ewilliams28/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-08-12 21:53:00 -06:00
Code Issues Packages Projects Releases Wiki Activity

fix(ollama): enable cloud max thinking (#121074)

Browse Source 
Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com>
This commit is contained in:
Vito Cappello
2026-08-10 22:06:54 -04:00
committed by GitHub
parent 498433a58a
commit 9320bd379e
10 changed files with 297 additions and 108 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/tools/thinking.md
+1 -1
View File
@@ -29,7 +29,7 @@ title: "Thinking levels"
- Anthropic Claude Opus 4.7+ also exposes `/think max`; it maps to the same provider-owned max effort path.
- Direct DeepSeek V4 models expose `/think xhigh|max`; both map to DeepSeek `reasoning_effort: "max"` while lower non-off levels map to `high`.
- OpenRouter-routed DeepSeek V4 models expose `/think xhigh` and send OpenRouter-supported `reasoning.effort` values instead of DeepSeek-native top-level `reasoning_effort`. Lower non-off levels map to `high`, and stored `max` overrides fall back to `xhigh`.
- 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.
- Ollama thinking-capable models expose `/think low|medium|high|max`. Verified full-effort Ollama Cloud families such as GLM 5.2 and DeepSeek V4 send each matching native `think` effort, including `max`; other models and local Ollama keep the compatible `high` mapping for `/think max`.
- 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.
- GPT-5.6 Sol and Terra expose native `/think ultra` through the Codex runtime. GPT-5.6 Luna exposes levels through `max` because its Codex catalog does not advertise Ultra.
- The embedded OpenClaw runtime exposes logical `/think ultra` for GPT-5.6 Sol, Terra, and Luna. It sends provider max effort and adds run-scoped proactive sub-agent orchestration guidance.