Implement DashScope ASR provider and enhance ASR service architecture

- Added DashScope ASR service implementation for real-time streaming.
- Updated ASR provider logic to support DashScope alongside existing providers.
- Enhanced runtime metadata resolution to include DashScope as a valid ASR provider.
- Modified configuration files and documentation to reflect the addition of DashScope.
- Introduced tests to validate DashScope integration and ASR service behavior.
- Refactored ASR service factory to accommodate new provider options and modes.

engine/config/agents/example.yaml

@@ -35,7 +35,11 @@ agent:
     speed: 1.0
 
   asr:
-    # provider: buffered | openai_compatible | siliconflow
+    # provider: buffered | openai_compatible | siliconflow | dashscope
+    # dashscope defaults (if omitted):
+    #   api_url: wss://dashscope.aliyuncs.com/api-ws/v1/realtime
+    #   model: qwen3-asr-flash-realtime
+    #   note: dashscope uses streaming ASR mode (chunk-by-chunk).
     provider: openai_compatible
     api_key: you_asr_api_key
     api_url: https://api.siliconflow.cn/v1/audio/transcriptions

engine/config/agents/tools.yaml

@@ -32,7 +32,11 @@ agent:
     speed: 1.0
 
   asr:
-    # provider: buffered | openai_compatible | siliconflow
+    # provider: buffered | openai_compatible | siliconflow | dashscope
+    # dashscope defaults (if omitted):
+    #   api_url: wss://dashscope.aliyuncs.com/api-ws/v1/realtime
+    #   model: qwen3-asr-flash-realtime
+    #   note: dashscope uses streaming ASR mode (chunk-by-chunk).
     provider: openai_compatible
     api_key: your_asr_api_key
     api_url: https://api.siliconflow.cn/v1/audio/transcriptions