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).

requirements.txt

@@ -0,0 +1,17 @@
+# Core skeleton has NO required third-party deps (mock mode is pure stdlib).
+# Install extras per backend you enable:
+
+# --- screen capture (WSAI_SOURCE=mss) ---
+# mss
+# pillow
+
+# --- cloud eyes + brain (WSAI_VISION=claude / WSAI_BRAIN=claude) ---
+# anthropic
+
+# --- planned voice backends (not yet implemented) ---
+# faster-whisper      # STT
+# sounddevice         # mic capture
+# (a TTS engine, e.g. MeloTTS)
+
+# --- dev ---
+# pytest