mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-14 04:09:09 +00:00
ec58b889cc
Each test below passed or failed on the same commit depending on test order or port timing in the CircleCI integration workflow - readiness probe only polls a port the launched proxy owns, so a stolen port no longer sends GET /health/integration-readiness to another test's wire server - team update tests seed fresh member users, since a proxy admin relocation adds team members to the destination org and leaked org_b membership into the shared INTERNAL_USER - realtime whisper tests wait until every proxy worker serves only the new gpt-realtime-whisper deployment, via a per-worker deployment id route - configured fallbacks test runs on its own proxy and database, because /config/update persists router settings and cannot unset fallbacks, which left [] and changed the no-fallback error text other tests assert - otel excluded services tests each get a private Redis so a sibling proxy cannot warm the budget registry cache the tenant span depends on - Langfuse audit upstream uses unique response ids instead of len(targets), which could repeat under concurrency and drop SpendLogs rows
40 lines
1.4 KiB
Python
40 lines
1.4 KiB
Python
import asyncio
|
|
import os
|
|
from concurrent.futures import ThreadPoolExecutor
|
|
from typing import Final
|
|
|
|
from fastapi import Response
|
|
from fastapi.responses import JSONResponse
|
|
from pydantic import TypeAdapter
|
|
|
|
READINESS_BODY: Final = TypeAdapter(dict[str, object])
|
|
|
|
|
|
def configure_executor() -> None:
|
|
asyncio.get_running_loop().set_default_executor(
|
|
ThreadPoolExecutor(max_workers=32, thread_name_prefix="integration-provider")
|
|
)
|
|
|
|
|
|
async def worker_readiness() -> JSONResponse:
|
|
from litellm.proxy.health_endpoints._health_endpoints import health_readiness
|
|
|
|
response: Final = Response()
|
|
body: Final = READINESS_BODY.validate_python(await health_readiness(response))
|
|
return JSONResponse(
|
|
content=body, status_code=response.status_code, headers={"x-integration-worker-pid": str(os.getpid())}
|
|
)
|
|
|
|
|
|
async def worker_deployment_ids(model_name: str) -> JSONResponse:
|
|
from litellm.proxy.proxy_server import llm_router
|
|
|
|
model_ids: Final = [] if llm_router is None else llm_router.get_model_ids(model_name=model_name)
|
|
return JSONResponse(content={"model_ids": model_ids}, headers={"x-integration-worker-pid": str(os.getpid())})
|
|
|
|
|
|
def configure_readiness() -> None:
|
|
from litellm.proxy.proxy_server import app
|
|
|
|
app.add_api_route("/health/integration-readiness", worker_readiness, include_in_schema=False)
|
|
app.add_api_route("/health/integration-deployment-ids", worker_deployment_ids, include_in_schema=False)
|