feat: Add Avian AI provider support

[avianion]

This PR adds support for the Avian AI provider to the inference package.

Changes

• Added new Avian provider implementation in packages/inference/src/providers/avian.ts
• Added Avian to the provider constants and configuration
• Integrated Avian provider into the getProviderHelper function
• Added tests for the Avian provider

Provider Details

Avian AI is integrated following the same pattern as other providers in the codebase, supporting the standard inference API endpoints.

---

Note

Low Risk
Mostly additive wiring for a new provider plus documentation and a skipped integration test; limited risk aside from any Avian-specific routing/endpoint assumptions.

Overview
Adds Avian as a supported Inference Provider for the conversational task by introducing AvianConversationalTask (pointing to https://api.avian.io) and wiring it into PROVIDERS, INFERENCE_PROVIDERS, PROVIDERS_HUB_ORGS, and the hardcoded model-mapping registry.

Updates the packages/inference README to list Avian and link to its supported-models endpoint, and adds a (skipped) vitest integration test covering chatCompletion and streaming with an injected Avian model mapping.

^{Reviewed by Cursor Bugbot for commit b438b9a. Bugbot is set up for automated code reviews on this repo. Configure here.}

[julien-c]

hey @avianion @avianio i tried sending an email to Kyle Dayne but it seems like it's bouncing?

[julien-c]

Hey there!

Thank you for your interest in becoming an Inference Provider and for the excellent work you've put into this integration!
We really appreciate the effort.

However, we're currently in a consolidation phase focusing on growing usage of Inference Providers via new features and integrations rather than expanding to new partners. This means we've temporarily paused onboarding new providers while we work on these improvements.

We're not able to provide a specific timeline for when we'll resume new provider onboarding, but we'd love to revisit this integration in the future.

In the meantime:

• Grow your presence on Hugging Face — publish models, datasets, and Spaces.
• Grow your Hugging Face organization — build a community around your work.
• Consider upgrading to a Team plan — this is a requirement for further integration as per the Inference Providers doc.

Thanks again for your contribution and understanding!

[avianion]

Addressed feedback: added Avian to PROVIDERS const and created changeset.

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit 8f0f73c. Configure here.}

[avianion]

Fixed route bug: moved /v1 prefix from base URL to route path for HF router compatibility.