jpmschweitzerandClaude
78066fab1b
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>
74 lines
1.9 KiB
Python
74 lines
1.9 KiB
Python
"""
|
|
Chat completion router.
|
|
OpenAI-compatible /v1/chat/completions endpoint.
|
|
"""
|
|
|
|
import json
|
|
import logging
|
|
from collections.abc import AsyncGenerator
|
|
|
|
from fastapi import APIRouter
|
|
from starlette.responses import StreamingResponse
|
|
|
|
from src.chat import service
|
|
from src.chat.schemas import (
|
|
ChatCompletionRequest,
|
|
ChatCompletionResponse,
|
|
)
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
router = APIRouter(prefix="/chat", tags=["chat"])
|
|
|
|
|
|
async def _stream_response(
|
|
request: ChatCompletionRequest,
|
|
) -> AsyncGenerator[str, None]:
|
|
"""
|
|
Generate SSE stream for chat completion.
|
|
|
|
Yields raw SSE-formatted strings matching OpenAI's format exactly:
|
|
data: {json}\n\n
|
|
"""
|
|
try:
|
|
async for chunk in service.create_chat_completion_stream(request):
|
|
yield f"data: {chunk.model_dump_json(exclude_unset=True)}\n\n"
|
|
|
|
yield "data: [DONE]\n\n"
|
|
|
|
except Exception as e:
|
|
logger.error(f"Error in streaming response: {e}")
|
|
error_data = json.dumps({"error": {"message": str(e), "type": "internal_error"}})
|
|
yield f"data: {error_data}\n\n"
|
|
|
|
|
|
@router.post("/completions", response_model=ChatCompletionResponse)
|
|
async def create_chat_completion(
|
|
request: ChatCompletionRequest,
|
|
) -> ChatCompletionResponse | StreamingResponse:
|
|
"""
|
|
Create chat completion (OpenAI-compatible).
|
|
|
|
Supports both regular and streaming responses.
|
|
|
|
Args:
|
|
request: Chat completion request
|
|
|
|
Returns:
|
|
Chat completion response or SSE stream
|
|
"""
|
|
logger.info(f"Chat completion request for model: {request.model}")
|
|
|
|
if request.stream:
|
|
logger.info("Streaming response requested")
|
|
return StreamingResponse(
|
|
_stream_response(request),
|
|
media_type="text/event-stream",
|
|
headers={
|
|
"Cache-Control": "no-store",
|
|
"X-Accel-Buffering": "no",
|
|
},
|
|
)
|
|
|
|
return await service.create_chat_completion(request)
|