feat(host-agent): persist UI-tree evidence and add overlay/action visualization
Tests / Test passed: 863
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:
@@ -223,18 +223,8 @@ def test_authenticated_task_detail_renders_complete_step_evidence(tmp_path) -> N
|
||||
task_id=task.id,
|
||||
scene={"screen": {"width": 10, "height": 20}, "elements": []},
|
||||
prompt="inspect the current UI tree",
|
||||
tool_call={"action": "get_ui_tree", "description": "inspect UI tree"},
|
||||
result={
|
||||
"result": [
|
||||
{
|
||||
"id": "search",
|
||||
"type": "button",
|
||||
"text": "Search",
|
||||
"bounds": {"x": 1, "y": 2, "width": 3, "height": 4},
|
||||
"confidence": 0.98,
|
||||
}
|
||||
]
|
||||
},
|
||||
tool_call={"action": "tap", "description": "tap search"},
|
||||
result={"ok": True},
|
||||
before_screenshot=PNG_10X20,
|
||||
after_screenshot=PNG_10X20 + b"after",
|
||||
ocr_results=[
|
||||
@@ -244,6 +234,15 @@ def test_authenticated_task_detail_renders_complete_step_evidence(tmp_path) -> N
|
||||
"confidence": 0.95,
|
||||
}
|
||||
],
|
||||
ui_tree_results=[
|
||||
{
|
||||
"id": "search",
|
||||
"type": "button",
|
||||
"text": "Search",
|
||||
"bounds": {"x": 1, "y": 2, "width": 3, "height": 4},
|
||||
"confidence": 0.98,
|
||||
}
|
||||
],
|
||||
)
|
||||
|
||||
client, _ = _build_client(
|
||||
@@ -278,3 +277,51 @@ def test_tasks_list_shows_empty_state(tmp_path) -> None:
|
||||
response = client.get("/tasks")
|
||||
assert response.status_code == 200
|
||||
assert "No executions recorded yet" in response.text
|
||||
|
||||
|
||||
def test_ui_tree_nodes_reads_persisted_field_directly() -> None:
|
||||
from host_agent.web.app import _ui_tree_nodes
|
||||
|
||||
record = {
|
||||
"ui_tree_results": [
|
||||
{"id": "search", "type": "button", "text": "Search"},
|
||||
"not-a-dict",
|
||||
]
|
||||
}
|
||||
assert _ui_tree_nodes(record) == [
|
||||
{"id": "search", "type": "button", "text": "Search"}
|
||||
]
|
||||
|
||||
|
||||
def test_ui_tree_nodes_defaults_to_empty_for_legacy_record() -> None:
|
||||
from host_agent.web.app import _ui_tree_nodes
|
||||
|
||||
assert _ui_tree_nodes({}) == []
|
||||
assert _ui_tree_nodes({"ui_tree_results": "not-a-list"}) == []
|
||||
|
||||
|
||||
def test_overlay_payload_combines_scene_dimensions_and_elements() -> None:
|
||||
from host_agent.web.app import _overlay_payload
|
||||
|
||||
record = {
|
||||
"scene": {
|
||||
"screen": {"width": 100, "height": 200},
|
||||
"elements": [{"id": "ui-000", "source": "ui"}, "not-a-dict"],
|
||||
}
|
||||
}
|
||||
assert _overlay_payload(record) == {
|
||||
"width": 100,
|
||||
"height": 200,
|
||||
"elements": [{"id": "ui-000", "source": "ui"}],
|
||||
}
|
||||
|
||||
|
||||
def test_overlay_payload_defaults_gracefully_for_legacy_record() -> None:
|
||||
from host_agent.web.app import _overlay_payload
|
||||
|
||||
assert _overlay_payload({}) == {"width": 0, "height": 0, "elements": []}
|
||||
assert _overlay_payload({"scene": "not-a-dict"}) == {
|
||||
"width": 0,
|
||||
"height": 0,
|
||||
"elements": [],
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user