feat(audio): add native audio support to type system and model clients

- Add AudioSource interface and 'audio' variant to MessageContentPart union
- Update buildUserMessage() to create audio content parts from attachments
- Add attachmentToAudioSource(), hasAudio(), stripAudioParts() helpers
- Gemini: native audio via inlineData (same format as images)
- OpenAI/GitHub: native audio via input_audio content parts
- Anthropic/Bedrock: graceful fallback to transcript text
- Update getMessageTextWithTools() to handle audio blocks for local models

src/models/index.ts

@@ -10,15 +10,20 @@ export { withRetry, isRetryable, DEFAULT_RETRY_CONFIG, type RetryConfig } from '
 export { estimateCost, MODEL_COSTS_PER_MILLION } from './costs.js';
 export {
   isSupportedImage,
+  isSupportedAudio,
   attachmentToImageSource,
+  attachmentToAudioSource,
   buildUserMessage,
   getMessageText,
   hasImages,
+  hasAudio,
+  stripAudioParts,
 } from './media.js';
 export type {
   Message,
   MessageContentPart,
   ImageSource,
+  AudioSource,
   ChatRequest,
   ChatResponse,
   ChatStreamEvent,