diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json index 03ec136c5..ee866c45e 100644 --- a/.openclaw-sync/source.json +++ b/.openclaw-sync/source.json @@ -1,5 +1,5 @@ { "repository": "openclaw/openclaw", - "sha": "56a9fd4b34a47e2f91318111fec5e622ac9f81bd", - "syncedAt": "2026-04-16T20:20:21.423Z" + "sha": "a2753e2d9fa66ab7b9fb80b968264437d9e8c894", + "syncedAt": "2026-04-17T00:29:01.323Z" } diff --git a/docs/tools/thinking.md b/docs/tools/thinking.md index 3fc3c06ae..91c3359f5 100644 --- a/docs/tools/thinking.md +++ b/docs/tools/thinking.md @@ -15,12 +15,14 @@ title: "Thinking Levels" - low → “think hard” - medium → “think harder” - high → “ultrathink” (max budget) - - xhigh → “ultrathink+” (GPT-5.2 + Codex models only) - - adaptive → provider-managed adaptive reasoning budget (supported for Anthropic Claude 4.6 model family) + - xhigh → “ultrathink+” (GPT-5.2 + Codex models and Anthropic Claude Opus 4.7 effort) + - adaptive → provider-managed adaptive thinking (supported for Anthropic Claude 4.6 and Opus 4.7) - `x-high`, `x_high`, `extra-high`, `extra high`, and `extra_high` map to `xhigh`. - `highest`, `max` map to `high`. - Provider notes: - Anthropic Claude 4.6 models default to `adaptive` when no explicit thinking level is set. + - Anthropic Claude Opus 4.7 does not default to adaptive thinking. Its API effort default remains provider-owned unless you explicitly set a thinking level. + - Anthropic Claude Opus 4.7 maps `/think xhigh` to adaptive thinking plus `output_config.effort: "xhigh"`, because `/think` is a thinking directive and `xhigh` is the Opus 4.7 effort setting. - 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`). - Moonshot (`moonshot/*`) maps `/think off` to `thinking: { type: "disabled" }` and any non-`off` level to `thinking: { type: "enabled" }`. When thinking is enabled, Moonshot only accepts `tool_choice` `auto|none`; OpenClaw normalizes incompatible values to `auto`. @@ -31,7 +33,7 @@ title: "Thinking Levels" 2. Session override (set by sending a directive-only message). 3. Per-agent default (`agents.list[].thinkingDefault` in config). 4. Global default (`agents.defaults.thinkingDefault` in config). -5. Fallback: `adaptive` for Anthropic Claude 4.6 models, `low` for other reasoning-capable models, `off` otherwise. +5. Fallback: `adaptive` for Anthropic Claude 4.6 models, `off` for Anthropic Claude Opus 4.7 unless explicitly configured, `low` for other reasoning-capable models, `off` otherwise. ## Setting a session default @@ -104,8 +106,9 @@ title: "Thinking Levels" - The web chat thinking selector mirrors the session's stored level from the inbound session store/config when the page loads. - Picking another level writes the session override immediately via `sessions.patch`; it does not wait for the next send and it is not a one-shot `thinkingOnce` override. -- The first option is always `Default ()`, where the resolved default comes from the active session model: `adaptive` for Claude 4.6 on Anthropic/Bedrock, `low` for other reasoning-capable models, `off` otherwise. +- The first option is always `Default ()`, where the resolved default comes from the active session model: `adaptive` for Claude 4.6 on Anthropic, `off` for Anthropic Claude Opus 4.7 unless configured, `low` for other reasoning-capable models, `off` otherwise. - The picker stays provider-aware: - most providers show `off | minimal | low | medium | high | adaptive` + - Anthropic Claude Opus 4.7 shows `off | minimal | low | medium | high | xhigh | adaptive` - Z.AI shows binary `off | on` - `/think:` still works and updates the same stored session level, so chat directives and the picker stay in sync.