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.
68 lines
2.3 KiB
Python
68 lines
2.3 KiB
Python
"""Harness: docker run <image> [cmd...] invocation patterns.
|
|
|
|
These tests MUST pass on the current tini-based image AND continue to
|
|
pass after the Phase 2 s6 migration. Any behavior drift is a regression.
|
|
|
|
The harness expects ``built_image`` and ``container_name`` fixtures from
|
|
``tests/docker/conftest.py``. When Docker isn't available every test
|
|
here is skipped at collection time.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import subprocess
|
|
|
|
|
|
def test_no_args_starts_hermes(built_image: str) -> None:
|
|
"""``docker run <image>`` should start hermes cleanly.
|
|
|
|
We invoke ``--version`` so the call exits without needing a configured
|
|
model. Exit code may be 0 (printed version) or 1 (config bootstrapping
|
|
failure on a fresh volume), but never a stack trace.
|
|
"""
|
|
r = subprocess.run(
|
|
["docker", "run", "--rm", built_image, "--version"],
|
|
capture_output=True, text=True, timeout=60,
|
|
)
|
|
assert r.returncode in (0, 1), (
|
|
f"Unexpected exit {r.returncode}: stderr={r.stderr!r}"
|
|
)
|
|
assert "Traceback" not in r.stderr
|
|
|
|
|
|
def test_chat_subcommand_passthrough(built_image: str) -> None:
|
|
"""``docker run <image> chat --help`` should exec ``hermes chat --help``.
|
|
|
|
Uses ``--help`` so the call doesn't need an upstream model configured.
|
|
"""
|
|
r = subprocess.run(
|
|
["docker", "run", "--rm", built_image, "chat", "--help"],
|
|
capture_output=True, text=True, timeout=60,
|
|
)
|
|
assert r.returncode == 0
|
|
combined = (r.stdout + r.stderr).lower()
|
|
assert "chat" in combined or "usage" in combined
|
|
|
|
|
|
|
|
|
|
def test_bash_pattern(built_image: str) -> None:
|
|
"""``docker run <image> bash -c 'echo ok'`` should exec bash directly."""
|
|
r = subprocess.run(
|
|
["docker", "run", "--rm", built_image, "bash", "-c", "echo ok"],
|
|
capture_output=True, text=True, timeout=30,
|
|
)
|
|
assert r.returncode == 0
|
|
assert "ok" in r.stdout
|
|
|
|
|
|
def test_container_exit_code_matches_inner_exit(built_image: str) -> None:
|
|
"""The container exit code must match the inner process's exit code.
|
|
|
|
Critical for CI: ``docker run <image> hermes batch ...`` returns a
|
|
non-zero status when batch fails. Phase 2 (s6) must preserve this.
|
|
"""
|
|
r = subprocess.run(
|
|
["docker", "run", "--rm", built_image, "sh", "-c", "exit 42"],
|
|
capture_output=True, text=True, timeout=30,
|
|
)
|
|
assert r.returncode == 42
|