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/providers/route.js

@@ -110,7 +110,7 @@ export async function POST(request) {
     if (!provider || !isValidProvider) {
       return NextResponse.json({ error: "Invalid provider" }, { status: 400 });
     }
-    if (!apiKey) {
+    if (!apiKey && provider !== "ollama-local") {
       return NextResponse.json({ error: `${isWebCookieProvider ? "Cookie value" : "API Key"} is required` }, { status: 400 });
     }
     if (!name) {
@@ -185,7 +185,7 @@ export async function POST(request) {
       provider,
       authType: isWebCookieProvider ? "cookie" : "apikey",
       name,
-      apiKey,
+      apiKey: apiKey || "",
       priority: priority || 1,
       globalPriority: globalPriority || null,
       defaultModel: defaultModel || null,