feat: add audio input support to v2 providers

Add Audio struct alongside Image for sending audio attachments to
multimodal LLMs. OpenAI uses input_audio content parts (wav/mp3),
Google Gemini uses genai.NewPartFromBytes, and Anthropic skips
audio gracefully since it's not supported.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

v2/anthropic/anthropic.go

@@ -204,6 +204,8 @@ func (p *Provider) buildRequest(req provider.Request) anth.MessagesRequest {
 			}
 		}
 
+		// Audio is not supported by Anthropic — skip silently.
+
 		// Merge consecutive same-role messages (Anthropic requires alternating)
 		if len(msgs) > 0 && msgs[len(msgs)-1].Role == role {
 			msgs[len(msgs)-1].Content = append(msgs[len(msgs)-1].Content, m.Content...)