Agent code overwrites the LLM callbacks

[rakeshgohel01]

Issue

When I supplied callbacks directly to LLM object before passing to Agent constructor, the callbacks set by me were never called

Explanation

If an LLM is created with callbacks and assigned to agent, it gets overwritten in agent initialization when pydantic finishes validation.

code

@model_validator(mode="after")
def set_agent_executor(self) -> "Agent":
    """set agent executor is set."""
    if hasattr(self.llm, "model_name"):
        self.llm.callbacks = [ **//THIS OVERRIDES THE LLM CALLBACKS**
            TokenCalcHandler(self.llm.model_name, self._token_process)
        ]
    if not self.agent_executor:
        self.set_cache_handler(self.cache_handler)
    return self

Ideally it should append TokenCalcHandler to callbacks not assigned

[github-actions[bot]]

This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.

[github-actions[bot]]

This issue was closed because it has been stalled for 5 days with no activity.