feat: add Avian as an LLM provider

[avianion]

Summary

Adds AvianClient as a new LLM provider for the Avian API (https://api.avian.io/v1), an OpenAI-compatible inference service.

• Implements AvianClient in graphiti_core/llm_client/avian_client.py following the same patterns as OpenAIGenericClient
• Supports structured outputs (json_schema response format), retry logic, and tracing
• Registers 'avian' as a provider type for telemetry/tracing
• Adds comprehensive unit tests covering initialization, response generation, rate limiting, and retry behavior

Avian API Details

Model	Context (Input/Output)	Price (Input/Output per 1M tokens)
deepseek/deepseek-v3.2 (default)	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

Usage

from graphiti_core.llm_client.avian_client import AvianClient
from graphiti_core.llm_client.config import LLMConfig

# Using environment variable (AVIAN_API_KEY)
client = AvianClient()

# Or with explicit config
client = AvianClient(
    config=LLMConfig(
        api_key="your-api-key",
        model="deepseek/deepseek-v3.2",
    )
)

graphiti = Graphiti(
    uri,
    llm_client=client,
    embedder=embedder,
)

Files Changed

• graphiti_core/llm_client/avian_client.py — New AvianClient class
• graphiti_core/llm_client/__init__.py — Export AvianClient
• graphiti_core/llm_client/client.py — Register 'avian' in _get_provider_type()
• tests/llm_client/test_avian_client.py — Unit tests

Test Plan

• All ruff lint checks pass
• All ruff format checks pass
• Unit tests cover initialization, response generation, rate limiting, retries, and provider type detection
• CI unit tests pass

cc @danielchalef @prasmussen15

[danielchalef]

All contributors have signed the CLA ✍️ ✅
_{Posted by the CLA Assistant Lite bot.}

[avianion]

I have read the CLA Document and I hereby sign the CLA

[avianion]

Hey @prasmussen15 @danielchalef, would love your review on this when you get a chance. Happy to address any feedback!

[avianion]

Friendly follow-up — this PR is still active and ready for review. Would appreciate a look when you get a chance! cc @prasmussen15 @danielchalef

[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 @prasmussen15 @danielchalef

[avianion]

Hey @danielchalef @prasmussen15 — 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!