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>
226 lines
8.3 KiB
Python
226 lines
8.3 KiB
Python
"""Task #154: evidence() must populate files_changed + use full PR diff.
|
|
|
|
Bug:
|
|
ContentActions.evidence() hard-coded ``files_changed=[]`` and called
|
|
``git.diff(branch_name=..., base="HEAD~1")``. Result: QA / reviewers
|
|
inspecting a real PR saw an empty change list and only the latest
|
|
commit's delta, even when GitHub showed a multi-commit change set.
|
|
|
|
Fix:
|
|
Pull files via ``git.list_changed_files(branch_name=...)`` (no base
|
|
→ full diff vs parent branch). Pull diff with ``base=None`` so the
|
|
full PR diff comes through. Both use git as the authoritative source
|
|
instead of the legacy ``work_session.files_modified`` field, which
|
|
the gateway ``commit()`` does not populate.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
from roboco.services.gateway.content_actions import ContentActions, ContentActionsDeps
|
|
|
|
|
|
def _deps_for_evidence(
|
|
task_svc: AsyncMock,
|
|
git_svc: AsyncMock,
|
|
workspace_svc: AsyncMock,
|
|
evidence_repo: AsyncMock,
|
|
) -> ContentActionsDeps:
|
|
# 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=[])))
|
|
)
|
|
)
|
|
return ContentActionsDeps(
|
|
task=task_svc,
|
|
git=git_svc,
|
|
a2a=AsyncMock(),
|
|
journal=AsyncMock(),
|
|
workspace=workspace_svc,
|
|
notifications=AsyncMock(),
|
|
notification_delivery=AsyncMock(),
|
|
evidence_repo=evidence_repo,
|
|
)
|
|
|
|
|
|
def _task_with_pr(task_id: object, *, commits: list[str]) -> MagicMock:
|
|
return MagicMock(
|
|
id=task_id,
|
|
status="awaiting_qa",
|
|
assigned_to=None,
|
|
branch_name="feature/backend/abc12345--def67890",
|
|
work_session_id=uuid4(),
|
|
commits=commits,
|
|
pr_number=20,
|
|
pr_url="https://github.com/org/repo/pull/20",
|
|
dev_notes="see PR description",
|
|
acceptance_criteria_status=[],
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_evidence_populates_files_changed_from_git() -> None:
|
|
"""The smoke-9 regression: PR #20 has README change on GitHub but
|
|
evidence() reports files_changed=[]. The fix queries git directly."""
|
|
agent_id = uuid4()
|
|
task_id = uuid4()
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = _task_with_pr(task_id, commits=["abc", "def"])
|
|
git_svc = AsyncMock()
|
|
git_svc.diff.return_value = "diff --git a/README.md b/README.md\n+added line\n"
|
|
git_svc.list_changed_files.return_value = ["README.md", "docs/guide.md"]
|
|
workspace_svc = AsyncMock()
|
|
evidence_repo = AsyncMock()
|
|
evidence_repo.journal_highlights_for_task.return_value = []
|
|
|
|
ca = ContentActions(
|
|
_deps_for_evidence(task_svc, git_svc, workspace_svc, evidence_repo)
|
|
)
|
|
env = await ca.evidence(agent_id=agent_id, task_id=task_id)
|
|
body = env.as_dict()
|
|
|
|
assert body["error"] is None
|
|
assert body["evidence"]["files_changed"] == ["README.md", "docs/guide.md"]
|
|
assert "diff --git" in body["evidence"]["pr_diff_summary"]
|
|
git_svc.list_changed_files.assert_awaited_once()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_evidence_uses_full_pr_diff_not_head_minus_one() -> None:
|
|
"""git.diff must be called with base=None (full PR diff vs parent),
|
|
not base='HEAD~1' (only the last commit)."""
|
|
agent_id = uuid4()
|
|
task_id = uuid4()
|
|
task_svc = AsyncMock()
|
|
# Multi-commit branch — the pre-fix code passed base='HEAD~1' when
|
|
# task.commits was non-empty, masking earlier commits' changes.
|
|
task_svc.get.return_value = _task_with_pr(task_id, commits=["sha1", "sha2", "sha3"])
|
|
git_svc = AsyncMock()
|
|
git_svc.diff.return_value = "full diff"
|
|
git_svc.list_changed_files.return_value = []
|
|
workspace_svc = AsyncMock()
|
|
evidence_repo = AsyncMock()
|
|
evidence_repo.journal_highlights_for_task.return_value = []
|
|
|
|
ca = ContentActions(
|
|
_deps_for_evidence(task_svc, git_svc, workspace_svc, evidence_repo)
|
|
)
|
|
await ca.evidence(agent_id=agent_id, task_id=task_id)
|
|
|
|
git_svc.diff.assert_awaited_once()
|
|
call_kwargs = git_svc.diff.await_args.kwargs
|
|
# Pre-fix bug: kwargs['base'] would be 'HEAD~1' for any multi-commit
|
|
# branch. Post-fix: base is omitted (or explicitly None).
|
|
base = call_kwargs.get("base")
|
|
assert base in (None, ""), (
|
|
f"git.diff must use full-PR diff (base=None), got base={base!r}"
|
|
)
|
|
assert call_kwargs.get("branch_name") == "feature/backend/abc12345--def67890"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_evidence_populates_journal_highlights() -> None:
|
|
"""evidence() must return journal_highlights so QA gets the dev's
|
|
decision/reflection context — same as qa.py's claim_review evidence."""
|
|
agent_id = uuid4()
|
|
task_id = uuid4()
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = _task_with_pr(task_id, commits=["abc"])
|
|
git_svc = AsyncMock()
|
|
git_svc.diff.return_value = ""
|
|
git_svc.list_changed_files.return_value = []
|
|
workspace_svc = AsyncMock()
|
|
evidence_repo = AsyncMock()
|
|
highlights = [
|
|
{"scope": "decision", "title": "Use README format X", "content": "..."},
|
|
{"scope": "reflect", "title": "Lesson learned", "content": "..."},
|
|
]
|
|
evidence_repo.journal_highlights_for_task.return_value = highlights
|
|
|
|
ca = ContentActions(
|
|
_deps_for_evidence(task_svc, git_svc, workspace_svc, evidence_repo)
|
|
)
|
|
env = await ca.evidence(agent_id=agent_id, task_id=task_id)
|
|
body = env.as_dict()
|
|
assert body["evidence"]["journal_highlights"] == highlights
|
|
evidence_repo.journal_highlights_for_task.assert_awaited_once_with(
|
|
task_id, include_ancestors=True
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_evidence_commits_session_before_git_work() -> None:
|
|
"""2026-07-29 pool exhaustion: evidence() must release its DB transaction
|
|
(commit) BEFORE the fetch/diff git work — those can run for minutes on a
|
|
cold workspace, and an open transaction pins a pool connection for the
|
|
whole duration."""
|
|
order: list[str] = []
|
|
agent_id = uuid4()
|
|
task_id = uuid4()
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = _task_with_pr(task_id, commits=["abc"])
|
|
task_svc.session.commit = AsyncMock(side_effect=lambda: order.append("commit"))
|
|
git_svc = AsyncMock()
|
|
git_svc.diff.return_value = ""
|
|
git_svc.list_changed_files.return_value = []
|
|
workspace_svc = AsyncMock()
|
|
workspace_svc.fetch_branch_for_inspection = AsyncMock(
|
|
side_effect=lambda **_kw: order.append("fetch")
|
|
)
|
|
evidence_repo = AsyncMock()
|
|
evidence_repo.journal_highlights_for_task.return_value = []
|
|
|
|
ca = ContentActions(
|
|
_deps_for_evidence(task_svc, git_svc, workspace_svc, evidence_repo)
|
|
)
|
|
env = await ca.evidence(agent_id=agent_id, task_id=task_id)
|
|
|
|
assert env.as_dict()["error"] is None
|
|
assert order == ["commit", "fetch"], (
|
|
f"session must be committed before git work, got order={order}"
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_evidence_no_branch_skips_git_calls() -> None:
|
|
"""A task without a branch_name has no PR yet — skip git entirely,
|
|
still return a valid envelope with empty files_changed."""
|
|
agent_id = uuid4()
|
|
task_id = uuid4()
|
|
task_svc = AsyncMock()
|
|
no_branch = MagicMock(
|
|
id=task_id,
|
|
status="claimed",
|
|
assigned_to=agent_id,
|
|
branch_name=None,
|
|
work_session_id=None,
|
|
commits=[],
|
|
pr_number=None,
|
|
pr_url=None,
|
|
dev_notes=None,
|
|
acceptance_criteria_status=[],
|
|
)
|
|
task_svc.get.return_value = no_branch
|
|
git_svc = AsyncMock()
|
|
workspace_svc = AsyncMock()
|
|
evidence_repo = AsyncMock()
|
|
evidence_repo.journal_highlights_for_task.return_value = []
|
|
|
|
ca = ContentActions(
|
|
_deps_for_evidence(task_svc, git_svc, workspace_svc, evidence_repo)
|
|
)
|
|
env = await ca.evidence(agent_id=agent_id, task_id=task_id)
|
|
body = env.as_dict()
|
|
assert body["error"] is None
|
|
assert body["evidence"]["files_changed"] == []
|
|
assert body["evidence"]["pr_diff_summary"] == ""
|
|
git_svc.diff.assert_not_awaited()
|
|
git_svc.list_changed_files.assert_not_awaited()
|