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.
101 lines
3 KiB
Python
101 lines
3 KiB
Python
"""Tests for tool token estimation and curses_ui status_fn support."""
|
|
|
|
|
|
import pytest
|
|
|
|
# tiktoken is not in core/[all] deps — skip estimation tests when unavailable
|
|
_has_tiktoken = True
|
|
try:
|
|
import tiktoken # noqa: F401
|
|
except ImportError:
|
|
_has_tiktoken = False
|
|
|
|
_needs_tiktoken = pytest.mark.skipif(not _has_tiktoken, reason="tiktoken not installed")
|
|
|
|
|
|
# ─── Token Estimation Tests ──────────────────────────────────────────────────
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ─── Status Function Tests ───────────────────────────────────────────────────
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_status_fn_empty_selection():
|
|
"""Status function with no tools selected should return ~0 tokens."""
|
|
import hermes_cli.tools_config as tc
|
|
|
|
tc._tool_token_cache = None
|
|
tokens = tc._estimate_tool_tokens()
|
|
if not tokens:
|
|
pytest.skip("tiktoken unavailable")
|
|
|
|
from hermes_cli.tools_config import CONFIGURABLE_TOOLSETS
|
|
from toolsets import resolve_toolset
|
|
|
|
ts_keys = [ts_key for ts_key, _, _ in CONFIGURABLE_TOOLSETS]
|
|
|
|
def status_fn(chosen: set) -> str:
|
|
all_tools: set = set()
|
|
for idx in chosen:
|
|
all_tools.update(resolve_toolset(ts_keys[idx]))
|
|
total = sum(tokens.get(name, 0) for name in all_tools)
|
|
if total >= 1000:
|
|
return f"Est. tool context: ~{total / 1000:.1f}k tokens"
|
|
return f"Est. tool context: ~{total} tokens"
|
|
|
|
result = status_fn(set())
|
|
assert "~0 tokens" in result
|
|
|
|
|
|
# ─── Curses UI Status Bar Tests ──────────────────────────────────────────────
|
|
|
|
|
|
def test_curses_checklist_numbered_fallback_shows_status(monkeypatch, capsys):
|
|
"""The numbered fallback should print the status_fn output."""
|
|
from hermes_cli.curses_ui import _numbered_fallback
|
|
|
|
def my_status(chosen):
|
|
return f"Selected {len(chosen)} items"
|
|
|
|
# Simulate user pressing Enter immediately (empty input → confirm)
|
|
monkeypatch.setattr("builtins.input", lambda _prompt="": "")
|
|
|
|
result = _numbered_fallback(
|
|
"Test title",
|
|
["Item A", "Item B", "Item C"],
|
|
{0, 2},
|
|
{0, 2},
|
|
status_fn=my_status,
|
|
)
|
|
|
|
captured = capsys.readouterr()
|
|
assert "Selected 2 items" in captured.out
|
|
assert result == {0, 2}
|
|
|
|
|
|
|
|
|
|
# ─── Registry get_schema Tests ───────────────────────────────────────────────
|
|
|
|
|
|
def test_registry_get_schema_returns_schema():
|
|
"""registry.get_schema() should return a tool's schema dict."""
|
|
from tools.registry import registry
|
|
|
|
# Import to trigger discovery
|
|
import model_tools # noqa: F401
|
|
|
|
schema = registry.get_schema("terminal")
|
|
assert schema is not None
|
|
assert "name" in schema
|
|
assert schema["name"] == "terminal"
|
|
assert "parameters" in schema
|
|
|
|
|