feat: add auto-fetch for missing dependencies from upstream registries

Add auto_fetch parameter to dependency resolution endpoint that fetches
missing dependencies from upstream registries (PyPI) when resolving.

- Add RegistryClient abstraction with PyPIRegistryClient implementation
- Extract fetch_and_cache_pypi_package() for reuse
- Add resolve_dependencies_with_fetch() async function
- Extend MissingDependency schema with fetch_attempted/fetch_error
- Add fetched list to DependencyResolutionResponse
- Add auto_fetch_max_depth config setting (default: 3)
- Remove Usage section from Package page UI
- Add 6 integration tests for auto-fetch functionality
This commit is contained in:
Mondo Diaz
2026-02-04 12:01:49 -06:00
parent b82bd1c85a
commit 5cff4092e3
10 changed files with 1348 additions and 65 deletions

View File

@@ -0,0 +1,416 @@
"""
Registry client abstraction for upstream package registries.
Provides a pluggable interface for fetching packages from upstream registries
(PyPI, npm, Maven, etc.) during dependency resolution with auto-fetch enabled.
"""
import hashlib
import logging
import os
import re
import tempfile
from abc import ABC, abstractmethod
from dataclasses import dataclass
from typing import List, Optional, TYPE_CHECKING
from urllib.parse import urljoin, urlparse
import httpx
from packaging.specifiers import SpecifierSet, InvalidSpecifier
from packaging.version import Version, InvalidVersion
from sqlalchemy.orm import Session
if TYPE_CHECKING:
from .storage import S3Storage
from .http_client import HttpClientManager
logger = logging.getLogger(__name__)
@dataclass
class VersionInfo:
"""Information about a package version from an upstream registry."""
version: str
download_url: str
filename: str
sha256: Optional[str] = None
size: Optional[int] = None
content_type: Optional[str] = None
@dataclass
class FetchResult:
"""Result of fetching a package from upstream."""
artifact_id: str # SHA256 hash
size: int
version: str
filename: str
already_cached: bool = False
class RegistryClient(ABC):
"""Abstract base class for upstream registry clients."""
@property
@abstractmethod
def source_type(self) -> str:
"""Return the source type this client handles (e.g., 'pypi', 'npm')."""
pass
@abstractmethod
async def get_available_versions(self, package_name: str) -> List[str]:
"""
Get all available versions of a package from upstream.
Args:
package_name: The normalized package name
Returns:
List of version strings, sorted from oldest to newest
"""
pass
@abstractmethod
async def resolve_constraint(
self, package_name: str, constraint: str
) -> Optional[VersionInfo]:
"""
Find the best version matching a constraint.
Args:
package_name: The normalized package name
constraint: Version constraint (e.g., '>=1.9', '<2.0,>=1.5', '*')
Returns:
VersionInfo with download URL, or None if no matching version found
"""
pass
@abstractmethod
async def fetch_package(
self,
package_name: str,
version_info: VersionInfo,
db: Session,
storage: "S3Storage",
) -> Optional[FetchResult]:
"""
Fetch and cache a package from upstream.
Args:
package_name: The normalized package name
version_info: Version details including download URL
db: Database session for creating records
storage: S3 storage for caching the artifact
Returns:
FetchResult with artifact_id, or None if fetch failed
"""
pass
class PyPIRegistryClient(RegistryClient):
"""PyPI registry client using the JSON API."""
# Timeout configuration for PyPI requests
CONNECT_TIMEOUT = 30.0
READ_TIMEOUT = 60.0
DOWNLOAD_TIMEOUT = 300.0 # Longer timeout for file downloads
def __init__(
self,
http_client: httpx.AsyncClient,
upstream_sources: List,
pypi_api_url: str = "https://pypi.org/pypi",
):
"""
Initialize PyPI registry client.
Args:
http_client: Shared async HTTP client
upstream_sources: List of configured upstream sources for auth
pypi_api_url: Base URL for PyPI JSON API
"""
self.client = http_client
self.sources = upstream_sources
self.api_url = pypi_api_url
@property
def source_type(self) -> str:
return "pypi"
def _normalize_package_name(self, name: str) -> str:
"""Normalize a PyPI package name per PEP 503."""
return re.sub(r"[-_.]+", "-", name).lower()
def _get_auth_headers(self) -> dict:
"""Get authentication headers from configured sources."""
headers = {"User-Agent": "Orchard-Registry-Client/1.0"}
if self.sources:
source = self.sources[0]
if hasattr(source, "auth_type"):
if source.auth_type == "bearer":
password = (
source.get_password()
if hasattr(source, "get_password")
else getattr(source, "password", None)
)
if password:
headers["Authorization"] = f"Bearer {password}"
elif source.auth_type == "api_key":
custom_headers = (
source.get_headers()
if hasattr(source, "get_headers")
else {}
)
if custom_headers:
headers.update(custom_headers)
return headers
def _get_basic_auth(self) -> Optional[tuple]:
"""Get basic auth credentials if configured."""
if self.sources:
source = self.sources[0]
if hasattr(source, "auth_type") and source.auth_type == "basic":
username = getattr(source, "username", None)
if username:
password = (
source.get_password()
if hasattr(source, "get_password")
else getattr(source, "password", "")
)
return (username, password or "")
return None
async def get_available_versions(self, package_name: str) -> List[str]:
"""Get all available versions from PyPI JSON API."""
normalized = self._normalize_package_name(package_name)
url = f"{self.api_url}/{normalized}/json"
headers = self._get_auth_headers()
auth = self._get_basic_auth()
timeout = httpx.Timeout(self.READ_TIMEOUT, connect=self.CONNECT_TIMEOUT)
try:
response = await self.client.get(
url, headers=headers, auth=auth, timeout=timeout
)
if response.status_code == 404:
logger.debug(f"Package {normalized} not found on PyPI")
return []
if response.status_code != 200:
logger.warning(
f"PyPI API returned {response.status_code} for {normalized}"
)
return []
data = response.json()
releases = data.get("releases", {})
# Filter to valid versions and sort
versions = []
for v in releases.keys():
try:
Version(v)
versions.append(v)
except InvalidVersion:
continue
versions.sort(key=lambda x: Version(x))
return versions
except httpx.RequestError as e:
logger.warning(f"Failed to query PyPI for {normalized}: {e}")
return []
except Exception as e:
logger.warning(f"Error parsing PyPI response for {normalized}: {e}")
return []
async def resolve_constraint(
self, package_name: str, constraint: str
) -> Optional[VersionInfo]:
"""Find best version matching constraint from PyPI."""
normalized = self._normalize_package_name(package_name)
url = f"{self.api_url}/{normalized}/json"
headers = self._get_auth_headers()
auth = self._get_basic_auth()
timeout = httpx.Timeout(self.READ_TIMEOUT, connect=self.CONNECT_TIMEOUT)
try:
response = await self.client.get(
url, headers=headers, auth=auth, timeout=timeout
)
if response.status_code == 404:
logger.debug(f"Package {normalized} not found on PyPI")
return None
if response.status_code != 200:
logger.warning(
f"PyPI API returned {response.status_code} for {normalized}"
)
return None
data = response.json()
releases = data.get("releases", {})
# Handle wildcard - return latest version
if constraint == "*":
latest_version = data.get("info", {}).get("version")
if latest_version and latest_version in releases:
return self._get_version_info(
normalized, latest_version, releases[latest_version]
)
return None
# Parse constraint
try:
specifier = SpecifierSet(constraint)
except InvalidSpecifier:
# Invalid constraint - treat as wildcard
logger.warning(
f"Invalid version constraint '{constraint}' for {normalized}, "
"treating as wildcard"
)
latest_version = data.get("info", {}).get("version")
if latest_version and latest_version in releases:
return self._get_version_info(
normalized, latest_version, releases[latest_version]
)
return None
# Find matching versions
matching = []
for v_str, files in releases.items():
if not files: # Skip versions with no files
continue
try:
v = Version(v_str)
if v in specifier:
matching.append((v_str, v, files))
except InvalidVersion:
continue
if not matching:
logger.debug(
f"No versions of {normalized} match constraint '{constraint}'"
)
return None
# Sort by version and return highest match
matching.sort(key=lambda x: x[1], reverse=True)
best_version, _, best_files = matching[0]
return self._get_version_info(normalized, best_version, best_files)
except httpx.RequestError as e:
logger.warning(f"Failed to query PyPI for {normalized}: {e}")
return None
except Exception as e:
logger.warning(f"Error resolving {normalized}@{constraint}: {e}")
return None
def _get_version_info(
self, package_name: str, version: str, files: List[dict]
) -> Optional[VersionInfo]:
"""Extract download info from PyPI release files."""
if not files:
return None
# Prefer wheel over sdist
wheel_file = None
sdist_file = None
for f in files:
filename = f.get("filename", "")
if filename.endswith(".whl"):
# Prefer platform-agnostic wheels
if "py3-none-any" in filename or wheel_file is None:
wheel_file = f
elif filename.endswith(".tar.gz") and sdist_file is None:
sdist_file = f
selected = wheel_file or sdist_file
if not selected:
# Fall back to first available file
selected = files[0]
return VersionInfo(
version=version,
download_url=selected.get("url", ""),
filename=selected.get("filename", ""),
sha256=selected.get("digests", {}).get("sha256"),
size=selected.get("size"),
content_type="application/zip"
if selected.get("filename", "").endswith(".whl")
else "application/gzip",
)
async def fetch_package(
self,
package_name: str,
version_info: VersionInfo,
db: Session,
storage: "S3Storage",
) -> Optional[FetchResult]:
"""Fetch and cache a PyPI package."""
# Import here to avoid circular imports
from .pypi_proxy import fetch_and_cache_pypi_package
normalized = self._normalize_package_name(package_name)
logger.info(
f"Fetching {normalized}=={version_info.version} from upstream PyPI"
)
result = await fetch_and_cache_pypi_package(
db=db,
storage=storage,
http_client=self.client,
package_name=normalized,
filename=version_info.filename,
download_url=version_info.download_url,
expected_sha256=version_info.sha256,
)
if result is None:
return None
return FetchResult(
artifact_id=result["artifact_id"],
size=result["size"],
version=version_info.version,
filename=version_info.filename,
already_cached=result.get("already_cached", False),
)
def get_registry_client(
source_type: str,
http_client: httpx.AsyncClient,
upstream_sources: List,
) -> Optional[RegistryClient]:
"""
Factory function to get a registry client for a source type.
Args:
source_type: The registry type ('pypi', 'npm', etc.)
http_client: Shared async HTTP client
upstream_sources: List of configured upstream sources
Returns:
RegistryClient for the source type, or None if not supported
"""
if source_type == "pypi":
# Filter to PyPI sources
pypi_sources = [s for s in upstream_sources if getattr(s, "source_type", "") == "pypi"]
return PyPIRegistryClient(http_client, pypi_sources)
# Future: Add npm, maven, etc.
logger.debug(f"No registry client available for source type: {source_type}")
return None