refactor: extrai coordenação da conversa para VoiceSession

README.md

@@ -25,7 +25,8 @@ A modular voice pipeline for streaming audio input, speech transcription, agent
 ```mermaid
 flowchart TB
     C[Audio Client] <-->|WebSocket /ws/audio · JSON + binary PCM| G[Audio Gateway · FastAPI]
-    G --> P[VoicePipeline]
+    G --> U[VoiceSession · conversation lifecycle]
+    U --> P[VoicePipeline]
     P --- S[SessionState · session and audio sequence]
     P --- T[TurnManager · semantic turn state]
     G --> STT[NVIDIA ASR · STT per turn]
@@ -37,7 +38,7 @@ flowchart TB
     G -->|Streamed audio| C
 ```
 
-The **Audio Gateway** handles transport and protocol messages. **VoicePipeline** coordinates processing and task ownership. **SessionState** tracks session and audio sequence; **TurnManager** enforces turn transitions. A new STT adapter is created for each turn, while Agent and TTS adapters are created per session.
+The **Audio Gateway** handles transport, protocol validation, and application composition. **VoiceSession** coordinates STT, finalization, interruption, rollback, and provider cleanup. **VoicePipeline** retains processing, turn-state operations, and execution-task ownership. **SessionState** tracks session and audio sequence; **TurnManager** enforces turn transitions. A new STT adapter is created for each turn, while Agent and TTS adapters are created per session.
 
 ## Architecture Backbone & Abstraction Boundaries
 
@@ -57,6 +58,7 @@ The architecture separates five concerns:
 flowchart TB
     Client["Web Client / Audio Client"]
     Gateway["Audio Gateway<br/>FastAPI · WebSocket"]
+    UseCase["VoiceSession<br/>Conversation Lifecycle"]
     Pipeline["VoicePipeline<br/>Orchestration & Streaming"]
     Session["SessionState<br/>Session Lifecycle"]
     Turns["TurnManager<br/>Semantic Turn Lifecycle"]
@@ -83,7 +85,8 @@ flowchart TB
     end
 
     Client <-->|"JSON Events + Binary PCM"| Gateway
-    Gateway --> Pipeline
+    Gateway --> UseCase
+    UseCase --> Pipeline
 
     Pipeline --- Session
     Pipeline --- Turns
@@ -144,7 +147,9 @@ The primary configuration components are:
 | Dynamic provider loading | `providers.py` |
 | Session lifecycle | `domain/session.py` |
 | Semantic turn lifecycle | `turn_manager.py` |
-| Execution orchestration | `voice_pipeline.py` |
+| Conversation lifecycle | `application/voice_session.py` |
+| Application output events | `application/events.py` |
+| Processing and execution tasks | `voice_pipeline.py` |
 
 ### Streaming Execution Backbone
 
@@ -176,7 +181,8 @@ flowchart TB
     Output["WebSocket PCM Output"]
 
     Input --> Gateway
-    Gateway --> STT
+    Gateway --> UseCase["VoiceSession"]
+    UseCase --> STT
     STT --> Transcript
     Transcript --> Agent
 
@@ -381,6 +387,7 @@ The script reads `audios/chafik_normalize.wav` (16 kHz, mono, 16-bit PCM), sends
 config/                         Environment YAML and provider catalog
 src/voice_assistant/
   audio_gateway/app/            WebSocket endpoint and protocol
+  application/                  VoiceSession and transport-independent events
   domain/                       Session state and domain rules
   audio/                        Canonical audio models
   stt/                          STT contract, mock and NVIDIA adapter