feat: add Volcengine provider with configurable Ark models

[囍博士 (qkmaosjtu)]

Description

Adds Volcengine (Ark) as a provider and enables users to configure custom Ark model IDs from the UI, rather than hardcoding endpoints.

Related Issue

Fixes #

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation update
• Refactoring (no functional changes)

Checklist

• I have read the Contributing Guide
• I have tested my changes locally (npm run lint)
• My changes generate no new warnings
• Any dependent changes have been merged and published

Screenshots (if applicable)

Add screenshots to demonstrate UI changes.

Additional Notes

• Volcengine Ark model IDs are user-specific, so models are now stored as custom entries rather than hardcoded.
• Uses ARK_API_KEY and calls Ark via OpenAI-compatible Responses API.

[囍博士 (qkmaosjtu)]

Fixes #46

[囍博士 (qkmaosjtu)]

The screenshot shows the model selector: Volcengine appears in the provider list and is selected; the model panel says “No models available,” with actions for “Edit API Key” and “Add Model.”

Because Ark model IDs are typically random, we need to support custom model names.

[囍博士 (qkmaosjtu)]

align Volcengine icon color with provider list style

[Christian Bromann (christian-bromann)]

LGTM 👍

[Hunter Lovell (hntrl)]

Hey 囍博士 (@qkmaosjtu)! We're looking to keep the supported provider list for openwork pretty small at the moment since things are early. I think the pecking order will go (1) add support for openai/anthropic/google model proxies, then (2) add third party model providers on a case-by-case basis (or have some option to bring custom chat models). Closing this in lieu of that, but I'd encourage you to keep a close eye to model-related improvements coming in the near future and evaluate if that works for your needs.

[囍博士 (qkmaosjtu)]

Hey 囍博士 (@qkmaosjtu)! We're looking to keep the supported provider list for openwork pretty small at the moment since things are early. I think the pecking order will go (1) add support for openai/anthropic/google model proxies, then (2) add third party model providers on a case-by-case basis (or have some option to bring custom chat models). Closing this in lieu of that, but I'd encourage you to keep a close eye to model-related improvements coming in the near future and evaluate if that works for your needs.

Thanks for the clarification and the context! That makes sense given where things are today. I’ll keep iterating on some tools for my own needs and will keep an eye on upcoming model-related improvements — hopefully I’ll be able to contribute something back to the community down the line.