feat: add OrcaRouter as a first-class model provider - #2386
Open
kuswardhanietidims-svg wants to merge 1 commit into
Open
feat: add OrcaRouter as a first-class model provider#2386kuswardhanietidims-svg wants to merge 1 commit into
kuswardhanietidims-svg wants to merge 1 commit into
Conversation
Registers OrcaRouter (https://www.orcarouter.ai) in the unified model management as a named provider alongside OpenAI / Anthropic / DeepSeek. It is wired through the same OpenAI-compatible client and params handler as the existing QIAN_FAN / TENCENT / SILICON providers, so users can select "OrcaRouter" in the platform UI, point it at https://api.orcarouter.ai/v1 and use namespaced routes such as orcarouter/auto. Backend: - Add LLMServerType.ORCAROUTER and dispatch it to ChatOpenAICompatible with the shared _get_openai_params handler. - Add unit tests locking the dispatch mapping. Frontend (platform): - Add OrcaRouter to the provider dropdown and the per-provider config form (Base URL defaults to https://api.orcarouter.ai/v1). - Add OrcaRouter API key / model catalog links. - Map orcarouter to the openai-llm advanced-params template.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Adds OrcaRouter as a first-class model provider in BISHENG's unified model management. OrcaRouter is an OpenAI-compatible AI gateway built for both models and agents — like OpenRouter, it exposes a provider/model namespace across many models, but it also combines adaptive routing, automatic failover, zero-markup inference, observability, guardrails, and agent-tool governance behind the same endpoint. Adding it as a named provider means BISHENG users can use that stack directly, without treating OrcaRouter as an anonymous custom base URL. 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.
Why
BISHENG already ships named entries for OpenAI / Anthropic / DeepSeek / Qwen / SiliconFlow and friends in
modelProvider(src/frontend/platform/src/pages/ModelPage/manage/ModelConfig.tsx). OrcaRouter fits the same slot: it speaks the OpenAIchat/completionscontract thatChatOpenAICompatiblealready targets, so it needs no new client — just registration.How
Mirrors the existing
silicon/qianfan/tencentwiring:LLMServerType.ORCAROUTERinllm/domain/const.py, dispatched toChatOpenAICompatiblewith the shared_get_openai_paramshandler inllm/domain/llm/llm.py.https://api.orcarouter.ai/v1, API key), key/catalog links inuseLink.ts, and theopenai-llmadvanced-params template mapping.Test
pnpm lint+pnpm typecheck+pnpm check-i18npass locallytest/llm/test_orcarouter_provider.py) passes; existingtest/llm/test_provider_chatmodels.pystays greenhttps://api.orcarouter.ai/v1/chat/completionswithorcarouter/autoreturned200Related
I'm an engineer on the OrcaRouter team.