We don't publish
your competitive advantage.

IFWhen using hierarchical process with crewAI, the manager LLM (especially gpt-4o-mini) may pass a dictionary object instead of a plain string for the 'task' or 'context' parameters in the Delegate work to coworker tool, causing Pydantic validation error: 'Input should be a valid string'.

THENTo mitigate, ensure that task and context are provided as plain strings. Consider updating the tool's input schema to accept both string and dict using Union[str, dict] with a custom validator to coerce dict values into string. Alternatively, use a more capable model like gpt-4o that is less prone to this behavior. Also verify that task descriptions in YAML configuration are simple strings, not objects.

IFDelegateWorkToolSchema validation fails because the manager LLM passes dictionary objects instead of plain strings for the 'task' and 'context' parameters when delegating tasks in a CrewAI hierarchical process.

THENUse a more capable LLM (e.g., gpt-4o instead of gpt-4o-mini) as the manager model. Configure the manager_llm parameter in the Crew object with a model known to produce correct string arguments, for example: ChatOpenAI(model_name='gpt-4o').