feat(opencode): add local server provider with auto model discovery

[hmblair]

Closes #6231

Type of change

New feature

What it does

Adds a built-in local provider that automatically discovers models from any OpenAI-compatible /models endpoint. Configure a baseURL, and the provider fetches available models at startup — no manual model listing required.

Also fixes the CUSTOM_LOADERS loop to allow custom loaders that don't have a models.dev entry (previously they were silently skipped).

Why this approach

PR #17670 solves the same problem with 700+ lines across 3 files and a new dynamicModelList config flag. This PR does it in ~50 lines with no new config surface. The local provider is a first-class built-in: it hits /models, registers whatever it finds, and returns autoload: true. If the endpoint is unreachable or returns nothing useful, it silently returns autoload: false. Nothing new to learn, nothing to break.

How to use it

{
  "provider": {
    "local": {
      "options": {
        "baseURL": "http://localhost:11434/v1"
      }
    }
  }
}

With an API key (e.g. LM Studio):

{
  "provider": {
    "local": {
      "options": {
        "baseURL": "http://localhost:1234/v1",
        "apiKey": "lm-studio"
      }
    }
  }
}

Tests

Three tests covering successful discovery, unreachable endpoint, and missing baseURL.

[github-actions]

Hey! Your PR title Add local server provider with auto model discovery doesn't follow conventional commit format.

Please update it to start with one of:

• feat: or feat(scope): new feature
• fix: or fix(scope): bug fix
• docs: or docs(scope): documentation changes
• chore: or chore(scope): maintenance tasks
• refactor: or refactor(scope): code refactoring
• test: or test(scope): adding or updating tests

Where scope is the package name (e.g., app, desktop, opencode).

See CONTRIBUTING.md for details.

[github-actions]

The following comment was made by an LLM, it may be inaccurate:

I found a highly relevant duplicate PR:

Potential Duplicate:

• PR feat(opencode): dynamic model discovery for local providers (LM Studio, llama.cpp, etc.) #17670: "feat(opencode): dynamic model discovery for local providers (LM Studio, llama.cpp, etc.)"
  • feat(opencode): dynamic model discovery for local providers (LM Studio, llama.cpp, etc.) #17670

This PR appears to be addressing the exact same feature — dynamic model discovery for local providers including LM Studio and llama.cpp, which are the core use cases mentioned in PR #17688.

Related (but different scope):

• PR feat(opencode): add LiteLLM provider with auto model discovery #14468: "feat(opencode): add LiteLLM provider with auto model discovery"
  • feat(opencode): add LiteLLM provider with auto model discovery #14468
  • Also implements auto model discovery, but specifically for the LiteLLM provider rather than a generic local server provider

You should investigate PR #17670 to determine if it's already addressing this functionality or if there's overlap in approach.

[github-actions]

Thanks for updating your PR! It now meets our contributing guidelines. 👍

[github-actions]

This PR doesn't fully meet our contributing guidelines and PR template.

What needs to be fixed:

• PR description is missing required template sections. Please use the PR template.

Please edit this PR description to address the above within 2 hours, or it will be automatically closed.

If you believe this was flagged incorrectly, please let a maintainer know.

[github-actions]

This pull request has been automatically closed because it was not updated to meet our contributing guidelines within the 2-hour window.

Feel free to open a new pull request that follows our guidelines.