opencode zen models tool calls are not parsed correctly mid conversation

Description

Switching models mid conversation leads to tool calls not being parsed.

Happened to me today while switching from sonnet 4.5 to kimi k2, happened to me in the past with GLM and big pickle as well

OpenCode version

0.15.29

Steps to reproduce

started conversation in plan mode with sonnet 4.5 (anthropic api key)
switched to build mode with kimi k2 (zen)
Got weird output that looks to me like tool calls that are not parsed correctly

Screenshot and/or share link

Operating System

Arch

Terminal

Ghostty + tmux

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

Do not send reasoning traces and tool calls made during reasoning when switching from reasoning model to non reasoning model #3035: Model switching between reasoning and non-reasoning models causing tool call issues
Tool Calls Section End Token (<|tool_calls_section_end|>) Parsing Failures #1021: Tool Calls Section End Token parsing failures with various models
groq + kimi k2: Failed to call a function #1018: Failed tool calls when using Groq + Kimi K2 (closed but similar)
GLM-4.6 model fails to use web search tools after processing complex mathematical problems, and subsequently loses all tool use capability even when explicitly prompted. #2903: GLM-4.6 model losing tool use capability (closed but similar pattern)
Qwen3 as well as Kimi K2 keep stopping mid-chat #1522: Kimi K2 stopping mid-chat issues

Feel free to ignore if none of these address your specific case.

Yeah looks like a duplicate of 1021

Addition: when switching back to anthropic the problem disappears

this is just the model failing to call tools, it isnt calling them correctly, this can happen for many providers and models just happens more frequently with some than others

@rekram1-node

This happens consistently with kimi k2 thinking. Is there any recommended way to work around it? @rekram1-node

This should be fixed in next release:
df64612

I tried 1.0.150 and it's still happening. Not sure if it's happening less or not.

@DamianPereira

@DamianPereira yeah this is an upstream bug for us, our kimi k2 thinking provider (for zen) has a bug on their end, once they fix it this should resolve.

Basically if I enable proper interleaved thinking for kimi k2 thinking on their inference rn, it would loop infinitely (bug on their end), so rn I can't use interleaved thinking for it yet which is why sometimes it does dumb stuff like what you are seeing there.

I'll update once it has been addressed!

Thanks a lot for the fix and quick answer.

can confirm the fix is working beautifully, thanks 👍🏻

Navigation Menu

Repository navigation

opencode zen models tool calls are not parsed correctly mid conversation #3561

Description

OpenCode version

Steps to reproduce

Screenshot and/or share link

Operating System

Terminal

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

opencode zen models tool calls are not parsed correctly mid conversation #3561

Description

Description

OpenCode version

Steps to reproduce

Screenshot and/or share link

Operating System

Terminal

Activity

github-actions commented on Oct 30, 2025

tsah commented on Oct 30, 2025

tsah commented on Oct 30, 2025

rekram1-node commented on Oct 30, 2025

Adictya commented on Dec 5, 2025

rekram1-node commented on Dec 9, 2025

DamianPereira commented on Dec 12, 2025

rekram1-node commented on Dec 12, 2025

rekram1-node commented on Dec 12, 2025

DamianPereira commented on Dec 12, 2025

Adictya commented on Dec 13, 2025

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions