fix: bound unproven profile submissions and support single-worker takeover

modelhub_submmit_api/main.py

@@ -47,6 +47,7 @@ from official_capabilities import (
     OfficialCapabilityUnavailable,
 )
 from outcome_tracker import DEFAULT_OUTCOMES_PATH, OutcomeTracker
+from profile_admission import filter_profile_batch
 from routing_engine import DEFAULT_ROUTING_STATE_PATH, SuccessFirstRoutingEngine
 from submission_claims import DEFAULT_CLAIMS_PATH, SubmissionClaimStore, candidate_key, diversify_candidates
 from submission_exclusions import DEFAULT_SUBMISSION_EXCLUSIONS_PATH, SubmissionExclusionStore
@@ -737,6 +738,8 @@ def process_model_for_candidates(
         inspection = hf_discovery.inspect_model(model)
     except Exception as exc:
         return [], skipped, [{"repoId": model.repo_id, "reason": str(exc)}]
+    if "library:mlx" in {str(tag).lower() for tag in model.tags}:
+        inspection.model_card_metadata = {**inspection.model_card_metadata, "library_name": "mlx"}
 
     def evaluate_pending_routes(pending_routes: list[tuple[str, list[str], set[str]]]) -> int:
         before_count = len(candidates)
@@ -1703,6 +1706,7 @@ def run_submission(
             owner_id=instance_id,
         )
         attempted_keys: set[str] = set()
+        profile_stats = outcome_tracker.get_stats_report()
         attempt_multiplier = max(1, int(getattr(args, "scan_multiplier", 4) or 1))
         max_submit_attempts = min(
             len(diversified_candidates),
@@ -1721,6 +1725,13 @@ def run_submission(
                 and not submission_exclusion_store.is_blocked(candidate["repoId"], candidate["targetGpu"])
             ]
             remaining_candidates = one_candidate_per_model(remaining_candidates)
+            remaining_candidates, profile_deferred = filter_profile_batch(
+                remaining_candidates, outcome_tracker.pending_records(), profile_stats,
+            )
+            for candidate in profile_deferred:
+                attempted_keys.add(candidate_key(candidate))
+                skipped.append({"repoId": candidate["repoId"], "targetGpu": candidate["targetGpu"],
+                                "reason": "profile_feedback_deferred", "deferred": True})
             desired_count = min(
                 target_submit_count - len(submitted),
                 max_submit_attempts - len(attempted_candidates),