q792602257andClaude Opus 4.6
ec261d57c2
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>
48 lines
1.3 KiB
Python
48 lines
1.3 KiB
Python
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass, field
|
|
from typing import TYPE_CHECKING, Any
|
|
|
|
from core.models import Scene
|
|
from runtime.context import TaskContext
|
|
|
|
if TYPE_CHECKING:
|
|
from world.models import WorldState
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class PlannedStep:
|
|
action: str
|
|
description: str
|
|
args: dict[str, Any] = field(default_factory=dict)
|
|
expected_text: str | None = None
|
|
# The actual prompt sent to the LLM for this step (AI planners only).
|
|
# ``None`` for non-LLM planners; TaskRunner falls back to the task goal.
|
|
prompt: str | None = None
|
|
|
|
|
|
class Planner:
|
|
def plan(
|
|
self,
|
|
*,
|
|
goal: str,
|
|
scene: Scene,
|
|
context: TaskContext,
|
|
world: "WorldState | None" = None,
|
|
screenshot: bytes | None = None,
|
|
) -> list[PlannedStep]:
|
|
if context.step_results:
|
|
return []
|
|
return [
|
|
PlannedStep(
|
|
action="describe_screen",
|
|
description=f"Observe current screen for goal: {goal}",
|
|
args={},
|
|
)
|
|
]
|
|
|
|
def goal_reached(self, *, goal: str, scene: Scene, context: TaskContext) -> bool:
|
|
return bool(context.step_results) and all(
|
|
result.success for result in context.step_results
|
|
)
|