Qwen3.7 Plus produces broken markdown output in agent mode

[yslicn]

Description

Environment:

• OpenCode Go
• Model: Qwen3.7 Plus
• Task type: long-form agent workflow

Problem:
When using Qwen3.7 Plus in agent mode, the output formatting becomes corrupted.

Symptoms:

• Markdown bullet lists are split into incomplete lines
• Sentences are truncated
• The response sometimes stops in the middle of a structured answer

Example:
Expected:

• Item 1
• Item 2
• Item 3

Actual:
•
是否需要为每个

•
模板生成更

•
详细的使用说明文档

The same workflow works normally with other models.

Possible cause:

• Streaming parser compatibility
• Markdown rendering issue
• Model response format handling

Please check Qwen3.7 Plus compatibility in OpenCode Go.

Plugins

No response

OpenCode version

No response

Steps to reproduce

No response

Screenshot and/or share link

No response

Operating System

No response

Terminal

No response

[github-actions]

This issue doesn't fully meet our contributing guidelines.

What needs to be fixed:

• OpenCode version is empty — please provide the exact version you are using
• Steps to reproduce is empty — please provide steps to reproduce the issue
• Operating System and Terminal are empty — this context helps narrow down the cause

Please edit this issue to address the above within 2 hours, or it will be automatically closed.

---

This issue might be a duplicate of existing issues. Please check:

• Streaming response truncates at backticks when using separate reasoning_content with LM Studio + Qwen3.5 #15774: Streaming response truncation with Qwen models — similar symptom of responses being cut off or corrupted mid-stream

If you believe this was flagged incorrectly, please let a maintainer know.

[github-actions]

This issue has been automatically closed because it was not updated to meet our contributing guidelines within the 2-hour window.

Feel free to open a new issue that follows our issue templates.