mirror of
https://github.com/langgenius/dify-official-plugins.git
synced 2026-07-21 17:45:23 -04:00
OpenAI-API-compatible plugin Qwen3 model does not take effect when the "enable_thinking" option is turned off #951
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @junjiem on GitHub (Jan 27, 2026).
Self Checks
Dify version
1.11.4
Plugin version
0.0.30, 0.0.31
Cloud or Self Hosted
Cloud, Self Hosted (Docker), Self Hosted (Source)
Steps to reproduce
The OpenAI-API-compatible plugin Qwen3 model does not take effect when the "enable_thinking" option is turned off; it still outputs the thinking content.
The "enable_thinking" parameter does not necessarily have to be included in the "chat_template_kwargs" parameter; it can be placed at the same level as other parameters.
✔️ Error log
No response
@dosubot[bot] commented on GitHub (Jan 27, 2026):
This is a known regression in plugin versions 0.0.28–0.0.31 for the Qwen3 model: disabling
enable_thinkingdoes not fully suppress thinking content, and you may still see<think></think>tags or empty reasoning blocks in the output. This happens because the plugin streams areasoning_contentfield with empty or newline content, which Dify renders as thinking blocks, regardless of the parameter's placement (inside or outsidechat_template_kwargs)—the code sets both for compatibility, but not all backends honor them the same way [source] [source] [source].Workarounds: filter out
<think>tags or empty reasoning blocks on the frontend, or patch the backend/plugin to suppress empty reasoning content before it reaches the UI. Settingreasoning_formattoseparatedin your workflow node may help, but does not fully resolve the issue in these plugin versions. Recent plugin updates (see PR #2151) add support forthinkingandthinking_modeparameters alongsideenable_thinking, which may improve compatibility for some models, but robust suppression still depends on backend support [source].For best results, check your model/provider documentation for the correct parameter(s) to use, and consider upgrading when a fix is released.
To reply, just mention @dosu.
How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other