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.
75 lines
2.1 KiB
Python
75 lines
2.1 KiB
Python
"""Tests for MCP tools interactive configuration in hermes_cli.tools_config."""
|
|
|
|
from unittest.mock import patch
|
|
|
|
from hermes_cli.tools_config import _configure_mcp_tools_interactive
|
|
|
|
# Patch targets: imports happen inside the function body, so patch at source
|
|
_PROBE = "tools.mcp_tool.probe_mcp_server_tools"
|
|
_CHECKLIST = "hermes_cli.curses_ui.curses_checklist"
|
|
_SAVE = "hermes_cli.tools_config.save_config"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_disabling_tool_writes_include_list(capsys):
|
|
"""Unchecking a tool produces an include list of the still-chosen tools.
|
|
|
|
Standardized on tools.include (whitelist) across the codebase — the
|
|
catalog flow, `hermes mcp configure`, and this UI all write the same
|
|
shape so users don\'t see config drift across UIs.
|
|
"""
|
|
config = {
|
|
"mcp_servers": {
|
|
"github": {"command": "npx"},
|
|
}
|
|
}
|
|
tools = [
|
|
("create_issue", "Create an issue"),
|
|
("delete_repo", "Delete a repo"),
|
|
("search_repos", "Search repos"),
|
|
]
|
|
|
|
# User unchecks delete_repo (index 1)
|
|
with patch(_PROBE, return_value={"github": tools}), \
|
|
patch(_CHECKLIST, return_value={0, 2}), \
|
|
patch(_SAVE) as mock_save:
|
|
_configure_mcp_tools_interactive(config)
|
|
|
|
mock_save.assert_called_once()
|
|
tools_cfg = config["mcp_servers"]["github"]["tools"]
|
|
assert tools_cfg["include"] == ["create_issue", "search_repos"]
|
|
assert "exclude" not in tools_cfg
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_empty_tools_server_skipped(capsys):
|
|
"""Server with no tools shows info message and skips checklist."""
|
|
config = {
|
|
"mcp_servers": {
|
|
"empty": {"command": "npx"},
|
|
}
|
|
}
|
|
checklist_calls = []
|
|
|
|
def fake_checklist(title, labels, pre_selected, **kwargs):
|
|
checklist_calls.append(title)
|
|
return pre_selected
|
|
|
|
with patch(_PROBE, return_value={"empty": []}), \
|
|
patch(_CHECKLIST, side_effect=fake_checklist), \
|
|
patch(_SAVE):
|
|
_configure_mcp_tools_interactive(config)
|
|
|
|
assert len(checklist_calls) == 0
|
|
captured = capsys.readouterr()
|
|
assert "no tools found" in captured.out
|