atlas-iac/testing/tests/test_hermes_execution_pool_recovery.py

"""Lease-failure recovery contracts for the execution-pool coordinator.

The independent review reproduced a wedge in which a Kanban write that failed
during lease expiry left a ``lease_failed`` row that was invisible, immortal,
and fatal. These tests pin the recovered behaviour: the row stays retryable, is
only collected on authoritative terminal evidence, and survives a restart on the
PVC the store lives on.
"""

from __future__ import annotations

import sys
from pathlib import Path


ROOT = Path(__file__).parents[2]
SCRIPTS = ROOT / "services/hermes/scripts"
SCM_SCRIPTS = ROOT / "services/hermes/scm-common/scripts"
sys.path[:0] = [str(SCRIPTS), str(SCM_SCRIPTS)]

import execution_pool_coordinator as coordinator  # noqa: E402
import execution_pool_maintenance as maintenance  # noqa: E402
import execution_pool_store as pool_store  # noqa: E402
from testing.tests.test_hermes_execution_pool_coordinator_v2 import (  # noqa: E402
    MASTER,
    assignment_payload,
    binding,
    install_kanban,
    task,
)
from testing.tests.test_hermes_execution_pool_support import (  # noqa: E402
    LOCKED,
    age,
    clear_pool_deferrals,  # noqa: F401 - autouse fixture, resolved by name
    exhausted_store,
    states,
)


def test_locked_board_at_lease_expiry_stays_retryable_and_never_wedges(
    tmp_path, monkeypatch, capsys
):
    """The exact review repro: a locked board must not strand the run."""
    live = task()
    kanban = install_kanban(monkeypatch, [live], tmp_path)
    monkeypatch.setattr(
        coordinator, "assignment_payload",
        lambda _db, _connection, _task, _board: assignment_payload(),
    )

    def locked(*_args, **_kwargs):
        raise LOCKED

    kanban.block_task = locked
    store = exhausted_store(tmp_path / "wedge.db")
    pool = coordinator.Coordinator(MASTER, store)

    pool.expire_leases()
    assert states(store) == [("23", 0, 3, "lease_failed")]
    assert store.available_ordinals() == [0, 1, 2]
    assert "lease park" in capsys.readouterr().err

    # 1. The row is never collected while its outcome is unconfirmed.
    age(store, 10 * 365 * 86400)
    assert store.garbage_collect(0) == 0
    assert states(store) == [("23", 0, 3, "lease_failed")]

    # 2. reconcile() no longer hits the conflicting-duplicate primary key.
    for _cycle in range(3):
        pool.reconcile()
    assert states(store) == [("23", 0, 3, "lease_failed")]

    # 3. dispatch() makes no spurious Kanban mutation.
    monkeypatch.setattr(
        maintenance.cli_lane_dispatch, "claim_ready",
        lambda *_args, **_kwargs: [("metis", live.id)],
    )
    pool.dispatch()
    assert kanban.blocked == []
    assert states(store) == [("23", 0, 3, "lease_failed")]

    # 4. Once the board recovers, the retry records the exact run and settles.
    kanban.block_task = lambda _connection, task_id, **values: (
        kanban.blocked.append((task_id, values)) or True
    )
    pool.expire_leases()
    assert kanban.blocked[-1][1] == {
        "reason": "Distributed worker lease expired after 3 fenced attempts",
        "kind": "transient",
        "expected_run_id": 23,
    }
    assert states(store) == [("23", 0, 3, "finalized")]

    # 5. Only now, with authoritative evidence, is the row collectable.
    age(store, 10 * 365 * 86400)
    assert store.garbage_collect(0) == 1
    assert states(store) == []


def test_refused_exact_run_park_keeps_the_row_for_the_next_pass(tmp_path, monkeypatch):
    """No terminal state without evidence, even when the write is refused."""
    live = task()
    kanban = install_kanban(monkeypatch, [live], tmp_path)
    kanban.block_task = lambda _connection, task_id, **values: (
        kanban.blocked.append((task_id, values)) or False
    )
    store = exhausted_store(tmp_path / "refused.db")
    pool = coordinator.Coordinator(MASTER, store)

    pool.expire_leases()
    assert states(store) == [("23", 0, 3, "lease_failed")]
    assert len(kanban.blocked) == 1

    # The next pass retries rather than giving up on the run.
    pool.expire_leases()
    assert len(kanban.blocked) == 2
    assert states(store) == [("23", 0, 3, "lease_failed")]


def test_lease_failure_settles_stale_when_the_run_moved_or_vanished(
    tmp_path, monkeypatch
):
    moved = task(current_run_id=99)
    kanban = install_kanban(monkeypatch, [moved], tmp_path)
    store = exhausted_store(tmp_path / "moved.db")
    coordinator.Coordinator(MASTER, store).expire_leases()
    assert states(store) == [("23", 0, 3, "stale")]
    assert kanban.blocked == []

    kanban.tasks.clear()
    gone = exhausted_store(tmp_path / "gone.db", binding(task_id="t_gone", attempt=3))
    coordinator.Coordinator(MASTER, gone).expire_leases()
    assert states(gone) == [("23", 0, 3, "stale")]


def test_lease_failure_settles_finalized_when_kanban_already_parked_the_run(
    tmp_path, monkeypatch
):
    parked = task(status="blocked")
    kanban = install_kanban(monkeypatch, [parked], tmp_path)
    store = exhausted_store(tmp_path / "parked.db")
    coordinator.Coordinator(MASTER, store).expire_leases()
    assert states(store) == [("23", 0, 3, "finalized")]
    assert kanban.blocked == []


def test_noncanonical_run_lease_failure_is_released_without_a_board_call(
    tmp_path, monkeypatch
):
    kanban = install_kanban(monkeypatch, [task()], tmp_path)
    store = exhausted_store(
        tmp_path / "bad-run.db", binding(run_id="run-bad", attempt=3)
    )
    coordinator.Coordinator(MASTER, store).expire_leases()
    assert states(store) == [("run-bad", 0, 3, "stale")]
    assert kanban.blocked == []


def test_lease_expiry_releases_only_a_trusted_publication_retry(tmp_path, monkeypatch):
    """An OOM-style lease expiry returns one receipt before parking the native run."""
    kanban = install_kanban(monkeypatch, [task()], tmp_path)
    store = pool_store.PoolStore(tmp_path / "resume-lease.db")
    exact = binding(attempt=3)
    store.add(exact, assignment_payload(scm_resume={"source": {"worker_ordinal": 0}}))
    store.offer(0)
    with store._connect() as connection:
        connection.execute("UPDATE assignments SET lease_until=1")
    released = []
    monkeypatch.setattr(
        coordinator.supervisor_state, "reissue_publication_retry",
        lambda *values: released.append(values) or True,
    )
    coordinator.Coordinator(MASTER, store).expire_leases()
    assert released and released[0][2] == "23"
    assert kanban.blocked[-1][1]["kind"] == "transient"


def test_a_durable_row_in_any_state_blocks_conflicting_re_adoption(tmp_path, monkeypatch):
    """known_runs() covers terminal and retrying rows, not just live ones."""
    live = task()
    install_kanban(monkeypatch, [live], tmp_path)
    monkeypatch.setattr(
        coordinator, "assignment_payload",
        lambda _db, _connection, _task, _board: assignment_payload(context="different"),
    )
    store = pool_store.PoolStore(tmp_path / "known.db")
    store.add(binding(), assignment_payload())
    pool = coordinator.Coordinator(MASTER, store)
    for state in ("lease_failed", "finalized", "stale"):
        with store._connect() as connection:
            connection.execute("UPDATE assignments SET state=?", (state,))
        assert store.known_runs() == {("metis", "t_deadbeef", "23")}
        pool.reconcile()
        assert states(store) == [("23", 0, 1, state)]