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>
This commit is contained in:
2026-07-14 12:47:49 +08:00
co-authored by Claude Opus 4.6
parent c049c3c1b1
commit ec261d57c2
59 changed files with 3801 additions and 122 deletions
+56 -4
View File
@@ -10,6 +10,7 @@ authentication can be added later without changing route signatures.
from __future__ import annotations
import json
from typing import TYPE_CHECKING, Callable, Literal
from cloud.auth import (
@@ -32,6 +33,8 @@ from cloud.sdk.models import (
TaskAttemptResponse,
TaskListItem,
TaskListResponse,
TaskPlannerDecisionItem,
TaskPlannerDecisionListResponse,
TaskStatusResponse,
TaskSubmissionRequest,
TaskSubmissionResponse,
@@ -144,14 +147,16 @@ def create_cloud_router(
failure_reason=task.failure_reason,
target_host_id=task.constraints.target_host_id,
target_device_id=task.constraints.target_device_id,
progress_step_index=task.progress_step_index,
progress_step_status=task.progress_step_status,
progress_summary=task.progress_summary,
progress_updated_at=task.progress_updated_at,
)
@router.get("/tasks", response_model=TaskListResponse)
def list_tasks(
request: Request,
status_filter: Literal[
"queued", "assigned", "dispatched", "done", "failed"
]
status_filter: Literal["queued", "assigned", "dispatched", "done", "failed"]
| None = Query(default=None, alias="status"),
limit: int = Query(default=50, ge=1, le=100),
offset: int = Query(default=0, ge=0),
@@ -177,6 +182,10 @@ def create_cloud_router(
target_host_id=task.constraints.target_host_id,
target_device_id=task.constraints.target_device_id,
created_at=task.created_at,
progress_step_index=task.progress_step_index,
progress_step_status=task.progress_step_status,
progress_summary=task.progress_summary,
progress_updated_at=task.progress_updated_at,
)
for task in tasks
],
@@ -218,6 +227,47 @@ def create_cloud_router(
for attempt in attempts
]
@router.get(
"/tasks/{task_id}/planner-decisions",
response_model=TaskPlannerDecisionListResponse,
)
def list_task_planner_decisions(
task_id: str,
request: Request,
attempt: int = Query(ge=0),
) -> TaskPlannerDecisionListResponse:
_authorize(request, TASKS_READ_SCOPE)
task = scheduler.store.get_task(task_id)
if task is None:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail=f"task {task_id!r} not found",
)
records = scheduler.store.list_planner_decisions(
task_id=task_id,
attempt=attempt,
)
items: list[TaskPlannerDecisionItem] = []
for rec in records:
try:
parsed_args = (
json.loads(rec.arguments_json) if rec.arguments_json else {}
)
except Exception:
parsed_args = {}
items.append(
TaskPlannerDecisionItem(
step_index=rec.step_index,
attempt=rec.attempt,
system_prompt=rec.system_prompt,
user_prompt=rec.user_prompt,
tool_name=rec.tool_name,
arguments=parsed_args,
created_at=rec.created_at,
)
)
return TaskPlannerDecisionListResponse(items=items)
@router.get("/devices", response_model=list[DeviceResponse])
def list_devices(request: Request) -> list[DeviceResponse]:
_authorize(request, POOL_READ_SCOPE)
@@ -332,7 +382,9 @@ def _validate_task_target(pool, constraints) -> None:
raise ValueError("target_device_id requires target_host_id")
if constraints.target_host_id is None:
return
if not any(host.host_id == constraints.target_host_id for host in pool.list_hosts()):
if not any(
host.host_id == constraints.target_host_id for host in pool.list_hosts()
):
raise ValueError(f"target host {constraints.target_host_id!r} is not known")
if constraints.target_device_id is not None and not any(
device.host_id == constraints.target_host_id