mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +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.
137 lines
3.5 KiB
Python
137 lines
3.5 KiB
Python
import json
|
|
import sys
|
|
|
|
from hermes_cli.session_export import export_record_count, render_sessions_export
|
|
from hermes_cli.session_export_html import (
|
|
_generate_messages_html,
|
|
generate_multi_session_html_export,
|
|
)
|
|
|
|
|
|
def _sample_session():
|
|
return {
|
|
"id": "sess-123",
|
|
"source": "cli",
|
|
"model": "test/model",
|
|
"title": "Debug auth flow",
|
|
"started_at": 1700000000,
|
|
"message_count": 5,
|
|
"messages": [
|
|
{
|
|
"id": 1,
|
|
"role": "system",
|
|
"content": "hidden system context",
|
|
"timestamp": 1700000000,
|
|
},
|
|
{
|
|
"id": 2,
|
|
"role": "user",
|
|
"content": "Why is login broken?",
|
|
"timestamp": 1700000001,
|
|
"platform_message_id": "evt-2",
|
|
},
|
|
{
|
|
"id": 3,
|
|
"role": "assistant",
|
|
"content": "I will inspect the auth middleware.",
|
|
"timestamp": 1700000002,
|
|
},
|
|
{
|
|
"id": 4,
|
|
"role": "tool",
|
|
"tool_name": "read_file",
|
|
"content": "def redirect_after_login(): pass",
|
|
"timestamp": 1700000003,
|
|
},
|
|
{
|
|
"id": 5,
|
|
"role": "user",
|
|
"content": [{"type": "text", "text": "Only show me the prompts."}],
|
|
"timestamp": 1700000004,
|
|
},
|
|
],
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_html_export_escapes_tool_call_names():
|
|
payload = '<img src=x onerror="alert(document.domain)">'
|
|
|
|
rendered = _generate_messages_html(
|
|
[
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"tool_calls": [
|
|
{
|
|
"id": "call_1",
|
|
"type": "function",
|
|
"function": {"name": payload, "arguments": "<b>x</b>"},
|
|
}
|
|
],
|
|
}
|
|
]
|
|
)
|
|
|
|
assert payload not in rendered
|
|
assert '<img src=x onerror="alert(document.domain)">' in rendered
|
|
assert "<b>x</b>" in rendered
|
|
|
|
|
|
|
|
|
|
def test_export_record_count_switches_unit_for_prompt_only_exports():
|
|
assert export_record_count([_sample_session()]) == (1, "session")
|
|
assert export_record_count([_sample_session()], only="user-prompts") == (
|
|
2,
|
|
"prompt",
|
|
)
|
|
|
|
|
|
def test_sessions_export_cli_prompt_only_stdout(monkeypatch, capsys):
|
|
import hermes_cli.main as main_mod
|
|
import hermes_state
|
|
|
|
captured = {}
|
|
|
|
class FakeDB:
|
|
def resolve_session_id(self, session_id):
|
|
captured["resolved_from"] = session_id
|
|
return "sess-123"
|
|
|
|
def export_session(self, session_id):
|
|
captured["exported"] = session_id
|
|
return _sample_session()
|
|
|
|
def close(self):
|
|
captured["closed"] = True
|
|
|
|
monkeypatch.setattr(hermes_state, "SessionDB", lambda: FakeDB())
|
|
monkeypatch.setattr(
|
|
sys,
|
|
"argv",
|
|
["hermes", "sessions", "export", "-", "--session-id", "sess", "--only", "user-prompts"],
|
|
)
|
|
|
|
main_mod.main()
|
|
|
|
output = capsys.readouterr().out
|
|
records = [json.loads(line) for line in output.splitlines()]
|
|
assert [record["text"] for record in records] == [
|
|
"Why is login broken?",
|
|
"Only show me the prompts.",
|
|
]
|
|
assert captured == {
|
|
"resolved_from": "sess",
|
|
"exported": "sess-123",
|
|
"closed": True,
|
|
}
|
|
|
|
|