feat: surface task execution progress across Host Agent and Cloud

Host Agent now persists step-level execution detail locally (via a real TaskMetadataStore/Timeline wired into TaskRunner) and reports a bounded in-progress snapshot piggybacked on lease renewal. Cloud persists that snapshot per active assignment and exposes it through the existing task list/detail query path; Cloud Console renders it as a live badge. Host Agent's local console gains authenticated, read-only task list and detail/timeline pages (same-origin, server-rendered) with inlined screenshots. Also fixes a pre-existing gap in the shared Timeline: the actual per-step LLM prompt is now recorded instead of the task goal, benefiting both Runtime and Host Agent consoles. When a host uses the cloud planner transport, each decide call's prompt and resulting tool decision are durably logged in a new planner_decision_log table (with bounded retention) and browsable from Cloud Console; direct-transport hosts explicitly surface a "not reported" state. Includes Alembic migrations 0008 (progress columns on scheduled_tasks) and 0009 (planner_decision_log), bounded Host-Agent-local retention, dual-backend repository parity, and Vitest + pytest coverage. Task 6.5 (manual end-to-end device verification) remains. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-07-14 12:47:49 +08:00
parent c049c3c1b1
commit ec261d57c2
59 changed files with 3801 additions and 122 deletions
@@ -0,0 +1,210 @@
+"""Tests for Host Agent console /tasks routes (task 5.4)."""
+
+from __future__ import annotations
+
+import re
+from datetime import UTC, datetime
+
+from fastapi.testclient import TestClient
+
+from device.manager import DeviceManager
+from host_agent.config import HostAgentConfig
+from host_agent.history import ConsoleHistoryStore
+from host_agent.identity import HostIdentityStore
+from host_agent.local_account import LocalAccountStore
+from host_agent.status import AgentStatusTracker
+from host_agent.web.app import create_console_app
+from host_agent.web.auth import SessionManager
+from storage.artifact_store import ArtifactStore
+from storage.device_config import DeviceConfigStore
+from storage.task_metadata import TaskMetadataStore
+from storage.timeline import Timeline
+from tests.fakes import PNG_10X20
+
+CSRF_PATTERN = re.compile(r'name="csrf_token" value="([^"]+)"')
+
+
+def _build_client(
+    tmp_path,
+    *,
+    metadata_store: TaskMetadataStore | None = None,
+    timeline: Timeline | None = None,
+    create_account: bool = True,
+) -> tuple[TestClient, dict]:
+    config = HostAgentConfig(
+        control_plane_url="https://control.example",
+        host_id="host-a",
+        token="secret",
+        enrollment_managed=False,
+        console_session_ttl_seconds=3600.0,
+    )
+    manager = DeviceManager()
+    config_store = DeviceConfigStore(tmp_path / "devices.sqlite3")
+    local_account_store = LocalAccountStore(tmp_path / "host_local_account.json")
+    if create_account:
+        local_account_store.create("operator", "correct horse battery staple")
+    identity_store = HostIdentityStore(tmp_path / "host_identity.json")
+    history_store = ConsoleHistoryStore(tmp_path / "history.sqlite3")
+    status_tracker = AgentStatusTracker()
+    session_manager = SessionManager(ttl_seconds=3600.0)
+
+    if metadata_store is None:
+        metadata_store = TaskMetadataStore(tmp_path / "task_progress.sqlite3")
+    if timeline is None:
+        timeline = Timeline(ArtifactStore(tmp_path / "history"))
+
+    app = create_console_app(
+        config=config,
+        manager=manager,
+        config_store=config_store,
+        local_account_store=local_account_store,
+        identity_store=identity_store,
+        history_store=history_store,
+        status_tracker=status_tracker,
+        session_manager=session_manager,
+        enrollment_client=None,
+        metadata_store=metadata_store,
+        timeline=timeline,
+    )
+    client = TestClient(app)
+    context = {
+        "metadata_store": metadata_store,
+        "timeline": timeline,
+        "session_manager": session_manager,
+    }
+    return client, context
+
+
+def _login(client: TestClient) -> str:
+    response = client.post(
+        "/login",
+        data={"username": "operator", "password": "correct horse battery staple"},
+    )
+    assert response.status_code == 200
+    match = CSRF_PATTERN.search(response.text)
+    assert match is not None
+    return match.group(1)
+
+
+# --------------------------------------------------------------------------- #
+# Unauthenticated requests rejected
+# --------------------------------------------------------------------------- #
+
+
+def test_unauthenticated_tasks_list_redirects_to_login(tmp_path) -> None:
+    client, _ = _build_client(tmp_path)
+
+    response = client.get("/tasks", follow_redirects=False)
+
+    assert response.status_code == 303
+    assert response.headers["location"] == "/login"
+
+
+def test_unauthenticated_task_detail_redirects_to_login(tmp_path) -> None:
+    client, _ = _build_client(tmp_path)
+
+    response = client.get("/tasks/some-id", follow_redirects=False)
+
+    assert response.status_code == 303
+    assert response.headers["location"] == "/login"
+
+
+def test_unauthenticated_devices_page_also_redirects_for_parity(tmp_path) -> None:
+    """Confirm /tasks has the same auth behavior as the existing /devices route."""
+    client, _ = _build_client(tmp_path)
+
+    response = client.get("/devices", follow_redirects=False)
+
+    assert response.status_code == 303
+    assert response.headers["location"] == "/login"
+
+
+# --------------------------------------------------------------------------- #
+# Authenticated list/detail render
+# --------------------------------------------------------------------------- #
+
+
+def test_authenticated_tasks_list_renders_completed_task(tmp_path) -> None:
+    from core.models import Task
+
+    metadata_store = TaskMetadataStore(tmp_path / "task_progress.sqlite3")
+    timeline = Timeline(ArtifactStore(tmp_path / "history"))
+
+    task = Task(
+        id="task-visible",
+        goal="open settings",
+        device_id="iphone-1",
+        status="completed",
+        created_at=datetime(2026, 7, 10, tzinfo=UTC),
+        updated_at=datetime(2026, 7, 10, 1, tzinfo=UTC),
+        completed_at=datetime(2026, 7, 10, 1, tzinfo=UTC),
+    )
+    metadata_store.create_task(task)
+
+    client, _ = _build_client(
+        tmp_path, metadata_store=metadata_store, timeline=timeline
+    )
+    _login(client)
+
+    response = client.get("/tasks")
+    assert response.status_code == 200
+    assert "task-visible" in response.text
+    assert "completed" in response.text
+
+
+def test_authenticated_task_detail_renders_timeline_with_screenshot(tmp_path) -> None:
+    from core.models import Task
+
+    metadata_store = TaskMetadataStore(tmp_path / "task_progress.sqlite3")
+    timeline = Timeline(ArtifactStore(tmp_path / "history"))
+
+    task = Task(
+        id="task-detail",
+        goal="tap search",
+        device_id="iphone-1",
+        status="completed",
+        created_at=datetime(2026, 7, 10, tzinfo=UTC),
+        updated_at=datetime(2026, 7, 10, 1, tzinfo=UTC),
+    )
+    metadata_store.create_task(task)
+
+    timeline.append(
+        task_id="task-detail",
+        scene={"screen": {"width": 10, "height": 20}, "elements": []},
+        prompt="find search button",
+        tool_call={"action": "tap", "x": 5, "y": 10},
+        result={"ok": True},
+        screenshot=PNG_10X20,
+    )
+
+    client, _ = _build_client(
+        tmp_path, metadata_store=metadata_store, timeline=timeline
+    )
+    _login(client)
+
+    response = client.get("/tasks/task-detail")
+    assert response.status_code == 200
+    assert "task-detail" in response.text
+    # Timeline step visible.
+    assert "Step 1" in response.text
+    assert "find search button" in response.text
+    # Screenshot inlined as base64 data URI.
+    assert "data:image/png;base64," in response.text
+
+
+def test_task_detail_404_for_unknown_task(tmp_path) -> None:
+    client, _ = _build_client(tmp_path)
+    _login(client)
+
+    response = client.get("/tasks/nonexistent")
+    assert response.status_code == 404
+
+
+def test_tasks_list_shows_empty_state(tmp_path) -> None:
+    metadata_store = TaskMetadataStore(tmp_path / "task_progress.sqlite3")
+    client, _ = _build_client(tmp_path, metadata_store=metadata_store)
+    _login(client)
+
+    response = client.get("/tasks")
+    assert response.status_code == 200
+    assert "No tasks recorded" in response.text