feat(recovery): normalize harbor queue receipt fields

apps/api/src/services/harbor_registry_controlled_recovery_receipt.py

@@ -212,6 +212,12 @@ def validate_harbor_registry_controlled_recovery_receipt(
             "gitea_queue_cd_jobs_run_id_mismatch": gitea_queue[
                 "cd_run_jobs_run_id_mismatch"
             ],
+            "gitea_queue_normalized_classifier_field_count": gitea_queue[
+                "normalized_classifier_field_count"
+            ],
+            "gitea_queue_normalized_classifier_field_ids": gitea_queue[
+                "normalized_classifier_field_ids"
+            ],
             "deploy_marker_readback_seen": deploy_marker["receipt_seen"],
             "deploy_marker_verified": deploy_marker["deploy_marker_verified"],
             "deploy_marker_blocker_count": deploy_marker["blocker_count"],
@@ -591,6 +597,9 @@ def _gitea_queue_readback(value: Any) -> dict[str, Any]:
             "harbor_110_repair_jobs_unexpected_names": [],
             "harbor_110_repair_jobs_labels": [],
             "harbor_110_repair_jobs_runner_names": [],
+            "normalized_classifier_fields": [],
+            "normalized_classifier_field_count": 0,
+            "normalized_classifier_field_ids": [],
             "operation_boundary_violation": False,
             "blockers": [],
             "blocker_count": 0,
@@ -653,6 +662,16 @@ def _gitea_queue_readback(value: Any) -> dict[str, Any]:
         rollups.get("cd_run_jobs_run_id_mismatch") is True
         or readback.get("cd_run_jobs_run_id_mismatch") is True
     )
+    cd_jobs_payload_classifier = str(
+        rollups.get("cd_run_jobs_payload_classifier")
+        or readback.get("cd_run_jobs_payload_classifier")
+        or ""
+    )
+    harbor_jobs_payload_classifier = str(
+        rollups.get("harbor_110_repair_jobs_payload_classifier")
+        or readback.get("harbor_110_repair_jobs_payload_classifier")
+        or ""
+    )
     boundary_violation = any(
         operation_boundaries.get(flag) is True
         for flag in (
@@ -675,6 +694,12 @@ def _gitea_queue_readback(value: Any) -> dict[str, Any]:
         blocked=blocked,
         boundary_violation=boundary_violation,
     )
+    normalized_classifier_fields = _gitea_queue_normalized_classifier_fields(
+        cd_jobs_payload_classifier=cd_jobs_payload_classifier,
+        harbor_jobs_payload_classifier=harbor_jobs_payload_classifier,
+        no_matching_label=no_matching_label,
+        blockers=blockers,
+    )
     return {
         "receipt_seen": True,
         "schema_version": str(value.get("schema_version") or ""),
@@ -692,11 +717,7 @@ def _gitea_queue_readback(value: Any) -> dict[str, Any]:
         ),
         "current_cd_harbor_retrying_unavailable": current_cd_harbor_retrying,
         "cd_run_jobs_stale_or_mismatched": cd_jobs_stale,
-        "cd_run_jobs_payload_classifier": str(
-            rollups.get("cd_run_jobs_payload_classifier")
-            or readback.get("cd_run_jobs_payload_classifier")
-            or ""
-        ),
+        "cd_run_jobs_payload_classifier": cd_jobs_payload_classifier,
         "cd_run_jobs_head_sha_mismatch": cd_jobs_head_sha_mismatch,
         "cd_run_jobs_run_id_mismatch": cd_jobs_run_id_mismatch,
         "cd_run_jobs_expected_run_id": str(
@@ -719,11 +740,7 @@ def _gitea_queue_readback(value: Any) -> dict[str, Any]:
         "harbor_110_repair_blocked": blocked,
         "harbor_110_repair_jobs_stale_or_mismatched": jobs_stale,
         "harbor_110_repair_jobs_cross_workflow_mismatch": jobs_cross_workflow,
-        "harbor_110_repair_jobs_payload_classifier": str(
-            rollups.get("harbor_110_repair_jobs_payload_classifier")
-            or readback.get("harbor_110_repair_jobs_payload_classifier")
-            or ""
-        ),
+        "harbor_110_repair_jobs_payload_classifier": harbor_jobs_payload_classifier,
         "harbor_110_repair_jobs_expected_names": _strings(
             readback.get("harbor_110_repair_jobs_expected_names")
         ),
@@ -736,6 +753,11 @@ def _gitea_queue_readback(value: Any) -> dict[str, Any]:
         "harbor_110_repair_jobs_runner_names": _strings(
             readback.get("harbor_110_repair_jobs_runner_names")
         ),
+        "normalized_classifier_fields": normalized_classifier_fields,
+        "normalized_classifier_field_count": len(normalized_classifier_fields),
+        "normalized_classifier_field_ids": [
+            item["field_id"] for item in normalized_classifier_fields
+        ],
         "operation_boundary_violation": boundary_violation,
         "blockers": blockers,
         "blocker_count": len(blockers),
@@ -745,6 +767,48 @@ def _gitea_queue_readback(value: Any) -> dict[str, Any]:
     }
 
 
+def _gitea_queue_normalized_classifier_fields(
+    *,
+    cd_jobs_payload_classifier: str,
+    harbor_jobs_payload_classifier: str,
+    no_matching_label: str,
+    blockers: list[str],
+) -> list[dict[str, Any]]:
+    return [
+        {
+            "field_id": "cd_run_jobs_payload_classifier",
+            "value": cd_jobs_payload_classifier,
+            "blockers": [
+                item for item in blockers if item.startswith("gitea_queue_cd_jobs_")
+            ],
+            "metadata_only": True,
+            "raw_output_returned": False,
+        },
+        {
+            "field_id": "harbor_110_repair_jobs_payload_classifier",
+            "value": harbor_jobs_payload_classifier,
+            "blockers": [
+                item
+                for item in blockers
+                if item.startswith("gitea_queue_harbor_110_repair_jobs_")
+            ],
+            "metadata_only": True,
+            "raw_output_returned": False,
+        },
+        {
+            "field_id": "latest_visible_harbor_110_repair_no_matching_runner_label",
+            "value": no_matching_label,
+            "blockers": [
+                item
+                for item in blockers
+                if item == "gitea_queue_harbor_110_repair_no_matching_runner"
+            ],
+            "metadata_only": True,
+            "raw_output_returned": False,
+        },
+    ]
+
+
 def _gitea_queue_blockers(
     *,
     no_matching_runner: bool,

apps/api/tests/test_harbor_registry_controlled_recovery_receipt.py

@@ -254,6 +254,25 @@ def test_harbor_recovery_receipt_surfaces_gitea_queue_blockers() -> None:
     assert queue["harbor_110_repair_no_matching_runner_label"] == "awoooi-host"
     assert queue["harbor_110_repair_jobs_stale_or_mismatched"] is True
     assert queue["harbor_110_repair_jobs_unexpected_names"] == ["ai-code-review"]
+    normalized = {
+        item["field_id"]: item for item in queue["normalized_classifier_fields"]
+    }
+    assert queue["normalized_classifier_field_count"] == 3
+    assert queue["normalized_classifier_field_ids"] == [
+        "cd_run_jobs_payload_classifier",
+        "harbor_110_repair_jobs_payload_classifier",
+        "latest_visible_harbor_110_repair_no_matching_runner_label",
+    ]
+    assert normalized[
+        "latest_visible_harbor_110_repair_no_matching_runner_label"
+    ]["value"] == "awoooi-host"
+    assert normalized[
+        "latest_visible_harbor_110_repair_no_matching_runner_label"
+    ]["blockers"] == ["gitea_queue_harbor_110_repair_no_matching_runner"]
+    assert all(
+        item["metadata_only"] is True and item["raw_output_returned"] is False
+        for item in normalized.values()
+    )
     assert queue["raw_output_returned"] is False
     assert queue["top_visible_runs_returned"] is False
     assert payload["rollups"]["gitea_queue_blocker_count"] == 2
@@ -304,6 +323,19 @@ def test_harbor_recovery_receipt_surfaces_cross_workflow_queue_payload() -> None
     assert payload["rollups"]["gitea_queue_harbor_110_jobs_payload_classifier"] == (
         "cd_workflow_jobs_returned_for_harbor_110_repair_run"
     )
+    normalized = {
+        item["field_id"]: item
+        for item in payload["readback"]["gitea_actions_queue"][
+            "normalized_classifier_fields"
+        ]
+    }
+    assert normalized["harbor_110_repair_jobs_payload_classifier"]["value"] == (
+        "cd_workflow_jobs_returned_for_harbor_110_repair_run"
+    )
+    assert normalized["harbor_110_repair_jobs_payload_classifier"]["blockers"] == [
+        "gitea_queue_harbor_110_repair_jobs_cross_workflow_mismatch",
+        "gitea_queue_harbor_110_repair_jobs_stale_or_mismatched",
+    ]
 
 
 def test_harbor_recovery_receipt_surfaces_cd_jobs_payload_classifier() -> None:
@@ -338,6 +370,22 @@ def test_harbor_recovery_receipt_surfaces_cd_jobs_payload_classifier() -> None:
     assert payload["rollups"]["gitea_queue_cd_jobs_payload_classifier"] == (
         "cd_jobs_api_head_sha_mismatch_for_visible_cd_run"
     )
+    assert payload["rollups"]["gitea_queue_normalized_classifier_field_count"] == 3
+    assert payload["rollups"]["gitea_queue_normalized_classifier_field_ids"] == [
+        "cd_run_jobs_payload_classifier",
+        "harbor_110_repair_jobs_payload_classifier",
+        "latest_visible_harbor_110_repair_no_matching_runner_label",
+    ]
+    normalized = {
+        item["field_id"]: item for item in queue["normalized_classifier_fields"]
+    }
+    assert normalized["cd_run_jobs_payload_classifier"]["value"] == (
+        "cd_jobs_api_head_sha_mismatch_for_visible_cd_run"
+    )
+    assert normalized["cd_run_jobs_payload_classifier"]["blockers"] == [
+        "gitea_queue_cd_jobs_head_sha_mismatch",
+        "gitea_queue_cd_jobs_stale_or_mismatched",
+    ]
 
 
 def test_harbor_recovery_receipt_waits_for_deploy_marker_readback() -> None: