mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
* 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>
214 lines
7.5 KiB
Python
214 lines
7.5 KiB
Python
"""resume transitions a paused task back to in_progress for the assignee.
|
|
|
|
Audit J33 — `paused -> in_progress` is a valid lifecycle transition but no
|
|
agent-callable verb implemented it. `i_will_work_on` only handles
|
|
needs_revision/pending/claimed; the closure dispatcher pauses owned
|
|
in_progress work on `i_am_idle` but nothing wakes it back up. `resume` fills
|
|
that gap. These tests pin the four behaviors:
|
|
|
|
- happy path: paused -> in_progress for the assignee
|
|
- not_found: unknown task id returns the not_found envelope
|
|
- not_authorized: only the current claimant can resume
|
|
- invalid_state: only paused tasks can be resumed
|
|
"""
|
|
|
|
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.services.gateway.choreographer import Choreographer, ChoreographerDeps
|
|
|
|
|
|
def _make_deps(**overrides: Any) -> ChoreographerDeps:
|
|
"""Local dep-builder. Established pattern: per-test-file, not centralized."""
|
|
base: dict[str, Any] = {
|
|
"task": AsyncMock(),
|
|
"work_session": AsyncMock(),
|
|
"git": AsyncMock(),
|
|
"a2a": AsyncMock(),
|
|
"journal": AsyncMock(),
|
|
"audit": AsyncMock(),
|
|
"evidence_repo": AsyncMock(),
|
|
}
|
|
base.update(overrides)
|
|
# 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).
|
|
base["task"].session.execute = AsyncMock(
|
|
return_value=MagicMock(
|
|
scalars=MagicMock(return_value=MagicMock(all=MagicMock(return_value=[])))
|
|
)
|
|
)
|
|
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",
|
|
):
|
|
getattr(repo, method).return_value = []
|
|
# C8: default-fresh journal:decision so PM-decision gate passes.
|
|
# Tests that exercise the gate boundary stub their own value.
|
|
# The check matches MagicMock and AsyncMock (the two default sentinel
|
|
# types pytest's unittest.mock leaves on un-stubbed return_values).
|
|
_ldef = base["journal"].latest_decision_at.return_value
|
|
if type(_ldef).__name__ in ("MagicMock", "AsyncMock"):
|
|
base["journal"].latest_decision_at.return_value = datetime.now(UTC)
|
|
return ChoreographerDeps(**base)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resume_transitions_paused_to_in_progress() -> None:
|
|
aid = uuid4()
|
|
tid = uuid4()
|
|
t = MagicMock(id=tid, status="paused", assigned_to=aid, team="backend")
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = t
|
|
task_svc.agent_for.return_value = MagicMock(
|
|
id=aid, role="developer", team="backend", slug=None
|
|
)
|
|
task_svc.resume_for_agent.return_value = MagicMock(
|
|
id=tid, status="in_progress", assigned_to=aid
|
|
)
|
|
# VerbRunner wraps composed actions in session.begin_nested(); wire up
|
|
# an async-context-manager mock so the runner doesn't fail on dispatch.
|
|
task_svc.session = MagicMock()
|
|
task_svc.session.begin_nested = MagicMock(
|
|
return_value=MagicMock(
|
|
__aenter__=AsyncMock(return_value=None),
|
|
__aexit__=AsyncMock(return_value=False),
|
|
)
|
|
)
|
|
deps = _make_deps(task=task_svc)
|
|
c = Choreographer(deps)
|
|
|
|
env = await c.resume(aid, tid)
|
|
|
|
assert env.error is None
|
|
task_svc.resume_for_agent.assert_awaited_once_with(tid, aid)
|
|
assert env.status == "in_progress"
|
|
assert env.task_id == str(tid)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resume_returns_not_found_for_unknown_task() -> None:
|
|
aid = uuid4()
|
|
tid = uuid4()
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = None
|
|
deps = _make_deps(task=task_svc)
|
|
c = Choreographer(deps)
|
|
|
|
env = await c.resume(aid, tid)
|
|
|
|
assert env.error == "not_found"
|
|
task_svc.resume_for_agent.assert_not_awaited()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resume_rejects_when_not_claimant() -> None:
|
|
aid = uuid4()
|
|
other = uuid4()
|
|
tid = uuid4()
|
|
t = MagicMock(id=tid, status="paused", assigned_to=other, team="backend")
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = t
|
|
task_svc.agent_for.return_value = MagicMock(
|
|
id=aid, role="developer", team="backend", slug=None
|
|
)
|
|
deps = _make_deps(task=task_svc)
|
|
c = Choreographer(deps)
|
|
|
|
env = await c.resume(aid, tid)
|
|
|
|
# The spec gate accepts (developer is in resume's allowed_roles and
|
|
# status is paused); the reassignment-rejection branch (Task 6 fix in
|
|
# commit a5d358d) is what rejects with "current owner".
|
|
assert env.error == "not_authorized"
|
|
assert "current owner" in (env.message or "")
|
|
task_svc.resume_for_agent.assert_not_awaited()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resume_rejects_invalid_state() -> None:
|
|
aid = uuid4()
|
|
tid = uuid4()
|
|
# Task is owned but not paused. resume's IntentSpec composes=("resume",)
|
|
# and the resume ActionSpec's source_statuses is {PAUSED}, so the spec
|
|
# gate rejects with invalid_state — VerbRunner never runs.
|
|
t = MagicMock(id=tid, status="in_progress", assigned_to=aid)
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = t
|
|
task_svc.agent_for.return_value = MagicMock(
|
|
id=aid, role="developer", team="backend", slug=None
|
|
)
|
|
task_svc.resume_for_agent.return_value = None
|
|
deps = _make_deps(task=task_svc)
|
|
c = Choreographer(deps)
|
|
|
|
env = await c.resume(aid, tid)
|
|
|
|
assert env.error == "invalid_state"
|
|
# Spec gate rejects before the runner dispatches, so resume_for_agent
|
|
# is NOT called.
|
|
task_svc.resume_for_agent.assert_not_awaited()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resume_rejection_writes_audit_row() -> None:
|
|
"""Every rejection envelope must call audit.log_event (Task 6 contract)."""
|
|
aid = uuid4()
|
|
tid = uuid4()
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = None
|
|
audit_svc = AsyncMock()
|
|
deps = _make_deps(task=task_svc, audit=audit_svc)
|
|
c = Choreographer(deps)
|
|
|
|
env = await c.resume(aid, tid)
|
|
|
|
assert env.error == "not_found"
|
|
audit_svc.log_event.assert_awaited_once()
|
|
kwargs = audit_svc.log_event.await_args.kwargs
|
|
assert kwargs["event_type"] == "gateway.rejected"
|
|
assert kwargs["details"]["verb"] == "resume"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resume_success_writes_heartbeat() -> None:
|
|
"""Heartbeat fires on success — agent is back to active work."""
|
|
aid = uuid4()
|
|
tid = uuid4()
|
|
t = MagicMock(id=tid, status="paused", assigned_to=aid, team="backend")
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = t
|
|
task_svc.agent_for.return_value = MagicMock(
|
|
id=aid, role="developer", team="backend", slug=None
|
|
)
|
|
task_svc.resume_for_agent.return_value = MagicMock(
|
|
id=tid, status="in_progress", assigned_to=aid
|
|
)
|
|
# VerbRunner wraps composed actions in session.begin_nested(); wire up
|
|
# an async-context-manager mock so the runner doesn't fail on dispatch.
|
|
task_svc.session = MagicMock()
|
|
task_svc.session.begin_nested = MagicMock(
|
|
return_value=MagicMock(
|
|
__aenter__=AsyncMock(return_value=None),
|
|
__aexit__=AsyncMock(return_value=False),
|
|
)
|
|
)
|
|
deps = _make_deps(task=task_svc)
|
|
c = Choreographer(deps)
|
|
|
|
env = await c.resume(aid, tid)
|
|
|
|
assert env.error is None
|
|
task_svc.heartbeat.assert_awaited_once_with(tid)
|