4e2450e800
- Removed the backend client compatibility wrapper and associated methods to streamline backend integration. - Updated session management to utilize control plane gateways and runtime configuration providers. - Adjusted TTS service implementations to remove the EdgeTTS service and simplify service dependencies. - Enhanced documentation to reflect changes in backend integration and service architecture. - Updated configuration files to remove deprecated TTS provider options and clarify available settings.
1.4 KiB
1.4 KiB
Engine Extension Ports (Draft)
This document defines the draft port set used to keep core runtime extensible.
Port Modules
core/ports/control_plane.pyAssistantRuntimeConfigProviderConversationHistoryStoreKnowledgeRetrieverToolCatalogControlPlaneGateway
core/ports/llm.pyLLMServiceSpecLLMPort- optional extensions:
LLMCancellable,LLMRuntimeConfigurable
core/ports/tts.pyTTSServiceSpecTTSPort
core/ports/asr.pyASRServiceSpecASRPort- optional extensions:
ASRInterimControl,ASRBufferControl
core/ports/service_factory.pyRealtimeServiceFactory
Adapter Layer
app/service_factory.pyprovidesDefaultRealtimeServiceFactory.- It maps resolved provider specs to concrete adapters.
- Core orchestration (
core/duplex_pipeline.py) depends on the factory port/specs, not concrete provider classes.
Provider Behavior (Current)
- LLM:
- supported providers:
openai,openai_compatible,openai-compatible,siliconflow - fallback:
MockLLMService
- supported providers:
- TTS:
- supported providers:
dashscope,openai_compatible,openai-compatible,siliconflow - fallback:
MockTTSService
- supported providers:
- ASR:
- supported providers:
openai_compatible,openai-compatible,siliconflow - fallback:
BufferedASRService
- supported providers:
Notes
- This is a draft contract set; follow-up work can add explicit capability negotiation and contract-version fields.