Skip to content

Commit c76a25e

Browse files
committed
docs: add effort setting to configuration reference
1 parent 6c133c1 commit c76a25e

1 file changed

Lines changed: 1 addition & 0 deletions

File tree

docs/configuration.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -73,6 +73,7 @@ The `config` object holds runtime behaviour options.
7373
| `model` | string \| null | provider default | Model ID to use. When absent, the provider's default is used (e.g. `claude-sonnet-4-6` for Anthropic, `gpt-4o` for OpenAI). |
7474
| `max_tokens` | integer \| null | 8192 | Maximum tokens per model response. |
7575
| `provider` | string \| null | `"anthropic"` | Active provider. See the [Providers](#providers) section. |
76+
| `effort` | string \| null | unset | Reasoning effort for new turns: `"none"`, `"minimal"`, `"low"`, `"medium"`, `"high"`, `"xhigh"`, `"max"`, or `"ultracode"`. When unset, no thinking-budget or temperature override is applied at all — this is not the same as `"medium"`, which has its own explicit values. |
7677

7778
### Permission mode
7879

0 commit comments

Comments
 (0)