feat: scaffold watch-screen AI pipeline (mock-runnable skeleton)

Modular async pipeline: FrameSource->Vision->context and STT/text->Brain->TTS.
All stages are Protocols; mock backends run end-to-end with no deps/keys.
Real backends included: mss screen capture, Claude vision+brain (guarded imports).

wsai/config.py

@@ -0,0 +1,53 @@
+"""Configuration. Each field names a backend; the factory maps names -> classes.
+
+Defaults are all "mock" so the skeleton runs out of the box. Flip individual
+fields (via env or code) as real backends land.
+
+Env overrides (optional):
+    WSAI_SOURCE, WSAI_VISION, WSAI_STT, WSAI_TTS, WSAI_BRAIN, WSAI_TEXT
+    WSAI_CAPTURE_INTERVAL
+"""
+
+from __future__ import annotations
+
+import os
+from dataclasses import dataclass
+
+
+@dataclass
+class Settings:
+    source: str = "mock"       # mock | mss
+    vision: str = "mock"       # mock | claude
+    stt: str | None = "mock"   # mock | (whisper) | None
+    tts: str | None = "mock"   # mock | (melo)    | None
+    brain: str = "mock"        # mock | claude
+    text: str | None = None    # None | (discord)
+
+    capture_interval: float = 1.5
+    anthropic_model: str = "claude-sonnet-4-5"
+
+    @classmethod
+    def from_env(cls) -> "Settings":
+        def opt(name: str, default):
+            v = os.environ.get(name)
+            return default if v is None else (None if v.lower() == "none" else v)
+
+        return cls(
+            source=opt("WSAI_SOURCE", "mock"),
+            vision=opt("WSAI_VISION", "mock"),
+            stt=opt("WSAI_STT", "mock"),
+            tts=opt("WSAI_TTS", "mock"),
+            brain=opt("WSAI_BRAIN", "mock"),
+            text=opt("WSAI_TEXT", None),
+            capture_interval=float(os.environ.get("WSAI_CAPTURE_INTERVAL", "1.5")),
+        )
+
+    @classmethod
+    def mock(cls) -> "Settings":
+        return cls()
+
+    @classmethod
+    def live(cls) -> "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")