feat: add STT support, Gemini TTS, and expand usage tracking

- Speech-to-Text: full pipeline with sttCore handler, /v1/audio/transcriptions
  endpoint, sttConfig for OpenAI, Gemini, Groq, Deepgram, AssemblyAI,
  HuggingFace, NVIDIA Parakeet; new 9router-stt skill
- Gemini TTS: add gemini provider with 30 prebuilt voices and TTS_PROVIDER_CONFIG
- Usage: implement GLM (intl/cn) and MiniMax (intl/cn) quota fetchers; refactor
  Gemini CLI usage to use retrieveUserQuota with per-model buckets
- Disabled models: lowdb-backed disabledModelsDb + /api/models/disabled route
- Header search: reusable Zustand store (headerSearchStore) wired into Header
- CLI tools: add Claude Cowork tool card and cowork-settings API
- Providers: introduce mediaPriority sorting in getProvidersByKind, add
  Kimi K2.6, reorder hermes, drop qwen STT kind
- UI: expand media-providers/[kind]/[id] page (+314), enhance OAuthModal,
  ModelSelectModal, ProviderTopology, ProxyPools, ProviderLimits
- Assets: refresh provider PNGs (alicode, byteplus, cloudflare-ai, nvidia,
  ollama, vertex, volcengine-ark) and add aws-polly, fal-ai, jina-ai, recraft,
  runwayml, stability-ai, topaz, black-forest-labs

src/app/api/models/route.js

@@ -1,20 +1,29 @@
 import { NextResponse } from "next/server";
 import { getModelAliases, setModelAlias } from "@/models";
+import { getDisabledModels } from "@/lib/disabledModelsDb";
 import { AI_MODELS } from "@/shared/constants/config";
+import { getProviderAlias } from "@/shared/constants/providers";
 
 // GET /api/models - Get models with aliases
 export async function GET() {
   try {
     const modelAliases = await getModelAliases();
-    
-    const models = AI_MODELS.map((m) => {
-      const fullModel = `${m.provider}/${m.model}`;
-      return {
-        ...m,
-        fullModel,
-        alias: modelAliases[fullModel] || m.model,
-      };
-    });
+    const disabled = await getDisabledModels();
+
+    const models = AI_MODELS
+      .filter((m) => {
+        const alias = getProviderAlias(m.provider) || m.provider;
+        const list = disabled[alias] || disabled[m.provider] || [];
+        return !list.includes(m.model);
+      })
+      .map((m) => {
+        const fullModel = `${m.provider}/${m.model}`;
+        return {
+          ...m,
+          fullModel,
+          alias: modelAliases[fullModel] || m.model,
+        };
+      });
 
     return NextResponse.json({ models });
   } catch (error) {