Skip to content

Commit 6cc8695

Browse files
committed
docs: note google effort ladders assert thinkingLevel support
1 parent c1f9561 commit 6cc8695

1 file changed

Lines changed: 1 addition & 1 deletion

File tree

  • docs-site/src/content/docs/reference/configuration

‎docs-site/src/content/docs/reference/configuration/providers.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -79,7 +79,7 @@ differing backup and rewrites known legacy namespaced selected ids to bare ids.
7979
| `codexAccountMode?` | `"pool" \| "direct"` | Canonical `openai` only; defaults to Pool. Direct bypasses pool state. |
8080
| `refreshPolicy?` | `"proactive" \| "lazy-only" \| "disabled"` | Override this OAuth provider's Token Guardian policy. |
8181
| `reasoningEfforts?` | `string[]` | Provider-wide Codex reasoning labels to advertise and send. |
82-
| `modelReasoningEfforts?` | `Record<string, string[]>` | Per-model labels. An empty list hides effort control. |
82+
| `modelReasoningEfforts?` | `Record<string, string[]>` | Per-model labels. An empty list hides effort control. For `google`-adapter providers a configured ladder is also a capability assertion: the selected effort is sent on the wire as `generationConfig.thinkingConfig.thinkingLevel` (except Cloud Code Assist and image-capable models), so only configure a ladder for models that accept that field. |
8383
| `modelSupportsReasoningSummaries?` | `Record<string, boolean>` | Set a model to `false` to stop advertising summaries and strip summary-delivery fields. |
8484
| `modelReasoningSummaryDelivery?` | `Record<string, "sequential" \| "sequential_cutoff" \| "concurrent" \| "concurrent_cutoff">` | Per-model Responses delivery enum; rewrites an existing delivery field. |
8585
| `modelAdapters?` | `Record<string, string>` | Per-model `openai-chat` or `openai-responses` wire override for mixed-wire gateways. Explicit entries beat registry defaults; DeepSeek's preset can select native Responses for `deepseek-v4-flash`, and GitHub Copilot declares Responses-only defaults for its GPT-5 family (`gpt-5.3-codex`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.5`, `gpt-5.6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`) because those models reject `/chat/completions` for agent traffic. Models without a built-in default (for example `gpt-5.4-nano`) can be opted in here. Single-wire upstream pins and canonical ChatGPT forward reject overrides. |

0 commit comments

Comments
 (0)