feat(audio): add audio.transcribe tool with Whisper-compatible API support

- Add createAudioTranscribeTool with OpenAI/Groq/Ollama/llama.cpp provider support
- Refactor audio config schema to nested audio.enabled + audio.provider structure
- Move audio tool registration to initTools() for conditional enablement
- Fix duplication bug in audio-transcribe.ts URL download handler
- Support base64 data and URL-based audio input with format detection

src/config/schema.ts

@@ -314,10 +314,16 @@ const webSearchSchema = z.object({
   max_results: z.number().min(1).max(20).default(5),
 }).default({});
 
+const audioProviderSchema = z.object({
+  type: z.enum(['openai', 'groq', 'ollama', 'llamacpp', 'custom']),
+  endpoint: z.string().optional(),
+  api_key: z.string().optional(),
+  model: z.string().optional(),
+});
+
 const audioSchema = z.object({
-  transcription_endpoint: z.string().optional(),
-  transcription_api_key: z.string().optional(),
-  transcription_model: z.string().default('whisper-1'),
+  enabled: z.boolean().default(false),
+  provider: audioProviderSchema.optional(),
 }).default({});
 
 // ── Tool policy schemas ──────────────────────────────────────────────