Add platform adapters and tests for CLIProxyAPI, OneHub, Sub2API, and title hint detection

- Implemented `CliProxyApiAdapter` with detection logic for CLIProxyAPI.
- Added tests for `CliProxyApiAdapter` to verify detection and response handling.
- Created `OneHubAdapter` with methods for fetching models and user groups.
- Added tests for `OneHubAdapter` to ensure correct fallback and response parsing.
- Developed `Sub2ApiAdapter` with detection and user info fetching capabilities.
- Added comprehensive tests for `Sub2ApiAdapter` covering various scenarios.
- Introduced `TitleHintPlatform` type and detection logic based on HTML title.
- Implemented tests for title hint detection to identify platforms from URLs.

src/server/routes/proxy/upstreamEndpoint.test.ts

@@ -0,0 +1,116 @@
+import { beforeEach, describe, expect, it, vi } from 'vitest';
+
+const fetchModelPricingCatalogMock = vi.fn(async (_arg?: unknown) => null);
+
+vi.mock('../../services/modelPricingService.js', () => ({
+  fetchModelPricingCatalog: (arg: unknown) => fetchModelPricingCatalogMock(arg),
+}));
+
+import { resolveUpstreamEndpointCandidates } from './upstreamEndpoint.js';
+
+const baseContext = {
+  site: {
+    id: 1,
+    url: 'https://upstream.example.com',
+    platform: '',
+    apiKey: null,
+  },
+  account: {
+    id: 2,
+    accessToken: 'token-demo',
+    apiToken: null,
+  },
+};
+
+describe('resolveUpstreamEndpointCandidates', () => {
+  beforeEach(() => {
+    fetchModelPricingCatalogMock.mockReset();
+    fetchModelPricingCatalogMock.mockResolvedValue(null);
+  });
+
+  it('uses responses -> messages -> chat for unknown platforms', async () => {
+    const openaiOrder = await resolveUpstreamEndpointCandidates(
+      {
+        ...baseContext,
+        site: { ...baseContext.site, platform: 'new-api' },
+      },
+      'gpt-5.3',
+      'openai',
+    );
+    expect(openaiOrder).toEqual(['responses', 'messages', 'chat']);
+
+    const claudeOrder = await resolveUpstreamEndpointCandidates(
+      {
+        ...baseContext,
+        site: { ...baseContext.site, platform: 'new-api' },
+      },
+      'gpt-5.3',
+      'claude',
+    );
+    expect(claudeOrder).toEqual(['responses', 'messages', 'chat']);
+
+    const responsesOrder = await resolveUpstreamEndpointCandidates(
+      {
+        ...baseContext,
+        site: { ...baseContext.site, platform: 'new-api' },
+      },
+      'gpt-5.3',
+      'responses',
+    );
+    expect(responsesOrder).toEqual(['responses', 'messages', 'chat']);
+  });
+
+  it('keeps explicit platform priority rules', async () => {
+    const openaiOrder = await resolveUpstreamEndpointCandidates(
+      {
+        ...baseContext,
+        site: { ...baseContext.site, platform: 'openai' },
+      },
+      'gpt-5.3',
+      'openai',
+    );
+    expect(openaiOrder).toEqual(['chat', 'responses']);
+
+    const openaiResponsesOrder = await resolveUpstreamEndpointCandidates(
+      {
+        ...baseContext,
+        site: { ...baseContext.site, platform: 'openai' },
+      },
+      'gpt-5.3',
+      'responses',
+    );
+    expect(openaiResponsesOrder).toEqual(['responses', 'chat']);
+
+    const claudeOrder = await resolveUpstreamEndpointCandidates(
+      {
+        ...baseContext,
+        site: { ...baseContext.site, platform: 'claude' },
+      },
+      'claude-opus-4-6',
+      'claude',
+    );
+    expect(claudeOrder).toEqual(['messages']);
+  });
+
+  it('keeps anyrouter messages-first special case', async () => {
+    const openaiOrder = await resolveUpstreamEndpointCandidates(
+      {
+        ...baseContext,
+        site: { ...baseContext.site, platform: 'anyrouter' },
+      },
+      'claude-opus-4-6',
+      'openai',
+    );
+    expect(openaiOrder).toEqual(['messages', 'chat']);
+
+    const responsesOrder = await resolveUpstreamEndpointCandidates(
+      {
+        ...baseContext,
+        site: { ...baseContext.site, platform: 'anyrouter' },
+      },
+      'claude-opus-4-6',
+      'responses',
+    );
+    expect(responsesOrder).toEqual(['responses', 'messages', 'chat']);
+  });
+});

src/server/routes/proxy/upstreamEndpoint.ts

@@ -381,13 +381,9 @@ function preferredEndpointOrder(downstreamFormat: EndpointPreference, sitePlatfo
     return ['messages'];
   }
 
-  if (downstreamFormat === 'responses') {
-    return ['responses', 'chat', 'messages'];
-  }
-
-  return downstreamFormat === 'claude'
-    ? ['messages', 'chat']
-    : ['chat', 'messages'];
+  // Unknown/generic upstreams: try the most expressive protocol first,
+  // then degrade to anthropic messages, and finally chat completions.
+  return ['responses', 'messages', 'chat'];
 }
 
 export async function resolveUpstreamEndpointCandidates(