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>
124 lines
4.6 KiB
Python
124 lines
4.6 KiB
Python
"""Tests for ContentActions.notify_get — read-one-notification (marks read).
|
|
|
|
`notify_get` used to swallow ANY exception from
|
|
`get_for_recipient_and_mark_read` into `Envelope.not_found` — including a DB
|
|
error from the mark-read UPDATE (e.g. hitting `lock_timeout`), which poisoned
|
|
the session for the rest of the transaction and surfaced later as an opaque
|
|
`PendingRollbackError`, while also lying to the calling agent that an
|
|
existing notification didn't exist. The fix narrows the catch to the two real
|
|
domain outcomes (`NotFoundError`, `PermissionError`); anything else must
|
|
propagate so the session actually rolls back.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
from roboco.services.base import NotFoundError
|
|
from roboco.services.gateway.content_actions import ContentActions, ContentActionsDeps
|
|
from sqlalchemy.exc import OperationalError
|
|
|
|
|
|
def _make_deps(**overrides: AsyncMock) -> ContentActionsDeps:
|
|
task = overrides.get("task", AsyncMock())
|
|
git = overrides.get("git", AsyncMock())
|
|
a2a = overrides.get("a2a", AsyncMock())
|
|
journal = overrides.get("journal", AsyncMock())
|
|
workspace = overrides.get("workspace", AsyncMock())
|
|
notifications = overrides.get("notifications", AsyncMock())
|
|
notification_delivery = overrides.get("notification_delivery", AsyncMock())
|
|
return ContentActionsDeps(
|
|
task=task,
|
|
git=git,
|
|
a2a=a2a,
|
|
journal=journal,
|
|
workspace=workspace,
|
|
notifications=notifications,
|
|
notification_delivery=notification_delivery,
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_notify_get_not_found_error_maps_to_not_found() -> None:
|
|
"""A genuinely missing notification -> Envelope.not_found."""
|
|
notification_id = uuid4()
|
|
notif_delivery = AsyncMock()
|
|
notif_delivery.get_for_recipient_and_mark_read.side_effect = NotFoundError(
|
|
resource_type="Notification", resource_id=str(notification_id)
|
|
)
|
|
deps = _make_deps(notification_delivery=notif_delivery)
|
|
ca = ContentActions(deps)
|
|
|
|
env = await ca.notify_get(agent_id=uuid4(), notification_id=notification_id)
|
|
body = env.as_dict()
|
|
|
|
assert body["error"] == "not_found"
|
|
assert str(notification_id) in body["message"]
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_notify_get_permission_error_maps_to_not_found() -> None:
|
|
"""A recipient mismatch -> Envelope.not_found (never leaks a 403/details)."""
|
|
notification_id = uuid4()
|
|
notif_delivery = AsyncMock()
|
|
notif_delivery.get_for_recipient_and_mark_read.side_effect = PermissionError(
|
|
"view notification: not a recipient"
|
|
)
|
|
deps = _make_deps(notification_delivery=notif_delivery)
|
|
ca = ContentActions(deps)
|
|
|
|
env = await ca.notify_get(agent_id=uuid4(), notification_id=notification_id)
|
|
body = env.as_dict()
|
|
|
|
assert body["error"] == "not_found"
|
|
assert str(notification_id) in body["message"]
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_notify_get_db_error_propagates() -> None:
|
|
"""A DB-shaped failure (e.g. the mark-read UPDATE hitting lock_timeout)
|
|
must NOT be swallowed into not_found — it has to propagate so the
|
|
session actually rolls back instead of silently poisoning the
|
|
transaction for the caller's later commit."""
|
|
notification_id = uuid4()
|
|
notif_delivery = AsyncMock()
|
|
notif_delivery.get_for_recipient_and_mark_read.side_effect = OperationalError(
|
|
"UPDATE notifications ...", {}, Exception("lock timeout")
|
|
)
|
|
deps = _make_deps(notification_delivery=notif_delivery)
|
|
ca = ContentActions(deps)
|
|
|
|
with pytest.raises(OperationalError):
|
|
await ca.notify_get(agent_id=uuid4(), notification_id=notification_id)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_notify_get_success_returns_notification_and_marks_read() -> None:
|
|
"""Happy path: the resolved notification's fields land in evidence."""
|
|
notification_id = uuid4()
|
|
from_agent = uuid4()
|
|
n = MagicMock()
|
|
n.id = notification_id
|
|
n.type = "alert"
|
|
n.priority = "normal"
|
|
n.subject = "subject line"
|
|
n.body = "body text"
|
|
n.requires_ack = False
|
|
n.from_agent = from_agent
|
|
|
|
notif_delivery = AsyncMock()
|
|
notif_delivery.get_for_recipient_and_mark_read.return_value = n
|
|
deps = _make_deps(notification_delivery=notif_delivery)
|
|
ca = ContentActions(deps)
|
|
|
|
env = await ca.notify_get(agent_id=uuid4(), notification_id=notification_id)
|
|
body = env.as_dict()
|
|
|
|
assert body["error"] is None
|
|
assert body["evidence"]["id"] == str(notification_id)
|
|
assert body["evidence"]["subject"] == "subject line"
|
|
assert body["evidence"]["from_agent"] == str(from_agent)
|
|
notif_delivery.get_for_recipient_and_mark_read.assert_awaited_once()
|