Re-deploy after a FAILED prod deploy wedged the task on `deploy`: the sentinel markers (approve-requested/initiated/result) are keyed by the stable work_item_id, so after the БАГ-8 rollback (deploy -> development) and a developer fix, Phase B's idempotency-guard saw a STALE `initiated` and became a no-op — the detached hook never re-launched and the finalizer was never enqueued. Add self_deploy.clear_state (never-raise, idempotent) and call it on the check_deploy_status FAILED rollback and at the start of Phase A, so every fresh prod-deploy pass starts clean. Also document the new ORCH_SELF_DEPLOY_* / ORCH_DEPLOY_* descriptors in the canonical .env.example (CLAUDE.md rule #8, ТЗ §2.6), modelled on the ORCH-043 merge-gate block (placeholders only, secrets not committed). Contracts untouched: STAGE_TRANSITIONS, QG_CHECKS, _parse_deploy_status, БАГ-8, merge-gate. Refs: ORCH-036 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
142 lines
5.6 KiB
Python
142 lines
5.6 KiB
Python
"""ORCH-036 TC-10: a FAILED prod deploy rolls back deploy -> development (AC-4).
|
|
|
|
The finalizer (Phase C) reads the hook ``result`` sentinel, maps a non-zero exit
|
|
to ``deploy_status: FAILED`` and then drives the EXISTING deploy contract via
|
|
``advance_stage(finished_agent="deployer")``. With a FAILED verdict the БАГ-8
|
|
rollback fires: deploy -> development, ``set_issue_blocked`` + Telegram alert, and
|
|
(for the self-hosting repo) the merge-lease is released so the branch is not
|
|
wedged. The hook exit-code -> verdict mapping is unit-tested in
|
|
``test_deploy_hook_mapping.py``; here we assert the engine REACTION.
|
|
"""
|
|
|
|
import os
|
|
import tempfile
|
|
|
|
import pytest
|
|
|
|
_test_db = os.path.join(tempfile.gettempdir(), "test_orch_deploy_rollback.db")
|
|
os.environ["ORCH_DB_PATH"] = _test_db
|
|
os.environ["ORCH_REPOS_DIR"] = tempfile.gettempdir()
|
|
os.environ.setdefault("ORCH_GITEA_TOKEN", "test-token")
|
|
os.environ.setdefault("ORCH_PLANE_API_TOKEN", "test-token")
|
|
|
|
from unittest.mock import MagicMock # noqa: E402
|
|
|
|
import src.db as _db # noqa: E402
|
|
from src.db import init_db, get_db # noqa: E402
|
|
from src import stage_engine # noqa: E402
|
|
from src import self_deploy # noqa: E402
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def fresh_db(monkeypatch, tmp_path):
|
|
monkeypatch.setattr(_db.settings, "db_path", _test_db)
|
|
if os.path.exists(_test_db):
|
|
os.unlink(_test_db)
|
|
init_db()
|
|
monkeypatch.setattr(self_deploy.settings, "repos_dir", str(tmp_path))
|
|
monkeypatch.setattr(self_deploy.settings, "host_repos_dir", str(tmp_path))
|
|
# The finalizer's deploy-log write touches a git worktree we don't have here;
|
|
# the verdict it drives comes from check_deploy_status (monkeypatched below).
|
|
monkeypatch.setattr(stage_engine.self_deploy, "write_deploy_log", MagicMock(return_value=True))
|
|
yield
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def silence_side_effects(monkeypatch):
|
|
for name in (
|
|
"notify_stage_change", "notify_qg_failure", "notify_approve_requested",
|
|
"send_telegram", "plane_notify_stage", "plane_notify_qg", "plane_add_comment",
|
|
"set_issue_in_review", "set_issue_needs_input", "set_issue_in_progress",
|
|
"set_issue_blocked", "set_issue_done",
|
|
):
|
|
monkeypatch.setattr(stage_engine, name, MagicMock())
|
|
|
|
|
|
def _make_task(stage, repo="orchestrator", branch="feature/ORCH-036-x", wi="ORCH-036"):
|
|
conn = get_db()
|
|
cur = conn.execute(
|
|
"INSERT INTO tasks (plane_id, work_item_id, repo, branch, stage) "
|
|
"VALUES (?, ?, ?, ?, ?)",
|
|
(f"plane-{wi}", wi, repo, branch, stage),
|
|
)
|
|
task_id = cur.lastrowid
|
|
conn.commit()
|
|
conn.close()
|
|
return task_id
|
|
|
|
|
|
def _stage(task_id):
|
|
conn = get_db()
|
|
row = conn.execute("SELECT stage FROM tasks WHERE id=?", (task_id,)).fetchone()
|
|
conn.close()
|
|
return row[0]
|
|
|
|
|
|
def _fail(reason):
|
|
def _f(*a, **k):
|
|
return (False, reason)
|
|
return _f
|
|
|
|
|
|
def test_tc10_failed_deploy_rolls_back_to_development(monkeypatch):
|
|
# Hook reported exit 1 (rolled back) -> the host wrapper wrote result=1.
|
|
self_deploy.write_marker("orchestrator", "ORCH-036", self_deploy.RESULT, "1")
|
|
# The deploy-log verdict the gate reads is FAILED.
|
|
monkeypatch.setattr(
|
|
stage_engine, "QG_CHECKS",
|
|
{**stage_engine.QG_CHECKS, "check_deploy_status": _fail("Deploy status: FAILED")},
|
|
)
|
|
task_id = _make_task("deploy")
|
|
|
|
stage_engine.run_deploy_finalizer(
|
|
{"task_id": task_id, "repo": "orchestrator", "id": 1, "agent": "deploy-finalizer"}
|
|
)
|
|
|
|
# БАГ-8 rollback fired: NOT done, back on development, blocked + alerted.
|
|
assert _stage(task_id) == "development"
|
|
assert stage_engine.set_issue_blocked.called
|
|
assert stage_engine.send_telegram.called
|
|
assert stage_engine.set_issue_done.called is False
|
|
|
|
|
|
def test_tc11_re_deploy_after_rollback_not_wedged(monkeypatch):
|
|
"""FAILED deploy -> rollback wipes stale markers so a later Phase B re-initiates.
|
|
|
|
Regression for the re-deploy-after-rollback contract (AC-4/AC-10): markers are
|
|
keyed by the (stable) work_item_id, so without cleanup the STALE `initiated` from
|
|
the first failed attempt would make Phase B's idempotency-guard a no-op on the
|
|
retry and wedge the task on `deploy` forever.
|
|
"""
|
|
repo, wi, branch = "orchestrator", "ORCH-036", "feature/ORCH-036-x"
|
|
# First (failed) pass left BOTH the idempotency-guard and the verdict behind.
|
|
self_deploy.write_marker(repo, wi, self_deploy.INITIATED, "123")
|
|
self_deploy.write_marker(repo, wi, self_deploy.RESULT, "1")
|
|
monkeypatch.setattr(
|
|
stage_engine, "QG_CHECKS",
|
|
{**stage_engine.QG_CHECKS, "check_deploy_status": _fail("Deploy status: FAILED")},
|
|
)
|
|
task_id = _make_task("deploy")
|
|
|
|
stage_engine.run_deploy_finalizer(
|
|
{"task_id": task_id, "repo": repo, "id": 1, "agent": "deploy-finalizer"}
|
|
)
|
|
|
|
# Rollback fired AND the stale deploy-state sentinels were wiped.
|
|
assert _stage(task_id) == "development"
|
|
assert self_deploy.has_marker(repo, wi, self_deploy.INITIATED) is False
|
|
assert self_deploy.has_marker(repo, wi, self_deploy.RESULT) is False
|
|
assert self_deploy.read_result(repo, wi) == (False, None)
|
|
|
|
# Second pass: the task reaches `deploy` again and the human re-approves. Phase B
|
|
# must ACTUALLY initiate (no stale `initiated` -> not a no-op), proving the retry
|
|
# is no longer wedged.
|
|
init = MagicMock(return_value=(True, "ok"))
|
|
monkeypatch.setattr(stage_engine.self_deploy, "initiate_deploy", init)
|
|
result = stage_engine.AdvanceResult(from_stage="deploy")
|
|
stage_engine._handle_self_deploy_phase_b(task_id, repo, wi, branch, result)
|
|
|
|
assert init.called
|
|
assert result.note == "self-deploy-initiated"
|
|
assert self_deploy.has_marker(repo, wi, self_deploy.INITIATED) is True
|