BerriAI/litellm · error · HTTPException

Failed to initialize prompt

Error message

Failed to initialize prompt

What it means

Post-create guard: the DB insert succeeded but InMemoryPromptRegistry.initialize_prompt returned None, meaning the new prompt could not be registered in memory (initialization hook failure), so creation is reported as failed with 500.

Source

Thrown at litellm/proxy/prompts/prompt_endpoints.py:804

                "environment": environment,
                "created_by": user_api_key_dict.user_id,
                "litellm_params": request.litellm_params.model_dump_json(),
                "prompt_info": (
                    request.prompt_info.model_dump_json()
                    if request.prompt_info
                    else PromptInfo(prompt_type="db").model_dump_json()
                ),
            }
        )

        # Create versioned prompt spec
        prompt_spec: Final = create_versioned_prompt_spec(db_prompt=prompt_db_entry)

        # Initialize the prompt
        initialized_prompt = IN_MEMORY_PROMPT_REGISTRY.initialize_prompt(prompt=prompt_spec, config_file_path=None)

        if initialized_prompt is None:
            raise HTTPException(status_code=500, detail="Failed to initialize prompt")

        return initialized_prompt

    except Exception as e:
        verbose_proxy_logger.exception("Error creating prompt: %s", e)
        raise HTTPException(status_code=500, detail=str(e))


@router.put(
    "/prompts/{prompt_id}",
    tags=["Prompt Management"],
    dependencies=[Depends(user_api_key_auth)],
)
async def update_prompt(
    prompt_id: str,
    request: Prompt,
    user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
):

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Check proxy logs for the initialization failure (DB write, invalid template); fix the prompt payload and retry.

When it happens

Trigger: Thrown at litellm/proxy/prompts/prompt_endpoints.py:804 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/ccde7a16ec0c20b4. Report an issue: GitHub.