# Engine Extension Ports (Draft)

This document defines the draft port set used to keep core runtime extensible.

## Port Modules

- `runtime/ports/control_plane.py`
  - `AssistantRuntimeConfigProvider`
  - `ConversationHistoryStore`
  - `KnowledgeRetriever`
  - `ToolCatalog`
  - `ControlPlaneGateway`
- `runtime/ports/llm.py`
  - `LLMServiceSpec`
  - `LLMPort`
  - optional extensions: `LLMCancellable`, `LLMRuntimeConfigurable`
- `runtime/ports/tts.py`
  - `TTSServiceSpec`
  - `TTSPort`
- `runtime/ports/asr.py`
  - `ASRServiceSpec`
  - `ASRPort`
  - explicit mode ports: `OfflineASRPort`, `StreamingASRPort`
- `runtime/ports/service_factory.py`
  - `RealtimeServiceFactory`

## Adapter Layer

- `providers/factory/default.py` provides `DefaultRealtimeServiceFactory`.
- It maps resolved provider specs to concrete adapters.
- Runtime orchestration (`runtime/pipeline/duplex.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`
- TTS:
  - supported providers: `dashscope`, `volcengine`, `openai_compatible`, `openai-compatible`, `siliconflow`
  - fallback: `MockTTSService`
- ASR:
  - supported providers: `openai_compatible`, `openai-compatible`, `siliconflow`, `dashscope`, `volcengine`
  - fallback: `BufferedASRService`

## Notes

- This is a draft contract set; follow-up work can add explicit capability negotiation and contract-version fields.