Unable to generate files when using local Ollama #29996

Activity

1. github-actions

   assigned

   StarpTech

   on May 30, 2026
2. github-actions commented on May 30, 2026

   

   github-actionsBot

   on May 30, 2026 – with GitHub Actions

   Contributor

   More actions

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

   • Ollama (qwen2.5-coder): tool calls (edit/write) show as executed but no files are created/modified #7030: Ollama tool calls (edit/write) show as executed but no files are created/modified — same symptom of file operations not being applied to disk
   • local model keeps returning json and doesn't create any files #18454: Local model keeps returning JSON and doesn't create any files — same core problem with Ollama + local models
   • Opencode + Qwen gives JSON output instead of writing to disk #29757: OpenCode + Qwen gives JSON output instead of writing to disk — very similar issue with Ollama local provider and file generation

   These issues share the same root cause: local models via Ollama often lack reliable tool-calling support, causing write/edit tool calls to be printed as JSON in the chat instead of being executed. The behavior you're seeing is a known limitation with some local models that don't properly support the function/tool calling protocol required by OpenCode.
3. spitzerd commented on Jun 7, 2026

   

   spitzerd

   on Jun 7, 2026

   Last edited by spitzerd

   More actions

   Gemma4 and Gemini are closely related, see https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/
   In OpenCode, there is a lot of Gemini specific code. For example, there is a specific system prompt for Gemini, see https://github.com/anomalyco/opencode/blob/dev/packages/opencode/src/session/system.ts#L28

   I fixed the issue as follows:

   1. Create modelfile gemma4

   FROM gemma4:12b
   PARAMETER num_ctx 64000
   PARAMETER temperature 1.0
   PARAMETER top_k 64
   PARAMETER top_p 0.95
   

   2. Run ollama create gemini-gemma4:12b -f gemma4
   3. Run ollama launch opencode --model gemini-gemma4:12b

   My opencode.jsonc is empty.
   This way, OpenCode threats Gemma4 as Gemini model.
4. rekram1-node commented on Jun 23, 2026

   

   rekram1-node

   on Jun 23, 2026

   Contributor

   More actions

   Automated: closing question issues.

   GitHub Issues are for bug reports and feature requests only — questions / support are no longer tracked here.

   • For help & questions: https://discord.gg/opencode
   • Billing issues with Opencode Go / Zen: help@anoma.ly

   If this is a bug or feature request, please open a new issue with the appropriate template.
5. rekram1-node

   closed this as not plannedon Jun 23, 2026