ci: add ruff linting and mypy type checking

Add ruff and mypy to dev dependencies with configuration in pyproject.toml.
Add a lint CI job that runs ruff check, ruff format --check, and mypy.
Auto-fix import sorting and formatting across the codebase. Exclude
alembic/versions from linting (auto-generated migrations). Ignore B008
(FastAPI Depends pattern) and RUF001 (unicode in user-facing strings).

21 ruff lint errors and 50 mypy errors remain for manual review.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

app/services/domains/runs/application.py

@@ -25,21 +25,21 @@ from app.services.domains.runs.types import (
 )
 
 __all__ = [
+    "QUEUE_STATUS_DROPPED",
     "QUEUE_STATUS_QUEUED",
     "QUEUE_STATUS_RETRYING",
-    "QUEUE_STATUS_DROPPED",
-    "QueueListItem",
     "QueueClearResult",
+    "QueueListItem",
     "QueueTransitionError",
+    "clear_queue_item_for_user",
+    "drop_queue_item_for_user",
     "extract_run_summary",
+    "get_manual_run_by_idempotency_key",
+    "get_queue_item_for_user",
+    "get_run_for_user",
+    "list_queue_items_for_user",
     "list_recent_runs_for_user",
     "list_runs_for_user",
-    "get_run_for_user",
-    "get_manual_run_by_idempotency_key",
-    "list_queue_items_for_user",
-    "get_queue_item_for_user",
-    "retry_queue_item_for_user",
-    "drop_queue_item_for_user",
-    "clear_queue_item_for_user",
     "queue_status_counts_for_user",
+    "retry_queue_item_for_user",
 ]

app/services/domains/runs/events.py

@@ -1,14 +1,16 @@
 import asyncio
 import json
 import logging
-from typing import Any, AsyncGenerator, Dict, Set
+from collections.abc import AsyncGenerator
+from typing import Any
 
 logger = logging.getLogger(__name__)
 
+
 class RunEventPublisher:
     def __init__(self) -> None:
         # Maps run_id to a set of subscriber queues
-        self._subscribers: Dict[int, Set[asyncio.Queue]] = {}
+        self._subscribers: dict[int, set[asyncio.Queue]] = {}
 
     def subscribe(self, run_id: int) -> asyncio.Queue:
         if run_id not in self._subscribers:
@@ -27,12 +29,9 @@ class RunEventPublisher:
     async def publish(self, run_id: int, event_type: str, data: dict[str, Any]) -> None:
         if run_id not in self._subscribers:
             return
-        
-        message = {
-            "type": event_type,
-            "data": data
-        }
-        
+
+        message = {"type": event_type, "data": data}
+
         # Fan-out to all active subscribers for this run
         for queue in list(self._subscribers[run_id]):
             try:
@@ -40,8 +39,10 @@ class RunEventPublisher:
             except asyncio.QueueFull:
                 logger.warning(f"Subscriber queue full for run {run_id}, dropping message")
 
+
 run_events = RunEventPublisher()
 
+
 async def event_generator(run_id: int) -> AsyncGenerator[str, None]:
     queue = run_events.subscribe(run_id)
     try:

app/services/domains/runs/queue_service.py

@@ -41,9 +41,7 @@ async def get_queue_item_for_user(
     queue_item_id: int,
 ) -> QueueListItem | None:
     result = await db_session.execute(
-        queue_item_select(user_id=user_id)
-        .where(IngestionQueueItem.id == queue_item_id)
-        .limit(1)
+        queue_item_select(user_id=user_id).where(IngestionQueueItem.id == queue_item_id).limit(1)
     )
     row = result.one_or_none()
     if row is None:

app/services/domains/runs/runs_service.py

@@ -35,9 +35,7 @@ async def list_runs_for_user(
         .limit(limit)
     )
     if failed_only:
-        stmt = stmt.where(
-            CrawlRun.status.in_([RunStatus.FAILED, RunStatus.PARTIAL_FAILURE])
-        )
+        stmt = stmt.where(CrawlRun.status.in_([RunStatus.FAILED, RunStatus.PARTIAL_FAILURE]))
     result = await db_session.execute(stmt)
     return list(result.scalars().all())
 

app/services/domains/runs/summary.py

@@ -24,9 +24,7 @@ def _summary_int_dict(summary: dict[str, Any], key: str) -> dict[str, int]:
     if not isinstance(value, dict):
         return {}
     return {
-        str(item_key): _safe_int(item_value, 0)
-        for item_key, item_value in value.items()
-        if isinstance(item_key, str)
+        str(item_key): _safe_int(item_value, 0) for item_key, item_value in value.items() if isinstance(item_key, str)
     }
 
 
@@ -34,11 +32,7 @@ def _summary_bool_dict(summary: dict[str, Any], key: str) -> dict[str, bool]:
     value = summary.get(key)
     if not isinstance(value, dict):
         return {}
-    return {
-        str(item_key): bool(item_value)
-        for item_key, item_value in value.items()
-        if isinstance(item_key, str)
-    }
+    return {str(item_key): bool(item_value) for item_key, item_value in value.items() if isinstance(item_key, str)}
 
 
 def _retry_counts(summary: dict[str, Any]) -> dict[str, int]: