Error Writing Large Files (at least with Kimi K2.5) #10967

Activity

1. marcoschwartz

   added

   bugSomething isn't workingSomething isn't working

   on Jan 28, 2026
2. github-actions

   assigned

   rekram1-node

   on Jan 28, 2026
3. github-actions commented on Jan 28, 2026

   

   github-actionsBot

   on Jan 28, 2026 – with GitHub Actions

   Contributor

   More actions

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

   • Qwen3 Coder on OpenCode Zen: Tool call metadata being printed to chat instead of actually being called #10855: Qwen3 Coder on OpenCode Zen: Tool call metadata being printed to chat instead of actually being called (similar tool execution failures with specific models)
   • Added Kimi API key invocation and the new model Kimi-k2.5 #10850: Added Kimi API key invocation and the new model Kimi-k2.5 (existing issues with the Kimi K2.5 model)
   • Google Models cannot call tools anymore #10953: Google Models cannot call tools anymore (broader pattern of tool calling failures across models)
   • Add metadata awareness and data type validation/blacklists for LLM tool execution #10820: Add metadata awareness and data type validation/blacklists for LLM tool execution (addresses root cause of data type validation issues)

   Feel free to ignore if none of these address your specific case.
4. ideallove commented on Jan 28, 2026

   

   ideallove

   on Jan 28, 2026

   Contributor

   More actions

   I also encountered the same issue. I was working on Agent Skill yesterday and today. Yesterday it was completely correct, but today it failed.
   The SKILL I was using involved generating JSON, HTML, and escape characters, and the same problem occurred with the write component.
   I was using the Windows platform, with LLM being Claude Opus 4.5 and Minimax M2.1.
   Just now, I removed OpenCode and Desktop for version 1.1.39. After reverting to version 1.1.36, there were no abnormalities.

   Therefore, the temporary solution is to revert to version 1.1.36.
   I am currently attempting to analyze and review the updates from 1.1.37 to 1.1.39.
   Thank you to the developers for their work.

   👍React with 👍2Reacted by Yifan Xiong and Chindriș Mihai - Alexandru
5. ideallove commented on Jan 28, 2026

   

   ideallove

   on Jan 28, 2026

   Contributor

   More actions

   @marcoschwartz I have fixed the problem I encountered. Maybe your problem has also been resolved.

   ❤️React with ❤️2Reacted by maxcurrent420 and Chindriș Mihai - Alexandru
6. Mithrillion commented on Jan 28, 2026

   

   Mithrillion

   on Jan 28, 2026

   Last edited by Mithrillion

   More actions

   I think equally frustrating is that when you encounter this issue with Kimi K2.5, the agent just stops instead of retrying or continuing the task with a different approach, like in typical tool failures. And if it is in a subagent and the subagent fails, you often have to scrap the whole run, because you cannot simply ask it to continue.
7. ideallove commented on Jan 29, 2026

   

   ideallove

   on Jan 29, 2026

   Contributor

   More actions

   Why This Causes invalid Tool Errors?

   • Without maxOutputTokens: The AI SDK doesn't send a max_tokens parameter to the provider
   • Provider uses default limit: Many providers default to a low value (e.g., kimi K2.5 default 32768 from https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart)
   • Large tool calls get truncated: When writing files with substantial content, the JSON output exceeds the default limit
   • JSON becomes incomplete: Output is cut mid-string, e.g., {"content": "# -*- coding... (missing closing "})
   • Parse error occurs: JSON Parse error: Unterminated string
   • Fallback to invalid tool: The experimental_repairToolCall handler marks it as invalid

   It is more likely to trigger in the subagent. In conclusion, hardcoding will definitely cause problems.

   Apart from reverting to the previous version, adding a detection for JSON parsing might make the system more stable.
8. rekram1-node

   closed this as completedin #10995on Jan 29, 2026