feat: add list_embedding_models_async to OpenRouterProvider

[majiayu000]

Summary

• Add list_embedding_models_async() method to OpenRouterProvider class
• Return hardcoded EmbeddingConfig objects for OpenAI embedding models supported by OpenRouter
• Add unit tests for the new functionality

Problem

When using OpenRouter as an LLM provider, Letta cannot discover embedding models because OpenRouter's /models endpoint only returns LLM models, not embedding models.

Current behavior:

• Only letta/letta-free embedding model appears in the UI/API
• OpenRouter embedding models (e.g., openai/text-embedding-3-small) are not discoverable

Root cause:
OpenRouter's /models endpoint doesn't list embedding models, but they support OpenAI's embedding models via the /embeddings endpoint.

Solution

Added list_embedding_models_async() method to OpenRouterProvider class that returns hardcoded EmbeddingConfig objects for:

• openai/text-embedding-3-small (1536 dimensions)
• openai/text-embedding-3-large (3072 dimensions)

Test plan

• Added unit test test_openrouter_embedding_models_without_api_key that verifies embedding models are returned correctly without making API calls
• Added integration test test_openrouter (requires OPENROUTER_API_KEY)

Fixes #3086