mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +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.
100 lines
2.8 KiB
Python
100 lines
2.8 KiB
Python
"""Tests for skill fuzzy patching via tools.fuzzy_match."""
|
|
|
|
import json
|
|
|
|
import pytest
|
|
|
|
from tools.skill_manager_tool import (
|
|
_create_skill,
|
|
_patch_skill,
|
|
_write_file,
|
|
skill_manage,
|
|
)
|
|
|
|
|
|
SKILL_CONTENT = """\
|
|
---
|
|
name: test-skill
|
|
description: A test skill for unit testing.
|
|
---
|
|
|
|
# Test Skill
|
|
|
|
Step 1: Do the thing.
|
|
Step 2: Do another thing.
|
|
Step 3: Final step.
|
|
"""
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Fuzzy patching
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestFuzzyPatchSkill:
|
|
@pytest.fixture(autouse=True)
|
|
def setup_skills(self, tmp_path, monkeypatch):
|
|
skills_dir = tmp_path / "skills"
|
|
skills_dir.mkdir()
|
|
monkeypatch.setattr("tools.skill_manager_tool.SKILLS_DIR", skills_dir)
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
|
self.skills_dir = skills_dir
|
|
|
|
def test_exact_match_still_works(self):
|
|
_create_skill("test-skill", SKILL_CONTENT)
|
|
result = _patch_skill("test-skill", "Step 1: Do the thing.", "Step 1: Done!")
|
|
assert result["success"] is True
|
|
content = (self.skills_dir / "test-skill" / "SKILL.md").read_text()
|
|
assert "Step 1: Done!" in content
|
|
|
|
def test_whitespace_trimmed_match(self):
|
|
"""Patch with extra leading whitespace should still find the target."""
|
|
skill = """\
|
|
---
|
|
name: ws-skill
|
|
description: Whitespace test
|
|
---
|
|
|
|
# Commands
|
|
|
|
def hello():
|
|
print("hi")
|
|
"""
|
|
_create_skill("ws-skill", skill)
|
|
# Agent sends patch with no leading whitespace (common LLM behaviour)
|
|
result = _patch_skill("ws-skill", "def hello():\n print(\"hi\")", "def hello():\n print(\"hello world\")")
|
|
assert result["success"] is True
|
|
content = (self.skills_dir / "ws-skill" / "SKILL.md").read_text()
|
|
assert 'print("hello world")' in content
|
|
|
|
|
|
def test_multiple_matches_blocked_without_replace_all(self):
|
|
"""Multiple fuzzy matches should return an error without replace_all."""
|
|
skill = """\
|
|
---
|
|
name: dup-skill
|
|
description: Duplicate test
|
|
---
|
|
|
|
# Steps
|
|
|
|
word word word
|
|
"""
|
|
_create_skill("dup-skill", skill)
|
|
result = _patch_skill("dup-skill", "word", "replaced")
|
|
assert result["success"] is False
|
|
assert "match" in result["error"].lower()
|
|
|
|
|
|
def test_skill_manage_patch_uses_fuzzy(self):
|
|
"""The dispatcher should route to the fuzzy-matching patch."""
|
|
_create_skill("test-skill", SKILL_CONTENT)
|
|
raw = skill_manage(
|
|
action="patch",
|
|
name="test-skill",
|
|
old_string=" Step 1: Do the thing.", # extra leading space
|
|
new_string="Step 1: Updated.",
|
|
)
|
|
result = json.loads(raw)
|
|
# Should succeed via line-trimmed or indentation-flexible matching
|
|
assert result["success"] is True
|