mirror of
https://github.com/Significant-Gravitas/AutoGPT.git
synced 2026-02-10 23:05:17 -05:00
017a00af46
## Summary
Enables Anthropic's extended thinking feature for Claude models in
CoPilot via OpenRouter. This keeps the model's chain-of-thought
reasoning internal rather than outputting it to users.
## Problem
The CoPilot prompt was designed for a thinking agent (with
`<internal_reasoning>` tags), but extended thinking wasn't enabled on
the API side. This caused the model to output its reasoning as regular
text, leaking internal analysis to users.
## Solution
Added thinking configuration to the OpenRouter `extra_body` for
Anthropic models:
```python
extra_body["provider"] = {
"anthropic": {
"thinking": {
"type": "enabled",
"budget_tokens": config.thinking_budget_tokens,
}
}
}
```
## Configuration
New settings in `ChatConfig`:
| Setting | Default | Description |
|---------|---------|-------------|
| `thinking_enabled` | `True` | Enable extended thinking for Claude
models |
| `thinking_budget_tokens` | `10000` | Token budget for thinking
(1000-100000) |
## Changes
- `config.py`: Added `thinking_enabled` and `thinking_budget_tokens`
settings
- `service.py`: Added thinking config to all 3 places where `extra_body`
is built for LLM calls
## Testing
- Verify CoPilot responses no longer include internal reasoning text
- Check that Claude's extended thinking is working (should see thinking
tokens in usage)
- Confirm non-Anthropic models are unaffected
## Related
Discussion:
https://discord.com/channels/1126875755960336515/1126875756925046928/1470779843552612607
---------
Co-authored-by: Swifty <craigswift13@gmail.com>