217 lines
8.1 KiB
Python
217 lines
8.1 KiB
Python
from __future__ import annotations
|
|
|
|
import json
|
|
import tempfile
|
|
import unittest
|
|
import zipfile
|
|
from io import BytesIO
|
|
from pathlib import Path
|
|
|
|
from evaluation.client import EvalClientError, require_safe_base_url
|
|
from evaluation.audit import audit_repository, audit_security_repository
|
|
from evaluation.combine import combine_reports
|
|
from evaluation.inspect_bridge import export_inspect_jsonl
|
|
from evaluation.models import AssertionSpec, EvalConfigError, RunObservation
|
|
from evaluation.report import render_markdown, summarize
|
|
from evaluation.scoring import score_observation
|
|
from evaluation.suite import load_suite
|
|
|
|
|
|
class EvaluationSuiteTests(unittest.TestCase):
|
|
def test_smoke_suite_valid(self):
|
|
root = Path(__file__).resolve().parents[1]
|
|
suite = load_suite(root / "evaluation" / "datasets" / "smoke.json")
|
|
self.assertEqual(suite.name, "zcbot-smoke")
|
|
self.assertGreaterEqual(len(suite.cases), 4)
|
|
production = load_suite(
|
|
root / "evaluation" / "datasets" / "production_smoke.json"
|
|
)
|
|
self.assertEqual(production.default_repetitions, 1)
|
|
self.assertNotIn(
|
|
"security", {case.dimension for case in production.cases}
|
|
)
|
|
materials = load_suite(
|
|
root / "evaluation" / "datasets" / "materials_core.json"
|
|
)
|
|
self.assertEqual(len(materials.cases), 10)
|
|
full_safe = load_suite(
|
|
root / "evaluation" / "datasets" / "production_full_safe.json"
|
|
)
|
|
self.assertEqual(len(full_safe.cases), 3)
|
|
self.assertEqual(
|
|
{case.dimension for case in full_safe.cases},
|
|
{"task_quality", "reliability", "performance"},
|
|
)
|
|
|
|
def test_inspect_export(self):
|
|
root = Path(__file__).resolve().parents[1]
|
|
suite = load_suite(root / "evaluation" / "datasets" / "smoke.json")
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
output = Path(tmp) / "inspect.jsonl"
|
|
count = export_inspect_jsonl(suite, output)
|
|
records = [
|
|
json.loads(line)
|
|
for line in output.read_text(encoding="utf-8").splitlines()
|
|
]
|
|
self.assertEqual(count, len(suite.cases))
|
|
self.assertEqual(records[0]["id"], suite.cases[0].id)
|
|
self.assertIn("assertions", records[0]["metadata"])
|
|
|
|
def test_duplicate_case_id_rejected(self):
|
|
raw = {
|
|
"cases": [
|
|
{
|
|
"id": "same",
|
|
"dimension": "task_quality",
|
|
"prompt": "a",
|
|
"assertions": [{"type": "response_nonempty"}],
|
|
},
|
|
{
|
|
"id": "same",
|
|
"dimension": "task_quality",
|
|
"prompt": "b",
|
|
"assertions": [{"type": "response_nonempty"}],
|
|
},
|
|
]
|
|
}
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
path = Path(tmp) / "suite.json"
|
|
path.write_text(json.dumps(raw), encoding="utf-8")
|
|
with self.assertRaises(EvalConfigError):
|
|
load_suite(path)
|
|
|
|
|
|
class ScoringTests(unittest.TestCase):
|
|
def test_weighted_response_and_artifact_score(self):
|
|
observation = RunObservation(
|
|
response="CaCO3",
|
|
run_status="idle",
|
|
artifact_loader=lambda path: b"ok" if path == "a.txt" else b"",
|
|
)
|
|
specs = (
|
|
AssertionSpec("run_succeeded", weight=2),
|
|
AssertionSpec("response_contains", value="CaCO3", weight=2),
|
|
AssertionSpec("response_contains", value="wrong", weight=1),
|
|
AssertionSpec("artifact_exists", path="a.txt", weight=1),
|
|
)
|
|
score, results = score_observation(specs, observation)
|
|
self.assertAlmostEqual(score, 5 / 6)
|
|
self.assertEqual(sum(r.passed for r in results), 3)
|
|
|
|
def test_zip_validation(self):
|
|
stream = BytesIO()
|
|
with zipfile.ZipFile(stream, "w") as archive:
|
|
archive.writestr("x.txt", "ok")
|
|
observation = RunObservation(
|
|
artifact_loader=lambda _path: stream.getvalue()
|
|
)
|
|
score, _ = score_observation(
|
|
(AssertionSpec("artifact_zip_valid", path="x.pptx"),),
|
|
observation,
|
|
)
|
|
self.assertEqual(score, 1.0)
|
|
|
|
|
|
class ClientSafetyTests(unittest.TestCase):
|
|
def test_local_url_allowed(self):
|
|
self.assertEqual(
|
|
require_safe_base_url(
|
|
"http://127.0.0.1:8765", allow_remote=False
|
|
),
|
|
"http://127.0.0.1:8765/",
|
|
)
|
|
|
|
def test_remote_url_requires_explicit_opt_in(self):
|
|
with self.assertRaises(EvalClientError):
|
|
require_safe_base_url(
|
|
"https://zcbot.example.com", allow_remote=False
|
|
)
|
|
self.assertEqual(
|
|
require_safe_base_url(
|
|
"https://zcbot.example.com", allow_remote=True
|
|
),
|
|
"https://zcbot.example.com/",
|
|
)
|
|
|
|
|
|
class ReportTests(unittest.TestCase):
|
|
def test_combine_existing_dimension_reports(self):
|
|
engineering = {
|
|
"suite": {"name": "engineering", "version": "1"},
|
|
"generated_at": "2026-01-01T00:00:00+00:00",
|
|
"environment": {"git_commit": "abc"},
|
|
"dimensions": {
|
|
"engineering": {
|
|
"weight": 15,
|
|
"score": 40,
|
|
"case_count": 1,
|
|
}
|
|
},
|
|
"security_cap": {"failures": []},
|
|
"cases": [],
|
|
}
|
|
smoke = {
|
|
"suite": {"name": "smoke", "version": "1"},
|
|
"generated_at": "2026-01-02T00:00:00+00:00",
|
|
"environment": {"git_commit": "abc"},
|
|
"dimensions": {
|
|
"task_quality": {
|
|
"weight": 40,
|
|
"score": 100,
|
|
"case_count": 1,
|
|
},
|
|
"performance": {
|
|
"weight": 10,
|
|
"score": 100,
|
|
"case_count": 1,
|
|
},
|
|
},
|
|
"security_cap": {"failures": []},
|
|
"cases": [],
|
|
}
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
engineering_path = Path(tmp) / "engineering.json"
|
|
smoke_path = Path(tmp) / "smoke.json"
|
|
engineering_path.write_text(
|
|
json.dumps(engineering), encoding="utf-8"
|
|
)
|
|
smoke_path.write_text(json.dumps(smoke), encoding="utf-8")
|
|
combined = combine_reports([engineering_path, smoke_path])
|
|
self.assertEqual(combined["provisional_score"], 86.15)
|
|
self.assertIsNone(combined["total_score"])
|
|
self.assertFalse(combined["is_complete"])
|
|
self.assertEqual(len(combined["sources"]), 2)
|
|
|
|
def test_incomplete_dimensions_have_no_total(self):
|
|
root = Path(__file__).resolve().parents[1]
|
|
suite = load_suite(root / "evaluation" / "datasets" / "smoke.json")
|
|
summary = summarize(suite, [], repo_root=root)
|
|
self.assertIsNone(summary["total_score"])
|
|
self.assertFalse(summary["is_complete"])
|
|
self.assertIn("总分为 N/A", render_markdown(summary))
|
|
|
|
def test_audit_result_has_engineering_dimension(self):
|
|
# 用极短超时验证固定评分结构，不要求当前仓库全量命令在此测试内跑完。
|
|
root = Path(__file__).resolve().parents[1]
|
|
result = audit_repository(
|
|
root, timeout_s=0.001, write_evidence=False
|
|
)
|
|
self.assertEqual(result.case.dimension, "engineering")
|
|
types = {item.type for item in result.repetitions[0].assertions}
|
|
self.assertIn("unit_tests", types)
|
|
self.assertIn("coverage", types)
|
|
self.assertNotIn("pip-audit", types)
|
|
security = audit_security_repository(
|
|
root, timeout_s=0.001, write_evidence=False
|
|
)
|
|
self.assertEqual(security.case.dimension, "security")
|
|
security_types = {
|
|
item.type for item in security.repetitions[0].assertions
|
|
}
|
|
self.assertIn("bandit", security_types)
|
|
self.assertIn("pip-audit", security_types)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|