feat(gateway): restore Gate Set C exit-time guards

Choreographer.i_am_idle now refuses with INVALID_STATE when the caller
has any pending (assigned but never claimed) task. Pre-gateway this
was implicit because the orchestrator's auto-respawn would re-spawn
the agent for the assignment, leading to a tight respawn loop. The
explicit refusal lets the agent fix the state via i_will_work_on
(dev/qa/doc) or i_will_plan (pm) first.

Existing auto-pause for in_progress tasks is preserved (Gate Set C
spec calls this out as still required) — it runs AFTER the pending
guard, so an agent with a mix of pending+in_progress is told about
the pending task first instead of silently pausing in_progress and
then looping on the pending one.

Pre-gateway reference: roboco/runtime/orchestrator.py
auto-respawn loop guards (already preserved at HEAD); the explicit
agent-facing gate is new.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Renn F
2026-05-03 03:27:54 +02:00
co-authored by Claude Opus 4.7
parent 466cc8d8f7
commit 197b0f22dc
2 changed files with 206 additions and 4 deletions
+45 -4
View File
@@ -480,10 +480,18 @@ class Choreographer:
async def i_am_idle(self, agent_id: UUID) -> Envelope:
"""Report no more work. Soft-block if there are unread A2As or @mentions.
Before marking the agent idle, auto-pause every in_progress task this
agent owns so the orchestrator's PM-closure dispatcher can wake them
when subtasks finish, instead of leaving the parent stuck at
``in_progress`` forever.
Before marking the agent idle:
1. Bail with ``idle_with_unread`` when context_briefing has unread A2A
or @mentions (must address those first).
2. Refuse with INVALID_STATE if the agent has any pending tasks
assigned but never claimed — they must call i_will_work_on (dev/qa/
doc) or i_will_plan (pm) first. (Gate Set C, pre-gateway implicit
via the orchestrator's auto-respawn.)
3. Auto-pause every in_progress task this agent owns so the
orchestrator's PM-closure dispatcher can wake them when subtasks
finish, instead of leaving the parent stuck at ``in_progress``
forever.
"""
briefing = await self._briefing_for(agent_id, None)
if briefing.get("unread_a2a") or briefing.get("unread_mentions"):
@@ -496,6 +504,8 @@ class Choreographer:
),
context_briefing=briefing,
)
if guard := await self._pending_assignment_guard(agent_id, briefing):
return guard
await self._auto_pause_in_progress_tasks(agent_id)
await self.task.mark_agent_idle(agent_id)
return Envelope.ok(
@@ -505,6 +515,37 @@ class Choreographer:
context_briefing=briefing,
)
async def _pending_assignment_guard(
self, agent_id: UUID, briefing: dict[str, Any]
) -> Envelope | None:
"""Refuse i_am_idle when caller owns any pending (unclaimed) task.
Pre-gateway: the orchestrator would respawn the agent after
i_am_idle if they still owned pending work, leading to a tight
respawn loop. Now an explicit refusal lets the agent fix it via
i_will_work_on or i_will_plan before exiting.
"""
assigned = await self.task.list_assigned_for_agent(agent_id)
pending = [t for t in assigned if str(t.status) == "pending"]
if not pending:
return None
first = pending[0]
agent = await self.task.agent_for(agent_id)
verb = "i_will_plan" if agent and agent.role in ("cell_pm", "main_pm") else (
"i_will_work_on"
)
return Envelope.invalid_state(
message=(
f"You have task {first.id} assigned but never claimed; "
"cannot idle until claimed or unclaimed."
),
remediate=(
f"call {verb}(task_id='{first.id}') to start work, or"
" unclaim it first; then retry i_am_idle"
),
context_briefing=briefing,
)
async def _auto_pause_in_progress_tasks(self, agent_id: UUID) -> None:
"""Pause every in_progress task assigned to this agent.
@@ -0,0 +1,161 @@
"""Gate Set C: exit-time guards in Choreographer.i_am_idle.
Pre-gateway behavior: an agent that signaled idle while owning unclaimed
pending work was implicitly stuck because the orchestrator's PM-closure
dispatcher would respawn them. The gateway makes this explicit:
- pending-parent guard: refuse i_am_idle if caller has any pending task
assigned. They must call i_will_work_on / i_will_plan first.
- in_progress preserved: existing auto-pause for in_progress remains.
"""
from __future__ import annotations
from typing import Any
from unittest.mock import AsyncMock, MagicMock
from uuid import uuid4
import pytest
from roboco.services.gateway.choreographer import Choreographer, ChoreographerDeps
def _make_deps(**overrides: Any) -> ChoreographerDeps:
base: dict[str, Any] = {
"task": AsyncMock(),
"work_session": AsyncMock(),
"git": AsyncMock(),
"a2a": AsyncMock(),
"journal": AsyncMock(),
"audit": AsyncMock(),
"evidence_repo": AsyncMock(),
}
base.update(overrides)
repo = base["evidence_repo"]
for method in (
"list_unread_a2a",
"list_unread_mentions",
"list_pending_notifications",
"task_metadata_gaps",
"recent_team_activity",
"blockers_in_lane",
"journal_highlights_for_task",
):
getattr(repo, method).return_value = []
return ChoreographerDeps(**base)
@pytest.mark.asyncio
async def test_i_am_idle_refuses_when_pending_assignment_exists() -> None:
"""An agent with a pending (unclaimed) task assigned cannot exit."""
agent_id = uuid4()
pending_id = uuid4()
pending = MagicMock(id=pending_id, status="pending")
task_svc = AsyncMock()
task_svc.list_assigned_for_agent.return_value = [pending]
task_svc.list_in_progress_for_agent.return_value = []
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.i_am_idle(agent_id)
body = env.as_dict()
assert body["error"] == "invalid_state"
assert str(pending_id) in body["message"] or str(pending_id) in body["remediate"]
assert "i_will_work_on" in body["remediate"] or "i_will_plan" in body["remediate"]
task_svc.mark_agent_idle.assert_not_awaited()
task_svc.pause_for_agent.assert_not_awaited()
@pytest.mark.asyncio
async def test_i_am_idle_lets_pm_through_with_pending_remediate() -> None:
"""The pending guard recommends i_will_plan when the agent is a PM."""
agent_id = uuid4()
pending_id = uuid4()
pending = MagicMock(id=pending_id, status="pending")
task_svc = AsyncMock()
task_svc.list_assigned_for_agent.return_value = [pending]
task_svc.list_in_progress_for_agent.return_value = []
task_svc.agent_for.return_value = MagicMock(role="cell_pm", team="backend")
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.i_am_idle(agent_id)
body = env.as_dict()
assert body["error"] == "invalid_state"
assert "i_will_plan" in body["remediate"]
@pytest.mark.asyncio
async def test_i_am_idle_lets_dev_through_with_pending_remediate() -> None:
"""The pending guard recommends i_will_work_on for a developer."""
agent_id = uuid4()
pending_id = uuid4()
pending = MagicMock(id=pending_id, status="pending")
task_svc = AsyncMock()
task_svc.list_assigned_for_agent.return_value = [pending]
task_svc.list_in_progress_for_agent.return_value = []
task_svc.agent_for.return_value = MagicMock(role="developer", team="backend")
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.i_am_idle(agent_id)
body = env.as_dict()
assert body["error"] == "invalid_state"
assert "i_will_work_on" in body["remediate"]
@pytest.mark.asyncio
async def test_i_am_idle_ignores_non_pending_assigned_tasks() -> None:
"""Other active states (claimed/in_progress/etc) don't trigger pending guard."""
agent_id = uuid4()
in_progress = MagicMock(id=uuid4(), status="in_progress")
task_svc = AsyncMock()
# Even though list_assigned_for_agent includes in_progress, only pending
# triggers the guard.
task_svc.list_assigned_for_agent.return_value = [in_progress]
task_svc.list_in_progress_for_agent.return_value = [in_progress]
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.i_am_idle(agent_id)
body = env.as_dict()
assert body["error"] is None
# The auto-pause path should still fire for in_progress.
task_svc.pause_for_agent.assert_awaited_once_with(agent_id, in_progress.id)
task_svc.mark_agent_idle.assert_awaited_once()
@pytest.mark.asyncio
async def test_i_am_idle_with_no_assigned_tasks_proceeds_normally() -> None:
"""Empty assignment list: no pending guard, no auto-pause, idle goes through."""
agent_id = uuid4()
task_svc = AsyncMock()
task_svc.list_assigned_for_agent.return_value = []
task_svc.list_in_progress_for_agent.return_value = []
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.i_am_idle(agent_id)
body = env.as_dict()
assert body["error"] is None
assert body["status"] == "idle"
task_svc.pause_for_agent.assert_not_awaited()
task_svc.mark_agent_idle.assert_awaited_once()
@pytest.mark.asyncio
async def test_i_am_idle_pending_guard_runs_after_unread_check() -> None:
"""Unread A2A check still wins; pending guard only runs after."""
agent_id = uuid4()
pending = MagicMock(id=uuid4(), status="pending")
task_svc = AsyncMock()
task_svc.list_assigned_for_agent.return_value = [pending]
deps = _make_deps(task=task_svc)
deps.evidence_repo.list_unread_a2a.return_value = ["mention"]
c = Choreographer(deps)
env = await c.i_am_idle(agent_id)
body = env.as_dict()
# Unread takes precedence and returns ok+idle_with_unread, NOT invalid_state
assert body["error"] is None
assert body["status"] == "idle_with_unread"
task_svc.mark_agent_idle.assert_not_awaited()