refactor: вынос хардкода + LLM-анализ finding'ов

## Часть A: Вынос хардкода
- Новый модуль constants.py — все magic strings, лимиты, severity, ключи
  (104 хардкод-значения централизованы)
- Новый модуль queries.py — общие SQL-запросы (build_scan_list_query,
  build_package_list_query, get_dashboard_stats)
  Убрана дупликация между api/*.py и web/routes.py (~90%)

- config.py: добавлены NLP_ENABLED, nexus_timeout, guarddog_binary,
  log_syslog_facility, LLM-переменные
- nexus_client.py: таймауты из конфига, SHA256_CHUNK_SIZE из constants
- scanner.py: error-ключи из constants, GUARDDOG_OUTPUT_FORMAT из constants
- webhooks.py: RELEVANT_WEBHOOK_ACTIONS, METADATA_PATTERNS, ignore-строки
  из constants
- logging_setup.py: конфигурируемый syslog facility, APP_PACKAGE из constants
- main.py: APP_NAME, APP_DESCRIPTION, APP_PACKAGE из constants
- models.py: поле report: JSON | None в Finding для LLM-отчётов
- harvester.py: авто-очистка tmpdir через finally; ERROR_MESSAGE_MAX_LENGTH
  из constants; PACKAGE_EXTENSIONS вместо SUPPORTED_EXTENSIONS (с .gem)
- api/*.py + web/routes.py: используют build_*_query из queries.py,
  константы для лимитов и сортировок
- tests/conftest.py: SEVERITY_WARNING, DEFAULT_ECOSYSTEM из constants

## Часть B: LLM-анализ finding'ов
- llm.py: клиент для OpenAI-совместимых API с промптом security-аналитика
- harvester.py: авто-триггер после flagged scan, сохранение report в БД
- api/findings.py: POST /{id}/analyze — ручной триггер
- web/routes.py: POST /api/v1/findings/{id}/analyze — HTMX-фрагмент
- _llm_report_fragment.html: шаблон фрагмента с вердиктом
- scan_detail.html, package_detail.html: кнопка Analyze with LLM
  (htmx-post, spinner, inline-замена на LLM-отчёт)
- style.css: стили для .llm-report .verdict-safe/suspicious/malicious

## Часть C: Тесты
- 50 тестов, все зелёные
- Линтер чистый
- Тесты используют constants где нужно
This commit is contained in:
Marker689
2026-05-10 04:37:07 +03:00
parent c43e7c4c9b
commit 834138368a
21 changed files with 1094 additions and 476 deletions

View File

@@ -17,44 +17,12 @@ os.environ["NEXUS_PASSWORD"] = "admin123"
os.environ["LOG_SYSLOG_HOST"] = ""
os.environ["TEMP_DIR"] = "/tmp/guarddog-nexus-test"
from guarddog_nexus.constants import DEFAULT_ECOSYSTEM, SEVERITY_WARNING # noqa: E402
from guarddog_nexus.database import Base, get_session # noqa: E402
from guarddog_nexus.main import app # noqa: E402
from guarddog_nexus.models import Finding, Scan, ScanStatus # noqa: E402
@pytest_asyncio.fixture
async def sample_flagged_scan(db_session):
scan = Scan(
package_name="test-pkg",
package_version="1.0",
ecosystem="pypi",
repository="pypi-proxy",
nexus_asset_url="http://nexus:8081/repository/pypi-proxy/packages/test-pkg/1.0/test-pkg-1.0.tar.gz",
sha256="abc123",
status=ScanStatus.COMPLETED.value,
total_findings=1,
flagged=True,
)
db_session.add(scan)
await db_session.commit()
await db_session.refresh(scan)
finding = Finding(
scan_id=scan.id,
data={
"rule": "test_rule",
"severity": "WARNING",
"message": "Test finding",
"location": "test.py:1",
"code": "print('test')",
},
)
db_session.add(finding)
await db_session.commit()
await db_session.refresh(scan)
return scan
@pytest_asyncio.fixture
async def db_engine():
engine = create_async_engine(
@@ -92,6 +60,39 @@ async def client(db_engine):
app.dependency_overrides.clear()
@pytest_asyncio.fixture
async def sample_flagged_scan(db_session):
scan = Scan(
package_name="test-pkg",
package_version="1.0",
ecosystem=DEFAULT_ECOSYSTEM,
repository="pypi-proxy",
nexus_asset_url="http://nexus:8081/repository/pypi-proxy/packages/test-pkg/1.0/test-pkg-1.0.tar.gz",
sha256="abc123",
status=ScanStatus.COMPLETED.value,
total_findings=1,
flagged=True,
)
db_session.add(scan)
await db_session.commit()
await db_session.refresh(scan)
finding = Finding(
scan_id=scan.id,
data={
"rule": "test_rule",
"severity": SEVERITY_WARNING,
"message": "Test finding",
"location": "test.py:1",
"code": "print('test')",
},
)
db_session.add(finding)
await db_session.commit()
await db_session.refresh(scan)
return scan
@pytest.fixture
def sample_nexus_webhook():
return {
@@ -178,21 +179,21 @@ def guarddog_normalized_flagged():
"findings": [
{
"rule": "shady-links",
"severity": "WARNING",
"severity": SEVERITY_WARNING,
"message": "Package contains URL to suspicious domain",
"location": "setup.py:15",
"code": "url = 'http://evil.com'",
},
{
"rule": "exec-base64",
"severity": "WARNING",
"severity": SEVERITY_WARNING,
"message": "Base64-encoded code execution detected",
"location": "core.py:42",
"code": "exec(base64.b64decode(...))",
},
{
"rule": "empty_information",
"severity": "WARNING",
"severity": SEVERITY_WARNING,
"message": "Package description is empty",
"location": "",
"code": "",