vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 10:40:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(ollama): expose native thinking efforts

Browse Source
This commit is contained in:
Peter Steinberger
2026-04-26 22:49:06 +01:00
parent 2cd23957c0
commit ff570f3a61
7 changed files with 107 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/providers/ollama.md
View File

@@ -461,7 +461,7 @@ For the full setup and behavior details, see [Ollama Web Search](/tools/ollama-s
<Accordion title="Streaming configuration">
OpenClaw's Ollama integration uses the **native Ollama API** (`/api/chat`) by default, which fully supports streaming and tool calling simultaneously. No special configuration is needed.
For native `/api/chat` requests, OpenClaw also forwards thinking control directly to Ollama: `/think off` and `openclaw agent --thinking off` send top-level `think: false`, while non-`off` thinking levels send `think: true`.
For native `/api/chat` requests, OpenClaw also forwards thinking control directly to Ollama: `/think off` and `openclaw agent --thinking off` send top-level `think: false`, while `/think low|medium|high` send the matching top-level `think` effort string. `/think max` maps to Ollama's highest native effort, `think: "high"`.
<Tip>
If you need to use the OpenAI-compatible endpoint, see the "Legacy OpenAI-compatible mode" section above. Streaming and tool calling may not work simultaneously in that mode.

3
docs/tools/thinking.md
View File

@@ -15,7 +15,7 @@ title: "Thinking levels"
- high → “ultrathink” (max budget)
- xhigh → “ultrathink+” (GPT-5.2+ and Codex models, plus Anthropic Claude Opus 4.7 effort)
- adaptive → provider-managed adaptive thinking (supported for Claude 4.6 on Anthropic/Bedrock, Anthropic Claude Opus 4.7, and Google Gemini dynamic thinking)
- max → provider max reasoning (currently Anthropic Claude Opus 4.7)
- max → provider max reasoning (Anthropic Claude Opus 4.7; Ollama maps this to its highest native `think` effort)
- `x-high`, `x_high`, `extra-high`, `extra high`, and `extra_high` map to `xhigh`.
- `highest` maps to `high`.
- Provider notes:
@@ -26,6 +26,7 @@ title: "Thinking levels"
- 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.
- 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.
- 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.