mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
6b81590c55
Systematic prune per AGENTS.md test policy, one pass over every major test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli, cron, tui_gateway, honcho/openviking, root-level): - DELETE: source-reading tests (read_text/getsource on prod files), change-detector tests (exact catalog counts, model-name snapshots, config version literals), mock-echo tests (assert a mock returns what it was told), assertion-free/trivial tests, near-duplicate parametrizations (boundaries + one representative kept), async/sync twin duplicates, cosmetic within-file variations. - KEEP (mandatory): security/redaction/approval guards, message-role alternation invariants, prompt-caching/deterministic-call-id invariants, issue-number regression tests (deduped), E2E tests. - 6 test files deleted outright (script-style/no-assert or fully redundant); conftest.py, fakes/, fixtures/ untouched. - tests/acp/conftest.py added: autouse fixture stubs the live models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server tests performed on every session create — test_server.py 147s → 3.4s, and the tests are now genuinely hermetic. - Sleep-based slowness shrunk where safe (codex_ttfb_watchdog, compression_concurrent_fork, etc.); no wall-clock assertion tightened. Verification: full hermetic suite via scripts/run_tests.sh — 2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall (baseline: 583s wall, 13,564s subprocess CPU).
54 lines
1.7 KiB
Python
54 lines
1.7 KiB
Python
"""Tests for the AC-4 isolation certify seam + harness helpers.
|
|
|
|
The synthetic heavy-turn agent (``tui_gateway/synthetic_turn.py``) is a test
|
|
seam: dead unless ``HERMES_ISO_CERTIFY_SYNTH_TURN=1``. These tests pin (a) the
|
|
dead-when-unset contract, (b) that an armed turn holds for the requested wall
|
|
duration and streams deltas, (c) that interrupt aborts it promptly, and (d) the
|
|
harness percentile math.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import importlib.util
|
|
import threading
|
|
import time
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from tui_gateway.synthetic_turn import (
|
|
SyntheticHeavyAgent,
|
|
maybe_build_synthetic_agent,
|
|
synth_turn_armed,
|
|
)
|
|
|
|
REPO_ROOT = Path(__file__).resolve().parents[2]
|
|
|
|
|
|
def _load_iso_certify():
|
|
path = REPO_ROOT / "scripts" / "iso-certify.py"
|
|
spec = importlib.util.spec_from_file_location("iso_certify", path)
|
|
assert spec and spec.loader
|
|
mod = importlib.util.module_from_spec(spec)
|
|
spec.loader.exec_module(mod)
|
|
return mod
|
|
|
|
|
|
def test_synth_seam_dead_when_env_unset(monkeypatch):
|
|
monkeypatch.delenv("HERMES_ISO_CERTIFY_SYNTH_TURN", raising=False)
|
|
assert synth_turn_armed() is False
|
|
assert maybe_build_synthetic_agent("sid") is None
|
|
|
|
|
|
def test_harness_percentile_and_guard():
|
|
iso = _load_iso_certify()
|
|
assert iso.percentile([], 99) == 0.0
|
|
assert iso.percentile([5.0], 99) == 5.0
|
|
vals = [float(i) for i in range(1, 101)] # 1..100
|
|
assert 98.0 <= iso.percentile(vals, 99) <= 100.0
|
|
assert iso.percentile(vals, 50) == pytest.approx(50.5, abs=0.6)
|
|
# The empty-timeline INCONCLUSIVE floor: too few probe samples never PASSes.
|
|
assert iso.probe_thread_samples_ok([1.0, 2.0], [1.0, 2.0, 3.0]) is False
|
|
assert iso.probe_thread_samples_ok([1.0, 2.0, 3.0], [1.0, 2.0, 3.0]) is True
|
|
|
|
|