valknar/llmx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Support changing reasoning effort (#2435)

Browse Source 
https://github.com/user-attachments/assets/50198ee8-5915-47a3-bb71-69af65add1ef

Building up on #2431 #2428
This commit is contained in:
Ahmed Ibrahim
2025-08-19 10:55:07 -07:00
committed by GitHub
parent 8f544153a7
commit e91c3d6d1c
16 changed files with 428 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
codex-rs/config.md
View File

@@ -217,17 +217,14 @@ Users can specify config values at multiple levels. Order of precedence is as fo
## model_reasoning_effort
If the model name starts with `"o"` (as in `"o3"` or `"o4-mini"`) or `"codex"`, reasoning is enabled by default when using the Responses API. As explained in the [OpenAI Platform documentation](https://platform.openai.com/docs/guides/reasoning?api-mode=responses#get-started-with-reasoning), this can be set to:
If the selected model is known to support reasoning (for example: `o3`, `o4-mini`, `codex-*`, `gpt-5`), reasoning is enabled by default when using the Responses API. As explained in the [OpenAI Platform documentation](https://platform.openai.com/docs/guides/reasoning?api-mode=responses#get-started-with-reasoning), this can be set to:
- `"minimal"`
- `"low"`
- `"medium"` (default)
- `"high"`
To disable reasoning, set `model_reasoning_effort` to `"none"` in your config:
```toml
model_reasoning_effort = "none" # disable reasoning
```
Note: to minimize reasoning, choose `"minimal"`.
## model_reasoning_summary