feat: add OrcaRouter as a named alternative API provider

.env.example

@@ -61,3 +61,10 @@
 # ANTHROPIC_DEFAULT_OPUS_MODEL=kimi-k2.5
 # ANTHROPIC_DEFAULT_SONNET_MODEL=kimi-k2.5
 # ANTHROPIC_DEFAULT_HAIKU_MODEL=kimi-k2.5
+#
+# OrcaRouter:
+# ANTHROPIC_BASE_URL=https://api.orcarouter.ai
+# ANTHROPIC_AUTH_TOKEN=your-orcarouter-api-key
+# ANTHROPIC_DEFAULT_OPUS_MODEL=anthropic/claude-opus-5
+# ANTHROPIC_DEFAULT_SONNET_MODEL=anthropic/claude-sonnet-5
+# ANTHROPIC_DEFAULT_HAIKU_MODEL=anthropic/claude-haiku-4.5

CLAUDE.md

@@ -418,11 +418,11 @@ Run coding agents via Google Cloud Vertex AI:
 
 **Note:** Use `@` instead of `-` in model names for Vertex AI.
 
-### Alternative API Providers (GLM, Ollama, Kimi, Custom)
+### Alternative API Providers (GLM, Ollama, Kimi, OrcaRouter, Custom)
 
 Alternative providers are configured via the **Settings UI** (gear icon > API Provider section). Select a provider, set the base URL, auth token, and model — no `.env` changes needed.
 
-**Available providers:** Claude (default), GLM (Zhipu AI), Ollama (local models), Kimi (Moonshot), Custom
+**Available providers:** Claude (default), GLM (Zhipu AI), Ollama (local models), Kimi (Moonshot), OrcaRouter, Custom
 
 **Ollama notes:**
 - Requires Ollama v0.14.0+ with Anthropic API compatibility

README.md

@@ -332,14 +332,16 @@ When test progress increases, the agent sends:
 }
 ```
 
-### Alternative API Providers (GLM, Ollama, Kimi, Custom)
+### Alternative API Providers (GLM, Ollama, Kimi, OrcaRouter, Custom)
 
 Alternative providers are configured via the **Settings UI** (gear icon > API Provider). Select your provider, set the base URL, auth token, and model directly in the UI — no `.env` changes needed.
 
-Available providers: **Claude** (default), **GLM** (Zhipu AI), **Ollama** (local models), **Kimi** (Moonshot), **Custom**
+Available providers: **Claude** (default), **GLM** (Zhipu AI), **Ollama** (local models), **Kimi** (Moonshot), **OrcaRouter**, **Custom**
 
 For Ollama, install [Ollama v0.14.0+](https://ollama.com), run `ollama serve`, and pull a coding model (e.g., `ollama pull qwen3-coder`). Then select "Ollama" in the Settings UI.
 
+For OrcaRouter, get an API key at [https://www.orcarouter.ai](https://www.orcarouter.ai), then select "OrcaRouter" in the Settings UI and paste your API key. OrcaRouter routes to Claude and other models through a unified Anthropic-compatible endpoint (`https://api.orcarouter.ai/v1/messages`).
+
 ### Using Vertex AI
 
 Add these variables to your `.env` file to run agents via Google Cloud Vertex AI:

client.py

@@ -340,7 +340,7 @@ def create_client(
     }
     # Build environment overrides for API endpoint configuration
     # Uses get_effective_sdk_env() which reads provider settings from the database,
-    # ensuring UI-configured alternative providers (GLM, Ollama, Kimi, Custom) propagate
+    # ensuring UI-configured alternative providers (GLM, Ollama, Kimi, OrcaRouter, Custom) propagate
     # correctly to the Claude CLI subprocess
     from registry import get_effective_sdk_env, get_effort_setting
     sdk_env = get_effective_sdk_env()

registry.py

@@ -827,6 +827,18 @@ def get_all_settings() -> dict[str, str]:
         ],
         "default_model": "qwen3-coder",
     },
+    "orcarouter": {
+        "name": "OrcaRouter",
+        "base_url": "https://api.orcarouter.ai",
+        "requires_auth": True,
+        "auth_env_var": "ANTHROPIC_AUTH_TOKEN",
+        "models": [
+            {"id": "anthropic/claude-opus-5", "name": "Claude Opus"},
+            {"id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet"},
+            {"id": "anthropic/claude-haiku-4.5", "name": "Claude Haiku"},
+        ],
+        "default_model": "anthropic/claude-sonnet-5",
+    },
     "custom": {
         "name": "Custom Provider",
         "base_url": "",

server/routers/settings.py

@@ -107,12 +107,14 @@ async def get_settings():
 
     glm_mode = api_provider == "glm"
     ollama_mode = api_provider == "ollama"
+    orcarouter_mode = api_provider == "orcarouter"
 
     return SettingsResponse(
         yolo_mode=_parse_yolo_mode(all_settings.get("yolo_mode")),
         model=all_settings.get("model", DEFAULT_MODEL),
         glm_mode=glm_mode,
         ollama_mode=ollama_mode,
+        orcarouter_mode=orcarouter_mode,
         testing_agent_ratio=_parse_int(all_settings.get("testing_agent_ratio"), 1),
         playwright_headless=True,  # Always headless - embedded browser view replaces desktop windows
         batch_size=_parse_int(all_settings.get("batch_size"), 3),
@@ -179,12 +181,14 @@ async def update_settings(update: SettingsUpdate):
     api_provider = all_settings.get("api_provider", "claude")
     glm_mode = api_provider == "glm"
     ollama_mode = api_provider == "ollama"
+    orcarouter_mode = api_provider == "orcarouter"
 
     return SettingsResponse(
         yolo_mode=_parse_yolo_mode(all_settings.get("yolo_mode")),
         model=all_settings.get("model", DEFAULT_MODEL),
         glm_mode=glm_mode,
         ollama_mode=ollama_mode,
+        orcarouter_mode=orcarouter_mode,
         testing_agent_ratio=_parse_int(all_settings.get("testing_agent_ratio"), 1),
         playwright_headless=True,  # Always headless - embedded browser view replaces desktop windows
         batch_size=_parse_int(all_settings.get("batch_size"), 3),

server/schemas.py

@@ -480,6 +480,7 @@ class SettingsResponse(BaseModel):
     model: str = DEFAULT_MODEL
     glm_mode: bool = False  # True when api_provider is "glm"
     ollama_mode: bool = False  # True when api_provider is "ollama"
+    orcarouter_mode: bool = False  # True when api_provider is "orcarouter"
     testing_agent_ratio: int = 1  # Regression testing agents (0-3)
     playwright_headless: bool = True
     batch_size: int = 3  # Features per coding agent batch (1-15)

ui/src/components/SettingsModal.tsx

@@ -25,6 +25,7 @@ const PROVIDER_INFO_TEXT: Record<string, string> = {
   kimi: 'Get an API key at kimi.com',
   glm: 'Get an API key at open.bigmodel.cn',
   ollama: 'Run models locally. Install from ollama.com',
+  orcarouter: 'Get an API key at https://www.orcarouter.ai',
   custom: 'Connect to any OpenAI-compatible API endpoint.',
 }
 

ui/src/components/layout/ControlBar.tsx

@@ -49,6 +49,12 @@ export function ControlBar() {
         </Badge>
       )}
 
+      {settings?.orcarouter_mode && (
+        <Badge className="hidden sm:inline-flex bg-slate-700 text-white hover:bg-slate-800 text-[11px]">
+          OrcaRouter
+        </Badge>
+      )}
+
       <Tooltip>
         <TooltipTrigger asChild>
           <Button

ui/src/components/views/SettingsView.tsx

@@ -23,6 +23,7 @@ const PROVIDER_INFO_TEXT: Record<string, string> = {
   kimi: 'Get an API key at kimi.com',
   glm: 'Get an API key at open.bigmodel.cn',
   ollama: 'Run models locally. Install from ollama.com',
+  orcarouter: 'Get an API key at https://www.orcarouter.ai',
   custom: 'Connect to any OpenAI-compatible API endpoint.',
 }
 

ui/src/hooks/useProjects.ts

@@ -299,6 +299,7 @@ const DEFAULT_SETTINGS: Settings = {
   model: 'claude-opus-4-7',
   glm_mode: false,
   ollama_mode: false,
+  orcarouter_mode: false,
   testing_agent_ratio: 1,
   playwright_headless: true,
   batch_size: 3,

ui/src/lib/types.ts

@@ -649,6 +649,7 @@ export interface Settings {
   model: string
   glm_mode: boolean
   ollama_mode: boolean
+  orcarouter_mode: boolean
   testing_agent_ratio: number  // Regression testing agents (0-3)
   playwright_headless: boolean
   batch_size: number  // Features per coding agent batch (1-15)