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.
77 lines
2 KiB
Python
77 lines
2 KiB
Python
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from hermes_cli.session_export_md import (
|
|
append_manifest_entry,
|
|
render_session_markdown,
|
|
safe_session_filename,
|
|
verify_export_file,
|
|
write_session_markdown,
|
|
)
|
|
|
|
|
|
def _session(**overrides):
|
|
data = {
|
|
"id": "20260706_123456_abcd1234",
|
|
"title": "Export Test",
|
|
"source": "telegram",
|
|
"model": "gpt-5.5",
|
|
"billing_provider": "openai-codex",
|
|
"cwd": "/tmp/project",
|
|
"started_at": 1783331696.0,
|
|
"last_active": 1783331705.0,
|
|
"ended_at": 1783331710.0,
|
|
"message_count": 3,
|
|
"tool_call_count": 1,
|
|
"archived": 0,
|
|
"messages": [
|
|
{"role": "user", "content": "Hello", "created_at": 1783331697.0},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"tool_calls": [
|
|
{"function": {"name": "terminal", "arguments": "{\"command\": \"pwd\"}"}}
|
|
],
|
|
"created_at": 1783331698.0,
|
|
},
|
|
{"role": "tool", "name": "terminal", "content": "output", "created_at": 1783331699.0},
|
|
],
|
|
}
|
|
data.update(overrides)
|
|
return data
|
|
|
|
|
|
|
|
|
|
def test_safe_session_filename_is_deterministic_and_path_safe():
|
|
filename = safe_session_filename(
|
|
_session(id="20260706_123456_abcd1234", title="Bad / title: * ?"), fmt="qmd"
|
|
)
|
|
|
|
assert filename.startswith("20260706_123456_abcd1234-")
|
|
assert filename.endswith(".qmd")
|
|
assert "/" not in filename
|
|
assert ":" not in filename
|
|
assert "*" not in filename
|
|
assert "?" not in filename
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_verify_export_file_checks_count_and_sha(tmp_path):
|
|
session = _session()
|
|
path = write_session_markdown(session, tmp_path)
|
|
|
|
ok, reason = verify_export_file(path, session)
|
|
assert ok is True
|
|
assert reason == "ok"
|
|
|
|
path.write_text(path.read_text(encoding="utf-8").replace("Hello", "Tampered"), encoding="utf-8")
|
|
ok, reason = verify_export_file(path, session)
|
|
assert ok is False
|
|
assert "sha256" in reason
|
|
|
|
|