mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +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.
168 lines
5 KiB
Python
168 lines
5 KiB
Python
"""Tests for the kanban CLI surface (hermes_cli.kanban)."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import json
|
|
import os
|
|
import threading
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from hermes_cli import kanban as kc
|
|
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.setattr(Path, "home", lambda: tmp_path)
|
|
kb.init_db()
|
|
return home
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Workspace flag parsing
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# run_slash smoke tests (end-to-end via the same entry both CLI and gateway use)
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
def test_kanban_list_json_includes_session_id(kanban_home):
|
|
"""JSON output exposes `session_id` so external clients (Scarf, web
|
|
dashboards) don't need a side query to filter by chat session."""
|
|
from hermes_cli import kanban_db as kb
|
|
with kb.connect() as conn:
|
|
kb.create_task(
|
|
conn, title="acp task", assignee="alice", session_id="acp-x"
|
|
)
|
|
raw = kc.run_slash("list --json")
|
|
payload = json.loads(raw)
|
|
assert any(
|
|
row.get("title") == "acp task"
|
|
and row.get("session_id") == "acp-x"
|
|
for row in payload
|
|
)
|
|
|
|
|
|
def test_board_override_is_isolated_per_concurrent_call(kanban_home, monkeypatch):
|
|
kb.create_board("alpha")
|
|
kb.create_board("beta")
|
|
|
|
parser = argparse.ArgumentParser(prog="hermes", add_help=False)
|
|
sub = parser.add_subparsers(dest="command")
|
|
kc.build_parser(sub)
|
|
|
|
barrier = threading.Barrier(2)
|
|
original_init_db = kb.init_db
|
|
|
|
def slow_init_db(*args, **kwargs):
|
|
try:
|
|
barrier.wait(timeout=5)
|
|
except threading.BrokenBarrierError:
|
|
pass
|
|
return original_init_db(*args, **kwargs)
|
|
|
|
monkeypatch.setattr(kb, "init_db", slow_init_db)
|
|
|
|
failures: list[str] = []
|
|
|
|
def worker(board: str, title: str) -> None:
|
|
args = parser.parse_args(["kanban", "--board", board, "create", title])
|
|
rc = kc.kanban_command(args)
|
|
if rc != 0:
|
|
failures.append(f"{board}:{rc}")
|
|
|
|
t1 = threading.Thread(target=worker, args=("alpha", "alpha-task"))
|
|
t2 = threading.Thread(target=worker, args=("beta", "beta-task"))
|
|
t1.start()
|
|
t2.start()
|
|
t1.join()
|
|
t2.join()
|
|
|
|
assert failures == []
|
|
|
|
with kb.connect_closing(board="alpha") as conn:
|
|
alpha_titles = [row.title for row in kb.list_tasks(conn, limit=100)]
|
|
with kb.connect_closing(board="beta") as conn:
|
|
beta_titles = [row.title for row in kb.list_tasks(conn, limit=100)]
|
|
|
|
assert alpha_titles == ["alpha-task"]
|
|
assert beta_titles == ["beta-task"]
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Integration with the COMMAND_REGISTRY
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# reclaim + reassign CLI smoke tests
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def test_run_slash_reclaim_running_task(kanban_home):
|
|
import re
|
|
import time
|
|
import secrets
|
|
from hermes_cli import kanban_db as kb
|
|
|
|
out1 = kc.run_slash("create 'stuck worker task' --assignee broken-model")
|
|
m = re.search(r"(t_[a-f0-9]+)", out1)
|
|
assert m
|
|
tid = m.group(1)
|
|
|
|
# Simulate a running claim outside TTL.
|
|
conn = kb.connect()
|
|
try:
|
|
lock = secrets.token_hex(4)
|
|
conn.execute(
|
|
"UPDATE tasks SET status='running', claim_lock=?, claim_expires=?, "
|
|
"worker_pid=? WHERE id=?",
|
|
(lock, int(time.time()) + 3600, 4242, tid),
|
|
)
|
|
conn.execute(
|
|
"INSERT INTO task_runs (task_id, status, claim_lock, claim_expires, "
|
|
"worker_pid, started_at) VALUES (?, 'running', ?, ?, ?, ?)",
|
|
(tid, lock, int(time.time()) + 3600, 4242, int(time.time())),
|
|
)
|
|
rid = conn.execute("SELECT last_insert_rowid()").fetchone()[0]
|
|
conn.execute("UPDATE tasks SET current_run_id=? WHERE id=?", (rid, tid))
|
|
conn.commit()
|
|
finally:
|
|
conn.close()
|
|
|
|
out = kc.run_slash(f"reclaim {tid} --reason 'test'")
|
|
assert "Reclaimed" in out, out
|
|
# Status back to ready.
|
|
out2 = kc.run_slash(f"show {tid}")
|
|
assert "ready" in out2.lower()
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# /kanban specify — slash surface (same entry point CLI + gateway use)
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# /kanban help / no-args / unknown-action UX (issue #21794)
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|