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/backends/claude.py

@@ -0,0 +1,81 @@
+"""Cloud brain + vision via the Anthropic (Claude) API.
+
+Both share one client. Vision sends the frame as a base64 image; the brain is a
+plain chat call that receives the latest screen description as context.
+
+Requires: pip install anthropic
+Env: ANTHROPIC_API_KEY
+"""
+
+from __future__ import annotations
+
+import base64
+import os
+import time
+
+from ..interfaces import Frame, Reply, ScreenObservation
+
+
+def _client(api_key: str | None):
+    import anthropic
+
+    return anthropic.AsyncAnthropic(api_key=api_key or os.environ.get("ANTHROPIC_API_KEY"))
+
+
+class ClaudeVision:
+    def __init__(self, *, model: str = "claude-sonnet-4-5", api_key: str | None = None) -> None:
+        self.model = model
+        self._client = _client(api_key)
+
+    async def describe(self, frame: Frame, hint: str | None = None) -> ScreenObservation:
+        prompt = hint or (
+            "이건 디스코드 화면공유 캡처야. 지금 화면에서 무슨 일이 벌어지는지 "
+            "2~3문장으로 한국어로 간결하게 설명해줘. 코드/에러/게임/문서 등 맥락을 짚어줘."
+        )
+        b64 = base64.b64encode(frame.data).decode()
+        resp = await self._client.messages.create(
+            model=self.model,
+            max_tokens=300,
+            messages=[
+                {
+                    "role": "user",
+                    "content": [
+                        {
+                            "type": "image",
+                            "source": {"type": "base64", "media_type": frame.mime, "data": b64},
+                        },
+                        {"type": "text", "text": prompt},
+                    ],
+                }
+            ],
+        )
+        text = "".join(b.text for b in resp.content if b.type == "text")
+        return ScreenObservation(text=text.strip(), ts=frame.ts)
+
+
+class ClaudeBrain:
+    SYSTEM = (
+        "너는 사용자의 디스코드 화면공유를 실시간으로 함께 보는 AI 파트너야. "
+        "화면 설명을 참고해 자연스러운 반말/존댓말은 사용자에 맞추고, 짧고 대화하듯 답해. "
+        "화면을 못 봤으면 솔직히 말해."
+    )
+
+    def __init__(self, *, model: str = "claude-sonnet-4-5", api_key: str | None = None) -> None:
+        self.model = model
+        self._client = _client(api_key)
+
+    async def respond(self, user_text, screen, history) -> Reply:
+        msgs = []
+        for user, ai in history:
+            msgs.append({"role": "user", "content": user})
+            msgs.append({"role": "assistant", "content": ai})
+        screen_note = f"[지금 화면] {screen.text}\n\n" if screen else "[지금 화면] (아직 못 읽음)\n\n"
+        msgs.append({"role": "user", "content": screen_note + user_text})
+        resp = await self._client.messages.create(
+            model=self.model,
+            max_tokens=400,
+            system=self.SYSTEM,
+            messages=msgs,
+        )
+        text = "".join(b.text for b in resp.content if b.type == "text")
+        return Reply(text=text.strip(), ts=time.monotonic())