mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
93739a9dca
* fix(notifications): release re-escalation row locks per row; stop swallowing DB errors in notify_get The re-escalation sweep ran one tick-wide transaction, so each CAS claim's row lock was held across every remaining delivery until the single commit — a concurrent mark-read UPDATE on a claimed row starved into the 60s lock_timeout. The sweep now commits per row (claim commit releases the lock before delivery and makes the burned slot durable), re-fetches each row by snapshotted id so one row's rollback can't expire the rest of the tick, and savepoints each recipient's delivery. notify_get's bare except swallowed the resulting LockNotAvailableError into a false "notification not found" and returned a poisoned session to the commit-at-send middleware, which blew up with PendingRollbackError; it now catches only the two domain outcomes. defer_after_commit's listeners fire on SAVEPOINT release too, which would have drained deferred telegram/bus work before real durability — they now skip savepoint boundaries via get_nested_transaction() (the root get_transaction() is non-None inside the listener even at a real commit). acknowledge_for_recipient's Redis dedup-clear moved before the flush so the row lock never spans a Redis round-trip. The five best-effort CEO-notify swallows that persist notification rows are savepointed. * fix(services): contain swallowed best-effort DB write failures instead of poisoning the session Sweep of the same class as the notify_get incident: broad except-Exception handlers that swallow a failure whose try-body writes through the shared session leave the session rollback-pending, and the verb/request then dies later with PendingRollbackError at commit-at-send. Confirmed-dangerous sites now run the write inside a savepoint (safe since defer_after_commit skips savepoint boundaries): ceo_approve's verified-stamp, completion/pitch/postmortem-style CEO notifies, _inherit_upstream_base, _link_commit_to_task (covers every commit route), board-program LEARN records, the QA/PR-gate/PM-merge verified-stamps, and the documenter->PM handoff. _ack_pending_wake_notifications gets the same treatment so a wake-ack failure can't fail the A2A read. telegram_inbound's per-update loop and intake confirm roll back explicitly instead (their success paths commit mid-flow, so a savepoint doesn't fit). A swallowed savepoint rollback fully expires any ORM object mutated inside the block, and the next attribute read raises MissingGreenlet — strictly worse than the original bug. The two paths that keep using the object after the swallow (doc handoff's envelope build, base inheritance's claim continuation) refresh it in the except path; regression tests run against a real session and were verified to fail with the refresh reverted. * test: shape mocked session.execute results so sync accessors stop leaking unawaited coroutines An AsyncMock's auto-created children are themselves AsyncMock, so production code that correctly awaits session.execute() and then calls sync accessors (.scalars().all(), .scalar_one_or_none()) on the result was silently collecting unawaited coroutines in 22 test files — 80 RuntimeWarnings per unit run, and in test_flow_soup_guard one mock raised a real TypeError that a coincidentally-matching invalid_state envelope masked. Each affected fixture now returns a plain MagicMock shaped like a real Result. Zero AsyncMock warnings remain. * docs: document per-row sweep commits and the savepoint/refresh containment pattern --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com>
106 lines
4.3 KiB
Python
106 lines
4.3 KiB
Python
"""PM recovery of a rejected coordination task from needs_revision.
|
|
|
|
The in-path PR-review gate (and qa_fail / ceo_reject) can land a PM-owned
|
|
coordination/assembled task in ``needs_revision``. That state used to be
|
|
developer-claim-only, so the task had no actor and no exit but ``cancel`` — the
|
|
cell PM escalated in a loop. Now a PM re-claims its rejected task
|
|
(``i_will_plan``), revises the plan, and re-delegates the fixes.
|
|
|
|
Scope: ``pr_fail`` / ``qa_fail`` reassign the task to its owning PM, and
|
|
``give_me_work`` only ever offers an agent its OWN assigned tasks — so a PM is
|
|
never handed a developer's leaf, exactly as a developer is never handed a PM's
|
|
coordination root. (The scope lives in routing, not a gateway-only ownership
|
|
gate, which would break the spec=gateway parity invariant.)
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from types import SimpleNamespace
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
from roboco.foundation.policy import lifecycle as spec
|
|
from roboco.services.gateway.choreographer import Choreographer, ChoreographerDeps
|
|
|
|
# --------------------------------------------------------------------------- #
|
|
# Lifecycle authority: PMs may now claim needs_revision
|
|
# --------------------------------------------------------------------------- #
|
|
|
|
|
|
def test_pm_can_claim_needs_revision() -> None:
|
|
task = SimpleNamespace(
|
|
status="needs_revision", task_type="planning", assigned_to=None
|
|
)
|
|
for role in (spec.Role.CELL_PM, spec.Role.MAIN_PM):
|
|
assert spec.can_invoke_action(role, "claim", task).allowed
|
|
# Developers still own leaf revisions; QA / documenter still cannot claim it.
|
|
assert spec.can_invoke_action(spec.Role.DEVELOPER, "claim", task).allowed
|
|
assert not spec.can_invoke_action(spec.Role.QA, "claim", task).allowed
|
|
assert not spec.can_invoke_action(spec.Role.DOCUMENTER, "claim", task).allowed
|
|
|
|
|
|
def test_pm_claim_needs_revision_works_for_code_typed_root() -> None:
|
|
# Main-PM coordination roots can be code-typed, so the claim must NOT be
|
|
# task_type-gated — authority is status-based, scoped by routing.
|
|
task = SimpleNamespace(status="needs_revision", task_type="code", assigned_to=None)
|
|
assert spec.can_invoke_action(spec.Role.MAIN_PM, "claim", task).allowed
|
|
|
|
|
|
# --------------------------------------------------------------------------- #
|
|
# Routing scope: give_me_work offers a PM its OWN rejected coordination task
|
|
# --------------------------------------------------------------------------- #
|
|
|
|
|
|
def _make_deps(task_svc: AsyncMock) -> ChoreographerDeps:
|
|
# Findings-ledger reads (ReviewFindingsRepository.list_for_task) go
|
|
# through session.execute — an unconfigured AsyncMock's awaited result
|
|
# is itself an AsyncMock, so a plain sync `.scalars()` call on it leaks
|
|
# an unawaited coroutine. Empty scalars result (no findings).
|
|
task_svc.session.execute = AsyncMock(
|
|
return_value=MagicMock(
|
|
scalars=MagicMock(return_value=MagicMock(all=MagicMock(return_value=[])))
|
|
)
|
|
)
|
|
repo = AsyncMock()
|
|
for m in (
|
|
"list_unread_a2a",
|
|
"list_unread_mentions",
|
|
"list_pending_notifications",
|
|
"task_metadata_gaps",
|
|
"recent_team_activity",
|
|
"blockers_in_lane",
|
|
"journal_highlights_for_task",
|
|
"company_goals",
|
|
):
|
|
getattr(repo, m).return_value = []
|
|
return ChoreographerDeps(
|
|
task=task_svc,
|
|
work_session=AsyncMock(),
|
|
git=AsyncMock(),
|
|
a2a=AsyncMock(),
|
|
journal=AsyncMock(),
|
|
audit=AsyncMock(),
|
|
evidence_repo=repo,
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_give_me_work_offers_pm_its_needs_revision_task() -> None:
|
|
pm_id, task_id = uuid4(), uuid4()
|
|
task = MagicMock(
|
|
id=task_id, status="needs_revision", team="backend", dependency_ids=[]
|
|
)
|
|
task_svc = AsyncMock()
|
|
task_svc.list_pending_for_agent.return_value = []
|
|
task_svc.list_assigned_for_agent.return_value = [task]
|
|
task_svc.agent_for.return_value = MagicMock(role="cell_pm", team="backend")
|
|
c = Choreographer(_make_deps(task_svc))
|
|
|
|
env = await c.give_me_work(pm_id)
|
|
body = env.as_dict()
|
|
|
|
assert body["task_id"] == str(task_id)
|
|
# The PM is told to re-plan (revise) the rejected task, not a dev verb.
|
|
assert "i_will_plan" in body["next"]
|