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.
100 lines
3.7 KiB
Python
100 lines
3.7 KiB
Python
"""Regression tests for #21582 — per-profile concurrency cap in dispatcher.
|
|
|
|
When ``kanban.max_in_progress_per_profile`` is set, no single profile
|
|
gets more than N workers running at once even if the global
|
|
``max_in_progress`` cap would allow it. Prevents one profile's local
|
|
model / API quota / browser pool from being overwhelmed by a fan-out.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import sys
|
|
import tempfile
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture()
|
|
def isolated_kanban_home_with_profiles(monkeypatch):
|
|
"""Spin up a fresh HERMES_HOME with kanban DB + alpha/beta profiles."""
|
|
test_home = tempfile.mkdtemp(prefix="kanban_per_profile_cap_test_")
|
|
for prof in ("alpha", "beta", "default"):
|
|
os.makedirs(os.path.join(test_home, "profiles", prof), exist_ok=True)
|
|
monkeypatch.setenv("HERMES_HOME", test_home)
|
|
for mod in list(sys.modules.keys()):
|
|
if mod.startswith("hermes_cli") or mod.startswith("hermes_state") or mod == "hermes_constants":
|
|
del sys.modules[mod]
|
|
from hermes_cli import kanban_db
|
|
yield kanban_db
|
|
|
|
|
|
def _fake_spawn(*args, **kwargs):
|
|
return 12345
|
|
|
|
|
|
|
|
|
|
def test_cap_2_balances_two_profiles(isolated_kanban_home_with_profiles):
|
|
"""With cap=2: 2 alpha + 2 beta dispatched; remaining 3 alpha + 1 beta
|
|
deferred to skipped_per_profile_capped."""
|
|
kb = isolated_kanban_home_with_profiles
|
|
with kb.connect_closing() as conn:
|
|
kb.create_board(slug="default", name="Test")
|
|
for i in range(5):
|
|
kb.create_task(conn, title=f"a{i}", assignee="alpha")
|
|
for i in range(3):
|
|
kb.create_task(conn, title=f"b{i}", assignee="beta")
|
|
with kb.connect_closing() as conn:
|
|
res = kb.dispatch_once(
|
|
conn, spawn_fn=_fake_spawn, dry_run=True,
|
|
max_in_progress_per_profile=2,
|
|
)
|
|
spawn_assignees = [s[1] for s in res.spawned]
|
|
capped_assignees = [c[1] for c in res.skipped_per_profile_capped]
|
|
assert spawn_assignees.count("alpha") == 2
|
|
assert spawn_assignees.count("beta") == 2
|
|
assert capped_assignees.count("alpha") == 3
|
|
assert capped_assignees.count("beta") == 1
|
|
|
|
|
|
|
|
|
|
def test_capped_tasks_dispatched_on_subsequent_tick(isolated_kanban_home_with_profiles):
|
|
"""A task deferred this tick because its profile was at cap should be
|
|
eligible for dispatch on the next tick (after running tasks complete).
|
|
This verifies the cap is per-tick state, not a permanent block."""
|
|
kb = isolated_kanban_home_with_profiles
|
|
with kb.connect_closing() as conn:
|
|
kb.create_board(slug="default", name="Test")
|
|
ids = [kb.create_task(conn, title=f"a{i}", assignee="alpha") for i in range(3)]
|
|
|
|
# First tick: cap=1, only 1 alpha dispatched
|
|
with kb.connect_closing() as conn:
|
|
res1 = kb.dispatch_once(
|
|
conn, spawn_fn=_fake_spawn, dry_run=False,
|
|
max_in_progress_per_profile=1,
|
|
)
|
|
assert len(res1.spawned) == 1
|
|
assert len(res1.skipped_per_profile_capped) == 2
|
|
|
|
# Simulate the running task completing — set it back to done so the
|
|
# 'running' count drops
|
|
spawned_id = res1.spawned[0][0]
|
|
with kb.connect_closing() as conn:
|
|
with kb.write_txn(conn):
|
|
conn.execute(
|
|
"UPDATE tasks SET status = 'done', claim_lock = NULL WHERE id = ?",
|
|
(spawned_id,),
|
|
)
|
|
|
|
# Second tick: 1 more alpha should now dispatch
|
|
with kb.connect_closing() as conn:
|
|
res2 = kb.dispatch_once(
|
|
conn, spawn_fn=_fake_spawn, dry_run=False,
|
|
max_in_progress_per_profile=1,
|
|
)
|
|
assert len(res2.spawned) == 1
|
|
assert len(res2.skipped_per_profile_capped) == 1
|
|
assert res2.spawned[0][0] != spawned_id # different task this time
|
|
|
|
|