feat: add Avian as an LLM provider

[avianion]

Features

Add Avian as an OpenAI-compatible LLM provider. Avian provides access to multiple frontier models through a unified API endpoint at https://api.avian.io/v1 with Bearer token authentication (AVIAN_API_KEY).

Supported Models

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

• metagpt/configs/llm_config.py: Add LLMType.AVIAN enum value
• metagpt/provider/openai_api.py: Register LLMType.AVIAN with OpenAILLM (standard OpenAI-compatible provider)
• metagpt/utils/token_counter.py: Add token costs (TOKEN_COSTS) and context lengths (TOKEN_MAX) for all Avian models
• config/examples/avian-deepseek-v3.2.yaml: Example configuration file
• tests/metagpt/provider/mock_llm_config.py: Add mock config for Avian
• tests/metagpt/provider/test_avian_api.py: Unit tests (provider registration, client config, mock completions)

Usage

# config/config2.yaml
llm:
  api_type: "avian"
  base_url: "https://api.avian.io/v1"
  api_key: "YOUR_AVIAN_API_KEY"
  model: "deepseek/deepseek-v3.2"

This follows the same pattern as other OpenAI-compatible providers (DeepSeek, SiliconFlow, OpenRouter, Llama API, etc.) — no new dependencies required.

cc @garylin2099 @better629

[avianion]

Friendly follow-up — this PR is still active and ready for review. Would appreciate a look when you get a chance! cc @geekan @better629

[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 @better629

[avianion]

Hey @geekan @garylin2099 — 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!

[avianion]

Addressed feedback: updated cost tracking to use CostManager, added to LLMType enum

[avianion]

Hi — this PR is approved and the most recent CI run passes. The older failed run appears to be a stale timeout (720 hours). Could a maintainer merge or re-run the stale check to clear it? Thanks!

[avianion]

Pushed empty commit to retrigger CI and clear stale check.