init

skill/clickthrough_skill.py

@@ -0,0 +1,64 @@
+from dataclasses import dataclass
+from typing import Any, Dict
+
+import httpx
+
+
+@dataclass
+class ActionPlan:
+    grid_id: str
+    target_cell: str | None
+    action: str
+    text: str | None = None
+
+
+class ClickthroughSkill:
+    """Lightweight wrapper around the Clickthrough HTTP API."""
+
+    def __init__(self, server_url: str = "http://localhost:8000") -> None:
+        self._client = httpx.Client(base_url=server_url, timeout=10)
+
+    def describe_grid(
+        self,
+        screenshot_base64: str,
+        width: int,
+        height: int,
+        rows: int = 4,
+        columns: int = 4,
+    ) -> Dict[str, Any]:
+        payload = {
+            "width": width,
+            "height": height,
+            "rows": rows,
+            "columns": columns,
+            "screenshot_base64": screenshot_base64,
+            "memo": "agent-powered grid",
+        }
+        response = self._client.post("/grid/init", json=payload)
+        response.raise_for_status()
+        return response.json()
+
+    def plan_action(self, plan: ActionPlan) -> Dict[str, Any]:
+        payload = {
+            "grid_id": plan.grid_id,
+            "action": plan.action,
+            "target_cell": plan.target_cell,
+            "text": plan.text,
+            "comment": "skill-generated plan",
+        }
+        response = self._client.post("/grid/action", json=payload)
+        response.raise_for_status()
+        return response.json()
+
+
+if __name__ == "__main__":
+    import base64
+
+    dummy = base64.b64encode(b"fake-screenshot").decode()
+    skill = ClickthroughSkill()
+    grid = skill.describe_grid(dummy, width=800, height=600)
+    print("Grid cells:", len(grid.get("cells", [])))
+    if grid.get("cells"):
+        first_cell = grid["cells"][0]["cell_id"]
+        result = skill.plan_action(ActionPlan(grid_id=grid["grid_id"], target_cell=first_cell, action="click"))
+        print("Action result:", result)