vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 19:10:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(ollama): forward think:false for qwen3 chat requests (#69967)

Browse Source 
Forward top-level Ollama think flags on native /api/chat requests so --thinking off sends think:false.\n\nThanks @WZH8898.
This commit is contained in:
Zihao WAN
2026-04-22 06:49:16 +02:00
committed by GitHub
parent 276c00015c
commit d4f91a354e
4 changed files with 114 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/providers/ollama.md
View File

@@ -463,6 +463,8 @@ 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`.
<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.
</Tip>