dearwolf/aider
1
0
Fork 0
mirror of https://github.com/Aider-AI/aider.git synced 2025-06-12 15:45:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

docs: Update reasoning model compatibility and settings documentation

Browse source
This commit is contained in:
Paul Gauthier 2025-03-18 12:36:27 -07:00 • committed by Paul Gauthier (aider)
parent 7c10600044
commit 8d7300a522
1 changed files with 8 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

35
aider/website/docs/config/reasoning.md
View file

@ -26,7 +26,7 @@ This switch is useful for Sonnet 3.7.
### Model compatibility warnings
Not all models support both 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 will warn you when you use a setting that may not be supported by your chosen model:
```
Warning: The model claude-3-sonnet@20240229 may not support the 'reasoning_effort' setting.
@ -37,8 +37,8 @@ You can disable these warnings with the `--no-check-model-accepts-settings` flag
Each model has a predefined list of supported settings in its configuration. For example:
- OpenAI models generally support `reasoning_effort`
- Anthropic models (Claude) generally support `thinking_tokens`
- OpenAI reasoning models generally support `reasoning_effort`
- Anthropic reasoning models generally support `thinking_tokens`
## Thinking tokens in XML tags
@ -65,13 +65,6 @@ Aider will rely on the non-thinking output for instructions on how to make code
### Model-specific reasoning tags
Different models use different XML tags for their reasoning:
| Model | Reasoning Tag |
|-------|---------------|
| DeepSeek R1 | `think` |
| Deepseek V3 | `thinking` |
| Google Gemini | `reasoning` |
When using custom or self-hosted models, you may need to specify the appropriate reasoning tag in your configuration.
```yaml
@ -95,18 +88,6 @@ they sometimes prohibit streaming, use of temperature and/or the system prompt.
Aider is configured to work properly with these models
when served through major provider APIs.
### Model settings compatibility matrix
Here's a summary of common reasoning settings compatibility:
| Model Type | `reasoning_effort` | `thinking_tokens` | Notes |
|------------|-------------------|-------------------|-------|
| OpenAI reasoning models | ✅ | ❌ | Supports values 0-1 |
| Claude 3.7+ | ❌ | ✅ | Supports integer values |
| Claude 3.0-3.5 | ❌ | ❌ | Uses built-in reasoning |
| Google Gemini | ❌ | ❌ | Uses built-in reasoning |
| DeepSeek | ❌ | ❌ | Uses built-in reasoning |
If you're using a model through a different provider (like Azure or custom deployment),
you may need to [configure model settings](/docs/config/adv-model-settings.html)
if you see errors related to temperature or system prompt.
@ -135,6 +116,7 @@ for the model you are interested in, say o3-mini:
use_temperature: false # <---
editor_model_name: gpt-4o
editor_edit_format: editor-diff
accepts_settings: ["reasoning_effort"]
```
Pay attention to these settings, which must be set to `false`
@ -159,6 +141,7 @@ settings for a different provider.
use_temperature: false # <---
editor_model_name: azure/gpt-4o
editor_edit_format: editor-diff
accepts_settings: ["reasoning_effort"]
```
### Accepting settings configuration
@ -166,14 +149,12 @@ settings for a different provider.
Models define which reasoning settings they accept using the `accepts_settings` property:
```yaml
- name: gpt-4o
- name: a-fancy-reasoning-model
edit_format: diff
weak_model_name: gpt-4o-mini
use_repo_map: true
editor_model_name: gpt-4o
editor_edit_format: editor-diff
accepts_settings: # <---
- reasoning_effort # <---
```
This tells Aider that the model accepts the `reasoning_effort` setting but not `thinking_tokens`, which is why you'll get a warning if you try to use `--thinking-tokens` with this model.
This tells Aider that the model accepts the `reasoning_effort` setting but not `thinking_tokens`.
So you would get a warning if you try to use `--thinking-tokens` with this model.