fix(service): supervise canonical Mission Core lifecycle

tests/test_service_watchdog.py

@@ -0,0 +1,116 @@
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from threading import Event
+
+from k1link.service_watchdog import (
+    ConsecutiveHealthGate,
+    MissionCoreSelfWatchdog,
+    MissionCoreWatchdogJournal,
+    MissionCoreWatchdogPolicy,
+    watchdog_enabled,
+)
+
+
+def test_consecutive_health_gate_resets_after_recovery() -> None:
+    gate = ConsecutiveHealthGate(3)
+
+    assert gate.observe(False) is False
+    assert gate.observe(False) is False
+    assert gate.observe(True) is False
+    assert gate.consecutive_failures == 0
+    assert gate.observe(False) is False
+    assert gate.observe(False) is False
+    assert gate.observe(False) is True
+
+
+def test_self_watchdog_escalates_a_persistently_unhealthy_process(tmp_path: Path) -> None:
+    requested = Event()
+    forced = Event()
+    journal_path = tmp_path / "watchdog.jsonl"
+    watchdog = MissionCoreSelfWatchdog(
+        tmp_path,
+        policy=MissionCoreWatchdogPolicy(
+            startup_grace_seconds=0.01,
+            probe_interval_seconds=0.01,
+            probe_timeout_seconds=0.01,
+            consecutive_failure_limit=2,
+            graceful_shutdown_seconds=0.02,
+        ),
+        probe=lambda: False,
+        request_shutdown=requested.set,
+        force_shutdown=forced.set,
+        journal=MissionCoreWatchdogJournal(journal_path),
+    )
+
+    watchdog.start()
+
+    assert requested.wait(0.5)
+    assert forced.wait(0.5)
+    watchdog.stop()
+    events = [json.loads(line)["event"] for line in journal_path.read_text().splitlines()]
+    assert events == [
+        "watchdog-started",
+        "health-state-changed",
+        "restart-requested",
+        "restart-escalated",
+        "watchdog-stopped",
+    ]
+
+
+def test_self_watchdog_leaves_a_healthy_process_running(tmp_path: Path) -> None:
+    probed = Event()
+    requested = Event()
+    forced = Event()
+    journal_path = tmp_path / "watchdog.jsonl"
+
+    def healthy_probe() -> bool:
+        probed.set()
+        return True
+
+    watchdog = MissionCoreSelfWatchdog(
+        tmp_path,
+        policy=MissionCoreWatchdogPolicy(
+            startup_grace_seconds=0.01,
+            probe_interval_seconds=0.01,
+            probe_timeout_seconds=0.01,
+            consecutive_failure_limit=2,
+            graceful_shutdown_seconds=0.02,
+        ),
+        probe=healthy_probe,
+        request_shutdown=requested.set,
+        force_shutdown=forced.set,
+        journal=MissionCoreWatchdogJournal(journal_path),
+    )
+
+    watchdog.start()
+
+    assert probed.wait(0.5)
+    watchdog.stop()
+    assert requested.is_set() is False
+    assert forced.is_set() is False
+    events = [json.loads(line)["event"] for line in journal_path.read_text().splitlines()]
+    assert events == [
+        "watchdog-started",
+        "health-state-changed",
+        "watchdog-stopped",
+    ]
+
+
+def test_watchdog_journal_rotates_before_exceeding_bound(tmp_path: Path) -> None:
+    path = tmp_path / "watchdog.jsonl"
+    journal = MissionCoreWatchdogJournal(path, max_bytes=300)
+
+    journal.append("first", payload="x" * 180)
+    journal.append("second", payload="y" * 180)
+
+    assert path.is_file()
+    assert path.with_name("watchdog.jsonl.1").is_file()
+    assert json.loads(path.read_text())["event"] == "second"
+
+
+def test_watchdog_requires_exact_enable_marker() -> None:
+    assert watchdog_enabled({"MISSIONCORE_SERVICE_WATCHDOG": "1"}) is True
+    assert watchdog_enabled({"MISSIONCORE_SERVICE_WATCHDOG": "true"}) is False
+    assert watchdog_enabled({}) is False