Add grid planner, CI, and tests

tests/conftest.py

@@ -0,0 +1,29 @@
+import base64
+
+import pytest
+
+from server.main import manager
+
+
+@pytest.fixture
+def fake_screenshot() -> str:
+    """Return a reproducible base64 string representing a dummy screenshot."""
+    return base64.b64encode(b"clickthrough-dummy").decode()
+
+
+@pytest.fixture
+def default_grid_request(fake_screenshot):
+    return {
+        "width": 640,
+        "height": 480,
+        "screenshot_base64": fake_screenshot,
+        "rows": 3,
+        "columns": 3,
+    }
+
+
+@pytest.fixture(autouse=True)
+def reset_manager_state():
+    manager._grids.clear()
+    yield
+    manager._grids.clear()

tests/test_agent_runner.py

@@ -0,0 +1,53 @@
+from typing import Any, Dict
+
+from skill.agent_runner import ClickthroughAgentRunner
+from skill.clickthrough_skill import ActionPlan, ClickthroughSkill
+
+
+class DummySkill(ClickthroughSkill):
+    def __init__(self):
+        self.last_plan: ActionPlan | None = None
+
+    def describe_grid(
+        self,
+        screenshot_base64: str,
+        width: int,
+        height: int,
+        rows: int = 4,
+        columns: int = 4,
+    ) -> Dict[str, Any]:
+        return {
+            "grid_id": "dummy-grid",
+            "cells": [
+                {"cell_id": "dummy-grid-1", "label": "button", "bounds": [0, 0, 100, 100]},
+                {"cell_id": "dummy-grid-2", "label": "target", "bounds": [100, 0, 200, 100]},
+            ],
+        }
+
+    def plan_action(self, plan: ActionPlan) -> Dict[str, Any]:
+        self.last_plan = plan
+        return {"success": True, "target_cell": plan.target_cell}
+
+    def grid_summary(self, grid_id: str) -> Dict[str, Any]:
+        return {"grid_id": grid_id, "summary": "ok"}
+
+    def grid_history(self, grid_id: str) -> Dict[str, Any]:
+        return {"grid_id": grid_id, "history": []}
+
+
+def test_agent_runner_prefers_label():
+    runner = ClickthroughAgentRunner(DummySkill())
+    result = runner.run_once(
+        screenshot_base64="AA==",
+        width=120,
+        height=80,
+        preferred_label="target",
+    )
+    assert result.action["target_cell"] == "dummy-grid-2"
+    assert result.summary["summary"] == "ok"
+
+
+def test_agent_runner_defaults_to_center():
+    runner = ClickthroughAgentRunner(DummySkill())
+    result = runner.run_once(screenshot_base64="AA==", width=120, height=80)
+    assert result.action["target_cell"] == "dummy-grid-2"

tests/test_grid.py

@@ -0,0 +1,51 @@
+from server.config import ServerSettings
+from server.grid import GridManager
+from server.models import ActionPayload, ActionType, GridInitRequest
+
+
+def test_grid_creation_respects_dimensions(default_grid_request):
+    settings = ServerSettings(grid_rows=2, grid_cols=2)
+    manager = GridManager(settings)
+    request = GridInitRequest(**default_grid_request)
+    grid = manager.create_grid(request)
+
+    descriptor = grid.describe()
+    assert descriptor.grid_id
+    assert descriptor.rows == 3
+    assert descriptor.columns == 3
+    assert len(descriptor.cells) == 9
+    assert descriptor.metadata.get("width") == 640
+    assert descriptor.metadata.get("height") == 480
+
+
+def test_grid_action_records_history(default_grid_request):
+    manager = GridManager(ServerSettings())
+    request = GridInitRequest(**default_grid_request)
+    grid = manager.create_grid(request)
+    descriptor = grid.describe()
+    target_cell = descriptor.cells[0].cell_id
+
+    payload = ActionPayload(
+        grid_id=descriptor.grid_id,
+        action=ActionType.CLICK,
+        target_cell=target_cell,
+        comment="click test",
+    )
+    result = grid.apply_action(payload)
+
+    assert result.success
+    assert result.coordinates is not None
+    assert grid.action_history[-1]["coordinates"] == result.coordinates
+
+
+def test_manager_get_grid_missing(default_grid_request):
+    manager = GridManager(ServerSettings())
+    request = GridInitRequest(**default_grid_request)
+    _ = manager.create_grid(request)
+
+    try:
+        manager.get_grid("does-not-exist")
+        found = True
+    except KeyError:
+        found = False
+    assert not found