Malformed thinking block in toolcall (glm-4.7-free)

[kevingatera]

Description

There seems to be a malformed tool call in the thinking block on the glm-4.7-free available via opencode zen. I understand it's in beta, but I wanted to report this just in case, since there was no feedback button within opencode. I had to re-ask but was confused on whether the chat was still ongoing because it had stopped but I re-asked the question again (see screenshots attached)

OpenCode version

1.0.191

Steps to reproduce

It's intermittent so I am not sure

Screenshot and/or share link

Operating System

linux (Nobara)

Terminal

N/A

[github-actions[bot]]

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

• #3596: SSE Stream Bug: Out-of-Order thinking_delta via LiteLLM → AWS Bedrock - similar malformed thinking block issues in streaming
• #3077: Expected thinking or redacted_thinking, but found tool_use - related thinking block ordering problems
• #3743: Loop in certain models - GLM models occasionally showing tool call malfunction issues
• #3444: GLM-4.6 model gets stuck in infinite loop - similar behavior with GLM models getting stuck on tool calls

Feel free to ignore if your specific case with glm-4.7-free differs from these issues.

[ramarivera]

+1ing this one, the "it seems to have stopped completely" thing happens both on Zen GLM 4.7 and Z.AI coding plan's

[rekram1-node]

glm-4.7-free was incorrectly not configured as an interleaved reasoning model.

This should be fixed if you do opencode models --refresh

Your cache will automatically refresh but this just forces it to so that you can have the fix sooner

[rekram1-node]

fix

[ramarivera]

oh this is really sad for me :( I was working on a PR to to detect and extract the tool call from inside the thinking block cuz I assumed it was a GLM issue that required normalization in packages/opencode/src/provider/transform.ts

Guess I should have asked first 😓

[ramarivera]

so, even with this fix, I still get tool calls in thinking blocks which causes the opencode workflow to stop e.g.

Thinking: <tool_call>bash<arg_key>command</arg_key><arg_value>cat packages/portal/.generation-cache.json | jq '."volume", "artifact", "generatedAt", "tokens" | select(.volume == "openspec") | .artifact | .generatedAt | .tokens' 2>/dev/null</arg_value><arg_key>description</arg_key><arg_value>Check cache for openspec artifacts</arg_value></tool_call>

EDIT: more examples

Thinking: <tool_call>use_skill<arg_key>skill</arg_key><arg_value>handoff</arg_value></tool_call>

[crystech]

so, even with this fix, I still get tool calls in thinking blocks which causes the opencode workflow to stop e.g.

Thinking: <tool_call>bash<arg_key>command</arg_key><arg_value>cat packages/portal/.generation-cache.json | jq '."volume", "artifact", "generatedAt", "tokens" | select(.volume == "openspec") | .artifact | .generatedAt | .tokens' 2>/dev/null</arg_value><arg_key>description</arg_key><arg_value>Check cache for openspec artifacts</arg_value></tool_call>

EDIT: more examples

Thinking: <tool_call>use_skill<arg_key>skill</arg_key><arg_value>handoff</arg_value></tool_call>

+1 here. same issues on GLM 4.7 local llm

[rekram1-node]

if u are still running into it it is entirely dependent on ir provider, if opencode is properly sending thinking chunks (the interleaved setting for model is correct) then it is on the provider of the model to properly parse the tool calls out and send them as such