mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-01 12:02:05 +00:00
980622d0ec
The startup config/manifest reads used PyYAML's pure-Python SafeLoader, which is ~8x slower than the libyaml-backed CSafeLoader C extension. config.yaml is parsed several times during launch (cli config, raw config, early interface/redaction bridge, logging config) and every plugin manifest is parsed once — all on the slow path. Add utils.fast_safe_load (CSafeLoader-preferring, pure-Python fallback, true drop-in for safe_load) and route the hot startup parse sites through it: hermes_cli/config.py (config + manifest reads), hermes_cli/plugins.py (manifest parse), env_loader, cli.load_cli_config, hermes_logging, and the two pre-config early YAML bridges in main.py. Behavior is identical (same restricted safe tag set); only speed changes. safe_load calls on the startup path drop from ~79 to ~0, cutting the YAML parse cost from ~0.9s to ~0.15s under profiling. Adds tests/test_fast_safe_load.py asserting equivalence with safe_load across input shapes, empty-doc falsiness, C-loader preference, and that python/object tags are still rejected (safe, not full loader).
62 lines
2.1 KiB
Python
62 lines
2.1 KiB
Python
"""Invariants for utils.fast_safe_load.
|
|
|
|
fast_safe_load is a drop-in for yaml.safe_load that prefers the libyaml
|
|
CSafeLoader C extension for speed. These tests assert the behavior contract
|
|
(it parses identically to safe_load across input shapes), not a snapshot of
|
|
any particular document.
|
|
"""
|
|
|
|
import io
|
|
|
|
import yaml
|
|
|
|
from utils import fast_safe_load, _get_fast_yaml_loader
|
|
|
|
|
|
_DOCS = [
|
|
"", # empty document -> None
|
|
"a: 1\nb: two\nc: 3.5\n",
|
|
"list: [1, 2, 3]\nnested:\n k: v\n flag: true\n empty: null\n",
|
|
"name: skill-x\nmetadata:\n hermes:\n tags: [alpha, beta]\n category: devops\n",
|
|
"- one\n- two\n- three\n", # top-level sequence
|
|
"scalar string", # bare scalar
|
|
]
|
|
|
|
|
|
def test_equivalent_to_safe_load_for_strings():
|
|
for doc in _DOCS:
|
|
assert fast_safe_load(doc) == yaml.safe_load(doc), repr(doc)
|
|
|
|
|
|
def test_equivalent_to_safe_load_for_file_objects():
|
|
for doc in _DOCS:
|
|
assert fast_safe_load(io.StringIO(doc)) == yaml.safe_load(io.StringIO(doc)), repr(doc)
|
|
|
|
|
|
def test_empty_document_returns_none():
|
|
# Callers rely on ``fast_safe_load(...) or {}`` — empty must be falsy.
|
|
assert fast_safe_load("") is None
|
|
|
|
|
|
def test_prefers_c_loader_when_available():
|
|
loader = _get_fast_yaml_loader()
|
|
# If libyaml is compiled in, we must be using the C loader; otherwise the
|
|
# pure-Python SafeLoader is an acceptable fallback. Either way it must be a
|
|
# safe loader (never the unsafe full Loader).
|
|
c_loader = getattr(yaml, "CSafeLoader", None)
|
|
if c_loader is not None:
|
|
assert loader is c_loader
|
|
else:
|
|
assert loader is yaml.SafeLoader
|
|
|
|
|
|
def test_rejects_arbitrary_python_objects_like_safe_load():
|
|
# Safe loaders must not construct arbitrary Python objects. This tag is
|
|
# accepted by the unsafe Loader but rejected by Safe/CSafe loaders.
|
|
dangerous = "!!python/object/apply:os.system ['echo pwned']\n"
|
|
try:
|
|
fast_safe_load(dangerous)
|
|
raised = False
|
|
except yaml.YAMLError:
|
|
raised = True
|
|
assert raised, "fast_safe_load must reject python/object tags like safe_load"
|