From f7e5885b97cd88cbcbba20c981f2aefd5a0a242e Mon Sep 17 00:00:00 2001 From: "openclaw-docs-sync[bot]" Date: Mon, 27 Apr 2026 12:39:17 +0000 Subject: [PATCH] chore(sync): mirror docs from openclaw/openclaw@f3528e775584b34c67245d6eee9cbf5210c6677a --- .openclaw-sync/source.json | 4 ++-- docs/providers/openrouter.md | 14 +++++++------- docs/tools/thinking.md | 1 + 3 files changed, 10 insertions(+), 9 deletions(-) diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json index 44813a706..aeb78dd48 100644 --- a/.openclaw-sync/source.json +++ b/.openclaw-sync/source.json @@ -1,5 +1,5 @@ { "repository": "openclaw/openclaw", - "sha": "0931a1f11ea52a759ff81cf97345cf4ada7a2bc4", - "syncedAt": "2026-04-27T12:33:09.080Z" + "sha": "f3528e775584b34c67245d6eee9cbf5210c6677a", + "syncedAt": "2026-04-27T12:37:56.234Z" } diff --git a/docs/providers/openrouter.md b/docs/providers/openrouter.md index 8725c62b0..da030f663 100644 --- a/docs/providers/openrouter.md +++ b/docs/providers/openrouter.md @@ -53,12 +53,10 @@ available providers and models, see [/concepts/model-providers](/concepts/model- Bundled fallback examples: -| Model ref | Notes | -| ------------------------------------ | ----------------------------- | -| `openrouter/auto` | OpenRouter automatic routing | -| `openrouter/moonshotai/kimi-k2.6` | Kimi K2.6 via MoonshotAI | -| `openrouter/openrouter/healer-alpha` | OpenRouter Healer Alpha route | -| `openrouter/openrouter/hunter-alpha` | OpenRouter Hunter Alpha route | +| Model ref | Notes | +| --------------------------------- | ---------------------------- | +| `openrouter/auto` | OpenRouter automatic routing | +| `openrouter/moonshotai/kimi-k2.6` | Kimi K2.6 via MoonshotAI | ## Image generation @@ -136,7 +134,9 @@ does **not** inject those OpenRouter-specific headers or Anthropic cache markers On supported non-`auto` routes, OpenClaw maps the selected thinking level to OpenRouter proxy reasoning payloads. Unsupported model hints and - `openrouter/auto` skip that reasoning injection. + `openrouter/auto` skip that reasoning injection. Hunter Alpha also skips + proxy reasoning for stale configured model refs because OpenRouter could + return final answer text in reasoning fields for that retired route. diff --git a/docs/tools/thinking.md b/docs/tools/thinking.md index f733afc3f..a398f3f53 100644 --- a/docs/tools/thinking.md +++ b/docs/tools/thinking.md @@ -28,6 +28,7 @@ title: "Thinking levels" - Anthropic Claude Opus 4.7 also exposes `/think max`; it maps to the same provider-owned max effort path. - Ollama thinking-capable models expose `/think low|medium|high|max`; `max` maps to native `think: "high"` because Ollama's native API accepts `low`, `medium`, and `high` effort strings. - OpenAI GPT models map `/think` through model-specific Responses API effort support. `/think off` sends `reasoning.effort: "none"` only when the target model supports it; otherwise OpenClaw omits the disabled reasoning payload instead of sending an unsupported value. + - Stale configured OpenRouter Hunter Alpha refs skip proxy reasoning injection because that retired route could return final answer text through reasoning fields. - Google Gemini maps `/think adaptive` to Gemini's provider-owned dynamic thinking. Gemini 3 requests omit a fixed `thinkingLevel`, while Gemini 2.5 requests send `thinkingBudget: -1`; fixed levels still map to the closest Gemini `thinkingLevel` or budget for that model family. - MiniMax (`minimax/*`) on the Anthropic-compatible streaming path defaults to `thinking: { type: "disabled" }` unless you explicitly set thinking in model params or request params. This avoids leaked `reasoning_content` deltas from MiniMax's non-native Anthropic stream format. - Z.AI (`zai/*`) only supports binary thinking (`on`/`off`). Any non-`off` level is treated as `on` (mapped to `low`).