Add Dify integration and enhance workflow node specifications

- Introduce new fields `dify_api_url` and `dify_api_key` in `AssistantConfig` for Dify API integration.
- Update `requirements.txt` to include `dify-client-python` for Dify SDK support.
- Modify `config_resolver` to handle Dify connection information.
- Add a new `globalNode` type in workflow specifications to provide unified settings across workflows.
- Enhance node specifications with additional constraints and default values for better configuration management.
- Update frontend components to support the new `globalNode` type and its properties, improving workflow editor functionality.

backend/services/pipecat/service_factory.py

@@ -142,7 +142,7 @@ def create_tts(cfg: AssistantConfig):
     )
 
 
-def create_realtime_service(cfg: AssistantConfig):
+def create_realtime_service(cfg: AssistantConfig, *, instructions: str):
     """Create a speech-to-speech service that owns STT, LLM, and TTS."""
     if cfg.realtime_interface_type == "stepfun-realtime":
         from services.pipecat.stepfun_realtime import StepFunRealtimeService
@@ -151,7 +151,7 @@ def create_realtime_service(cfg: AssistantConfig):
             api_key=_require(cfg.realtime_api_key, "Realtime apiKey"),
             model=_require(cfg.realtimeModel, "Realtime modelId"),
             base_url=_require(cfg.realtime_base_url, "Realtime apiUrl"),
-            instructions=cfg.prompt,
+            instructions=instructions,
             voice=str(cfg.realtime_values.get("voice") or "linjiajiejie"),
             input_sample_rate=int(
                 cfg.realtime_values.get("inputSampleRate") or 24000