Teknium
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.
82 lines
2.3 KiB
Python
82 lines
2.3 KiB
Python
"""
|
|
Smoke tests for the darwinian-evolver optional skill.
|
|
|
|
We can't actually run the evolution loop in CI (it needs network + a paid LLM),
|
|
so these tests verify:
|
|
- SKILL.md frontmatter conforms to the hardline format
|
|
- shipped scripts parse as valid Python
|
|
- the scripts reference the right env var / module paths
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import ast
|
|
import re
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
import yaml
|
|
|
|
SKILL_DIR = Path(__file__).resolve().parents[2] / "optional-skills" / "research" / "darwinian-evolver"
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def frontmatter() -> dict:
|
|
src = (SKILL_DIR / "SKILL.md").read_text()
|
|
m = re.search(r"^---\n(.*?)\n---", src, re.DOTALL)
|
|
assert m, "SKILL.md missing YAML frontmatter"
|
|
return yaml.safe_load(m.group(1))
|
|
|
|
|
|
def test_skill_dir_exists() -> None:
|
|
assert SKILL_DIR.is_dir(), f"missing skill dir: {SKILL_DIR}"
|
|
|
|
|
|
|
|
|
|
def test_description_under_60_chars(frontmatter) -> None:
|
|
desc = frontmatter["description"]
|
|
assert len(desc) <= 60, f"description is {len(desc)} chars (hardline ≤60): {desc!r}"
|
|
|
|
|
|
|
|
|
|
def test_platforms_excludes_windows(frontmatter) -> None:
|
|
# Upstream uses func_timeout (POSIX signals) and uv subprocess pipelines; the
|
|
# skill is gated [linux, macos]. If we ever port to Windows, update this test
|
|
# to assert ["linux", "macos", "windows"].
|
|
assert "windows" not in frontmatter["platforms"]
|
|
assert set(frontmatter["platforms"]) >= {"linux", "macos"}
|
|
|
|
|
|
def test_author_credits_contributor(frontmatter) -> None:
|
|
author = frontmatter["author"]
|
|
assert "Bihruze" in author, f"author should credit the original contributor: {author!r}"
|
|
|
|
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"path",
|
|
[
|
|
"scripts/parrot_openrouter.py",
|
|
"scripts/show_snapshot.py",
|
|
"templates/custom_problem_template.py",
|
|
],
|
|
)
|
|
def test_shipped_scripts_parse(path: str) -> None:
|
|
src = (SKILL_DIR / path).read_text()
|
|
ast.parse(src) # raises SyntaxError on broken Python
|
|
|
|
|
|
def test_parrot_script_uses_openrouter() -> None:
|
|
src = (SKILL_DIR / "scripts" / "parrot_openrouter.py").read_text()
|
|
assert "OPENROUTER_API_KEY" in src, "parrot driver should read OPENROUTER_API_KEY"
|
|
assert "openrouter.ai/api/v1" in src, "parrot driver should target OpenRouter"
|
|
assert "EVOLVER_MODEL" in src, "model should be overridable via EVOLVER_MODEL"
|
|
|
|
|
|
|
|
|
|
|
|
|