+            resume
+            and state.get("status") == "failed"
+            and resume_compatible(state["fingerprint"], current)
+        ):
+            raise RuntimeError("resume fingerprint changed incompatibly")
+        state.setdefault("amendments", []).append(
+            {
+                "id": AMENDMENT,
+                "accepted_at": time.time(),
+                "reason": (
+                    "C00/P06 feasible through the original 2.3-rps "
+                    "upper extension"
+                ),
+                "completed_trials_before": len(
+                    state.get("completed_trials", [])
+                ),
+                "gpu_hours_before": state.get("gpu_hours"),
+                "old_fingerprint": state["fingerprint"],
+                "new_fingerprint": current,
+            }
+        )
     state["fingerprint"] = current
     state["status"] = "running"
     save_state(state)