docs: Update reasoning settings documentation for accepts_settings and --no-check-model-accepts-settings

This commit is contained in:
Paul Gauthier (aider) 2025-03-18 17:45:06 -07:00
parent e11c32bca5
commit 31e1604d99

View file

@ -24,16 +24,27 @@ You can use the `--thinking-tokens` switch to request
the model use a certain number of thinking tokens. the model use a certain number of thinking tokens.
This switch is useful for Sonnet 3.7. This switch is useful for Sonnet 3.7.
### Model compatibility warnings ### Model compatibility and settings
Not all models support these settings. Aider will warn you when you use a setting that may not be supported by your chosen model: Not all models support these settings. Aider uses the model's metadata to determine which settings each model accepts:
``` ```yaml
Warning: The model claude-3-sonnet@20240229 may not support the 'reasoning_effort' setting. - name: gpt-4o
Sending unsupported parameters can cause API calls to fail. Continue? [y/N] accepts_settings: ["reasoning_effort"]
``` ```
You can disable these warnings with the `--no-check-model-accepts-settings` flag. If you try to use a setting that a model doesn't explicitly support, Aider will warn you:
```
Warning: gpt-4o does not support 'thinking_tokens', ignoring.
Use --no-check-model-accepts-settings to force the 'thinking_tokens' setting.
```
The warning informs you that:
1. The setting won't be applied because the model doesn't list it in `accepts_settings`
2. You can use `--no-check-model-accepts-settings` to force the setting anyway
This functionality helps prevent API errors while still allowing you to experiment with settings when needed.
Each model has a predefined list of supported settings in its configuration. For example: Each model has a predefined list of supported settings in its configuration. For example: