mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
Delegation detail-fidelity + PM-loop hardening (#541)
* feat(gateway): delegation detail-fidelity — details survive hand-off, both directions
Details thinned out at every delegation hop: a PM child task mapped to no
parent criterion was legal (coverage only surfaced at submit_up, after the
whole wave ran — a 12-subtask docs tree grew through 8 review rounds that
way, one child titled 'docs page and route wrapper' shipping only the
page), and QA could pass work on a gestalt read (a 4-scene video brief
shipped 3 scenes past every gate because the features existed only in
prose). Three chokepoint gates:
- delegate (down): every child must declare covers_parent_criteria
resolving against the parent's real acceptance criteria — no mapping or
an unresolvable ref rejects naming every offending child and the valid
criteria; the success envelope carries parent_ac_coverage
{covered, uncovered} so a wave-planning PM sees remaining gaps in the
same turn. Full coverage stays enforced at submit_up (waves stay legal).
- pass_review (up): mandatory criteria_verified — one {criterion,
evidence} entry per task AC, matched by the findings ledger's
id-or-exact-text matcher, evidence soup-checked and capped; rejects
naming the unverified criteria; entries render deterministically into
qa_notes as '[AC] <criterion> — verified: <evidence>' lines. The old
count-only ac_verdicts gate is superseded (arg kept for back-compat).
- video briefs (structured detail at origination): an enumerable feature
list (release highlights, or input_props.highlights carried onto a
reject re-author) becomes its own scene acceptance criterion, bounded to
the AC caps; a re-author without highlights carries the
feedback-addressed criterion instead.
Extracted findings.py's criterion matcher into shared unmatched_criteria /
uncovered_acceptance_criteria instead of duplicating it; criteria_verified
joins the WAF free-text exclusion set like findings/issues.
* fix(gateway): break the block/unblock wedge — four hardening fixes from the live PM loop
A cell task looped fe-pm/main-pm block/unblock for hours (10 cycles, 43
spawns): a transient GitHub API error resolving CI became an unwaivable
blocker finding whose own fix text said no code change was required, the
submit freshness guard then demanded a commit no finding called for,
escalate_up auto-blocked, and main-pm's correct recovery plan 422'd on
the approach length cap, degrading it to a bare unblock. Four fixes:
- pr_pass CI-unresolvable refusal is now explicitly transient-worded:
retry pr_pass shortly, do NOT pr_fail over a CI-status lookup error —
a platform blip is not a code finding
- submit freshness guard grants ONE unchanged-head resubmission per
head sha when the findings ledger has zero open rows (all addressed
without code changes) — stamped via the resubmit_unchanged_head
marker so the same head can never loop a second time
- unblock carries a flip breaker: block_flip_count marker, and at the
third flip a one-shot CEO notification flags the task as structurally
wedged (unblock itself still succeeds — the breaker signals, it does
not wedge recovery)
- i_will_plan's approach cap truncates at 800 chars instead of
rejecting — an over-detailed plan must never cost the PM its turn
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
This commit is contained in:
@@ -0,0 +1,151 @@
|
||||
"""The block/unblock flip-flop breaker.
|
||||
|
||||
Live wedge: fe-pm's escalate_up auto-blocks a task and main_pm's unblock
|
||||
resolves it, repeat — 10 flips, 43 spawns, no forward progress, no cycle
|
||||
breaker. ``unblock`` now stamps a per-task flip counter
|
||||
(``markers.block_flip_count``) and, at exactly the 3rd flip, best-effort
|
||||
alerts the CEO once — the unblock itself always still succeeds.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from datetime import UTC, datetime
|
||||
from typing import Any
|
||||
from unittest.mock import AsyncMock, MagicMock
|
||||
from uuid import uuid4
|
||||
|
||||
import pytest
|
||||
from roboco.foundation.policy.content import markers
|
||||
from roboco.services.gateway.choreographer import Choreographer, ChoreographerDeps
|
||||
from roboco.services.notification import NotificationService
|
||||
|
||||
# Named constants — ruff PLR2004 forbids magic-value comparisons.
|
||||
_TWO_FLIPS = 2
|
||||
_THREE_FLIPS = 3
|
||||
_FOUR_FLIPS = 4
|
||||
|
||||
|
||||
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)
|
||||
base["journal"].has_decision_for_task.return_value = True
|
||||
base["journal"].latest_decision_at.return_value = datetime.now(UTC)
|
||||
return ChoreographerDeps(**base)
|
||||
|
||||
|
||||
def _flip_setup() -> tuple[Choreographer, Any, Any, Any]:
|
||||
"""A blocked task whose ``unblock_with_restore`` returns the SAME mock
|
||||
object each call, so the flip-counter marker persists across repeated
|
||||
unblock() calls the way it would on one real ORM row across requests.
|
||||
"""
|
||||
pm_id = uuid4()
|
||||
task_id = uuid4()
|
||||
t = MagicMock(
|
||||
id=task_id,
|
||||
status="blocked",
|
||||
pre_block_state="in_progress",
|
||||
pre_block_assignee=uuid4(),
|
||||
pre_block_metadata={},
|
||||
dependency_ids=[],
|
||||
orchestration_markers=None,
|
||||
)
|
||||
task_svc = AsyncMock()
|
||||
task_svc.get.return_value = t
|
||||
task_svc.unblock_with_restore.return_value = t
|
||||
task_svc.unmet_dependency_ids.return_value = []
|
||||
c = Choreographer(_make_deps(task=task_svc))
|
||||
return c, pm_id, task_id, t
|
||||
|
||||
|
||||
async def _unblock_once(c: Choreographer, pm_id: Any, task_id: Any, t: Any) -> Any:
|
||||
"""Re-block before each call — a fresh flip in the cycle."""
|
||||
t.status = "blocked"
|
||||
return await c.unblock(pm_id, task_id, "resolved upstream; restoring")
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_first_and_second_unblock_do_not_notify() -> None:
|
||||
c, pm_id, task_id, t = _flip_setup()
|
||||
cc: Any = c
|
||||
notify = AsyncMock()
|
||||
cc._notify_ceo_block_flip = notify
|
||||
|
||||
for _ in range(2):
|
||||
env = await _unblock_once(c, pm_id, task_id, t)
|
||||
assert env.error is None, env.as_dict()
|
||||
|
||||
notify.assert_not_awaited()
|
||||
assert markers.get_block_flip_count(t) == _TWO_FLIPS
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_third_unblock_notifies_ceo_once() -> None:
|
||||
c, pm_id, task_id, t = _flip_setup()
|
||||
cc: Any = c
|
||||
notify = AsyncMock()
|
||||
cc._notify_ceo_block_flip = notify
|
||||
|
||||
for _ in range(3):
|
||||
env = await _unblock_once(c, pm_id, task_id, t)
|
||||
assert env.error is None, env.as_dict()
|
||||
|
||||
notify.assert_awaited_once_with(task_id, _THREE_FLIPS)
|
||||
assert markers.is_block_flip_notified(t) is True
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_fourth_unblock_does_not_renotify() -> None:
|
||||
c, pm_id, task_id, t = _flip_setup()
|
||||
cc: Any = c
|
||||
notify = AsyncMock()
|
||||
cc._notify_ceo_block_flip = notify
|
||||
|
||||
for _ in range(4):
|
||||
env = await _unblock_once(c, pm_id, task_id, t)
|
||||
assert env.error is None, env.as_dict()
|
||||
|
||||
notify.assert_awaited_once()
|
||||
assert markers.get_block_flip_count(t) == _FOUR_FLIPS
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_notification_failure_does_not_fail_unblock(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
"""The real ``_notify_ceo_block_flip`` swallows a notify-service failure —
|
||||
unblock still succeeds on the 3rd flip."""
|
||||
c, pm_id, task_id, t = _flip_setup()
|
||||
monkeypatch.setattr(
|
||||
NotificationService,
|
||||
"send_block_flip_notification",
|
||||
AsyncMock(side_effect=RuntimeError("notification service down")),
|
||||
)
|
||||
|
||||
env = None
|
||||
for _ in range(3):
|
||||
env = await _unblock_once(c, pm_id, task_id, t)
|
||||
assert env.error is None, env.as_dict()
|
||||
|
||||
assert env is not None
|
||||
assert env.error is None
|
||||
assert markers.is_block_flip_notified(t) is True
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_counter_persists_via_marker_across_calls() -> None:
|
||||
c, pm_id, task_id, t = _flip_setup()
|
||||
cc: Any = c
|
||||
cc._notify_ceo_block_flip = AsyncMock()
|
||||
|
||||
await _unblock_once(c, pm_id, task_id, t)
|
||||
assert markers.get_block_flip_count(t) == 1
|
||||
await _unblock_once(c, pm_id, task_id, t)
|
||||
assert markers.get_block_flip_count(t) == _TWO_FLIPS
|
||||
Reference in New Issue
Block a user