A DB stage=done task with 0 active jobs flapped in Plane between `Awaiting Deploy` and `Monitoring after Deploy` instead of holding `Done` (verified live on ORCH-061, task 47): the three deploy-phase setters were terminal-blind, so any stale/duplicate/unknown caller under the bot token re-stamped an intermediate status over the terminal Done, forever. - New leaf src/deploy_status_guard.py (pure, never-raise, config-gated): decide() -> ALLOW | CONVERGE_DONE | SUPPRESS on the entry of set_issue_awaiting_deploy / set_issue_deploying / set_issue_monitoring. A deploy-phase status is legitimate iff the task is non-terminal OR (done AND post-deploy window active); otherwise done converges to Done idempotently, cancelled is suppressed (FR-2, D1/D2). - D3: move post_deploy.arm_monitor ABOVE the terminal-sync block in advance_stage so window_active is True when the legitimate first Monitoring is set (the task is already DB-done by then); a re-drive after the window closes converges to Done. - D4: run_post_deploy_monitor no-ops without a status PATCH / re-queue when the task became cancelled mid-window (zombie-tick guard, FR-3). - D5: additive `reason` kwarg on the three setters + one structured log line per verdict (work_item/caller/target/db_stage/window_active/verdict); new read-only db.get_task_by_work_item_id; post_deploy.window_active helper. - Flags deploy_status_guard_enabled (kill-switch -> 1:1) / deploy_status_guard_repos (CSV; empty = self-hosting only). STAGE_TRANSITIONS / QG_CHECKS / check_* / machine-verdict keys / DB schema untouched (reads existing tasks.stage). Tests: TC-01..TC-12 across 5 new test modules + config flags; updated the reason-kwarg assertions in test_deploy_terminal_sync / test_deploy_approve. Full regress green (1413). Docs: CHANGELOG, CLAUDE.md, docs/architecture/README.md (status -> реализовано), .env.example. Refs: ORCH-094 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
168 lines
7.1 KiB
Python
168 lines
7.1 KiB
Python
"""ORCH-036 TC-17: a SUCCESS prod deploy preserves the terminal-sync contract (AC-10).
|
|
|
|
When the finalizer (Phase C) reads exit 0 -> ``deploy_status: SUCCESS`` and drives
|
|
``advance_stage(finished_agent="deployer")``, the EXISTING deploy->done transition
|
|
must still fire unchanged: stage becomes ``done``, ``set_issue_done`` is called, no
|
|
agent is launched, and the merge-lease is released (terminal-sync, ORCH-43/БАГ-8
|
|
contract). ORCH-036 only changes HOW the verdict is produced, never the contract.
|
|
"""
|
|
|
|
import os
|
|
import tempfile
|
|
|
|
import pytest
|
|
|
|
_test_db = os.path.join(tempfile.gettempdir(), "test_orch_deploy_terminal.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))
|
|
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",
|
|
# ORCH-066 status setters.
|
|
"set_issue_analysis", "set_issue_awaiting_deploy", "set_issue_deploying",
|
|
"set_issue_monitoring",
|
|
):
|
|
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 _jobs():
|
|
conn = get_db()
|
|
rows = conn.execute("SELECT agent FROM jobs ORDER BY id").fetchall()
|
|
conn.close()
|
|
return [r[0] for r in rows]
|
|
|
|
|
|
def _pass(*a, **k):
|
|
return (True, "ok")
|
|
|
|
|
|
def test_tc17_success_deploy_syncs_terminal_done(monkeypatch):
|
|
# Hook reported exit 0 -> the host wrapper wrote result=0.
|
|
self_deploy.write_marker("orchestrator", "ORCH-036", self_deploy.RESULT, "0")
|
|
monkeypatch.setattr(
|
|
stage_engine, "QG_CHECKS",
|
|
{**stage_engine.QG_CHECKS, "check_deploy_status": _pass},
|
|
)
|
|
# Spy the merge-lease release to confirm the terminal-sync still frees it.
|
|
release = MagicMock()
|
|
monkeypatch.setattr(stage_engine.merge_gate, "release_merge_lease", release)
|
|
# ORCH-021 arms an orthogonal post-deploy-monitor reserved job at deploy->done
|
|
# for the self-hosting repo; disable it here so this test stays focused on the
|
|
# ORCH-036 terminal-sync contract (no PIPELINE agent launched leaving deploy).
|
|
monkeypatch.setattr(stage_engine.post_deploy.settings, "post_deploy_monitor_enabled", False)
|
|
|
|
task_id = _make_task("deploy")
|
|
stage_engine.run_deploy_finalizer(
|
|
{"task_id": task_id, "repo": "orchestrator", "id": 1, "agent": "deploy-finalizer"}
|
|
)
|
|
|
|
assert _stage(task_id) == "done"
|
|
assert stage_engine.set_issue_done.called
|
|
# The merge-lease is released on the deploy->done terminal-sync.
|
|
release.assert_called_once_with("orchestrator", "feature/ORCH-036-x")
|
|
# No agent is launched leaving deploy (terminal).
|
|
assert _jobs() == []
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# ORCH-066 TC-08 (AC-8): self-hosting deploy->done -> Monitoring after Deploy,
|
|
# NOT terminal Done. The post-deploy monitor finalises.
|
|
# ---------------------------------------------------------------------------
|
|
def test_tc08_self_deploy_done_sets_monitoring_not_done(monkeypatch):
|
|
self_deploy.write_marker("orchestrator", "ORCH-036", self_deploy.RESULT, "0")
|
|
monkeypatch.setattr(
|
|
stage_engine, "QG_CHECKS",
|
|
{**stage_engine.QG_CHECKS, "check_deploy_status": _pass},
|
|
)
|
|
monkeypatch.setattr(stage_engine.merge_gate, "release_merge_lease", MagicMock())
|
|
# post_deploy applies for the self-hosting repo with the monitor enabled.
|
|
monkeypatch.setattr(stage_engine.post_deploy.settings, "post_deploy_monitor_enabled", True)
|
|
monkeypatch.setattr(stage_engine.post_deploy.settings, "post_deploy_repos", "")
|
|
# arm_monitor is orthogonal; stub it so this test stays on the status contract.
|
|
monkeypatch.setattr(stage_engine.post_deploy, "arm_monitor", MagicMock(return_value=True))
|
|
|
|
task_id = _make_task("deploy")
|
|
stage_engine.run_deploy_finalizer(
|
|
{"task_id": task_id, "repo": "orchestrator", "id": 1, "agent": "deploy-finalizer"}
|
|
)
|
|
|
|
assert _stage(task_id) == "done"
|
|
# Self-hosting: the issue enters the Monitoring window, NOT terminal Done yet.
|
|
# ORCH-094: the terminal-sync caller now tags the reason (FR-4 observability).
|
|
stage_engine.set_issue_monitoring.assert_called_once_with(
|
|
"ORCH-036", reason="advance:deploy->done"
|
|
)
|
|
stage_engine.set_issue_done.assert_not_called()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# ORCH-066 TC-09 (AC-9): non-self repo deploy->done -> terminal Done (no regress).
|
|
# ---------------------------------------------------------------------------
|
|
def test_tc09_non_self_deploy_done_sets_done(monkeypatch):
|
|
self_deploy.write_marker("enduro-trails", "ET-042", self_deploy.RESULT, "0")
|
|
monkeypatch.setattr(
|
|
stage_engine, "QG_CHECKS",
|
|
{**stage_engine.QG_CHECKS, "check_deploy_status": _pass},
|
|
)
|
|
monkeypatch.setattr(stage_engine.merge_gate, "release_merge_lease", MagicMock())
|
|
# Monitor enabled, but the empty CSV means it applies ONLY to the self repo;
|
|
# a non-self repo therefore takes the unchanged terminal-Done path.
|
|
monkeypatch.setattr(stage_engine.post_deploy.settings, "post_deploy_monitor_enabled", True)
|
|
monkeypatch.setattr(stage_engine.post_deploy.settings, "post_deploy_repos", "")
|
|
|
|
task_id = _make_task("deploy", repo="enduro-trails", branch="feature/ET-042-x", wi="ET-042")
|
|
stage_engine.run_deploy_finalizer(
|
|
{"task_id": task_id, "repo": "enduro-trails", "id": 1, "agent": "deploy-finalizer"}
|
|
)
|
|
|
|
assert _stage(task_id) == "done"
|
|
stage_engine.set_issue_done.assert_called_once_with("ET-042")
|
|
stage_engine.set_issue_monitoring.assert_not_called()
|