# Forcing a Final Answer — Agent Loops, Stop Conditions and Token Budgets

Source: https://www.geekswithgeeks.com/en/agent-loops/end-forced-final

> Use a last call with no tools to summarise progress when the budget runs out.

## A last call that cannot use tools

When a limit is reached mid-task, do not just raise an error. Reserve a small budget for one **wrap-up call** with tools disabled, and ask the model to summarise what it did, what it found and what remains. The user gets something useful instead of silence.

## Stop with something useful

When a limit is hit, the best loops still return a partial result, save state and say what happened.

![Three parts of a good ending: result, state, explanation.](assets/figures/agent-loops/section-6-map.svg) — Figure 6.1 — Partial result, saved state and explanation.

## The wrap-up call

Omitting `tools` means the model can only write text. Keep the wrap-up request short and its `max_tokens` modest.

```python
def wrap_up(messages, reason):
    messages.append({"role": "user", "content":
        f"Stopping because: {reason}. Do not call tools. Summarise what you "
        "completed, what you found, and what still needs to be done."})
    reply = client.messages.create(model=MODEL, max_tokens=800, messages=messages)
    return final_text(reply)
```

## Reserve the budget first

Stop the main loop slightly before the hard limit (say at 90%) so the wrap-up call has room to run. A wrap-up that itself exceeds the budget defeats its purpose.

**Quiz:** Why disable tools in the wrap-up call?

- [x] So the model writes a summary instead of starting more work
- [ ] Tools cannot be used twice
- [ ] It makes the call free
- [ ] Tools break summaries

*Answer:* So the model writes a summary instead of starting more work. Without tools the only possible output is the final text.