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/shared/constants/cliTools.js

@@ -114,6 +114,22 @@ export const CLI_TOOLS = {
     description: "OpenCode AI Terminal Assistant",
     configType: "custom",
   },
+  cowork: {
+    id: "cowork",
+    name: "Claude Cowork",
+    image: "/providers/claude.png",
+    color: "#D97757",
+    description: "Claude Desktop Cowork (third-party inference)",
+    configType: "custom",
+  },
+  hermes: {
+    id: "hermes",
+    name: "Hermes Agent",
+    image: "/providers/hermes.png",
+    color: "#8B5CF6",
+    description: "Nous Research self-improving AI agent",
+    configType: "custom",
+  },
   droid: {
     id: "droid",
     name: "Factory Droid",
@@ -212,14 +228,6 @@ export const CLI_TOOLS = {
 }`,
     },
   },
-  hermes: {
-    id: "hermes",
-    name: "Hermes Agent",
-    image: "/providers/hermes.png",
-    color: "#8B5CF6",
-    description: "Nous Research self-improving AI agent",
-    configType: "custom",
-  },
   // HIDDEN: gemini-cli
   // "gemini-cli": {
   //   id: "gemini-cli",

src/shared/constants/skills.js

@@ -39,6 +39,13 @@ export const SKILLS = [
     endpoint: "/v1/audio/speech",
     icon: "record_voice_over",
   },
+  {
+    id: "9router-stt",
+    name: "Speech-to-Text",
+    description: "Transcribe audio via OpenAI Whisper, Groq, Gemini, Deepgram, AssemblyAI…",
+    endpoint: "/v1/audio/transcriptions",
+    icon: "mic",
+  },
   {
     id: "9router-embeddings",
     name: "Embeddings",

src/shared/constants/ttsProviders.js

@@ -109,4 +109,14 @@ export const TTS_PROVIDER_CONFIG = {
     hasVoiceIdInput: true,
     voiceSource: "config",
   },
+  "gemini": {
+    hasLanguageDropdown: false,
+    hasLanguageHint: true, // sends body.language to guide TTS pronunciation
+    hasModelSelector: true,
+    hasBrowseButton: false,
+    voiceSource: "hardcoded",
+    modelKey: "gemini-tts-models",
+    voiceKey: "gemini-tts-voices",
+    voicesPerModel: true,
+  },
 };