mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
39975613b1
Second, deeper pass over tools/gateway/hermes_cli plus first pass over the trees wave 1 missed (acp, acp_adapter, skills, computer_use, docker, dashboard, conformance, monitoring, secret_sources, hermes_state, providers). Same rubric as wave 1 (AGENTS.md test policy); security, alternation/caching invariants, issue-number regressions, and E2E kept. Real test-quality fixes found and rooted out along the way: - tests/tools/test_command_guards.py made real auxiliary-LLM HTTPS calls (DEFAULT_CONFIG smart-approval leaked in) — pinned approval mode=manual via autouse fixture: 17.4s → 0.4s. - test_model_switch_custom_providers.py / test_user_providers_model_switch.py silently probed live provider catalogs (~2s/test) — stubbed cached_provider_model_ids/provider_model_ids/fetch_api_models. - test_telegram_noise_filter.py: 15-platform copy-paste matrix over shared gateway.run logic → 3 representative platforms (55s → 3.9s). - test_gateway_shutdown.py: stop()'s 5s interrupt-deadline loop spun on MagicMock agents — interrupt.side_effect now clears _running_agents (22s → 1.0s). - test_gateway_inactivity_timeout.py poll-harness timings shrunk 3-5x (24s → 1.1s); test_mcp_stability.py backoff/SIGTERM-grace sleeps patched (15.4s → 2.5s); test_async_delegation.py negative-drain wait 5s → 0.5s. - test_telegram_init_deadline.py: loop-block margin restored to 1.0s with rationale comment — the watchdog-dump assertion needs the loop blocked well past deadline+grace under parallel load (flaked once in the 40-worker verification run at a 0.2s margin). Verification: full hermetic suite via scripts/run_tests.sh — 2,438 files, 21,718 tests passed, 0 failed, 293.9s wall. Suite totals vs original baseline: 46,820 → 19,757 test functions (−57.8%), wall 583.5s → 293.9s (−50%), subprocess CPU 13,564s → 11,623s.
79 lines
2.7 KiB
Python
79 lines
2.7 KiB
Python
"""Tests for the kanban dispatcher single-writer lock (issue #35240).
|
|
|
|
A ``hermes gateway run --replace`` / ``gateway restart`` from a shell on a
|
|
systemd/launchd host can leave an orphan dispatcher that escapes the
|
|
service cgroup, survives ``systemctl restart``, and becomes a second
|
|
long-lived writer on the same ``kanban.db`` — the documented root cause of
|
|
multi-writer SQLite WAL corruption. ``dispatch_once`` now wraps each tick in
|
|
a non-blocking, board-scoped dispatch lock so two dispatchers can never run
|
|
a reclaim/spawn/write tick concurrently. The losing dispatcher returns an
|
|
empty ``DispatchResult`` with ``skipped_locked=True`` and does no DB writes.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from hermes_cli import kanban_db as kb
|
|
|
|
|
|
@pytest.fixture
|
|
def kanban_home(tmp_path, monkeypatch):
|
|
home = tmp_path / ".hermes"
|
|
home.mkdir()
|
|
monkeypatch.setenv("HERMES_HOME", str(home))
|
|
monkeypatch.setenv("HERMES_KANBAN_HOME", str(home))
|
|
monkeypatch.setattr(Path, "home", lambda: tmp_path)
|
|
db_path = kb.kanban_db_path(board="default")
|
|
kb._INITIALIZED_PATHS.discard(str(db_path.resolve()))
|
|
kb.init_db()
|
|
return home
|
|
|
|
|
|
@pytest.fixture
|
|
def conn(kanban_home):
|
|
with kb.connect() as c:
|
|
yield c
|
|
|
|
|
|
|
|
|
|
def test_held_lock_skips_the_tick_without_writes(conn):
|
|
"""While another holder owns the board lock, dispatch_once must skip and
|
|
must NOT invoke spawn_fn (no DB writes happen on a skipped tick)."""
|
|
kb.create_task(conn, title="t", assignee="w")
|
|
db_path = kb.kanban_db_path(board="default")
|
|
|
|
spawn_calls: list = []
|
|
|
|
def spy_spawn(task, workspace_path, board=None):
|
|
spawn_calls.append(getattr(task, "id", task))
|
|
return 999999
|
|
|
|
# Hold the lock, then attempt a contended tick.
|
|
with kb._dispatch_tick_lock(db_path) as held:
|
|
assert held is True # we genuinely acquired it
|
|
result = kb.dispatch_once(conn, spawn_fn=spy_spawn)
|
|
|
|
assert result.skipped_locked is True
|
|
assert result.spawned == []
|
|
assert spawn_calls == [], "spawn_fn must not run while the tick is locked out"
|
|
|
|
|
|
|
|
|
|
def test_lock_is_board_scoped(conn):
|
|
"""Holding board A's dispatch lock must not block a tick on board B —
|
|
distinct boards have distinct DB files and tick independently."""
|
|
db_default = kb.kanban_db_path(board="default")
|
|
db_other = db_default.with_name("other-board-kanban.db")
|
|
|
|
# Two different lock files → both acquirable simultaneously.
|
|
with kb._dispatch_tick_lock(db_default) as held_a:
|
|
assert held_a is True
|
|
with kb._dispatch_tick_lock(db_other) as held_b:
|
|
assert held_b is True, "a lock on a different board must be independent"
|
|
|
|
|