orchestrator/tests/test_merge_lease_reclaim.py

"""ORCH-065: proactive stale/dead merge-lease reclaim (TC-10..TC-15).

Exercises merge_gate.reclaim_stale_lease / pid_alive directly with lease files
written into a tmp repos_dir. No git ops run (reclaim only removes the lease
file). pid liveness is monkeypatched so 'dead'/'alive' are deterministic.
"""
import json
import os
import tempfile
import time

import pytest

os.environ["ORCH_DB_PATH"] = os.path.join(tempfile.gettempdir(), "test_orch_lease.db")
os.environ["ORCH_REPOS_DIR"] = tempfile.gettempdir()
os.environ["ORCH_GITEA_TOKEN"] = "test-token"
os.environ["ORCH_PLANE_API_TOKEN"] = "test-token"

from src import merge_gate


@pytest.fixture
def repos_dir(tmp_path, monkeypatch):
    d = tmp_path / "repos"
    d.mkdir()
    monkeypatch.setattr(merge_gate.settings, "repos_dir", str(d))
    monkeypatch.setattr(merge_gate.settings, "lease_reclaim_enabled", True)
    monkeypatch.setattr(merge_gate.settings, "merge_gate_repos", "")  # self-hosting only
    monkeypatch.setattr(merge_gate.settings, "merge_lock_timeout_s", 300)
    return d


def _write_lease(repos_dir, repo, branch="feature/x", pid=1234, age_s=0):
    path = os.path.join(str(repos_dir), f".merge-lease-{repo}.json")
    holder = {
        "branch": branch,
        "work_item_id": "ORCH-1",
        "task_id": 1,
        "acquired_at": time.time() - age_s,
        "pid": pid,
    }
    with open(path, "w", encoding="utf-8") as f:
        f.write(json.dumps(holder))
    return path


def _no_telegram(monkeypatch):
    import src.notifications as notif
    monkeypatch.setattr(notif, "send_telegram", lambda *a, **k: None)


# --- TC-10: reclaim a lease with a DEAD pid, proactively --------------------
def test_tc10_reclaim_dead_pid(repos_dir, monkeypatch):
    _no_telegram(monkeypatch)
    path = _write_lease(repos_dir, "orchestrator", pid=999999, age_s=0)
    monkeypatch.setattr(merge_gate, "pid_alive", lambda pid: False)
    assert merge_gate.reclaim_stale_lease("orchestrator") is True
    assert not os.path.exists(path)  # lease removed


# --- TC-11: reclaim by TTL is preserved -------------------------------------
def test_tc11_reclaim_by_ttl(repos_dir, monkeypatch):
    _no_telegram(monkeypatch)
    # pid alive, but the lease is older than the TTL -> still reclaimed.
    path = _write_lease(repos_dir, "orchestrator", pid=4321, age_s=999)
    monkeypatch.setattr(merge_gate, "pid_alive", lambda pid: True)
    assert merge_gate.reclaim_stale_lease("orchestrator") is True
    assert not os.path.exists(path)


# --- TC-12: a LIVE lease within TTL is NOT released -------------------------
def test_tc12_live_lease_protected(repos_dir, monkeypatch):
    _no_telegram(monkeypatch)
    path = _write_lease(repos_dir, "orchestrator", pid=4321, age_s=10)
    monkeypatch.setattr(merge_gate, "pid_alive", lambda pid: True)
    assert merge_gate.reclaim_stale_lease("orchestrator") is False
    assert os.path.exists(path)  # untouched


# --- TC-13: conditional — non-self-hosting repos are a no-op ----------------
def test_tc13_non_scope_repo_noop(repos_dir, monkeypatch):
    _no_telegram(monkeypatch)
    path = _write_lease(repos_dir, "enduro-trails", pid=999999, age_s=999)
    monkeypatch.setattr(merge_gate, "pid_alive", lambda pid: False)
    assert merge_gate.reclaim_stale_lease("enduro-trails") is False
    assert os.path.exists(path)  # out of scope -> untouched


def test_tc13_merge_gate_repos_csv_scope(repos_dir, monkeypatch):
    _no_telegram(monkeypatch)
    monkeypatch.setattr(merge_gate.settings, "merge_gate_repos", "enduro-trails")
    path = _write_lease(repos_dir, "enduro-trails", pid=999999, age_s=0)
    monkeypatch.setattr(merge_gate, "pid_alive", lambda pid: False)
    assert merge_gate.reclaim_stale_lease("enduro-trails") is True
    assert not os.path.exists(path)


# --- TC-14: never-raise on a read/remove error ------------------------------
def test_tc14_never_raise_on_read_error(repos_dir, monkeypatch):
    _no_telegram(monkeypatch)
    _write_lease(repos_dir, "orchestrator", pid=1, age_s=999)

    def boom(path):
        raise OSError("simulated read failure")

    monkeypatch.setattr(merge_gate, "_read_lease", boom)
    # Must not raise; returns False (could not reclaim).
    assert merge_gate.reclaim_stale_lease("orchestrator") is False


def test_tc14_no_lease_file_is_noop(repos_dir, monkeypatch):
    _no_telegram(monkeypatch)
    assert merge_gate.reclaim_stale_lease("orchestrator") is False


# --- TC-15: kill-switch lease_reclaim_enabled=False -------------------------
def test_tc15_kill_switch(repos_dir, monkeypatch):
    _no_telegram(monkeypatch)
    monkeypatch.setattr(merge_gate.settings, "lease_reclaim_enabled", False)
    path = _write_lease(repos_dir, "orchestrator", pid=999999, age_s=999)
    monkeypatch.setattr(merge_gate, "pid_alive", lambda pid: False)
    assert merge_gate.reclaim_stale_lease("orchestrator") is False
    assert os.path.exists(path)  # proactive reclaim off -> untouched


# --- pid_alive semantics ----------------------------------------------------
def test_pid_alive_dead_process():
    # PID 999999999 almost certainly does not exist.
    assert merge_gate.pid_alive(999999999) is False


def test_pid_alive_self():
    assert merge_gate.pid_alive(os.getpid()) is True


def test_pid_alive_missing_pid_conservative():
    assert merge_gate.pid_alive(None) is True
    assert merge_gate.pid_alive(0) is True