mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
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.
196 lines
6.4 KiB
Python
196 lines
6.4 KiB
Python
import asyncio
|
|
import pytest
|
|
|
|
from pathlib import Path
|
|
from types import SimpleNamespace
|
|
from hermes_cli import kanban_db as kb
|
|
from unittest.mock import AsyncMock, MagicMock, patch
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Fixtures
|
|
# ---------------------------------------------------------------------------
|
|
|
|
@pytest.fixture
|
|
def kanban_home(tmp_path, monkeypatch):
|
|
home = tmp_path / ".hermes"
|
|
home.mkdir()
|
|
monkeypatch.setenv("HERMES_HOME", str(home))
|
|
monkeypatch.setattr(Path, "home", lambda: tmp_path)
|
|
# Allow the kanban notifier path-validator to upload artifacts the
|
|
# tests write under ``tmp_path``. Without this, every artifact-delivery
|
|
# test silently drops files because ``tmp_path`` isn't inside the
|
|
# default ``MEDIA_DELIVERY_SAFE_ROOTS`` cache dirs.
|
|
monkeypatch.setenv("HERMES_MEDIA_ALLOW_DIRS", str(tmp_path))
|
|
kb.init_db()
|
|
return home
|
|
|
|
|
|
def _assert_inherited_notify_sub(subs: list[dict]) -> None:
|
|
assert len(subs) == 1
|
|
assert subs[0]["platform"] == "telegram"
|
|
assert subs[0]["chat_id"] == "chat1"
|
|
assert subs[0]["thread_id"] == "topic1"
|
|
assert subs[0]["user_id"] == "user1"
|
|
assert subs[0]["notifier_profile"] == "default"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Regression: gateway watchers must not double-init the kanban DB.
|
|
#
|
|
# Both the notifier watcher (`_kanban_notifier_watcher`) and the dispatcher
|
|
# tick (`_tick_once_for_board`) used to call `_kb.connect(board=slug)`
|
|
# immediately followed by `_kb.init_db(board=slug)`. Since `connect()`
|
|
# already runs the schema + idempotent migration on first open per process,
|
|
# the explicit `init_db()` was redundant — and worse, `init_db()`
|
|
# deliberately busts the per-process cache and re-runs the migration on a
|
|
# *second* connection, which races the first. On legacy DBs this surfaced
|
|
# as `duplicate column name: <col>` (now tolerated by
|
|
# `_add_column_if_missing`) and intermittent `database is locked` errors
|
|
# (issue #21378).
|
|
#
|
|
# The fix removes the `init_db()` calls in both watchers; this regression
|
|
# test pins that behaviour so we don't reintroduce them.
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_gateway_create_autosubscribes_on_explicit_board(kanban_home):
|
|
"""`/kanban --board <slug> create ...` must subscribe on that board.
|
|
|
|
The gateway handler currently auto-subscribes after `/kanban create`,
|
|
but the create detection must still work when the shared `--board`
|
|
flag appears before the subcommand, and the subscription must land in
|
|
that board's DB rather than the ambient/default board.
|
|
"""
|
|
from gateway.run import GatewayRunner
|
|
from gateway.config import Platform
|
|
|
|
kb.create_board("projx")
|
|
|
|
runner = object.__new__(GatewayRunner)
|
|
source = SimpleNamespace(
|
|
platform=Platform.TELEGRAM,
|
|
chat_id="chat1",
|
|
chat_type="dm",
|
|
thread_id="20197",
|
|
user_id="u1",
|
|
)
|
|
event = SimpleNamespace(
|
|
text='/kanban --board projx create "hello" --assignee alice',
|
|
source=source,
|
|
message_id="462",
|
|
reply_to_message_id=None,
|
|
)
|
|
|
|
out = await GatewayRunner._handle_kanban_command(runner, event)
|
|
|
|
assert "subscribed" in out.lower()
|
|
|
|
conn = kb.connect(board="projx")
|
|
try:
|
|
subs = kb.list_notify_subs(conn)
|
|
tasks = kb.list_tasks(conn)
|
|
finally:
|
|
conn.close()
|
|
|
|
assert [t.title for t in tasks] == ["hello"]
|
|
assert len(subs) == 1
|
|
assert subs[0]["chat_id"] == "chat1"
|
|
assert subs[0]["thread_id"] == "20197"
|
|
assert subs[0]["delivery_metadata"] == {
|
|
"chat_type": "dm",
|
|
"direct_messages_topic_id": "20197",
|
|
"telegram_dm_topic_reply_fallback": True,
|
|
"telegram_reply_to_message_id": "462",
|
|
"thread_id": "20197",
|
|
}
|
|
|
|
conn = kb.connect(board="default")
|
|
try:
|
|
assert kb.list_notify_subs(conn) == []
|
|
finally:
|
|
conn.close()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_notifier_artifact_delivery_skips_missing_files(kanban_home, tmp_path, monkeypatch):
|
|
"""Missing artifact paths are silently skipped — they may have been
|
|
referenced by name only. The notifier must not crash and must still
|
|
deliver any artifacts that do exist."""
|
|
import hermes_cli.kanban_db as kb
|
|
from gateway.run import GatewayRunner
|
|
from gateway.config import Platform
|
|
from tools import kanban_tools as kt
|
|
|
|
# Allow ``tmp_path`` through the media-delivery safety filter. See the
|
|
# companion test for the full explanation.
|
|
monkeypatch.setenv("HERMES_MEDIA_ALLOW_DIRS", str(tmp_path))
|
|
|
|
real_pdf = tmp_path / "real.pdf"
|
|
real_pdf.write_bytes(b"%PDF-fake")
|
|
|
|
conn = kb.connect()
|
|
try:
|
|
tid = kb.create_task(conn, title="t", assignee="worker1")
|
|
kb.add_notify_sub(conn, task_id=tid, platform="telegram", chat_id="chat1")
|
|
finally:
|
|
conn.close()
|
|
|
|
import os
|
|
os.environ["HERMES_KANBAN_TASK"] = tid
|
|
try:
|
|
kt._handle_complete({
|
|
"summary": "one real, one ghost",
|
|
"artifacts": [str(real_pdf), "/tmp/definitely-does-not-exist.pdf"],
|
|
})
|
|
finally:
|
|
os.environ.pop("HERMES_KANBAN_TASK", None)
|
|
|
|
runner = object.__new__(GatewayRunner)
|
|
runner._running = True
|
|
runner._kanban_sub_fail_counts = {}
|
|
|
|
fake_adapter = MagicMock()
|
|
fake_adapter.name = "telegram"
|
|
|
|
documents_uploaded: list = []
|
|
|
|
async def _send(chat_id, msg, metadata=None):
|
|
runner._running = False
|
|
|
|
async def _send_document(chat_id, file_path, metadata=None, **_kw):
|
|
documents_uploaded.append(file_path)
|
|
|
|
fake_adapter.send = AsyncMock(side_effect=_send)
|
|
fake_adapter.send_document = AsyncMock(side_effect=_send_document)
|
|
fake_adapter.send_multiple_images = AsyncMock()
|
|
from gateway.platforms.base import BasePlatformAdapter
|
|
fake_adapter.extract_local_files = BasePlatformAdapter.extract_local_files
|
|
|
|
runner.adapters = {Platform.TELEGRAM: fake_adapter}
|
|
|
|
_orig_sleep = asyncio.sleep
|
|
|
|
async def _fast_sleep(_):
|
|
await _orig_sleep(0)
|
|
|
|
with patch("gateway.run.asyncio.sleep", side_effect=_fast_sleep):
|
|
await asyncio.wait_for(
|
|
runner._kanban_notifier_watcher(interval=1),
|
|
timeout=10.0,
|
|
)
|
|
|
|
# Only the real file was uploaded.
|
|
assert len(documents_uploaded) == 1
|
|
assert "real.pdf" in documents_uploaded[0]
|