Add ByteDance model support

[adambalogh]

Adds seed models

TODO:

• Enable model service in Ark Console

[Copilot]

Pull request overview

Adds ByteDance/BytePlus ModelArk (OpenAI-compatible) “Seed” model support to the gateway so requests can be routed/priced like existing OpenAI/Anthropic/Google/xAI models.

Changes:

• Register Seed models in the model registry (pricing + aliases).
• Add a new bytedance_api_key to runtime config and wire up a dedicated httpx.Client + routing branch in llm_backend.
• Document the new provider and add a small local smoke-test script.

Reviewed changes

Copilot reviewed 6 out of 6 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
tee_gateway/model_registry.py	Adds Seed model configs and aliases so the gateway can resolve/prices these model names.
tee_gateway/llm_backend.py	Introduces ByteDance routing via ChatOpenAI against a ModelArk base URL with a dedicated shared HTTP client.
tee_gateway/config.py	Extends ProviderConfig with bytedance_api_key.
tee_gateway/__main__.py	Accepts/logs bytedance_api_key during /v1/keys injection and includes it in the initialized-providers list.
scripts/test_bytedance.py	Adds a small local smoke-test to instantiate and invoke a Seed model.
CLAUDE.md	Documents the new API key env var and supported model prefixes.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 10 out of 10 changed files in this pull request and generated 1 comment.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.