Bug: Z.AI Coding Plan models return empty responses

[claudianus]

Description

When using the Z.AI Coding Plan (zhipuai-coding-plan provider) with reasoning capabilities like GLM-5.1, the agent returns empty responses. This happens because the thinking configuration is not being applied to the zhipuai-coding-plan provider ID in the transform logic, causing the stream to fail or not output correctly for reasoning models.

Plugins

None

OpenCode version

1.4.3 (or 0.0.0-dev)

Steps to reproduce

1. Configure OpenCode to use the zhipuai-coding-plan provider.
2. Select a reasoning model like GLM-5.1.
3. Send a prompt to the agent.
4. Observe that the agent appears to respond but no text is output to the terminal.

Screenshot and/or share link

N/A

Operating System

Linux

Terminal

Fish (or generic terminal)

[github-actions]

This issue doesn't fully meet our contributing guidelines.

What needs to be fixed:

• No issue template was used. Please use one of the three required templates: Bug Report, Feature Request, or Question
• Missing required fields for a bug report: steps to reproduce, expected behavior, actual behavior, and environment/version info

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:

• GLM models excluded from reasoning variants — no way to toggle thinking at runtime #18598: GLM models excluded from reasoning variants — thinking configuration cannot be toggled at runtime
• [BUG] GLM-5 model pollutes context window with broken thinking output #16903: GLM-5 model pollutes context window with broken thinking output (thinking tokens not properly handled)
• Garbled output with z.ai models #20453: Garbled output with z.ai models

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

[github-actions]

Thanks for updating the issue! It now meets the contributing guidelines and has everything needed — a clear description, steps to reproduce, version info, and system details. The compliance flag has been removed.