Implement StepFun Realtime service and enhance AssistantConfig

- Add new fields to AssistantConfig for realtime interface configuration, including types, values, and secrets.
- Introduce StepFunRealtimeService to handle speech-to-speech processing via WebSocket, integrating STT, LLM, and TTS functionalities.
- Refactor pipeline execution to support a new realtime mode, allowing direct text input processing and immediate responses.
- Update model resource testing to include validation for StepFun Realtime connections.
- Enhance service factory to create realtime services based on configuration settings.
- Modify README documentation to reflect new realtime capabilities and usage instructions.

backend/services/config_resolver.py

@@ -83,6 +83,11 @@ async def resolve_runtime_config(
         stt_secrets=(stt_resource.secrets or {}) if stt_resource else {},
         tts_values=(tts_resource.values or {}) if tts_resource else {},
         tts_secrets=(tts_resource.secrets or {}) if tts_resource else {},
+        realtime_interface_type=(
+            realtime_resource.interface_type if realtime_resource else ""
+        ),
+        realtime_values=(realtime_resource.values or {}) if realtime_resource else {},
+        realtime_secrets=(realtime_resource.secrets or {}) if realtime_resource else {},
         # 运行时连接信息(真 key + url):模型资源优先,否则 .env 兜底
         llm_api_key=_secret(llm_resource, "apiKey", config.LLM_API_KEY),
         llm_base_url=str(_value(llm_resource, "apiUrl", config.LLM_BASE_URL)),
@@ -90,4 +95,6 @@ async def resolve_runtime_config(
         stt_base_url=str(_value(stt_resource, "apiUrl", config.STT_BASE_URL)),
         tts_api_key=_secret(tts_resource, "apiKey", config.TTS_API_KEY),
         tts_base_url=str(_value(tts_resource, "apiUrl", config.TTS_BASE_URL)),
+        realtime_api_key=_secret(realtime_resource, "apiKey", ""),
+        realtime_base_url=str(_value(realtime_resource, "apiUrl", "")),
     )