feat(caretaker): update Firestore schema with error, and pr_number fields (#28467)

tools/caretaker-agent/cloudrun/ingestion-service/db/issuesStore.test.ts

@@ -55,11 +55,13 @@ describe('IssuesStore', () => {
       expect.anything(),
       expect.objectContaining({
         status: 'UNTRIAGED',
+        error: null,
         github_metadata: expect.objectContaining({
           owner: 'google',
           repo: 'gemini-cli',
           issue_number: 123,
           title: 'Test Title',
+          pr_number: null,
         }),
       }),
     );

tools/caretaker-agent/cloudrun/ingestion-service/db/issuesStore.ts

@@ -18,10 +18,11 @@ export type IssueStatus =
   | 'NEEDS_INFO'
   | 'TRIAGED'
   | 'NEEDS_HUMAN'
-  | 'LOW_QUALITY';
+  | 'AUTO_CLOSE';
 
 export interface IssueDocument {
   status: IssueStatus;
+  error?: string | null;
   triage_attempts: number;
   // The ingestion layer does not enforce the schema of workable_spec
   workable_spec: Record<string, unknown>;
@@ -36,6 +37,7 @@ export interface IssueDocument {
     repo: string;
     issue_number: number;
     title: string;
+    pr_number?: number | null;
   };
 }
 
@@ -74,6 +76,7 @@ export class IssuesStore {
         if (!snapshot.exists) {
           const newIssue: IssueDocument = {
             status: 'UNTRIAGED',
+            error: null,
             triage_attempts: 0,
             workable_spec: {},
             lock: {
@@ -87,6 +90,7 @@ export class IssuesStore {
               repo,
               issue_number: issueNumber,
               title,
+              pr_number: null,
             },
           };
 

tools/caretaker-agent/cloudrun/triage-worker/db/issues_store.py

@@ -72,7 +72,8 @@ class IssuesStore:
 
         if attempts >= 2:
             transaction.update(doc_ref, {
-                "status": "NEEDS_HUMAN", 
+                "status": "NEEDS_HUMAN",
+                "error": "Max triage attempts (2) exceeded due to prior worker crash or timeout",
                 "updated_at": firestore.SERVER_TIMESTAMP
             })
             return ClaimAction.NEEDS_HUMAN
@@ -152,6 +153,7 @@ class IssuesStore:
         success: bool,
         workable_spec: dict = None,
         status: str = None,
+        error: str = None,
     ) -> ReleaseAction:
         """Internal transactional handler to release processing lock."""
         snapshot = doc_ref.get(transaction=transaction)
@@ -173,6 +175,7 @@ class IssuesStore:
         if success:
             updates["status"] = status
             updates["workable_spec"] = workable_spec or {}
+            updates["error"] = None
             transaction.update(doc_ref, updates)
             return ReleaseAction.COMPLETE
         
@@ -184,6 +187,7 @@ class IssuesStore:
             return ReleaseAction.RETRY
         
         updates["status"] = "NEEDS_HUMAN"
+        updates["error"] = error or "Max triage attempts (2) exceeded."
         transaction.update(doc_ref, updates)
         return ReleaseAction.COMPLETE
 
@@ -196,6 +200,7 @@ class IssuesStore:
         success: bool,
         workable_spec: dict = None,
         status: str = None,
+        error: str = None,
     ) -> ReleaseAction:
         """
         Releases the processing lock for an issue and updates its final status.
@@ -211,6 +216,8 @@ class IssuesStore:
               is TRIAGED.
             status: Target issue status (TRIAGED, NEEDS_INFO, AUTO_CLOSE,
               or NEEDS_HUMAN).
+            error: Error string or failure details to store when status
+              transitions to NEEDS_HUMAN.
 
         Returns:
             ReleaseAction indicating COMPLETE or RETRY.
@@ -218,5 +225,5 @@ class IssuesStore:
         doc_ref = self._get_issue_ref(owner, repo, issue_number)
         transaction = self.db.transaction()
         return self._release_lock_tx(
-            transaction, doc_ref, lock_holder, success, workable_spec, status
+            transaction, doc_ref, lock_holder, success, workable_spec, status, error
         )

tools/caretaker-agent/cloudrun/triage-worker/main.py

@@ -88,8 +88,9 @@ def main() -> None:
         success, raw_output = process_issue_triage(payload)
     except Exception as e:
         print(f"[WORKER] Triage process failed with exception: {e}")
-        success, raw_output = False, ""
+        success, raw_output = False, f"Exception during triage execution: {e}"
     
+    error_message = None
     if success:
         try:
             triage_result = json.loads(raw_output)
@@ -158,13 +159,15 @@ def main() -> None:
                 
         except Exception as e:
             print(f"[WORKER] Validation failed: {e}")
-            success = False
+            success, error_message = False, f"Validation Error: {e}"
+    else:
+        error_message = raw_output
     
     # If an exception happens in json.loads or validate_triage_result 
     # If LLM inference itself fails inside process_issue_triage
     if not success:
         release_action = store.release_lock(
-            owner, repo, issue_number, lock_holder, success=False
+            owner, repo, issue_number, lock_holder, success=False, error=error_message
         )
         sys.exit(1 if release_action == ReleaseAction.RETRY else 0)
 

tools/caretaker-agent/cloudrun/triage-worker/tests/test_integration_main.py

@@ -275,7 +275,12 @@ class TestIntegrationMain(unittest.TestCase):
             "owner", "repo", 42, "test-workflow-exec-101"
         )
         self.mock_store.release_lock.assert_called_once_with(
-            "owner", "repo", 42, "test-workflow-exec-101", success=False
+            "owner",
+            "repo",
+            42,
+            "test-workflow-exec-101",
+            success=False,
+            error="Validation Error: Invalid or missing 'effort_estimate': HUGE",
         )
         self.assertEqual(self.stored_data["status"], "UNTRIAGED")
         self.assertIsNone(self.stored_data["lock"]["holder"])

tools/caretaker-agent/cloudrun/triage-worker/tests/test_issues_store.py

@@ -49,6 +49,10 @@ class TestIssuesStore(unittest.TestCase):
         self.transaction.update.assert_called_once()
         args, _ = self.transaction.update.call_args
         self.assertEqual(args[1]["status"], "NEEDS_HUMAN")
+        self.assertEqual(
+            args[1]["error"],
+            "Max triage attempts (2) exceeded due to prior worker crash or timeout",
+        )
 
     def test_acquire_lock_active_lock_by_other_holder(self):
         """acquire lock when active lock held by another worker should skip"""
@@ -131,6 +135,7 @@ class TestIssuesStore(unittest.TestCase):
         updates = args[1]
         self.assertEqual(updates["status"], "TRIAGED")
         self.assertEqual(updates["workable_spec"], workable_spec)
+        self.assertIsNone(updates["error"])
         self.assertIsNone(updates["lock.holder"])
         self.assertIsNone(updates["lock.expires_at"])
 
@@ -158,13 +163,16 @@ class TestIssuesStore(unittest.TestCase):
             "triage_attempts": 2,
         }
         
-        action = self.store.release_lock("owner", "repo", 123, self.lock_holder, success=False)
+        action = self.store.release_lock(
+            "owner", "repo", 123, self.lock_holder, success=False, error="LLM failed"
+        )
         
         self.assertEqual(action, ReleaseAction.COMPLETE)
         self.transaction.update.assert_called_once()
         args, _ = self.transaction.update.call_args
         updates = args[1]
         self.assertEqual(updates["status"], "NEEDS_HUMAN")
+        self.assertEqual(updates["error"], "LLM failed")
 
 if __name__ == "__main__":
     unittest.main()

tools/caretaker-agent/cloudrun/triage-worker/tests/test_main.py

@@ -175,7 +175,7 @@ class TestMainExecutionLoop(unittest.TestCase):
 
         self.assertEqual(ctx.exception.code, 1)
         self.mock_store.release_lock.assert_called_once_with(
-            "owner", "repo", 42, "exec-123", success=False
+            "owner", "repo", 42, "exec-123", success=False, error="LLM failed"
         )