OpenCode Go config

[fonnesbeck]

📝 Summary

Adds OpenCode Go to the set of built-in AI model providers. Follows the template used by other providers.

Closes #9208

📋 Pre-Review Checklist

• For large changes, or changes that affect the public API: this change was discussed or approved through an issue, on Discord, or the community discussions (Please provide a link if applicable).
• Any AI generated code has been reviewed line-by-line by the human PR author, who stands by it.
• Video or media evidence is provided for any visual changes (optional).

✅ Merge Checklist

• I have read the contributor guidelines.
• Documentation has been updated where applicable, including docstrings for API changes.
• Tests have been added for the changes made.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
marimo-docs	Ready	Preview, Comment	May 1, 2026 2:31am

[github-actions]

Thank you for your submission, we really appreciate it. Like many open-source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution. You can sign the CLA by just posting a Pull Request Comment same as the below format.

---

I have read the CLA Document and I hereby sign the CLA

---

_{You can retrigger this bot by commenting recheck in this Pull Request. Posted by the CLA Assistant Lite bot.}

[cubic-dev-ai]

No issues found across 13 files

Architecture diagram

sequenceDiagram
    participant User as User (Browser)
    participant UI as Frontend (Marimo UI)
    participant Server as Marimo Server
    participant Info as LLM Info Package
    participant Env as OS Environment
    participant Provider as OpenCode Go API

    Note over User, UI: Configuration Phase
    User->>UI: Inputs API Key & Base URL
    UI->>UI: NEW: Validate via UserConfigSchema
    UI->>Server: Save configuration (opencode_go)
    Server->>Server: Update marimo/_config/config.py

    Note over User, Provider: Runtime LLM Request
    User->>UI: Selects OpenCode Go model (e.g. GLM 5.1)
    UI->>Server: Request AI Completion
    
    Server->>Info: NEW: Fetch model metadata (models.yml)
    Info-->>Server: Return roles (chat/edit) & thinking capability
    
    Server->>Server: NEW: AnyProviderConfig.for_opencode_go()
    
    alt UI Config exists
        Server->>Server: Use configured API Key & Base URL
    else UI Config missing
        Server->>Env: NEW: Check OPENCODE_API_KEY
        Env-->>Server: Return fallback key
    end

    alt No key found
        Server-->>UI: 400 Bad Request (Error detail)
    else Key resolved
        Server->>Provider: NEW: POST request (OpenAI-compatible)
        Note right of Provider: Default: https://opencode.ai/zen/go/v1/
        Provider-->>Server: Stream completion
        Server-->>UI: Return response to user
    end

Loading

[fonnesbeck]

I have read the CLA Document and I hereby sign the CLA