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

tests/test_takeover_accuracy.py

@@ -0,0 +1,114 @@
+import copy
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+from unittest.mock import patch
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "modelhub_submmit_api"))
+from models import ModelInspection
+from candidate_preflight import CandidatePreflightAdvisor
+from profile_admission import filter_profile_batch, profile_key
+from outcome_tracker import OutcomeTracker
+from common import write_json
+from state_sync import StateGitSync
+from dulwich import porcelain
+
+
+class TakeoverAccuracyTests(unittest.TestCase):
+    def tracker(self, root):
+        return OutcomeTracker(root / "outcomes.jsonl", checkpoint_path=root / "checkpoint.json",
+                              recent_path=root / "recent.jsonl")
+
+    def test_mlx_and_unknown_quantization_not_plain_weights(self):
+        for config, expected in [({"quantization": {"bits": 4, "group_size": 64}}, "mlx"),
+                                 ({"quantization_config": {"bits": 4}}, "unknown")]:
+            inspection = ModelInspection(repo_id="owner/model", model_config=config)
+            self.assertEqual(expected, inspection.quantization_method)
+            advisor = CandidatePreflightAdvisor()
+            result = advisor.assess(inspection=inspection, task_type="text-generation",
+                                    target_gpu="MetaX_c-500", framework="vllm", config_params="x")
+            self.assertFalse(result.allowed)
+            self.assertEqual("preflight_unverified_weight_format", result.reason)
+        self.assertEqual("mlx", ModelInspection(repo_id="m", model_card_metadata={
+            "library_name": "mlx"}).quantization_method)
+        self.assertIsNone(ModelInspection(repo_id="m", model_config={}).quantization_method)
+
+    def test_encoding_fingerprints_distinguish_compressed_formats(self):
+        a = ModelInspection(repo_id="a", model_config={"quantization_config": {
+            "quant_method": "compressed-tensors", "format": "float-quantized"}})
+        b = ModelInspection(repo_id="b", model_config={"quantization_config": {
+            "quant_method": "compressed-tensors", "format": "pack-quantized"}})
+        self.assertNotEqual(a.quantization_signature, b.quantization_signature)
+
+    def candidate(self, model="a"):
+        return {"repoId": model, "targetGpu": "gpu", "framework": "vllm", "taskType": "text-generation",
+                "preflightMetadata": {"modelType": "family", "quantizationSignature": "awq:abc"}}
+
+    def test_batch_guard_counts_pending_and_same_batch_and_is_retryable(self):
+        candidate = self.candidate()
+        pending = {**candidate, "outcome": "pending"}
+        selected, deferred = filter_profile_batch([self.candidate(str(i)) for i in range(4)], [pending], {})
+        self.assertEqual(1, len(selected))
+        self.assertEqual(3, len(deferred))
+        selected, deferred = filter_profile_batch(deferred, [], {})
+        self.assertEqual(2, len(selected))
+
+    def test_proven_encoding_releases_cap_but_failures_do_not(self):
+        candidates = [self.candidate(str(i)) for i in range(4)]
+        key = "|".join(profile_key(candidates[0]))
+        stats = {"encodingCombinationStats": {key: {"successCount": 3, "failureCount": 0}}}
+        self.assertEqual(4, len(filter_profile_batch(candidates, [], stats)[0]))
+        stats["encodingCombinationStats"][key]["failureCount"] = 10
+        self.assertEqual(2, len(filter_profile_batch(candidates, [], stats)[0]))
+
+    def test_takeover_is_idempotent_and_does_not_invent_version(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            tracker = self.tracker(Path(tmp))
+            tasks = [{"taskId": "old", "modelId": "owner/model", "gpuType": "gpu", "status": "waiting"}]
+            self.assertEqual(1, tracker.adopt_active_tasks(tasks))
+            self.assertEqual(0, tracker.adopt_active_tasks(tasks))
+            self.assertEqual(1, tracker.pending_route_count_for_model("owner/model"))
+            self.assertNotIn("agentVersion", tracker.pending_records()[0])
+
+    def test_encoding_and_version_statistics_survive_compaction(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            root = Path(tmp)
+            tracker = self.tracker(root)
+            for i in range(3):
+                tracker.record_submission("m"+str(i), "gpu", "vllm", "text-generation", str(i),
+                    "2026-10-26T00:00:00+00:00", self.candidate()["preflightMetadata"])
+                tracker._update_record_from_task(tracker._by_task_id[str(i)], {"status": "success", "verifyResult": 1})
+            before = tracker.get_stats_report()
+            tracker._compact_if_needed(force=True)
+            restored = self.tracker(root).get_stats_report()
+            self.assertEqual(before["encodingCombinationStats"], restored["encodingCombinationStats"])
+            self.assertEqual(before["agentSummaries"], restored["agentSummaries"])
+
+    def test_state_rotation_preserves_remote_and_bounds_local_objects(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            root = Path(tmp)
+            remote = root / "remote.git"
+            with porcelain.init(remote, bare=True):
+                pass
+            project = root / "project"
+            project.mkdir()
+            manager = StateGitSync(project_root=project, credentials={"username": "u", "email": "u@x", "password": "p"},
+                                   remote=str(remote), history_depth=2, log_fn=lambda _: None)
+            try:
+                self.assertTrue(manager.restore())
+                for i in range(5):
+                    write_json(project / ".modelhub_state/account_capacity.json", {"generation": i})
+                    self.assertTrue(manager.sync("result"), manager.last_error)
+                self.assertTrue(manager.healthy)
+                self.assertEqual(manager._expected_remote_oid, manager._remote_oid())
+                with patch.object(manager, "_copy_snapshot", side_effect=AssertionError("idle writes should throttle")):
+                    self.assertTrue(manager.sync("cycle_no_slots"))
+                write_json(project / ".modelhub_state/account_capacity.json", {"generation": 99})
+                self.assertTrue(manager.sync("intent"))
+            finally:
+                manager.close()
+
+
+if __name__ == "__main__":
+    unittest.main()