fix(celery): Limiting connector_hierarchy_fetching jobs (#9381)

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.github/workflows/deployment.yml

@@ -455,7 +455,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ needs.determine-builds.outputs.is-test-run == 'true' && env.RUNS_ON_ECR_CACHE || env.REGISTRY_IMAGE }}
           flavor: |
@@ -529,7 +529,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ needs.determine-builds.outputs.is-test-run == 'true' && env.RUNS_ON_ECR_CACHE || env.REGISTRY_IMAGE }}
           flavor: |
@@ -607,7 +607,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ needs.determine-builds.outputs.is-test-run == 'true' && env.RUNS_ON_ECR_CACHE || env.REGISTRY_IMAGE }}
           flavor: |
@@ -668,7 +668,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ needs.determine-builds.outputs.is-test-run == 'true' && env.RUNS_ON_ECR_CACHE || env.REGISTRY_IMAGE }}
           flavor: |
@@ -750,7 +750,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ needs.determine-builds.outputs.is-test-run == 'true' && env.RUNS_ON_ECR_CACHE || env.REGISTRY_IMAGE }}
           flavor: |
@@ -836,7 +836,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ needs.determine-builds.outputs.is-test-run == 'true' && env.RUNS_ON_ECR_CACHE || env.REGISTRY_IMAGE }}
           flavor: |
@@ -894,7 +894,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ needs.determine-builds.outputs.is-test-run == 'true' && env.RUNS_ON_ECR_CACHE || env.REGISTRY_IMAGE }}
           flavor: |
@@ -967,7 +967,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ needs.determine-builds.outputs.is-test-run == 'true' && env.RUNS_ON_ECR_CACHE || env.REGISTRY_IMAGE }}
           flavor: |
@@ -1044,7 +1044,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ needs.determine-builds.outputs.is-test-run == 'true' && env.RUNS_ON_ECR_CACHE || env.REGISTRY_IMAGE }}
           flavor: |
@@ -1105,7 +1105,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ env.REGISTRY_IMAGE }}
           flavor: |
@@ -1178,7 +1178,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ env.REGISTRY_IMAGE }}
           flavor: |
@@ -1256,7 +1256,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ env.REGISTRY_IMAGE }}
           flavor: |
@@ -1317,7 +1317,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ needs.determine-builds.outputs.is-test-run == 'true' && env.RUNS_ON_ECR_CACHE || env.REGISTRY_IMAGE }}
           flavor: |
@@ -1397,7 +1397,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ needs.determine-builds.outputs.is-test-run == 'true' && env.RUNS_ON_ECR_CACHE || env.REGISTRY_IMAGE }}
           flavor: |
@@ -1480,7 +1480,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ needs.determine-builds.outputs.is-test-run == 'true' && env.RUNS_ON_ECR_CACHE || env.REGISTRY_IMAGE }}
           flavor: |

.github/workflows/pr-desktop-build.yml

@@ -105,7 +105,7 @@ jobs:
 
       - name: Upload build artifacts
         if: always()
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
         with:
           name: desktop-build-${{ matrix.platform }}-${{ github.run_id }}
           path: |

.github/workflows/pr-external-dependency-unit-tests.yml

@@ -174,7 +174,7 @@ jobs:
 
       - name: Upload Docker logs
         if: failure()
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
         with:
           name: docker-logs-${{ matrix.test-dir }}
           path: docker-logs/

.github/workflows/pr-golang-tests.yml

@@ -25,7 +25,7 @@ jobs:
     outputs:
       modules: ${{ steps.set-modules.outputs.modules }}
     steps:
-      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd
         with:
           persist-credentials: false
       - id: set-modules
@@ -39,7 +39,7 @@ jobs:
       matrix:
         modules: ${{ fromJSON(needs.detect-modules.outputs.modules) }}
     steps:
-      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # ratchet:actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # ratchet:actions/checkout@v6
         with:
           persist-credentials: false
       - uses: actions/setup-go@4dc6199c7b1a012772edbd06daecab0f50c9053c # zizmor: ignore[cache-poisoning]

.github/workflows/pr-integration-tests.yml

@@ -466,7 +466,7 @@ jobs:
 
       - name: Upload logs
         if: always()
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
         with:
           name: docker-all-logs-${{ matrix.edition }}-${{ matrix.test-dir.name }}
           path: ${{ github.workspace }}/docker-compose.log
@@ -587,7 +587,7 @@ jobs:
 
       - name: Upload logs (onyx-lite)
         if: always()
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
         with:
           name: docker-all-logs-onyx-lite
           path: ${{ github.workspace }}/docker-compose-onyx-lite.log
@@ -725,7 +725,7 @@ jobs:
 
       - name: Upload logs (multi-tenant)
         if: always()
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
         with:
           name: docker-all-logs-multitenant
           path: ${{ github.workspace }}/docker-compose-multitenant.log

.github/workflows/pr-jest-tests.yml

@@ -44,7 +44,7 @@ jobs:
 
       - name: Upload coverage reports
         if: always()
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
         with:
           name: jest-coverage-${{ github.run_id }}
           path: ./web/coverage

.github/workflows/pr-playwright-tests.yml

@@ -445,7 +445,7 @@ jobs:
         run: |
           npx playwright test --project ${PROJECT}
 
-      - uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+      - uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
         if: always()
         with:
           # Includes test results and trace.zip files
@@ -454,7 +454,7 @@ jobs:
           retention-days: 30
 
       - name: Upload screenshots
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
         if: always()
         with:
           name: playwright-screenshots-${{ matrix.project }}-${{ github.run_id }}
@@ -534,7 +534,7 @@ jobs:
             "s3://${PLAYWRIGHT_S3_BUCKET}/reports/pr-${PR_NUMBER}/${RUN_ID}/${PROJECT}/"
 
       - name: Upload visual diff summary
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
         if: always()
         with:
           name: screenshot-diff-summary-${{ matrix.project }}
@@ -543,7 +543,7 @@ jobs:
           retention-days: 5
 
       - name: Upload visual diff report artifact
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
         if: always()
         with:
           name: screenshot-diff-report-${{ matrix.project }}-${{ github.run_id }}
@@ -590,7 +590,7 @@ jobs:
 
       - name: Upload logs
         if: success() || failure()
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
         with:
           name: docker-logs-${{ matrix.project }}-${{ github.run_id }}
           path: ${{ github.workspace }}/docker-compose.log
@@ -674,7 +674,7 @@ jobs:
         working-directory: ./web
         run: npx playwright test --project lite
 
-      - uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+      - uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
         if: always()
         with:
           name: playwright-test-results-lite-${{ github.run_id }}
@@ -692,7 +692,7 @@ jobs:
 
       - name: Upload logs
         if: success() || failure()
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
         with:
           name: docker-logs-lite-${{ github.run_id }}
           path: ${{ github.workspace }}/docker-compose.log

.github/workflows/pr-python-model-tests.yml

@@ -122,7 +122,7 @@ jobs:
 
       - name: Upload logs
         if: always()
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
         with:
           name: docker-all-logs
           path: ${{ github.workspace }}/docker-compose.log

.github/workflows/reusable-nightly-llm-provider-chat.yml

@@ -319,7 +319,7 @@ jobs:
 
       - name: Upload logs
         if: always()
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f
         with:
           name: docker-all-logs-nightly-${{ matrix.provider }}-llm-provider
           path: |

.github/workflows/sandbox-deployment.yml

@@ -125,7 +125,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ env.REGISTRY_IMAGE }}
           flavor: |
@@ -195,7 +195,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ env.REGISTRY_IMAGE }}
           flavor: |
@@ -268,7 +268,7 @@ jobs:
 
       - name: Docker meta
         id: meta
-        uses: docker/metadata-action@c299e40c65443455700f0fdfc63efafe5b349051 # ratchet:docker/metadata-action@v5
+        uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # ratchet:docker/metadata-action@v6.0.0
         with:
           images: ${{ env.REGISTRY_IMAGE }}
           flavor: |

backend/onyx/background/celery/tasks/hierarchyfetching/tasks.py

@@ -29,6 +29,8 @@ from onyx.configs.constants import OnyxCeleryPriority
 from onyx.configs.constants import OnyxCeleryQueues
 from onyx.configs.constants import OnyxCeleryTask
 from onyx.configs.constants import OnyxRedisLocks
+from onyx.connectors.factory import ConnectorMissingException
+from onyx.connectors.factory import identify_connector_class
 from onyx.connectors.factory import instantiate_connector
 from onyx.connectors.interfaces import HierarchyConnector
 from onyx.connectors.models import HierarchyNode as PydanticHierarchyNode
@@ -55,6 +57,26 @@ logger = setup_logger()
 HIERARCHY_FETCH_INTERVAL_SECONDS = 24 * 60 * 60
 
 
+def _connector_supports_hierarchy_fetching(
+    cc_pair: ConnectorCredentialPair,
+) -> bool:
+    """Return True only for connectors whose class implements HierarchyConnector."""
+    try:
+        connector_class = identify_connector_class(
+            cc_pair.connector.source,
+        )
+    except ConnectorMissingException as e:
+        task_logger.warning(
+            "Skipping hierarchy fetching enqueue for source=%s input_type=%s: %s",
+            cc_pair.connector.source,
+            cc_pair.connector.input_type,
+            str(e),
+        )
+        return False
+
+    return issubclass(connector_class, HierarchyConnector)
+
+
 def _is_hierarchy_fetching_due(cc_pair: ConnectorCredentialPair) -> bool:
     """Returns boolean indicating if hierarchy fetching is due for this connector.
 
@@ -186,7 +208,10 @@ def check_for_hierarchy_fetching(self: Task, *, tenant_id: str) -> int | None:
                     cc_pair_id=cc_pair_id,
                 )
 
-                if not cc_pair or not _is_hierarchy_fetching_due(cc_pair):
+                if not cc_pair or not _connector_supports_hierarchy_fetching(cc_pair):
+                    continue
+
+                if not _is_hierarchy_fetching_due(cc_pair):
                     continue
 
                 task_id = _try_creating_hierarchy_fetching_task(

backend/tests/README.md

@@ -45,6 +45,21 @@ npx playwright test <TEST_NAME>
 Shared fixtures live in `backend/tests/conftest.py`. Test subdirectories can define
 their own `conftest.py` for directory-scoped fixtures.
 
+## Running Tests Repeatedly (`pytest-repeat`)
+
+Use `pytest-repeat` to catch flaky tests by running them multiple times:
+
+```bash
+# Run a specific test 50 times
+pytest --count=50 backend/tests/unit/path/to/test.py::test_name
+
+# Stop on first failure with -x
+pytest --count=50 -x backend/tests/unit/path/to/test.py::test_name
+
+# Repeat an entire test file
+pytest --count=10 backend/tests/unit/path/to/test_file.py
+```
+
 ## Best Practices
 
 ### Use `enable_ee` fixture instead of inlining

backend/tests/unit/onyx/background/celery/tasks/test_hierarchyfetching_queue.py

@@ -0,0 +1,194 @@
+from unittest.mock import MagicMock
+from unittest.mock import patch
+
+from onyx.background.celery.tasks.hierarchyfetching.tasks import (
+    _connector_supports_hierarchy_fetching,
+)
+from onyx.background.celery.tasks.hierarchyfetching.tasks import (
+    check_for_hierarchy_fetching,
+)
+from onyx.connectors.factory import ConnectorMissingException
+from onyx.connectors.interfaces import BaseConnector
+from onyx.connectors.interfaces import HierarchyConnector
+from onyx.connectors.interfaces import HierarchyOutput
+from onyx.connectors.interfaces import SecondsSinceUnixEpoch
+
+TASKS_MODULE = "onyx.background.celery.tasks.hierarchyfetching.tasks"
+
+
+class _NonHierarchyConnector(BaseConnector):
+    def load_credentials(self, credentials: dict) -> dict | None:  # noqa: ARG002
+        return None
+
+
+class _HierarchyCapableConnector(HierarchyConnector):
+    def load_credentials(self, credentials: dict) -> dict | None:  # noqa: ARG002
+        return None
+
+    def load_hierarchy(
+        self,
+        start: SecondsSinceUnixEpoch,  # noqa: ARG002
+        end: SecondsSinceUnixEpoch,  # noqa: ARG002
+    ) -> HierarchyOutput:
+        return
+        yield
+
+
+def _build_cc_pair_mock() -> MagicMock:
+    cc_pair = MagicMock()
+    cc_pair.connector.source = "mock-source"
+    cc_pair.connector.input_type = "mock-input-type"
+    return cc_pair
+
+
+def _build_redis_mock_with_lock() -> tuple[MagicMock, MagicMock]:
+    redis_client = MagicMock()
+    lock = MagicMock()
+    lock.acquire.return_value = True
+    lock.owned.return_value = True
+    redis_client.lock.return_value = lock
+    return redis_client, lock
+
+
+@patch(f"{TASKS_MODULE}.identify_connector_class")
+def test_connector_supports_hierarchy_fetching_false_for_non_hierarchy_connector(
+    mock_identify_connector_class: MagicMock,
+) -> None:
+    mock_identify_connector_class.return_value = _NonHierarchyConnector
+
+    assert _connector_supports_hierarchy_fetching(_build_cc_pair_mock()) is False
+    mock_identify_connector_class.assert_called_once_with("mock-source")
+
+
+@patch(f"{TASKS_MODULE}.task_logger.warning")
+@patch(f"{TASKS_MODULE}.identify_connector_class")
+def test_connector_supports_hierarchy_fetching_false_when_class_missing(
+    mock_identify_connector_class: MagicMock,
+    mock_warning: MagicMock,
+) -> None:
+    mock_identify_connector_class.side_effect = ConnectorMissingException("missing")
+
+    assert _connector_supports_hierarchy_fetching(_build_cc_pair_mock()) is False
+    mock_warning.assert_called_once()
+
+
+@patch(f"{TASKS_MODULE}.identify_connector_class")
+def test_connector_supports_hierarchy_fetching_true_for_supported_connector(
+    mock_identify_connector_class: MagicMock,
+) -> None:
+    mock_identify_connector_class.return_value = _HierarchyCapableConnector
+
+    assert _connector_supports_hierarchy_fetching(_build_cc_pair_mock()) is True
+    mock_identify_connector_class.assert_called_once_with("mock-source")
+
+
+@patch(f"{TASKS_MODULE}._try_creating_hierarchy_fetching_task")
+@patch(f"{TASKS_MODULE}._is_hierarchy_fetching_due")
+@patch(f"{TASKS_MODULE}.get_connector_credential_pair_from_id")
+@patch(f"{TASKS_MODULE}.fetch_indexable_standard_connector_credential_pair_ids")
+@patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+@patch(f"{TASKS_MODULE}.get_redis_client")
+@patch(f"{TASKS_MODULE}._connector_supports_hierarchy_fetching")
+def test_check_for_hierarchy_fetching_skips_unsupported_connectors(
+    mock_supports_hierarchy_fetching: MagicMock,
+    mock_get_redis_client: MagicMock,
+    mock_get_session: MagicMock,
+    mock_fetch_cc_pair_ids: MagicMock,
+    mock_get_cc_pair: MagicMock,
+    mock_is_due: MagicMock,
+    mock_try_create_task: MagicMock,
+) -> None:
+    redis_client, lock = _build_redis_mock_with_lock()
+    mock_get_redis_client.return_value = redis_client
+    mock_get_session.return_value.__enter__.return_value = MagicMock()
+    mock_fetch_cc_pair_ids.return_value = [123]
+    mock_get_cc_pair.return_value = _build_cc_pair_mock()
+    mock_supports_hierarchy_fetching.return_value = False
+    mock_is_due.return_value = True
+
+    task_app = MagicMock()
+    with patch.object(check_for_hierarchy_fetching, "app", task_app):
+        result = check_for_hierarchy_fetching.run(tenant_id="test-tenant")
+
+    assert result == 0
+    mock_is_due.assert_not_called()
+    mock_try_create_task.assert_not_called()
+    lock.release.assert_called_once()
+
+
+@patch(f"{TASKS_MODULE}._try_creating_hierarchy_fetching_task")
+@patch(f"{TASKS_MODULE}._is_hierarchy_fetching_due")
+@patch(f"{TASKS_MODULE}.get_connector_credential_pair_from_id")
+@patch(f"{TASKS_MODULE}.fetch_indexable_standard_connector_credential_pair_ids")
+@patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+@patch(f"{TASKS_MODULE}.get_redis_client")
+@patch(f"{TASKS_MODULE}._connector_supports_hierarchy_fetching")
+def test_check_for_hierarchy_fetching_creates_task_for_supported_due_connector(
+    mock_supports_hierarchy_fetching: MagicMock,
+    mock_get_redis_client: MagicMock,
+    mock_get_session: MagicMock,
+    mock_fetch_cc_pair_ids: MagicMock,
+    mock_get_cc_pair: MagicMock,
+    mock_is_due: MagicMock,
+    mock_try_create_task: MagicMock,
+) -> None:
+    redis_client, lock = _build_redis_mock_with_lock()
+    cc_pair = _build_cc_pair_mock()
+    db_session = MagicMock()
+    mock_get_redis_client.return_value = redis_client
+    mock_get_session.return_value.__enter__.return_value = db_session
+    mock_fetch_cc_pair_ids.return_value = [123]
+    mock_get_cc_pair.return_value = cc_pair
+    mock_supports_hierarchy_fetching.return_value = True
+    mock_is_due.return_value = True
+    mock_try_create_task.return_value = "task-id"
+
+    task_app = MagicMock()
+    with patch.object(check_for_hierarchy_fetching, "app", task_app):
+        result = check_for_hierarchy_fetching.run(tenant_id="test-tenant")
+
+    assert result == 1
+    mock_is_due.assert_called_once_with(cc_pair)
+    mock_try_create_task.assert_called_once_with(
+        celery_app=task_app,
+        cc_pair=cc_pair,
+        db_session=db_session,
+        r=redis_client,
+        tenant_id="test-tenant",
+    )
+    lock.release.assert_called_once()
+
+
+@patch(f"{TASKS_MODULE}._try_creating_hierarchy_fetching_task")
+@patch(f"{TASKS_MODULE}._is_hierarchy_fetching_due")
+@patch(f"{TASKS_MODULE}.get_connector_credential_pair_from_id")
+@patch(f"{TASKS_MODULE}.fetch_indexable_standard_connector_credential_pair_ids")
+@patch(f"{TASKS_MODULE}.get_session_with_current_tenant")
+@patch(f"{TASKS_MODULE}.get_redis_client")
+@patch(f"{TASKS_MODULE}._connector_supports_hierarchy_fetching")
+def test_check_for_hierarchy_fetching_skips_supported_connector_when_not_due(
+    mock_supports_hierarchy_fetching: MagicMock,
+    mock_get_redis_client: MagicMock,
+    mock_get_session: MagicMock,
+    mock_fetch_cc_pair_ids: MagicMock,
+    mock_get_cc_pair: MagicMock,
+    mock_is_due: MagicMock,
+    mock_try_create_task: MagicMock,
+) -> None:
+    redis_client, lock = _build_redis_mock_with_lock()
+    cc_pair = _build_cc_pair_mock()
+    mock_get_redis_client.return_value = redis_client
+    mock_get_session.return_value.__enter__.return_value = MagicMock()
+    mock_fetch_cc_pair_ids.return_value = [123]
+    mock_get_cc_pair.return_value = cc_pair
+    mock_supports_hierarchy_fetching.return_value = True
+    mock_is_due.return_value = False
+
+    task_app = MagicMock()
+    with patch.object(check_for_hierarchy_fetching, "app", task_app):
+        result = check_for_hierarchy_fetching.run(tenant_id="test-tenant")
+
+    assert result == 0
+    mock_is_due.assert_called_once_with(cc_pair)
+    mock_try_create_task.assert_not_called()
+    lock.release.assert_called_once()

backend/tests/unit/onyx/utils/test_threadpool_concurrency.py

@@ -32,15 +32,17 @@ def test_run_with_timeout_raises_on_timeout(slow: float, timeout: float) -> None
     """Test that a function that exceeds timeout raises TimeoutError"""
 
     def slow_function() -> None:
-        time.sleep(slow)  # Sleep for 2 seconds
+        time.sleep(slow)
 
+    start = time.monotonic()
     with pytest.raises(TimeoutError) as exc_info:
-        start = time.time()
-        run_with_timeout(timeout, slow_function)  # Set timeout to 0.1 seconds
-        end = time.time()
-        assert end - start >= timeout
-        assert end - start < (slow + timeout) / 2
+        run_with_timeout(timeout, slow_function)
+    elapsed = time.monotonic() - start
+
     assert f"timed out after {timeout} seconds" in str(exc_info.value)
+    assert elapsed >= timeout
+    # Should return around the timeout duration, not the full sleep duration
+    assert elapsed == pytest.approx(timeout, abs=0.8)
 
 
 @pytest.mark.filterwarnings("ignore::pytest.PytestUnhandledThreadExceptionWarning")

web/src/layouts/general-layouts.tsx

@@ -176,7 +176,10 @@ function AttachmentItemLayout({
     <Section flexDirection="row" gap={0.25} padding={0.25}>
       <div className={cn("h-[2.25rem] aspect-square rounded-08")}>
         <Section>
-          <div className="attachment-button__icon-wrapper">
+          <div
+            className="attachment-button__icon-wrapper"
+            data-testid="attachment-item-icon-wrapper"
+          >
             <Icon className="attachment-button__icon" />
           </div>
         </Section>
@@ -187,7 +190,7 @@ function AttachmentItemLayout({
         alignItems="center"
         gap={1.5}
       >
-        <div className="flex-1 min-w-0">
+        <div data-testid="attachment-item-title" className="flex-1 min-w-0">
           <Content
             title={title}
             description={description}

web/tests/e2e/chat/project_files_visual_regression.spec.ts

@@ -0,0 +1,181 @@
+import { expect, test, type Locator, type Page } from "@playwright/test";
+import { loginAsWorkerUser } from "@tests/e2e/utils/auth";
+import { OnyxApiClient } from "@tests/e2e/utils/onyxApiClient";
+import { expectElementScreenshot } from "@tests/e2e/utils/visualRegression";
+
+const TEST_PREFIX = "E2E-PROJECT-FILES-VISUAL";
+const ATTACHMENT_ITEM_TITLE_TEST_ID = "attachment-item-title";
+const ATTACHMENT_ITEM_ICON_WRAPPER_TEST_ID = "attachment-item-icon-wrapper";
+const LONG_FILE_NAME =
+  "CSE_202_Final_Project_Solution_Regression_Check_Long_Name.txt";
+const FILE_CONTENT = "Visual regression test content for long filename cards.";
+
+let projectId: number | null = null;
+
+type Geometry = {
+  elementLeft: number;
+  elementRight: number;
+  elementTop: number;
+  elementBottom: number;
+  cardLeft: number;
+  cardRight: number;
+  cardTop: number;
+  cardBottom: number;
+};
+
+function getFilesSection(page: Page): Locator {
+  return page
+    .locator("div")
+    .filter({ has: page.getByRole("button", { name: "Add Files" }) })
+    .filter({ hasText: "Chats in this project can access these files." })
+    .first();
+}
+
+async function uploadFileToProject(
+  page: Page,
+  targetProjectId: number,
+  fileName: string,
+  content: string
+): Promise<void> {
+  const response = await page.request.post("/api/user/projects/file/upload", {
+    multipart: {
+      project_id: String(targetProjectId),
+      files: {
+        name: fileName,
+        mimeType: "text/plain",
+        buffer: Buffer.from(content, "utf-8"),
+      },
+    },
+  });
+
+  expect(response.ok()).toBeTruthy();
+}
+
+async function getElementGeometryInCard(
+  element: Locator
+): Promise<Geometry | null> {
+  return element.evaluate((targetEl) => {
+    let cardEl: HTMLElement | null = targetEl.parentElement;
+
+    while (cardEl) {
+      const style = window.getComputedStyle(cardEl);
+      const hasBorder =
+        parseFloat(style.borderTopWidth) > 0 ||
+        parseFloat(style.borderLeftWidth) > 0;
+      const hasRadius = parseFloat(style.borderTopLeftRadius) > 0;
+
+      if (hasBorder && hasRadius) {
+        break;
+      }
+      cardEl = cardEl.parentElement;
+    }
+
+    if (!cardEl) {
+      return null;
+    }
+
+    const elementRect = targetEl.getBoundingClientRect();
+    const cardRect = cardEl.getBoundingClientRect();
+
+    return {
+      elementLeft: elementRect.left,
+      elementRight: elementRect.right,
+      elementTop: elementRect.top,
+      elementBottom: elementRect.bottom,
+      cardLeft: cardRect.left,
+      cardRight: cardRect.right,
+      cardTop: cardRect.top,
+      cardBottom: cardRect.bottom,
+    };
+  });
+}
+
+function expectGeometryWithinCard(geometry: Geometry | null): void {
+  expect(geometry).not.toBeNull();
+  expect(geometry!.elementLeft).toBeGreaterThanOrEqual(geometry!.cardLeft - 1);
+  expect(geometry!.elementRight).toBeLessThanOrEqual(geometry!.cardRight + 1);
+  expect(geometry!.elementTop).toBeGreaterThanOrEqual(geometry!.cardTop - 1);
+  expect(geometry!.elementBottom).toBeLessThanOrEqual(geometry!.cardBottom + 1);
+}
+
+test.describe("Project Files visual regression", () => {
+  test.beforeAll(async ({ browser }, workerInfo) => {
+    const context = await browser.newContext();
+    const page = await context.newPage();
+
+    await loginAsWorkerUser(page, workerInfo.workerIndex);
+    const client = new OnyxApiClient(page.request);
+
+    projectId = await client.createProject(`${TEST_PREFIX}-${Date.now()}`);
+    await uploadFileToProject(page, projectId, LONG_FILE_NAME, FILE_CONTENT);
+
+    await context.close();
+  });
+
+  test.afterAll(async ({ browser }, workerInfo) => {
+    if (!projectId) {
+      return;
+    }
+
+    const context = await browser.newContext();
+    const page = await context.newPage();
+
+    await loginAsWorkerUser(page, workerInfo.workerIndex);
+    const client = new OnyxApiClient(page.request);
+    await client.deleteProject(projectId);
+
+    await context.close();
+  });
+
+  test.beforeEach(async ({ page }, workerInfo) => {
+    if (projectId === null) {
+      throw new Error(
+        "Project setup failed in beforeAll; cannot run visual regression test"
+      );
+    }
+
+    await page.context().clearCookies();
+    await loginAsWorkerUser(page, workerInfo.workerIndex);
+    await page.goto(`/app?projectId=${projectId}`);
+    await page.waitForLoadState("networkidle");
+    await expect(
+      page.getByText("Chats in this project can access these files.")
+    ).toBeVisible();
+  });
+
+  test("long underscore filename stays visually contained in file card", async ({
+    page,
+  }) => {
+    const filesSection = getFilesSection(page);
+    await expect(filesSection).toBeVisible();
+
+    const fileTitle = filesSection
+      .locator(`[data-testid="${ATTACHMENT_ITEM_TITLE_TEST_ID}"]`)
+      .filter({ hasText: LONG_FILE_NAME })
+      .first();
+    await expect(fileTitle).toBeVisible();
+
+    // Wait for deterministic post-processing state before geometry checks/screenshot.
+    await expect(fileTitle).not.toContainText("Processing...", {
+      timeout: 30_000,
+    });
+    await expect(fileTitle).not.toContainText("Uploading...", {
+      timeout: 30_000,
+    });
+    await expect(fileTitle).toContainText("TXT", { timeout: 30_000 });
+
+    const iconWrapper = filesSection
+      .locator(`[data-testid="${ATTACHMENT_ITEM_ICON_WRAPPER_TEST_ID}"]`)
+      .first();
+    await expect(iconWrapper).toBeVisible();
+
+    await expectElementScreenshot(filesSection, {
+      name: "project-files-long-underscore-filename",
+    });
+
+    const iconGeometry = await getElementGeometryInCard(iconWrapper);
+    const titleGeometry = await getElementGeometryInCard(fileTitle);
+    expectGeometryWithinCard(iconGeometry);
+    expectGeometryWithinCard(titleGeometry);
+  });
+});