feat: add Avian as an LLM provider

[avianion]

Summary

Adds Avian as a new LLM provider. Avian exposes an OpenAI-compatible API (https://api.avian.io/v1) and offers competitively priced frontier models.

Models added

Model	Context	Max Output	Input $/1M	Output $/1M
deepseek/deepseek-v3.2	164K	65K	$0.26	$0.38
moonshotai/kimi-k2.5	131K	8K	$0.45	$2.20
z-ai/glm-5	131K	16K	$0.30	$2.55
minimax/minimax-m2.5	1M	1M	$0.30	$1.10

Changes

• API route (app/api/chat/avian/route.ts): Uses the OpenAI SDK with baseURL: "https://api.avian.io/v1", same pattern as the Groq provider
• Model definitions (lib/models/llm/avian-llm-list.ts): 4 models with pricing info
• Type system (types/): AvianLLMID type, "avian" added to ModelProvider, AVIAN_API_KEY to env/key types
• Chat setting limits: Context length and max output for each model
• Icon (components/icons/avian-svg.tsx): SVG icon component for model selector
• Profile settings: API key input field in the settings panel
• Server helpers: AVIAN_API_KEY env var mapping for server-side configuration
• API keys route: Avian included in the env key availability check
• Supabase migration: Adds avian_api_key column to profiles table

Configuration

Users can configure Avian in two ways:

1. Per-user: Enter API key in Profile Settings > API Keys
2. Server-wide: Set AVIAN_API_KEY environment variable

Test plan

• Set AVIAN_API_KEY env var and verify Avian models appear in model selector
• Enter API key in profile settings and verify models appear
• Send a chat message using an Avian model and verify streaming response
• Verify model icon displays correctly in light and dark themes
• Run Supabase migration and verify avian_api_key column is created

cc @mckaywrigley

[avianion]

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

[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 @mckaywrigley

[avianion]

Hey @mckaywrigley — 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!