Skip to content

[Feature] openai_compatible provider: support enableThinking parameter for thinking-capable models (Qwen3, DeepSeek-R1) #2149

Closed

Description

@7889545

Pre-submission checklist

  • I have searched existing issues and this hasn't been mentioned before
  • I have read the project documentation and confirmed this issue doesn't already exist
  • This issue is specific to MemOS and not a general software issue

Problem

Models like Qwen3 and DeepSeek-R1 support an enable_thinking parameter to control whether the model produces <think> reasoning blocks. When thinking is enabled, output contains <think>... tags before the actual response — which breaks JSON parsing in tasks that require structured output (capture summarization, L3 abstraction, skill crystallization).

Currently, the openai_compatible provider (core/llm/providers/openai.ts) has no support for the enableThinking config option. The complete() and stream() methods build the request body without considering config.enableThinking.

PR #2079 addressed this for the qwen3 preference extractor specifically, but the provider layer itself still lacks the capability.

Use Case

Users need to configure different thinking modes per LLM instance:

llm:
  model: "Qwen/Qwen3-8B"
  enableThinking: false    # Main LLM: no thinking (JSON output tasks)

skillEvolver:
  model: "Qwen/Qwen3-8B`
  enableThinking: true     # Skill evolution: with thinking (reasoning tasks)

Without provider-level support, the enableThinking config is ignored and all models use the provider default.

Proposed Solution

Add enableThinking patch to both complete() and stream() methods in openai.ts:

// In complete() method, after building body:
if (config.enableThinking === false) body.enable_thinking = false;
if (config.enableThinking === true) body.enable_thinking = true;

// Same patch in stream() method

This is a minimal, non-breaking change — when enableThinking is undefined (not set), the body is unchanged, preserving backward compatibility.

Debug Logging

Optionally add debug logging to help diagnose thinking mode:

if (config.enableThinking !== undefined) {
    log.info("enableThinking.debug", {
        model,
        enableThinking: config.enableThinking,
        bodyEnableThinking: body.enable_thinking,
    });
}

Alternatives Considered

The provider-level approach is complementary to per-task routing — both can coexist.

Environment

  • MemOS: v2.0.20 (memos-local-plugin)
  • LLM Provider: openai_compatible (SiliconFlow)
  • Model: Qwen/Qwen3-8B (supports enable_thinking parameter)

Activity

  1. added
    status:readyReady for implementation; waiting for assignee or AI dispatch | 可进入实现,等待认领或派发
    types:enhancementNew feature or improvement | 新功能或改进
    on Jul 23, 2026
  2. added a commit that references this issue on Aug 13, 2026
    616e744
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Labels

area:pluginOpenClaw & Hermesstatus:readyReady for implementation; waiting for assignee or AI dispatch | 可进入实现,等待认领或派发types:enhancementNew feature or improvement | 新功能或改进

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions