Skip to content

Commit ac0260b

Browse files
latemonkclaude
andcommitted
feat(providers): add BizRouter preset to the provider registry
BizRouter (api.bizrouter.ai) is a Korean enterprise LLM gateway with an OpenAI-compatible surface. Model ids are vendor-namespaced (`<vendor>/<model>`) and pass through to the upstream as-is. Live-verified 2026-07-24 against api.bizrouter.ai: - POST /v1/chat/completions accepts the `tools` field and streams SSE - GET /v1/models returns the per-API-key allowed catalog in the OpenAI list shape, so live model discovery narrows to what the key can use - End-to-end through the proxy: Codex CLI `/v1/responses` request routed to `bizrouter/anthropic/claude-haiku-4.5` returned the expected completion (non-streaming and streaming) Also adds "bizrouter" to EXPECTED_KEY_PROVIDER_IDS in the registry parity test. Co-Authored-By: Claude Fable 5 <[email protected]>
1 parent 9f953d8 commit ac0260b

2 files changed

Lines changed: 13 additions & 1 deletion

File tree

‎src/providers/registry.ts‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -644,6 +644,18 @@ export const PROVIDER_REGISTRY: readonly ProviderRegistryEntry[] = [
644644
preserveReasoningContentModels: ["deepseek/deepseek-v4-pro"],
645645
note: "OpenAI-compatible adaptive router. Default is a tool-capable model; orcarouter/auto (adaptive routing) is also selectable. Full catalog: https://www.orcarouter.ai/models",
646646
},
647+
{
648+
// BizRouter: Korean enterprise LLM gateway (api.bizrouter.ai). Model ids are
649+
// vendor-namespaced (`<vendor>/<model>`) and pass through to the upstream as-is.
650+
// Live-verified 2026-07-24: /v1/chat/completions accepts the `tools` field and
651+
// streams, and GET /v1/models returns the per-API-key allowed catalog in the
652+
// OpenAI list shape, so live model discovery narrows to what the key can use.
653+
id: "bizrouter", label: "BizRouter", adapter: "openai-chat", baseUrl: "https://api.bizrouter.ai/v1",
654+
authKind: "key", dashboardUrl: "https://bizrouter.ai/settings/keys",
655+
defaultModel: "openai/gpt-5.6-sol",
656+
models: ["openai/gpt-5.6-sol", "anthropic/claude-sonnet-5", "google/gemini-3.5-flash"],
657+
note: "Korean enterprise LLM gateway. Per-key allowed models are discovered live from /v1/models. Full catalog: https://bizrouter.ai/models",
658+
},
647659
{ id: "groq", label: "Groq", adapter: "openai-chat", baseUrl: "https://api.groq.com/openai/v1", authKind: "key", featured: true, dashboardUrl: "https://console.groq.com/keys" },
648660
// 2026-07-10 Gemini API refresh: Tier-2 ai.google.dev evidence recorded in
649661
// devlog/_plan/260710_provider_hardening/001_research_frontier.md.

‎tests/provider-registry-parity.test.ts‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -29,7 +29,7 @@ function nativeTemplate(): Record<string, unknown> {
2929
}
3030

3131
const EXPECTED_KEY_PROVIDER_IDS = [
32-
"anthropic-apikey", "openai-apikey", "umans", "opencode-go", "neuralwatt", "openrouter", "orcarouter", "groq", "google", "google-vertex", "azure-openai",
32+
"anthropic-apikey", "openai-apikey", "umans", "opencode-go", "neuralwatt", "openrouter", "orcarouter", "bizrouter", "groq", "google", "google-vertex", "azure-openai",
3333
"deepseek", "cerebras", "together", "fireworks", "firepass", "moonshot",
3434
"huggingface", "nvidia", "venice", "zai", "nanogpt", "synthetic", "siliconflow", "qwen-cloud", "tencent-coding-plan",
3535
"qianfan", "alibaba", "alibaba-token-plan", "alibaba-token-plan-intl", "parallel", "zenmux", "litellm", "ollama-cloud", "mistral",

0 commit comments

Comments
 (0)