feat: add webhook retry queue

tests/test_main.py

@@ -7,7 +7,14 @@ from datetime import datetime, timezone
 from pathlib import Path
 
 from cold_display_guard.cases import CaseStore
-from cold_display_guard.main import case_sink_path, deliver_runtime_webhooks, persist_case_updates, restore_runtime_state
+from cold_display_guard.main import (
+    case_sink_path,
+    deliver_runtime_webhooks,
+    persist_case_updates,
+    restore_runtime_state,
+    webhook_retry_sink_path,
+)
+from cold_display_guard.webhooks import load_retry_snapshots
 
 
 UTC = timezone.utc
@@ -22,6 +29,14 @@ class RuntimeRestoreTests(unittest.TestCase):
 
         self.assertEqual(path, (root / "logs" / "cases.jsonl").resolve())
 
+    def test_webhook_retry_sink_path_uses_default_logs_location(self) -> None:
+        with tempfile.TemporaryDirectory() as tmpdir:
+            root = Path(tmpdir)
+
+            path = webhook_retry_sink_path(root, {})
+
+        self.assertEqual(path, (root / "logs" / "webhook_retry.jsonl").resolve())
+
     def test_persist_case_updates_writes_case_snapshots(self) -> None:
         with tempfile.TemporaryDirectory() as tmpdir:
             path = Path(tmpdir) / "cases.jsonl"
@@ -99,6 +114,61 @@ class RuntimeRestoreTests(unittest.TestCase):
         self.assertEqual(deliveries[0][1]["kind"], "batch_event")
         self.assertEqual(deliveries[1][1]["kind"], "case_event")
 
+    def test_deliver_runtime_webhooks_enqueues_failure_and_drains_due_retry(self) -> None:
+        attempts = {"count": 0}
+
+        def flaky_post(url: str, payload: dict[str, object], timeout: tuple[float, float]) -> tuple[int, str]:
+            attempts["count"] += 1
+            if attempts["count"] == 1:
+                return 503, "down"
+            return 200, "ok"
+
+        with tempfile.TemporaryDirectory() as tmpdir:
+            audit_path = Path(tmpdir) / "webhook_delivery.jsonl"
+            retry_path = Path(tmpdir) / "webhook_retry.jsonl"
+            config = {
+                "webhooks": {
+                    "enabled": True,
+                    "event_url": "https://example.com/events",
+                    "retry_max_attempts": 3,
+                    "retry_backoff_seconds": 30,
+                }
+            }
+            deliver_runtime_webhooks(
+                [
+                    {
+                        "event": "time_alarm",
+                        "ts": datetime(2026, 6, 9, 9, 0, tzinfo=UTC).isoformat(),
+                        "batch_id": "batch_000001",
+                        "camera_id": "cam_01",
+                        "zone_id": "1",
+                        "zone_label": "区域 1",
+                        "severity": "alarm",
+                        "state": "alerted",
+                    }
+                ],
+                [],
+                config,
+                audit_path,
+                retry_path=retry_path,
+                http_post=flaky_post,
+                now=datetime(2026, 6, 9, 9, 0, tzinfo=UTC),
+            )
+            deliver_runtime_webhooks(
+                [],
+                [],
+                config,
+                audit_path,
+                retry_path=retry_path,
+                http_post=flaky_post,
+                now=datetime(2026, 6, 9, 9, 1, tzinfo=UTC),
+            )
+            retries = load_retry_snapshots(retry_path)
+
+        self.assertEqual(attempts["count"], 2)
+        self.assertEqual(retries[-1]["status"], "delivered")
+        self.assertEqual(retries[-1]["attempt_count"], 2)
+
     def test_restore_runtime_state_uses_stable_occupancy_when_raw_metrics_flicker(self) -> None:
         with tempfile.TemporaryDirectory() as tmpdir:
             diagnostics_path = Path(tmpdir) / "runtime_diagnostics.jsonl"