Add OpenRouter support to litellm_model_interface

[Copilot]

Adds OpenRouter as a supported provider in the litellm inference module.

Changes

• Added openrouter_api_key field to LiteLLMInferenceModelConfig
• Set OPENROUTER_API_KEY environment variable in set_os_env()
• Improved env var handling to only set when keys are non-empty (prevents overwriting existing vars)
• Added test coverage for OpenRouter configuration

Usage

config = LiteLLMInferenceModelConfig(
    model_name="openrouter/anthropic/claude-2",
    openrouter_api_key="sk-or-v1-..."
)
model = LiteLLMInferenceModel(config)

Models follow the openrouter/provider/model format per litellm convention.

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• docs.litellm.ai
  • Triggering command: /home/REDACTED/work/_temp/ghcca-node/node/bin/node /home/REDACTED/work/_temp/ghcca-node/node/bin/node --enable-source-maps /home/REDACTED/work/_temp/copilot-developer-action-main/dist/index.js (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

---

This section details on the original issue you should resolve

<issue_title>litellm_model_interface miss openrouter support</issue_title>
<issue_description>Add openrouter support to litellm module:

• just need to add the api key, then the models are accessed with openrouter/model_provider/model_name </issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes litellm_model_interface miss openrouter support #22

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.