anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-24 03:09:48 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

The <tool_call> tag cannot be rendered correctly, results in the conversation being interrupted and failing to proceed automatically #6973

New Issue
Open
opened 2026-02-16 18:05:46 -05:00 by yindo · 9 comments
yindo commented 2026-02-16 18:05:46 -05:00
Owner
Copy Link
Copy Source

Originally created by @LeoNardo-LB on GitHub (Jan 20, 2026).

Originally assigned to: @rekram1-node on GitHub.

Description

I am currently using this integration in conjunction with the Oh My Open Code plugin.

After a long conversation session, there is a high probability that the tool_call tag will fail to render correctly. In such cases, content related to the tool_call tag will be displayed during the thinking phase or other processes, and the conversation will stop proceeding automatically at this point.

Based on the content within the tool_call tag—for instance, in the observed case—the tag is supposed to render a clickable response box for users to answer the questions posed by the model.

Once this issue occurs, subsequent normal conversations (e.g., inputting the keyword "Continue") will almost always result in repeated rendering failures. However, executing the /compact command has a chance of resolving this problem temporarily.

show the tool_call tag, but not been rendered correctly
Image
after compact, everything goon normalize
Image

Plugins

oh-my-opencode

OpenCode version

1.1.27

Steps to reproduce

No response

Screenshot and/or share link

Image Image

Operating System

Windows 11

Terminal

Powershell or anyone

Originally created by @LeoNardo-LB on GitHub (Jan 20, 2026). Originally assigned to: @rekram1-node on GitHub. ### Description I am currently using this integration in conjunction with the **Oh My Open Code** plugin. After a long conversation session, there is a high probability that the **`tool_call`** tag will **fail to render correctly**. In such cases, content related to the `tool_call` tag will be displayed during the thinking phase or other processes, and the conversation will **stop proceeding automatically at this point**. Based on the content within the `tool_call` tag—for instance, in the observed case—the tag is supposed to render a **clickable response box** for users to answer the questions posed by the model. Once this issue occurs, subsequent normal conversations (e.g., inputting the keyword "Continue") will almost always result in repeated rendering failures. However, executing the **`/compact`** command has a chance of resolving this problem temporarily. ##### show the tool_call tag, but not been rendered correctly <img width="1280" height="1390" alt="Image" src="https://github.com/user-attachments/assets/0dd31a33-0036-4acd-ab07-e593914f1fa9" /> ##### after compact, everything goon normalize <img width="1280" height="1390" alt="Image" src="https://github.com/user-attachments/assets/9c3b6d8c-336b-4527-9f63-87287cdcaf91" /> ### Plugins oh-my-opencode ### OpenCode version 1.1.27 ### Steps to reproduce _No response_ ### Screenshot and/or share link <img width="1280" height="1390" alt="Image" src="https://github.com/user-attachments/assets/0dd31a33-0036-4acd-ab07-e593914f1fa9" /> <img width="1280" height="1390" alt="Image" src="https://github.com/user-attachments/assets/9c3b6d8c-336b-4527-9f63-87287cdcaf91" /> ### Operating System Windows 11 ### Terminal Powershell or anyone
yindo added the windowsbug labels 2026-02-16 18:05:46 -05:00
yindo commented 2026-02-16 18:05:46 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Jan 20, 2026):

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

  • #8877: 当输出出现tool call的时候，对话被终止 (Tool call rendering breaks conversation) - This appears to be the same issue in Chinese, also mentions the Oh My OpenCode plugin and tool_call tag failures during long conversations

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

@github-actions[bot] commented on GitHub (Jan 20, 2026): This issue might be a duplicate of existing issues. Please check: - #8877: 当输出出现tool call的时候，对话被终止 (Tool call rendering breaks conversation) - This appears to be the same issue in Chinese, also mentions the Oh My OpenCode plugin and tool_call tag failures during long conversations Feel free to ignore if none of these address your specific case.
yindo commented 2026-02-16 18:05:46 -05:00
Author
Owner
Copy Link
Copy Source

@LeoNardo-LB commented on GitHub (Jan 20, 2026):

I believe this is a very serious issue with opencode. It will cause sisyphus to be unable to work continuously, and it can only rely on its retry mechanism to complete tasks with a certain probability in a certain retry, which will greatly affect efficiency.

@LeoNardo-LB commented on GitHub (Jan 20, 2026): I believe this is a very serious issue with opencode. It will cause sisyphus to be unable to work continuously, and it can only rely on its retry mechanism to complete tasks with a certain probability in a certain retry, which will greatly affect efficiency.
yindo commented 2026-02-16 18:05:46 -05:00
Author
Owner
Copy Link
Copy Source

@LeoNardo-LB commented on GitHub (Jan 20, 2026):

Screenshot_2026-01-21-04-24-26-745_com.oray.sunlogin.jpg
this is the tool call loop

@LeoNardo-LB commented on GitHub (Jan 20, 2026): ![Screenshot_2026-01-21-04-24-26-745_com.oray.sunlogin.jpg](https://github.com/user-attachments/assets/d6265a64-705f-4518-a4fc-b4df745f1daf) this is the tool call loop
yindo commented 2026-02-16 18:05:46 -05:00
Author
Owner
Copy Link
Copy Source

@bi-kai commented on GitHub (Jan 22, 2026):

same issue，with version 1.1.27

mark & forcus

@bi-kai commented on GitHub (Jan 22, 2026): same issue，with version 1.1.27 mark & forcus
yindo commented 2026-02-16 18:05:46 -05:00
Author
Owner
Copy Link
Copy Source

@ApocalypseYun commented on GitHub (Jan 27, 2026):

Is there any progress on this issue?

@ApocalypseYun commented on GitHub (Jan 27, 2026): Is there any progress on this issue?
yindo commented 2026-02-16 18:05:46 -05:00
Author
Owner
Copy Link
Copy Source

@LeoNardo-LB commented on GitHub (Jan 27, 2026):

@ApocalypseYun No, I asked AI to help analyze the code. The possible reason is that when the tool was called, the JSON that should have been returned was accidentally output in xml format, causing the loop interrupted.

The root cause might be that when the context is too large (exceeding 70% occupancy), after the context is filtered by the filtering function, only the xml tool call references remain, and the LLM uses this as a case to imitate the output.

After executing the /compact command, it can return to normal.

But I don't understand ts code very well, so I can't be sure if this is the reason.

@LeoNardo-LB commented on GitHub (Jan 27, 2026): @ApocalypseYun No, I asked AI to help analyze the code. The possible reason is that when the tool was called, the JSON that should have been returned was accidentally output in xml format, causing the loop interrupted. The root cause might be that when the context is too large (exceeding 70% occupancy), after the context is filtered by the filtering function, only the xml tool call references remain, and the LLM uses this as a case to imitate the output. After executing the /compact command, it can return to normal. But I don't understand ts code very well, so I can't be sure if this is the reason.
yindo commented 2026-02-16 18:05:46 -05:00
Author
Owner
Copy Link
Copy Source

@Mikec78660 commented on GitHub (Jan 31, 2026):

Seeing the same. It seems like it happens when the tool call is tried in thinking mode so it doesn't actually get executed. Some models seem to not have this issue but some like the Big-Pickle model seem to do it often. I have seen it with as little as 20% context used. I didn't used to see it so much. Not sure if a prompt got updated or needs to be updated to expressly state that tool calls shouldn't be executed in thinking mode.

@Mikec78660 commented on GitHub (Jan 31, 2026): Seeing the same. It seems like it happens when the tool call is tried in thinking mode so it doesn't actually get executed. Some models seem to not have this issue but some like the Big-Pickle model seem to do it often. I have seen it with as little as 20% context used. I didn't used to see it so much. Not sure if a prompt got updated or needs to be updated to expressly state that tool calls shouldn't be executed in thinking mode.
yindo commented 2026-02-16 18:05:46 -05:00
Author
Owner
Copy Link
Copy Source

@LeoNardo-LB commented on GitHub (Feb 2, 2026):

I discovered that there is a significant issue with the coding plan of glm, and it is quite serious. The problem disappears when the model is switched to kimi k2.5 free.

@LeoNardo-LB commented on GitHub (Feb 2, 2026): I discovered that there is a significant issue with the coding plan of glm, and it is quite serious. The problem disappears when the model is switched to kimi k2.5 free.
yindo commented 2026-02-16 18:05:46 -05:00
Author
Owner
Copy Link
Copy Source

@imbible commented on GitHub (Feb 2, 2026):

I have GLM4.7 & kimi k2.5 self-hosted through exo. Both have the same issue.

@imbible commented on GitHub (Feb 2, 2026): I have GLM4.7 & kimi k2.5 self-hosted through exo. Both have the same issue.
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 windows
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#6973
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?