feat(host-agent): persist UI-tree evidence and add overlay/action visualization
Tests / Test passed: 863

Fixes issue 3: the host-agent console showed OCR results but never real
UI-tree data, because _ui_tree_nodes() checked for a get_ui_tree/ui_tree
tool action that has never existed anywhere in the codebase.

- storage/timeline.py: add a ui_tree_results field to TimelineRecord and
  Timeline.append(), mirroring the existing ocr_results field.
- runtime/task.py: _append_timeline() now extracts scene.elements with
  source == "ui" into ui_tree_results (scene_builder.build_scene() already
  preserved these; they were just never persisted).
- host_agent/web/app.py: _ui_tree_nodes() reads the new field directly
  instead of the dead tool-action check. New _overlay_payload() exposes
  each step's scene dimensions and fused element list for client-side
  rendering.
- task_detail.html: adds a toggle to overlay OCR (orange) and UI-tree
  (blue) bounding boxes on the before-action screenshot, plus a visual
  marker for the actually executed action (tap circle, or an animated
  swipe path) using an SVG viewBox so no manual coordinate-scaling JS is
  needed. Legacy/incomplete records degrade to no overlay, never an error.

Also corrects openspec/specs/runtime-task-evidence and
host-agent-console-task-pages, which had encoded the same nonexistent-tool
assumption, via the new host-agent-console-visual-evidence change.

600 tests passing; ruff/compileall/openspec validate all clean.
This commit is contained in:
2026-07-15 14:39:28 +08:00
parent 367fd0d412
commit 8162509158
12 changed files with 767 additions and 23 deletions
+41
View File
@@ -83,3 +83,44 @@ def test_timeline_records_before_and_after_screenshots_with_ocr(tmp_path) -> Non
assert Path(record["after_screenshot_path"]).read_bytes() == after
assert record["screenshot_path"] == record["after_screenshot_path"]
assert record["ocr_results"][0]["text"] == "Search"
def test_timeline_records_ui_tree_results(tmp_path) -> None:
timeline = Timeline(ArtifactStore(tmp_path / "history"))
timeline.append(
task_id="task-ui-tree",
scene={"screen": {"width": 100, "height": 200}, "elements": []},
prompt="goal",
tool_call={"action": "tap", "description": "tap search"},
result={"ok": True},
screenshot=PNG_10X20,
ui_tree_results=[
{
"id": "ui-000",
"type": "button",
"text": "Search",
"bounds": {"x": 1, "y": 2, "width": 3, "height": 4},
"confidence": None,
}
],
)
record = timeline.read("task-ui-tree")[0]
assert record["ui_tree_results"][0]["text"] == "Search"
def test_timeline_defaults_ui_tree_results_to_empty_list(tmp_path) -> None:
timeline = Timeline(ArtifactStore(tmp_path / "history"))
timeline.append(
task_id="task-no-ui-tree",
scene={"screen": {"width": 1, "height": 1}, "elements": []},
prompt="goal",
tool_call={"action": "input_text"},
result={"ok": True},
screenshot=PNG_10X20,
)
record = timeline.read("task-no-ui-tree")[0]
assert record["ui_tree_results"] == []