refactor(ui): use tokenlens as sole model source, remove provider listModels

Remove the per-provider listModels API (GET /providers/:id/models) and all
four provider implementations (OpenAI Compatible, OpenAI Responses, Anthropic,
Gemini). ModelCombobox now only shows tokenlens suggestions (tagged '推荐') plus
free-form custom input — no more unfiltered 'API' models from provider SDKs.

Fixes: switching provider type in ProviderDialog no longer shows stale models
from the original provider's API.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

src/controllers/llm-config.ts

@@ -55,29 +55,6 @@ llmConfigRouter.get('/providers/:id', (c) => {
   });
 });
 
-llmConfigRouter.get('/providers/:id/models', async (c) => {
-  const id = c.req.param('id');
-  const provider = providerRepo.getById(id);
-  if (!provider) return c.json({ message: 'Provider not found' }, 404);
-
-  if (!secretRepo.has(id)) {
-    return c.json({ message: 'No API key configured' }, 400);
-  }
-
-  try {
-    llmGateway.invalidateProvider(id);
-    const providerInstance = llmGateway.getProviderInstance(id);
-    if (!providerInstance.listModels) {
-      return c.json({ message: 'This provider does not support listing models' }, 501);
-    }
-
-    const models = await providerInstance.listModels();
-    return c.json({ models });
-  } catch (error: any) {
-    return c.json({ message: error.message || 'Failed to fetch models' }, 500);
-  }
-});
-
 llmConfigRouter.post('/providers', async (c) => {
   const body = await c.req.json<{
     name: string;

src/llm/providers/anthropic.ts

@@ -220,15 +220,6 @@ class AnthropicProvider implements LLMProvider {
     }
   }
 
-  async listModels(): Promise<string[]> {
-    const response = await this.client.models.list();
-    const models: string[] = [];
-    for await (const page of response.iterPages()) {
-      models.push(...page.data.map((model) => model.id));
-    }
-    return models;
-  }
-
   private wrapError(error: unknown): Error {
     if (error instanceof Anthropic.APIError) {
       if (error.status === 401) return new LLMAuthError(TYPE, error.message);

src/llm/providers/base.ts

@@ -33,8 +33,6 @@ export interface LLMProvider {
   /** Optional: embedding interface (only for providers that support it). */
   embed?(texts: string[]): Promise<number[][]>;
 
-  /** Optional: list available models for this provider. */
-  listModels?(): Promise<string[]>;
 }
 
 // ---------------------------------------------------------------------------

src/llm/providers/gemini.ts

@@ -203,17 +203,6 @@ class GeminiProvider implements LLMProvider {
     }
   }
 
-  async listModels(): Promise<string[]> {
-    const pager = await this.genAI.models.list();
-    const models: string[] = [];
-    for await (const model of pager) {
-      if (model.name) {
-        models.push(model.name.replace('models/', ''));
-      }
-    }
-    return models;
-  }
-
   private wrapError(error: unknown): Error {
     if (error instanceof Error) {
       const msg = error.message;

src/llm/providers/openai-compatible.ts

@@ -143,11 +143,6 @@ class OpenAICompatibleProvider implements LLMProvider {
     }
   }
 
-  async listModels(): Promise<string[]> {
-    const response = await this.client.models.list();
-    return response.data.map((model) => model.id);
-  }
-
   private wrapError(error: unknown): Error {
     if (error instanceof OpenAI.APIError) {
       if (error.status === 401) return new LLMAuthError(TYPE, error.message);

src/llm/providers/openai-responses.ts

@@ -182,11 +182,6 @@ class OpenAIResponsesProvider implements LLMProvider {
     }
   }
 
-  async listModels(): Promise<string[]> {
-    const response = await this.client.models.list();
-    return response.data.map((model) => model.id);
-  }
-
   private wrapError(error: unknown): Error {
     if (error instanceof OpenAI.APIError) {
       if (error.status === 401) return new LLMAuthError(TYPE, error.message);