Refactor type annotations for improved clarity and consistency across multiple files

Author: Zalfsten

.github/workflows/python-quality.yml

@@ -44,7 +44,7 @@ jobs:
 
     - name: Type checking with mypy
       run: |
-        uv run mypy middleware/ --ignore-missing-imports --strict-optional
+        uv run mypy middleware/
       continue-on-error: false
 
     - name: Security check with bandit

middleware/sql_to_arc/src/middleware/sql_to_arc/builder.py

@@ -6,7 +6,7 @@
 from collections import defaultdict
 from typing import Any, cast
 
-from arctrl import (  # type: ignore[import-untyped]
+from arctrl import (
     ARC,
     ArcAssay,
     ArcStudy,
@@ -150,7 +150,7 @@ def _add_publications_to_arc(
             study.Publications.append(map_publication(p_row))
 
 
-def _get_column_key(r: dict[str, Any]) -> tuple:
+def _get_column_key(r: dict[str, Any]) -> tuple[Any, ...]:
     """Extract a unique key for a column definition."""
     return (
         r.get("column_type"),
@@ -163,7 +163,7 @@ def _get_column_key(r: dict[str, Any]) -> tuple:
     )
 
 
-def _build_header(key: tuple) -> CompositeHeader | None:
+def _build_header(key: tuple[Any, ...]) -> CompositeHeader | None:
     """Build a CompositeHeader from a column key tuple."""
     c_type, c_io, c_val, c_ann_term, c_ann_uri, c_ann_ver, c_name = key
     try:
@@ -246,9 +246,9 @@ def _build_arc_table(t_name: str, rows: list[dict[str, Any]]) -> ArcTable | None
     if max_row_idx < 0:
         return None
 
-    col_keys: list[tuple] = []
+    col_keys: list[tuple[Any, ...]] = []
     seen_keys = set()
-    col_to_rows: dict[tuple, dict[int, dict[str, Any]]] = defaultdict(dict)
+    col_to_rows: dict[tuple[Any, ...], dict[int, dict[str, Any]]] = defaultdict(dict)
 
     for r in rows:
         key = _get_column_key(r)

middleware/sql_to_arc/src/middleware/sql_to_arc/mapper.py

@@ -3,7 +3,7 @@
 from datetime import datetime
 from typing import Any
 
-from arctrl import (  # type: ignore
+from arctrl import (
     ArcAssay,
     ArcInvestigation,
     ArcStudy,

middleware/sql_to_arc/src/middleware/sql_to_arc/processor.py

@@ -196,7 +196,7 @@ def _spawn_investigation_task(
     idx: int,
     batch_data: RelatedDataBatch,
     res: WorkerResources,
-    running_tasks: set[asyncio.Task],
+    running_tasks: set[asyncio.Task[None]],
 ) -> None:
     """Create worker context and spawn a processing task."""
     ctx = WorkerContext(
@@ -242,7 +242,7 @@ async def process_investigations(
         ) as executor,
         trace.get_tracer(__name__).start_as_current_span("process_investigations"),
     ):
-        running_tasks: set[asyncio.Task] = set()
+        running_tasks: set[asyncio.Task[None]] = set()
         inv_idx = 0
         investigation_gen = db.stream_investigations(stats=stats, limit=config.debug_limit)
 

middleware/sql_to_arc/tests/integration/test_workflow.py

@@ -8,10 +8,10 @@
 from unittest.mock import AsyncMock, MagicMock
 
 import pytest
-from arctrl import ARC  # type: ignore[import-untyped]
+from arctrl import ARC
 
-from middleware.api_client import ApiClient
-from middleware.shared.api_models.models import CreateOrUpdateArcsResponse
+from middleware.api_client import ApiClient, ArcMetadata, ArcResult, ArcStatus
+from middleware.api_client.models import ArcLifecycleStatus
 from middleware.shared.config.config_base import OtelConfig
 from middleware.sql_to_arc.config import Config
 from middleware.sql_to_arc.context import WorkerContext
@@ -61,11 +61,15 @@ def mock_db_connection(mock_db_cursor: AsyncMock) -> AsyncMock:
 def mock_api_client() -> AsyncMock:
     """Mock API client."""
     client = AsyncMock(spec=ApiClient)
-    client.create_or_update_arc.return_value = CreateOrUpdateArcsResponse(
-        client_id="test",
-        message="success",
-        rdi="test",
-        arcs=[],
+    client.create_or_update_arc.return_value = ArcResult(
+        arc_id="test",
+        status=ArcStatus.CREATED,
+        metadata=ArcMetadata(
+            arc_hash="",
+            status=ArcLifecycleStatus.ACTIVE,
+            first_seen="2026-01-01T00:00:00Z",
+            last_seen="2026-01-01T00:00:00Z",
+        ),
     )
     return client
 
@@ -121,15 +125,24 @@ def __init__(self, mocker: MagicMock, mock_api_client: AsyncMock) -> None:
         mocker.patch("middleware.sql_to_arc.main.configure_logging")
 
         # Capture ARCs on API call
-        async def capture_arc(rdi: str, arc: Any) -> CreateOrUpdateArcsResponse:
+        async def capture_arc(rdi: str, arc: Any) -> ArcResult:
             serialized_arc = arc
             if isinstance(arc, dict):
                 # Convert back to ARC object for test compatibility
                 # processor.py sends a dict, but legacy tests expect an ARC object
                 serialized_arc = ARC.from_rocrate_json_string(json.dumps(arc))
 
             self.captured_arcs.append(serialized_arc)
-            return CreateOrUpdateArcsResponse(client_id="test", message="success", rdi=rdi, arcs=[])
+            return ArcResult(
+                arc_id=rdi,
+                status=ArcStatus.CREATED,
+                metadata=ArcMetadata(
+                    arc_hash="",
+                    status=ArcLifecycleStatus.ACTIVE,
+                    first_seen="2026-01-01T00:00:00Z",
+                    last_seen="2026-01-01T00:00:00Z",
+                ),
+            )
 
         self.api_client.create_or_update_arc.side_effect = capture_arc
 

middleware/sql_to_arc/tests/unit/test_mapper.py

@@ -3,7 +3,7 @@
 import datetime
 
 import pytest
-from arctrl import (  # type: ignore[import-untyped, import-not-found]
+from arctrl import (
     ArcAssay,
     ArcInvestigation,
     ArcStudy,

pyproject.toml

@@ -136,6 +136,11 @@ exclude = [
 # ]
 # ignore_missing_imports = true
 
+# arctrl has no type stubs and no py.typed marker — suppress the resulting noise
+[[tool.mypy.overrides]]
+module = ["arctrl"]
+ignore_missing_imports = true
+
 # Docstring-Regeln aktivieren, damit es wie pylint C0114/15/16 meckert
 [tool.ruff.lint.pydocstyle]
 convention = "pep257" # oder "numpy", oder "google"