Add vision model enhancements and image processing capabilities

- Update `requirements.txt` to include Pillow for image handling.
- Refactor vision model validation logic in `voice_webrtc.py` to improve error handling for unsupported image input.
- Introduce new functions in `pipeline.py` for image data processing and analysis using vision models.
- Implement `VisionCaptureProcessor` to manage video frame requests for auxiliary vision model analysis.
- Enhance the pipeline to support image input requests and integrate vision model responses into the processing flow.

backend/requirements.txt

@@ -3,6 +3,7 @@
 # silero  -> 本地 VAD(判断用户说话起止),语音必备
 # openai  -> OpenAI 兼容的 LLM/STT/TTS 客户端(DeepSeek、SenseVoice、CosyVoice 都走它)
 pipecat-ai[webrtc,websocket,silero,openai]==1.3.0
+Pillow>=11.1.0,<13
 
 # FastGPT 类型助手:本地 SDK(包 /api/v1/chat/completions 流式 + chatId 会话)
 fastgpt-client @ file:///Users/wangx/Code/AI-VideoAssistant-Project/fastgpt-python-sdk