Vouch request: will-lms

[will-lms]

What do you want to work on?

I want to fix an issue with setting up LM Studio as a provider.

I am able to create an OpenAI provider that points to LM Studio

openshell provider create \
    --name lmstudio \
    --type openai \
    --credential OPENAI_API_KEY=lmstudio \
    --config OPENAI_BASE_URL=http://host.openshell.internal:1234/v1

But then

openshell inference set --provider lmstudio --model qwen-3.5-0.8b

fails with output

Error:   × failed to verify inference endpoint for provider 'lmstudio' and model 'qwen-3.5-0.8b' at 'http://host.openshell.internal:1234/v1': upstream returned unexpected HTTP 415 Unsupported Media Type. Response body: {"error":{"message":"Unsupported
  │ Media Type. POST requests must use 'application/json'","type":"invalid_request_error","code":"unsupported_media_type"}}. Next steps: confirm the endpoint URL, protocol, credentials, and model identifier, or retry with '--no-verify' if you
  │ want to skip verification

Looks like it should be as simple as adding the application/json header to the verification request.

Why this change?

I would like OpenShell to work great with LM Studio!

Checklist

• I wrote this request myself (not AI-generated)
• I have read CONTRIBUTING.md

[johntmyers]

/vouch

[github-actions[bot]]

@will-lms has been vouched by @johntmyers.

You can now submit pull requests to OpenShell. Welcome aboard.

Please read CONTRIBUTING.md before submitting.