# Checkpoints and Resume — Agent Loops, Stop Conditions and Token Budgets

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

> Save loop state after each step so a stopped or crashed run can continue.

## State you can reload

A long run will eventually hit a limit, a deploy or a crash. If you save the messages, the step counter and the budget used after every successful step, a new process can load them and continue, spending only what remains. Make tool actions **idempotent** (safe to run twice) where you can, because a resume may repeat the last step.

## Save and load

Writing to a temporary file and renaming it avoids a half-written checkpoint if the process dies mid-write.

```python
import json, os

def save(path, state):
    tmp = path + ".tmp"
    with open(tmp, "w") as f:
        json.dump(state, f)
    os.replace(tmp, path)          # atomic on the same filesystem

def load(path):
    with open(path) as f:
        return json.load(f)
```

**Quiz:** Why make tool actions idempotent when resuming is possible?

- [x] Resuming may repeat the last step
- [ ] Idempotent tools are faster
- [ ] The API requires it
- [ ] It avoids all errors

*Answer:* Resuming may repeat the last step. If the last step ran but was not recorded, a second run must not cause duplicate effects.