feat(voice): run pipeline eyes-free (STT -> Brain -> TTS), defer screen share

Make source/vision optional so the conversation loop runs with no screen
capture. Add Settings.voice() preset and `python -m wsai --voice` demo.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

PLAN.md

@@ -2,6 +2,12 @@
 
 디스코드 화면공유를 실시간으로 함께 보며 **음성으로** 대화하는 AI.
 
+## 방향 전환 (2026-08-11)
+
+- **화면공유(눈) 부분은 일단 보류**하고, 먼저 **음성 대화 루프 STT → 두뇌 → TTS**를 완성한다.
+- 파이프라인은 이제 눈 없이(source/vision = None) 돌아간다: `python -m wsai --voice`.
+- 화면공유 관문 1(DAVE) 성과는 아래에 보존. 나중에 눈을 다시 붙일 때 재사용한다.
+
 ## 확정된 결정 (2026-08-09)
 
 1. **캡처 방식 (눈)** — 사용자 요구: 스크린샷/브라우저 캡처 ❌,

tests/test_pipeline.py

@@ -35,6 +35,27 @@ def test_mock_pipeline_runs_and_replies(capsys):
     assert "화면:" in replies[0]
 
 
+def test_voice_only_pipeline_runs_without_eyes():
+    """Eyes-free config (no source/vision) still runs STT -> Brain -> TTS."""
+    replies: list[str] = []
+
+    class CapturingTTS(MockTTS):
+        async def speak(self, reply):
+            replies.append(reply.text)
+
+    pipe = Pipeline(
+        brain=MockBrain(),
+        stt=MockSTT(script=["안녕", "잘 있어"], interval=0.05),
+        tts=CapturingTTS(),
+    )
+
+    asyncio.run(asyncio.wait_for(pipe.run(), timeout=5))
+
+    assert len(replies) == 2, "voice loop did not reply to every utterance"
+    # No eyes → the brain must report it has not seen a screen.
+    assert "아직 화면을 못 읽었어요" in replies[0]
+
+
 def test_history_is_bounded():
     pipe = Pipeline(
         source=MockFrameSource(limit=0),

wsai/__main__.py

@@ -1,6 +1,7 @@
 """Entry point.
 
     python -m wsai              # mock pipeline (no deps, no keys) — runs a demo
+    python -m wsai --voice      # eyes-free voice loop demo (STT -> Brain -> TTS)
     python -m wsai --live       # capture this screen + Claude eyes/brain
     python -m wsai --env        # build from WSAI_* environment variables
 
@@ -25,7 +26,8 @@ async def _run(settings: Settings, demo: bool) -> None:
         from .pipeline import Pipeline
 
         pipe = build(settings)
-        pipe.source = MockFrameSource(interval=0.3, limit=4)
+        if pipe.source is not None:  # keep eyes-free configs eyes-free
+            pipe.source = MockFrameSource(interval=0.3, limit=4)
         if pipe.stt is not None:
             pipe.stt = MockSTT(interval=0.4)
         await pipe.run()
@@ -35,6 +37,7 @@ async def _run(settings: Settings, demo: bool) -> None:
 
 def main() -> None:
     ap = argparse.ArgumentParser(prog="wsai")
+    ap.add_argument("--voice", action="store_true", help="eyes-free voice loop (STT -> Brain -> TTS)")
     ap.add_argument("--live", action="store_true", help="capture screen + Claude backends")
     ap.add_argument("--env", action="store_true", help="build from WSAI_* env vars")
     ap.add_argument("-v", "--verbose", action="store_true")
@@ -45,7 +48,9 @@ def main() -> None:
         format="%(levelname)s %(name)s: %(message)s",
     )
 
-    if args.live:
+    if args.voice:
+        settings, demo = Settings.voice(), True
+    elif args.live:
         settings, demo = Settings.live(), False
     elif args.env:
         settings, demo = Settings.from_env(), False

wsai/config.py

@@ -16,12 +16,12 @@ from dataclasses import dataclass
 
 @dataclass
 class Settings:
-    source: str = "mock"       # mock | mss
+    source: str | None = "mock"  # mock | mss | None (eyes-free)
-    vision: str = "mock"       # mock | claude
+    vision: str | None = "mock"  # mock | claude | None (eyes-free)
-    stt: str | None = "mock"   # mock | (whisper) | None
+    stt: str | None = "mock"     # mock | (whisper) | None
-    tts: str | None = "mock"   # mock | (melo)    | None
+    tts: str | None = "mock"     # mock | (melo)    | None
-    brain: str = "mock"        # mock | claude
+    brain: str = "mock"          # mock | claude
-    text: str | None = None    # None | (discord)
+    text: str | None = None      # None | (discord)
 
     capture_interval: float = 1.5
     anthropic_model: str = "claude-sonnet-4-5"
@@ -51,3 +51,12 @@ class Settings:
         """A realistic local config: capture this screen, Claude eyes+brain,
         mock voice (until STT/TTS backends are wired)."""
         return cls(source="mss", vision="claude", brain="claude", stt="mock", tts="mock")
+
+    @classmethod
+    def voice(cls) -> "Settings":
+        """Eyes-free voice loop: no screen share, just STT -> Brain -> TTS.
+
+        Screen capture is deferred, so source/vision are off. Backends default
+        to mock so it runs out of the box; flip stt/tts/brain to real ones as
+        they land."""
+        return cls(source=None, vision=None, stt="mock", tts="mock", brain="mock")

wsai/factory.py

@@ -19,6 +19,8 @@ def build(settings: Settings) -> Pipeline:
 
 
 def _source(s: Settings):
+    if s.source in (None, "none"):
+        return None
     if s.source == "mss":
         from .backends.capture_mss import MSSFrameSource
 
@@ -29,6 +31,8 @@ def _source(s: Settings):
 
 
 def _vision(s: Settings):
+    if s.vision in (None, "none"):
+        return None
     if s.vision == "claude":
         from .backends.claude import ClaudeVision
 

wsai/pipeline.py

@@ -26,15 +26,16 @@ class Pipeline:
     * perception: FrameSource -> VisionBackend -> SharedScreenContext
     * conversation: (SpeechToText | TextChannel) -> Brain -> (TextToSpeech | TextChannel)
 
-    Either input/output half can be None, so you can run text-only, voice-only,
+    Any half can be omitted. With no source/vision it runs eyes-free as a pure
-    or a headless "just watch" configuration.
+    voice loop (STT -> Brain -> TTS); with no stt/tts it runs text-only; with no
+    conversation it is a headless "just watch" configuration.
     """
 
     def __init__(
         self,
         *,
-        source: FrameSource,
+        source: FrameSource | None = None,
-        vision: VisionBackend,
+        vision: VisionBackend | None = None,
         brain: Brain,
         stt: SpeechToText | None = None,
         tts: TextToSpeech | None = None,
@@ -53,6 +54,8 @@ class Pipeline:
 
     # -- perception -------------------------------------------------------- #
     async def _perceive(self) -> None:
+        if self.source is None or self.vision is None:
+            return  # eyes-free (voice-only) configuration
         async for frame in self.source.frames():
             try:
                 obs = await self.vision.describe(frame)