mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +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.
69 lines
2.4 KiB
Python
69 lines
2.4 KiB
Python
"""
|
|
Regression tests for the shared-container task_id mapping.
|
|
|
|
The top-level agent and all delegate_task subagents share a single
|
|
terminal sandbox keyed by ``"default"``. ``_resolve_container_task_id``
|
|
is the sole gatekeeper for which tool-call task_ids go to the shared
|
|
container vs. get their own isolated sandbox. RL / benchmark
|
|
environments opt in to isolation by calling
|
|
``register_task_env_overrides(task_id, {...})`` before the agent loop;
|
|
every other task_id collapses back to ``"default"``.
|
|
|
|
If you change the collapse logic, update both the helper and these
|
|
tests -- see `hermes-agent-dev` skill, "Why do subagents get their own
|
|
containers?" section, and the Container lifecycle paragraph under
|
|
Docker Backend in ``website/docs/user-guide/configuration.md``.
|
|
"""
|
|
|
|
import pytest
|
|
|
|
from tools import terminal_tool
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _clean_overrides():
|
|
"""Ensure no stray overrides from other tests leak in."""
|
|
before = dict(terminal_tool._task_env_overrides)
|
|
terminal_tool._task_env_overrides.clear()
|
|
yield
|
|
terminal_tool._task_env_overrides.clear()
|
|
terminal_tool._task_env_overrides.update(before)
|
|
|
|
|
|
def test_none_task_id_maps_to_default():
|
|
assert terminal_tool._resolve_container_task_id(None) == "default"
|
|
|
|
|
|
def test_empty_task_id_maps_to_default():
|
|
assert terminal_tool._resolve_container_task_id("") == "default"
|
|
|
|
|
|
def test_cwd_only_override_collapses_to_default():
|
|
"""CWD-only overrides (ACP adapter workspace tracking) must NOT trigger
|
|
container isolation — they should collapse to the shared 'default'
|
|
container so all surfaces (TUI, gateway, dashboard) share one sandbox.
|
|
Regression for #37361."""
|
|
terminal_tool.register_task_env_overrides(
|
|
"acp-session-abc", {"cwd": "/home/user/project"}
|
|
)
|
|
try:
|
|
assert (
|
|
terminal_tool._resolve_container_task_id("acp-session-abc")
|
|
== "default"
|
|
)
|
|
finally:
|
|
terminal_tool.clear_task_env_overrides("acp-session-abc")
|
|
|
|
|
|
def test_env_type_override_keeps_own_id():
|
|
"""env_type is an isolation key — must trigger per-task container."""
|
|
terminal_tool.register_task_env_overrides(
|
|
"bench-env", {"env_type": "sandbox", "cwd": "/work"}
|
|
)
|
|
try:
|
|
assert (
|
|
terminal_tool._resolve_container_task_id("bench-env")
|
|
== "bench-env"
|
|
)
|
|
finally:
|
|
terminal_tool.clear_task_env_overrides("bench-env")
|