feat(runtime): capture step evidence in console

tests/test_task_loop.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from pathlib import Path
+
 from core.models import Bounds, Scene, SceneElement, Task
 from runtime.executor import Executor, ExecutorConfig
 from runtime.planner import PlannedStep, Planner
@@ -112,3 +114,52 @@ def test_task_runner_stops_before_the_next_planned_action() -> None:
     assert result.status == "failed"
     assert result.failure_reason == "execution interrupted"
     assert actions == ["tap"]
+
+
+def test_task_runner_persists_action_evidence_and_raw_ocr(tmp_path) -> None:
+    scene = Scene(
+        width=10,
+        height=20,
+        elements=[],
+        ocr_elements=[
+            SceneElement(
+                id="ocr-001",
+                type="text",
+                text="Search",
+                bounds=Bounds(1, 2, 3, 4),
+                confidence=0.98,
+                source="ocr",
+            )
+        ],
+    )
+    screenshots = iter(
+        [
+            b"planning",
+            b"before-action",
+            b"after-action",
+            b"completion-check",
+        ]
+    )
+    timeline = Timeline(ArtifactStore(tmp_path / "history"))
+    runner = TaskRunner(
+        planner=ScriptedPlanner(
+            [PlannedStep(action="tap", description="tap search", args={})]
+        ),
+        executor=Executor(
+            tools={"tap": lambda **kwargs: {"ok": True}},
+            config=ExecutorConfig(max_retries=1, backoff_seconds=0),
+        ),
+        timeline=timeline,
+        config=TaskRunnerConfig(max_steps=2),
+        observer=lambda device_id: scene,
+        screenshot_provider=lambda device_id: next(screenshots),
+    )
+
+    result = runner.run(Task(goal="tap search", device_id="iphone-1"))
+
+    assert result.status == "completed"
+    record = timeline.read(result.id)[0]
+    assert Path(record["before_screenshot_path"]).read_bytes() == b"before-action"
+    assert Path(record["after_screenshot_path"]).read_bytes() == b"after-action"
+    assert record["tool_call"]["description"] == "tap search"
+    assert record["ocr_results"][0]["text"] == "Search"