perf: complete history bootstrap in one streaming phase

tests/test_poll_policy.py

@@ -17,60 +17,13 @@ sys.path.insert(0, str(PACKAGE_DIR))
 from outcome_tracker import OutcomeTracker  # noqa: E402
 from poll_runner import (  # noqa: E402
     _advance_architecture_history_backfill,
-    _bootstrap_architecture_history,
+    _complete_architecture_history_backfill,
     _load_task_compatibility_contexts,
     build_parser,
 )
 
 
 class PollPolicyTests(unittest.TestCase):
-    def test_architecture_bootstrap_falls_back_when_public_logs_are_hidden(self) -> None:
-        class HistoryClient:
-            @staticmethod
-            def list_tasks_page(**_kwargs):  # noqa: ANN003
-                return {
-                    "data": {
-                        "records": [
-                            {
-                                "taskId": "public-failure",
-                                "modelId": "public/model",
-                                "gpuType": "gpu",
-                                "status": "success",
-                                "verifyResult": -1,
-                                "logCosUrl": None,
-                            }
-                        ]
-                    }
-                }
-
-            @staticmethod
-            def list_tasks(**_kwargs):  # noqa: ANN003
-                return [
-                    {
-                        "taskId": "owned-success",
-                        "modelId": "owner/model",
-                        "gpuType": "gpu",
-                        "modelTaskLevelId": 23,
-                        "status": "success",
-                        "verifyResult": 1,
-                        "updateTime": datetime.now(timezone.utc).isoformat(),
-                    }
-                ]
-
-        with tempfile.TemporaryDirectory() as temporary_dir:
-            root = Path(temporary_dir)
-            tracker = OutcomeTracker(root / "outcomes.jsonl")
-            summary = _bootstrap_architecture_history(
-                modelhub_client=HistoryClient(),  # type: ignore[arg-type]
-                outcome_tracker=tracker,
-                ledger_path=root / "ledger.jsonl",
-                now=datetime.now(timezone.utc),
-            )
-
-        self.assertEqual("owned_recent_bounded", summary["source"])
-        self.assertEqual(1, summary["terminalRecords"])
-        self.assertEqual(0, summary["communityUsableFailureDetails"])
-
     def test_architecture_history_backfill_resumes_and_keeps_only_decision_state(self) -> None:
         class PagedHistoryClient:
             calls: list[int] = []
@@ -109,7 +62,7 @@ class PollPolicyTests(unittest.TestCase):
 
         with tempfile.TemporaryDirectory() as temporary_dir, patch.dict(
             "os.environ",
-            {"MODELHUB_ARCHITECTURE_BACKFILL_PAGES_PER_CYCLE": "1"},
+            {"MODELHUB_ARCHITECTURE_BACKFILL_PAGES_PER_BATCH": "1"},
         ):
             root = Path(temporary_dir)
             outcomes = root / "outcomes.jsonl"
@@ -154,6 +107,53 @@ class PollPolicyTests(unittest.TestCase):
             self.assertNotIn("owner/model", persisted_progress)
             self.assertNotIn("logs.invalid", persisted_progress)
 
+    def test_cold_start_backfill_finishes_all_pages_in_one_phase(self) -> None:
+        class ThreePageClient:
+            calls: list[int] = []
+
+            def list_tasks_page(self, **kwargs):  # noqa: ANN003, ANN201
+                current = int(kwargs["current"])
+                self.calls.append(current)
+                return {
+                    "data": {
+                        "records": [
+                            {
+                                "taskId": f"task-{current}",
+                                "modelId": f"owner/model-{current}",
+                                "gpuType": "gpu-a",
+                                "status": "success",
+                                "verifyResult": 1,
+                            }
+                        ],
+                        "pages": 3,
+                    }
+                }
+
+        with tempfile.TemporaryDirectory() as temporary_dir, patch.dict(
+            "os.environ",
+            {"MODELHUB_ARCHITECTURE_BACKFILL_PAGES_PER_BATCH": "1"},
+        ):
+            root = Path(temporary_dir)
+            tracker = OutcomeTracker(
+                root / "outcomes.jsonl",
+                checkpoint_path=root / "checkpoint.json",
+                recent_path=root / "recent.jsonl",
+            )
+            client = ThreePageClient()
+            durable_phases: list[str] = []
+            progress = _complete_architecture_history_backfill(
+                modelhub_client=client,  # type: ignore[arg-type]
+                outcome_tracker=tracker,
+                ledger_path=root / "ledger.jsonl",
+                progress_path=root / "backfill.json",
+                sync_callback=lambda phase: durable_phases.append(phase) or True,
+            )
+
+        self.assertTrue(progress["complete"])
+        self.assertEqual([1, 2, 3], client.calls)
+        self.assertEqual(["history_backfill"], durable_phases)
+        self.assertEqual(3, tracker.get_stats_report()["terminalRecords"])
+
     def test_cleanup_contexts_merge_outcomes_with_older_ledger_entries(self) -> None:
         with tempfile.TemporaryDirectory() as temporary_dir:
             root = Path(temporary_dir)