crewAIInc/crewAI · error · ValueError

Mind name is not set.

Error message

Mind name is not set.

What it means

AIMindTool._run() sends the query to the Minds API using self.mind_name as the model name. The constructor normally sets self.mind_name from the created mind (mind.name), so hitting this ValueError means the attribute is None at run time — typically because construction was bypassed, the attribute was overwritten, or object state was mutated/restored (e.g. pickling) without it.

Source

Thrown at lib/crewai-tools/src/crewai_tools/tools/ai_mind_tool/ai_mind_tool.py:91

            )
            datasources.append(config)

        name = f"{AIMindToolConstants.MIND_NAME_PREFIX}_{secrets.token_hex(5)}"

        mind = minds_client.minds.create(
            name=name, datasources=datasources, replace=True
        )

        self.mind_name = mind.name

    def _run(self, query: str) -> str | None:
        # The Minds API is OpenAI compatible and therefore, the OpenAI client can be used.
        openai_client = OpenAI(
            base_url=AIMindToolConstants.MINDS_API_BASE_URL, api_key=self.api_key
        )

        if self.mind_name is None:
            raise ValueError("Mind name is not set.")

        completion = openai_client.chat.completions.create(
            model=self.mind_name,
            messages=[{"role": "user", "content": query}],
            stream=False,
        )
        if not isinstance(completion, ChatCompletion):
            raise ValueError("Invalid response from AI-Mind")

        return completion.choices[0].message.content

View on GitHub (pinned to 754d7323be)

Solutions

1. Ensure the tool is created normally via AIMindTool(api_key=..., datasources=...) so __init__ completes mind creation and sets mind_name.
2. If state was mutated, re-set it: tool.mind_name = <name from Minds dashboard> before running.
3. Avoid serializing the tool instance; recreate it per run instead.
4. Check for swallowed exceptions during construction that leave the object half-initialized.

Example fix

# before
openai_client = OpenAI(...)
result = tool._run(query)  # mind_name is None

# after
assert tool.mind_name, "AIMindTool not fully initialized; recreate the tool"
result = tool._run(query)

def aimind_ready(tool) -> bool:
    return getattr(tool, "mind_name", None) is not None

def is_initialized_aimind(tool: object) -> bool:
    return bool(getattr(tool, "mind_name", None)) and bool(getattr(tool, "api_key", None))

try:
    result = tool._run(query)
except ValueError as e:
    if "Mind name is not set" in str(e):
        tool = AIMindTool(api_key=..., datasources=[...])  # re-create properly
        result = tool._run(query)
    else:
        raise

When it happens

Trigger: Calling tool._run(query) on an instance whose __init__ did not complete the mind-creation step (e.g. an exception swallowed after client creation); serializing/deserializing the tool without the attribute; manually setting tool.mind_name = None; subclass overrides skipping super().__init__.

Common situations: Deep-copying or caching tool instances; crew flows that rebuild tools from config and skip the constructor; tests constructing the object via __new__ or mocks.

Related errors

• Client is not initialized
• Failed to initialize MCP Adapter: {e}
• MCP server not started, run `mcp_server.start()` first befor
• max_bytes must be positive, got {max_bytes}.
• Invalid response from AI-Mind

AI-assisted analysis of crewAIInc/crewAI@754d7323be (2026-08-15). Data as JSON: /api/errors/f61ae31617922fe8. Report an issue: GitHub.