feat: add Avian as a new LLM provider

[avianion]

Summary

• Adds Avian as a new LLM provider for bolt.diy
• Avian provides fast inference for top open-source models via an OpenAI-compatible API at api.avian.io/v1
• Uses @ai-sdk/openai with custom baseURL (no new dependencies)
• Supports both static model list and dynamic model discovery via /v1/models

Available Models

Model	Context
DeepSeek V3.2	164K
Kimi K2.5	131K
GLM-5	131K
MiniMax M2.5	131K

Changes

• app/lib/modules/llm/providers/avian.ts — New provider class extending BaseProvider, follows the Moonshot pattern
• app/lib/modules/llm/registry.ts — Import and export AvianProvider
• .env.example — Add AVIAN_API_KEY entry

Test plan

• Provider appears in the model selector UI
• API key can be entered in provider settings
• Static models are listed correctly
• Dynamic model fetching works with a valid API key
• Chat completions work with each model

[avianion]

Hey @Stijnus — just following up on this PR. It adds Avian as a new LLM provider following the same pattern as the Cerebras + Fireworks PR (#2113).

Only 3 files changed:

• New AvianProvider class extending BaseProvider (uses @ai-sdk/openai, no new deps)
• Registry export (2 lines)
• .env.example entry

CI is green and it's mergeable. Would appreciate a review when you get a chance!

[avianion]

Friendly follow-up — this PR is still active and ready for review. Would appreciate a look when you get a chance! cc @Stijnus

[avianion]

Friendly follow-up — this PR is still active and ready for review. All feedback has been addressed. Would appreciate a look when you get a chance! cc @Stijnus

[avianion]

Hey @thecodacus @dustinwloring1988 — friendly follow-up on this PR. Avian is an OpenAI-compatible inference provider that's already live and powering apps like ISEKAI ZERO. This is a lightweight integration (standard OpenAI-compatible endpoint) and we're happy to address any feedback or make adjustments. Would love to get this merged if you have a moment to review. Thanks!