feat: add OrcaRouter as a named LLM backend - #552
Open
JinhaoSong322 wants to merge 1 commit into
Open
Conversation
Add a first-class 'orcarouter' backend mirroring the existing vLLM/SGLang OpenAI-client wiring, targeting the OpenAI-compatible gateway at https://api.orcarouter.ai/v1: - aios/llm_core/adapter.py: register ORCAROUTER_API_KEY in _setup_api_keys and add the 'orcarouter' case in _initialize_single_llm (default base_url https://api.orcarouter.ai/v1, key from config/env). - aios/config/config_manager.py: map orcarouter -> ORCAROUTER_API_KEY. - aios/config/config.yaml.example: document the orcarouter api_key and model. - aios/utils/commands/launch.py: list ORCAROUTER_API_KEY in aios env list. - README.md: document the backend, key, and Supported LLM Cores entry. Signed-off-by: JinhaoSong322 <jinhao.song@myflashcloud.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR adds OrcaRouter as a first-class LLM backend, mirroring the existing vLLM/SGLang OpenAI-client wiring.
OrcaRouter is an OpenAI-compatible gateway that exposes 160+ models (OpenAI, Anthropic, DeepSeek, Qwen, and more) behind a single API key at
https://api.orcarouter.ai/v1. It also runs gateway-level, zero-trust security for AI agents on the same endpoint — screening every prompt/response and governing every tool call on a default-deny basis, with no application code changes.Changes
aios/llm_core/adapter.py: registerORCAROUTER_API_KEYin_setup_api_keysand add a dedicatedorcaroutercase in_initialize_single_llm(default base URLhttps://api.orcarouter.ai/v1, key from config/env, optionalhostnameoverride).aios/config/config_manager.py: maporcarouter→ORCAROUTER_API_KEYinget_api_key.aios/config/config.yaml.example: document theorcarouterapi_key entry and an example model.aios/utils/commands/launch.py: listORCAROUTER_API_KEYinaios env list.README.md: document the backend, API key setup, and add an OrcaRouter row to the Supported LLM Cores table.Verification
python3 -m py_compilepasses on all changed Python files.https://api.orcarouter.ai/v1with modelorcarouter/autoreturned HTTP 200 and a valid completion.Disclosure: I'm an engineer on the OrcaRouter team.