style: apply ruff's automatic fixes and formatter

Mechanical only, and separated from the judgment calls that follow so the
reviewable changes are not buried in a 98-file whitespace diff.

227 automatic fixes: 60 blank lines carrying whitespace, 60 unsorted import
blocks, 34 Optional[X] to X | None, 28 unused imports, 16 deprecated typing
imports, 12 datetime.timezone.utc to datetime.UTC, and assorted smaller
modernisations. Then `ruff format` over src and tests: 98 files reformatted,
35 already conforming.

No file among the unused-import findings defines __all__ or is an __init__.py,
so nothing here removes a re-export.

`make test`: 658 passed, unchanged from HEAD.

Two things observed while verifying, neither addressed here:

`pytest tests/` cannot collect — tests/e2e/test_orchestration_e2e.py uses an
`e2e` marker that is not registered, and the config is strict about markers.
This fails identically at HEAD, so it predates this change; `make test` passes
because it ignores tests/e2e, tests/integration and tests/contracts.

test_tatlock_tool_call_logging_calculator is flaky. It failed once in a full run
with these changes and passed on the next, passes in isolation with them, and
fails in isolation at HEAD. It is order- or timing-dependent, not a regression
from this commit — established by running the full suite both ways rather than
by reasoning about which change could have caused it.

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

src/chat/router.py

@@ -2,9 +2,10 @@
 Chat completion router.
 OpenAI-compatible /v1/chat/completions endpoint.
 """
+
 import json
 import logging
-from typing import AsyncGenerator
+from collections.abc import AsyncGenerator
 
 from fastapi import APIRouter
 from starlette.responses import StreamingResponse

src/chat/schemas.py

@@ -2,6 +2,7 @@
 OpenAI-compatible chat completion schemas.
 Following OpenAI API specification for compatibility.
 """
+
 from typing import Literal
 
 from pydantic import Field
@@ -11,6 +12,7 @@ from src.core.models import CustomBaseModel
 
 class ChatMessage(CustomBaseModel):
     """OpenAI-compatible chat message."""
+
     role: Literal["system", "user", "assistant"]
     content: str
     name: str | None = None
@@ -18,6 +20,7 @@ class ChatMessage(CustomBaseModel):
 
 class ChatCompletionRequest(CustomBaseModel):
     """OpenAI-compatible chat completion request."""
+
     model: str = Field(..., description="Model to use for completion")
     messages: list[ChatMessage] = Field(..., description="List of messages")
     temperature: float | None = Field(default=0.7, ge=0.0, le=2.0)
@@ -29,6 +32,7 @@ class ChatCompletionRequest(CustomBaseModel):
 
 class ChatCompletionChoice(CustomBaseModel):
     """Choice in chat completion response."""
+
     index: int
     message: ChatMessage
     finish_reason: str | None
@@ -36,6 +40,7 @@ class ChatCompletionChoice(CustomBaseModel):
 
 class ChatCompletionUsage(CustomBaseModel):
     """Token usage information."""
+
     prompt_tokens: int
     completion_tokens: int
     total_tokens: int
@@ -43,6 +48,7 @@ class ChatCompletionUsage(CustomBaseModel):
 
 class ChatCompletionResponse(CustomBaseModel):
     """OpenAI-compatible chat completion response."""
+
     id: str
     object: str = "chat.completion"
     created: int
@@ -53,6 +59,7 @@ class ChatCompletionResponse(CustomBaseModel):
 
 class ChatCompletionChunkDelta(CustomBaseModel):
     """Delta in streaming chunk."""
+
     role: str | None = None
     content: str | None = None
     reasoning_content: str | None = None  # For thinking/reasoning (DeepSeek R1 format)
@@ -60,6 +67,7 @@ class ChatCompletionChunkDelta(CustomBaseModel):
 
 class ChatCompletionChunkChoice(CustomBaseModel):
     """Choice in streaming chunk."""
+
     index: int
     delta: ChatCompletionChunkDelta
     finish_reason: str | None = None
@@ -67,6 +75,7 @@ class ChatCompletionChunkChoice(CustomBaseModel):
 
 class ChatCompletionChunk(CustomBaseModel):
     """OpenAI-compatible streaming chunk."""
+
     id: str
     object: str = "chat.completion.chunk"
     created: int

src/chat/service.py

@@ -4,17 +4,17 @@ Chat completion service.
 Wrapper around Responses API that converts to Chat Completions format.
 Embeds reasoning in <think> tags for Open WebUI compatibility.
 """
-import asyncio
+
 import time
 import uuid
-from typing import AsyncGenerator
+from collections.abc import AsyncGenerator
 
 from src.chat import constants
 from src.chat.schemas import (
+    ChatCompletionChoice,
     ChatCompletionChunk,
     ChatCompletionChunkChoice,
     ChatCompletionChunkDelta,
-    ChatCompletionChoice,
     ChatCompletionRequest,
     ChatCompletionResponse,
     ChatCompletionUsage,
@@ -43,10 +43,7 @@ async def create_chat_completion(
     created_at = int(time.time())
 
     # Convert Chat request to Responses request
-    input_messages = [
-        {"role": msg.role, "content": msg.content}
-        for msg in request.messages
-    ]
+    input_messages = [{"role": msg.role, "content": msg.content} for msg in request.messages]
 
     response_request = ResponseRequest(
         model=request.model,
@@ -54,7 +51,9 @@ async def create_chat_completion(
         reasoning={"effort": "medium", "summary": "auto"},  # Enable reasoning
         temperature=request.temperature or 1.0,
         max_output_tokens=request.max_tokens,
-        stop=request.stop if isinstance(request.stop, list) else ([request.stop] if request.stop else None),
+        stop=request.stop
+        if isinstance(request.stop, list)
+        else ([request.stop] if request.stop else None),
     )
 
     # Call Responses API (will use Steward for Tatlock)
@@ -118,16 +117,13 @@ async def create_chat_completion_stream(
     Yields:
         Chat completion chunks with reasoning as <think> tags
     """
-    from src.responses.streaming import StreamingCoordinator, StreamEventType
+    from src.responses.streaming import StreamEventType, StreamingCoordinator
 
     completion_id = f"chatcmpl-{uuid.uuid4().hex[:24]}"
     created_at = int(time.time())
 
     # Convert Chat request to Responses request
-    input_messages = [
-        {"role": msg.role, "content": msg.content}
-        for msg in request.messages
-    ]
+    input_messages = [{"role": msg.role, "content": msg.content} for msg in request.messages]
 
     response_request = ResponseRequest(
         model=request.model,
@@ -135,7 +131,9 @@ async def create_chat_completion_stream(
         reasoning={"effort": "medium", "summary": "auto"},
         temperature=request.temperature or 1.0,
         max_output_tokens=request.max_tokens,
-        stop=request.stop if isinstance(request.stop, list) else ([request.stop] if request.stop else None),
+        stop=request.stop
+        if isinstance(request.stop, list)
+        else ([request.stop] if request.stop else None),
         stream=True,
     )