BerriAI/litellm · error · HTTPException

Internal server error: {e}

Error message

Internal server error: {e}

What it means

Catch-all wrapper raised by an agent management endpoint when an unexpected exception escapes the handler body; the original error's text is embedded in the HTTP 500 detail. It marks an unhandled server-side failure (usually database or serialization) rather than any client-input problem — the chained exception in the logs holds the real cause.

Source

Thrown at litellm/proxy/agent_endpoints/endpoints.py:344

                    AGENT_HEALTH_CHECK_GATHER_TIMEOUT_SECONDS,
                )
                health_results = [
                    {
                        "agent_id": agent.agent_id,
                        "healthy": False,
                        "error": "Health check timed out",
                    }
                    for agent in agents_with_url
                ]
            healthy_ids: Final = {result["agent_id"] for result in health_results if result["healthy"]}
            returned_agents = [agent for agent in agents_with_url if agent.agent_id in healthy_ids] + agents_without_url

        return returned_agents
    except HTTPException:
        raise
    except Exception as e:
        verbose_proxy_logger.exception("litellm.proxy.agent_endpoints.get_agents(): Exception occurred - %s", e)
        raise HTTPException(status_code=500, detail={"error": f"Internal server error: {e}"})


#### CRUD ENDPOINTS FOR AGENTS ####

from litellm.proxy.agent_endpoints.agent_registry import (
    agents_table,
)
from litellm.proxy.agent_endpoints.agent_registry import (
    global_agent_registry as AGENT_REGISTRY,
)


@router.post(
    "/v1/agents",
    tags=["[beta] A2A Agents"],
    dependencies=[Depends(user_api_key_auth)],
    response_model=AgentResponse,
)

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Check proxy logs for the exception detail; validate the request payload.

Example fix

Inspect server logs for the stack trace.

When it happens

Trigger: Thrown at litellm/proxy/agent_endpoints/endpoints.py:344 when the library encounters an invalid state.

Common situations: See trigger scenarios.

Understand the failure class

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

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/e9abdc266e2aef2f. Report an issue: GitHub.