anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 02:05:26 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

opencode zen models tool calls are not parsed correctly mid conversation #2355

New Issue
Closed
opened 2026-02-16 17:35:17 -05:00 by yindo · 11 comments
yindo commented 2026-02-16 17:35:17 -05:00
Owner
Copy Link
Copy Source

Originally created by @tsah on GitHub (Oct 30, 2025).

Originally assigned to: @rekram1-node on GitHub.

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

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

Screenshot and/or share link

Image

Operating System

Arch

Terminal

Ghostty + tmux

Originally created by @tsah on GitHub (Oct 30, 2025). Originally assigned to: @rekram1-node on GitHub. ### 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 1. started conversation in plan mode with sonnet 4.5 (anthropic api key) 2. switched to build mode with kimi k2 (zen) 3. Got weird output that looks to me like tool calls that are not parsed correctly ### Screenshot and/or share link <img width="1761" height="607" alt="Image" src="https://github.com/user-attachments/assets/8bb0bcda-b478-4670-baa9-5b6d15b8a7f7" /> ### Operating System Arch ### Terminal Ghostty + tmux
yindo added the bug label 2026-02-16 17:35:17 -05:00
yindo closed this issue 2026-02-16 17:35:17 -05:00
yindo commented 2026-02-16 17:35:17 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Oct 30, 2025):

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

  • #3035: Model switching between reasoning and non-reasoning models causing tool call issues
  • #1021: Tool Calls Section End Token parsing failures with various models
  • #1018: Failed tool calls when using Groq + Kimi K2 (closed but similar)
  • #2903: GLM-4.6 model losing tool use capability (closed but similar pattern)
  • #1522: Kimi K2 stopping mid-chat issues

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

@github-actions[bot] commented on GitHub (Oct 30, 2025): This issue might be a duplicate of existing issues. Please check: - #3035: Model switching between reasoning and non-reasoning models causing tool call issues - #1021: Tool Calls Section End Token parsing failures with various models - #1018: Failed tool calls when using Groq + Kimi K2 (closed but similar) - #2903: GLM-4.6 model losing tool use capability (closed but similar pattern) - #1522: Kimi K2 stopping mid-chat issues Feel free to ignore if none of these address your specific case.
yindo commented 2026-02-16 17:35:17 -05:00
Author
Owner
Copy Link
Copy Source

@tsah commented on GitHub (Oct 30, 2025):

Yeah looks like a duplicate of 1021

@tsah commented on GitHub (Oct 30, 2025): Yeah looks like a duplicate of 1021
yindo commented 2026-02-16 17:35:17 -05:00
Author
Owner
Copy Link
Copy Source

@tsah commented on GitHub (Oct 30, 2025):

Addition: when switching back to anthropic the problem disappears

@tsah commented on GitHub (Oct 30, 2025): Addition: when switching back to anthropic the problem disappears
yindo commented 2026-02-16 17:35:17 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 30, 2025):

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 commented on GitHub (Oct 30, 2025): 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
yindo commented 2026-02-16 17:35:18 -05:00
Author
Owner
Copy Link
Copy Source

@Adictya commented on GitHub (Dec 5, 2025):

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

Image
@Adictya commented on GitHub (Dec 5, 2025): This happens consistently with kimi k2 thinking. Is there any recommended way to work around it? @rekram1-node <img width="2540" height="774" alt="Image" src="https://github.com/user-attachments/assets/b909d36c-1347-4ea1-9187-279c6bb4d9e0" />
yindo commented 2026-02-16 17:35:18 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 9, 2025):

This should be fixed in next release:
https://github.com/sst/opencode/commit/df64612d540a86d44e12c7f1c516b8ab62a28b65

@rekram1-node commented on GitHub (Dec 9, 2025): This should be fixed in next release: https://github.com/sst/opencode/commit/df64612d540a86d44e12c7f1c516b8ab62a28b65
yindo commented 2026-02-16 17:35:18 -05:00
Author
Owner
Copy Link
Copy Source

@DamianPereira commented on GitHub (Dec 12, 2025):

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

Image
@DamianPereira commented on GitHub (Dec 12, 2025): I tried 1.0.150 and it's still happening. Not sure if it's happening less or not. <img width="2059" height="91" alt="Image" src="https://github.com/user-attachments/assets/215ff329-144e-4dea-9b35-129b4c8d1383" />
yindo commented 2026-02-16 17:35:18 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 12, 2025):

@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.

@rekram1-node commented on GitHub (Dec 12, 2025): @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.
yindo commented 2026-02-16 17:35:18 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 12, 2025):

I'll update once it has been addressed!

@rekram1-node commented on GitHub (Dec 12, 2025): I'll update once it has been addressed!
yindo commented 2026-02-16 17:35:18 -05:00
Author
Owner
Copy Link
Copy Source

@DamianPereira commented on GitHub (Dec 12, 2025):

Thanks a lot for the fix and quick answer.

@DamianPereira commented on GitHub (Dec 12, 2025): Thanks a lot for the fix and quick answer.
yindo commented 2026-02-16 17:35:18 -05:00
Author
Owner
Copy Link
Copy Source

@Adictya commented on GitHub (Dec 12, 2025):

can confirm the fix is working beautifully, thanks 👍🏻

@Adictya commented on GitHub (Dec 12, 2025): can confirm the fix is working beautifully, thanks 👍🏻
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
acp
bad
bug
discussion
docs
documentation
enhancement
extension
good first issue
growth
help-wanted
mcp
model-problem
needs:compliance
nix
opentui
perf
pull-request
Mirrored from GitHub Pull Request
 tui
web
windows
zen
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#2355
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?