claude-bot
2f4c553fd8
Extend pipeline responsibility past deploy->done: after the terminal
transition for an applicable repo, arm a ~15min observation window that
probes prod and reacts to a degradation the restart-time health-check
missed ("green deploy, red prod").
- src/post_deploy.py: new leaf module (config + lazy qg/db only).
Sentinel-file restart-safe state (.post-deploy-state-<repo>/<wi>/),
no DB migration. probe_signals/classify/decide_action/run_rollback,
all never-raise.
- Reserved-agent job `post-deploy-monitor` (no-LLM, Variant B, calque of
deploy-finalizer): self-requeues each tick via enqueue_job.
- Deterministic classify: DEGRADED iff >= fail_threshold consecutive
health failures OR window 5xx ratio > 5xx_threshold; fail-safe HEALTHY.
- Self-hosting invariant (BR-5/AC-8): a tick NEVER restarts the prod
orchestrator container -> orchestrator is ALWAYS ALERT_ONLY.
- Conditionality (ORCH-35/36/43/58): kill-switch + CSV repos, empty ->
self-hosting only.
- QG_CHECKS / STAGE_TRANSITIONS / schema unchanged (AC-12).
- Docs: CHANGELOG, CLAUDE artefact list (16-post-deploy-log.md),
architecture README, .env.example (ORCH_POST_DEPLOY_*).
Refs: ORCH-021
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
109 lines
4.0 KiB
Python
109 lines
4.0 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",
|
|
):
|
|
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() == []
|