BerriAI/litellm · error · HTTPException

Internal Server Error

Error message

Internal Server Error

What it means

Raised as HTTPException 500 in the example_logging_api FastAPI app — a reference implementation showing how to build a custom /log-event callback receiver for litellm proxy logging callbacks. Any exception while parsing the inbound request (most commonly request.json() failing on a non-JSON body) is converted to a bare 500 with no detail.

Source

Thrown at enterprise/litellm_enterprise/enterprise_callbacks/example_logging_api.py:21

app = FastAPI()


@app.post("/log-event")
async def log_event(request: Request):
    try:
        print("Received /log-event request")  # noqa
        # Assuming the incoming request has JSON data
        data = await request.json()
        print("Received request data:")  # noqa
        print(data)  # noqa

        # Your additional logic can go here
        # For now, just printing the received data

        return {"message": "Request received successfully"}
    except Exception:
        raise HTTPException(status_code=500, detail="Internal Server Error")


if __name__ == "__main__":
    import uvicorn

    uvicorn.run(app, host="127.0.0.1", port=8000)

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Treat this as example code — do not deploy it unmodified in production; copy it into your own service and add real error handling.
2. Reproduce the failing payload from the proxy logs and validate it parses as JSON.
3. Ensure the sender sets Content-Type: application/json.
4. Replace the bare except with one that logs the exception (e.g. via app logger / exception(logger)) before returning 500.

Example fix

# before
    except Exception:
        raise HTTPException(status_code=500, detail="Internal Server Error")

# after
    except Exception:
        import logging
        logging.exception("failed to process /log-event payload")
        raise HTTPException(status_code=400, detail="Invalid JSON payload")

@app.post("/log-event")
async def log_event(request: Request):
    try:
        data = await request.json()
    except json.JSONDecodeError as e:
        logging.warning("invalid callback payload: %s", e)
        return {"status": "ignored"}  # never 500 the proxy's callback sender
    return {"message": "ok"}

When it happens

Trigger: The litellm proxy is configured with a generic logging callback POSTing to this example server, and a callback payload arrives that is not valid JSON (content-type mismatch, truncated body), causing await request.json() to raise. This is example code, not production API surface.

Common situations: Users running the example callback server as-is and sending test events with curl without a JSON content-type; proxy versions whose callback payload shape changed; treating this demo server as a production logging endpoint.

Understand the failure class

• HTTP status errors: handling 4xx and 5xx responses — how to handle 4xx and 5xx responses properly.

Related errors

• Invalid content moderation response: {redacted_text}
• Error saving email settings to general_settings: {str(e)}
• Keyword banned. Keyword={word}
• File not found. blocked_user_list={blocked_user_list}
• An error occurred: {str(e)}, blocked_user_list={blocked_user

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/851c031f99f73942. Report an issue: GitHub.