mem0ai/mem0 · error · ValueError

One of user_id, agent_id, run_id must be provided

Error message

One of user_id, agent_id, run_id must be provided

What it means

Mem0Proxy.completion()/the proxy's chat entry point requires exactly this: at least one of user_id, agent_id, or run_id so it knows which memory scope to read and write. Without a scope it cannot store or retrieve memories, so it refuses immediately with ValueError. All three parameters must not be simultaneously falsy.

Source

Thrown at mem0/proxy/main.py:98

        tool_choice: Optional[Union[str, dict]] = None,
        logprobs: Optional[bool] = None,
        top_logprobs: Optional[int] = None,
        parallel_tool_calls: Optional[bool] = None,
        deployment_id=None,
        extra_headers: Optional[dict] = None,
        # soon to be deprecated params by OpenAI
        functions: Optional[List] = None,
        function_call: Optional[str] = None,
        # set api_base, api_version, api_key
        base_url: Optional[str] = None,
        api_version: Optional[str] = None,
        api_key: Optional[str] = None,
        model_list: Optional[list] = None,  # pass in a list of api_base,keys, etc.
    ):
        if messages is None:
            messages = []
        if not any([user_id, agent_id, run_id]):
            raise ValueError("One of user_id, agent_id, run_id must be provided")

        if not litellm.supports_function_calling(model):
            raise ValueError(
                f"Model '{model}' does not support function calling. Please use a model that supports function calling."
            )

        prepared_messages = self._prepare_messages(messages)
        if prepared_messages[-1]["role"] == "user":
            self._async_add_to_memory(messages, user_id, agent_id, run_id, metadata, filters)
            relevant_memories = self._fetch_relevant_memories(messages, user_id, agent_id, run_id, filters, top_k)
            logger.debug(f"Retrieved {len(relevant_memories)} relevant memories")
            prepared_messages[-1]["content"] = self._format_query_with_memories(messages, relevant_memories)

        response = litellm.completion(
            model=model,
            messages=prepared_messages,
            temperature=temperature,
            top_p=top_p,

View on GitHub (pinned to 001c235229)

Solutions

1. Pass a scope explicitly: completion(messages=..., model=..., user_id='alice') (or agent_id/run_id for agent/session scoped memory)
2. If wrapping the proxy, forward and validate user_id/agent_id/run_id before calling
3. For per-user apps, derive user_id from your auth context and fail loudly upstream when it is missing

Example fix

# before
resp = mem0_proxy.completion(messages=messages, model="gpt-4o-mini")

# after
resp = mem0_proxy.completion(messages=messages, model="gpt-4o-mini", user_id=user_id)

if not any([user_id, agent_id, run_id]):
    raise ValueError("user_id/agent_id/run_id required before calling proxy completion")

When it happens

Trigger: Calling mem0_proxy.completion(messages=..., model=...) without any of user_id/agent_id/run_id; passing them under wrong kwarg names (e.g. 'user' instead of 'user_id'); building a thin wrapper that forwards **kwargs but drops the scope arguments; per-user deployments where the caller assumed the proxy remembered the ID from init.

Common situations: Migrating code from direct litellm/openai calls (which need no user scope) to the Mem0 proxy and forgetting the new required arg; multi-user API gateways where the user_id is extracted from auth and is None for unauthenticated test requests.

Related errors

• LiteLLM failed: ${message}
• Model '{model}' does not support function calling. Please us
• Add requires at least one of User ID, Agent ID, Run ID, or A
• Provide text or metadata to update
• Mem0 memory event ${eventId} failed: ${reason}

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/d21565eb035224f2. Report an issue: GitHub.