apify 3.3.1b6__tar.gz → 3.3.2b2__tar.gz

{apify-3.3.1b6 → apify-3.3.2b2}/.github/workflows/_check_code.yaml

@@ -7,6 +7,9 @@ on:
   # Runs when invoked by another workflow.
   workflow_call:
 
+permissions:
+  contents: read
+
 jobs:
   actions_lint_check:
     name: Actions lint check

{apify-3.3.1b6 → apify-3.3.2b2}/.github/workflows/_check_docs.yaml

@@ -7,6 +7,9 @@ on:
   # Runs when invoked by another workflow.
   workflow_call:
 
+permissions:
+  contents: read
+
 jobs:
   doc_checks:
     name: Doc checks

{apify-3.3.1b6 → apify-3.3.2b2}/.github/workflows/_release_docs.yaml

@@ -11,6 +11,9 @@ on:
         required: true
         type: string
 
+permissions:
+  contents: read
+
 env:
   NODE_VERSION: 22
   PYTHON_VERSION: 3.14
@@ -79,7 +82,7 @@ jobs:
           path: ./website/build
 
       - name: Deploy artifact to GitHub Pages
-        uses: actions/deploy-pages@v4
+        uses: actions/deploy-pages@v5
 
       - name: Invalidate CloudFront cache
         run: |

{apify-3.3.1b6 → apify-3.3.2b2}/.github/workflows/_tests.yaml

@@ -7,6 +7,9 @@ on:
   # Runs when invoked by another workflow.
   workflow_call:
 
+permissions:
+  contents: read
+
 jobs:
   unit_tests:
     name: Unit tests

{apify-3.3.1b6 → apify-3.3.2b2}/.github/workflows/manual_release_stable.yaml

@@ -25,6 +25,9 @@ concurrency:
   group: release
   cancel-in-progress: false
 
+permissions:
+  contents: read
+
 jobs:
   code_checks:
     name: Code checks
@@ -51,6 +54,8 @@ jobs:
   changelog_update:
     name: Changelog update
     needs: [release_prepare]
+    permissions:
+      contents: write
     uses: apify/workflows/.github/workflows/python_bump_and_update_changelog.yaml@main
     with:
       version_number: ${{ needs.release_prepare.outputs.version_number }}
@@ -61,6 +66,8 @@ jobs:
     name: GitHub release
     needs: [release_prepare, changelog_update]
     runs-on: ubuntu-latest
+    permissions:
+      contents: write
     env:
       GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
     steps:
@@ -95,13 +102,83 @@ jobs:
       - name: Publish package to PyPI
         uses: pypa/gh-action-pypi-publish@release/v1
 
+  version_docs:
+    name: Version docs
+    needs: [release_prepare, changelog_update, pypi_publish]
+    runs-on: ubuntu-latest
+    outputs:
+      version_docs_commitish: ${{ steps.commit_versioned_docs.outputs.commit_long_sha }}
+    permissions:
+      contents: write
+    env:
+      NODE_VERSION: 22
+      PYTHON_VERSION: 3.14
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v6
+        with:
+          token: ${{ secrets.APIFY_SERVICE_ACCOUNT_GITHUB_TOKEN }}
+          ref: ${{ needs.changelog_update.outputs.changelog_commitish }}
+
+      - name: Set up Node
+        uses: actions/setup-node@v6
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+
+      - name: Set up uv package manager
+        uses: astral-sh/setup-uv@v7
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+
+      - name: Install Python dependencies
+        run: uv run poe install-dev
+
+      - name: Install website dependencies
+        run: |
+          cd website
+          corepack enable
+          yarn install
+
+      - name: Snapshot the current version
+        run: |
+          cd website
+          VERSION="$(python -c "import tomllib, pathlib; print(tomllib.loads(pathlib.Path('../pyproject.toml').read_text())['project']['version'])")"
+          MAJOR_MINOR="$(echo "$VERSION" | cut -d. -f1-2)"
+          export MAJOR_MINOR
+          # Remove existing version if present (patch releases override)
+          rm -rf "versioned_docs/version-${MAJOR_MINOR}"
+          rm -rf "versioned_sidebars/version-${MAJOR_MINOR}-sidebars.json"
+          jq 'map(select(. != env.MAJOR_MINOR))' versions.json > tmp.json && mv tmp.json versions.json
+          # Build API reference and create version snapshots
+          bash build_api_reference.sh
+          npx docusaurus docs:version "$MAJOR_MINOR"
+          npx docusaurus api:version "$MAJOR_MINOR"
+
+      - name: Commit and push versioned docs
+        id: commit_versioned_docs
+        uses: EndBug/add-and-commit@v10
+        with:
+          add: "website/versioned_docs website/versioned_sidebars website/versions.json"
+          message: "docs: version ${{ needs.release_prepare.outputs.version_number }} docs [skip ci]"
+          default_author: github_actions
+
   doc_release:
     name: Doc release
-    needs: [changelog_update, pypi_publish]
+    needs: [changelog_update, pypi_publish, version_docs]
+    permissions:
+      contents: write
+      pages: write
+      id-token: write
     uses: ./.github/workflows/_release_docs.yaml
     with:
-      # Use the ref from the changelog update to include the updated changelog.
-      ref: ${{ needs.changelog_update.outputs.changelog_commitish }}
+      # Use the version_docs commit to include both changelog and versioned docs.
+      ref: ${{ needs.version_docs.outputs.version_docs_commitish }}
     secrets: inherit
 
   trigger_docker_build:

{apify-3.3.1b6 → apify-3.3.2b2}/.github/workflows/on_issue.yaml

@@ -6,6 +6,9 @@ on:
     types:
       - opened
 
+permissions:
+  contents: read
+
 jobs:
   label_issues:
     name: Add labels

{apify-3.3.1b6 → apify-3.3.2b2}/.github/workflows/on_master.yaml

@@ -11,6 +11,9 @@ concurrency:
   group: release
   cancel-in-progress: false
 
+permissions:
+  contents: read
+
 jobs:
   doc_checks:
     name: Doc checks
@@ -21,6 +24,10 @@ jobs:
     if: startsWith(github.event.head_commit.message, 'docs')
     name: Doc release
     needs: [doc_checks]
+    permissions:
+      contents: write
+      pages: write
+      id-token: write
     uses: ./.github/workflows/_release_docs.yaml
     with:
       # Use the same ref as the one that triggered the workflow.
@@ -64,6 +71,8 @@ jobs:
   changelog_update:
     name: Changelog update
     needs: [release_prepare]
+    permissions:
+      contents: write
     uses: apify/workflows/.github/workflows/python_bump_and_update_changelog.yaml@main
     with:
       version_number: ${{ needs.release_prepare.outputs.version_number }}
@@ -95,6 +104,10 @@ jobs:
   doc_release_post_publish:
     name: Doc release post publish
     needs: [changelog_update, pypi_publish]
+    permissions:
+      contents: write
+      pages: write
+      id-token: write
     uses: ./.github/workflows/_release_docs.yaml
     with:
       # Use the ref from the changelog update to include the updated changelog.

{apify-3.3.1b6 → apify-3.3.2b2}/.github/workflows/on_pull_request.yaml

@@ -4,6 +4,10 @@ on:
   # Runs whenever a pull request is opened or updated.
   pull_request:
 
+permissions:
+  contents: read
+  pull-requests: read
+
 jobs:
   pr_title_check:
     name: PR title check

{apify-3.3.1b6 → apify-3.3.2b2}/CHANGELOG.md

@@ -3,7 +3,16 @@
 All notable changes to this project will be documented in this file.
 
 <!-- git-cliff-unreleased-start -->
-## 3.3.1 - **not yet released**
+## 3.3.2 - **not yet released**
+
+### 🐛 Bug Fixes
+
+- **scrapy:** Resolve Crawlee&#x27;s request data round-trip failure in request conversion ([#832](https://github.com/apify/apify-sdk-python/pull/832)) ([3b9d588](https://github.com/apify/apify-sdk-python/commit/3b9d5888611597a522300c742014c06cc0b857b9)) by [@vdusek](https://github.com/vdusek)
+- Treat `default` alias as default storage when in schema ([#827](https://github.com/apify/apify-sdk-python/pull/827)) ([1610d0d](https://github.com/apify/apify-sdk-python/commit/1610d0dda40ba30bd3b4dea28d9fef04c9b7c839)) by [@Pijukatel](https://github.com/Pijukatel)
+
+
+<!-- git-cliff-unreleased-end -->
+## [3.3.1](https://github.com/apify/apify-sdk-python/releases/tag/v3.3.1) (2026-03-11)
 
 ### 🐛 Bug Fixes
 
@@ -14,7 +23,6 @@ All notable changes to this project will be documented in this file.
 - Keep track of synthetic apify-default-dataset-item events ([#814](https://github.com/apify/apify-sdk-python/pull/814)) ([50c4b6c](https://github.com/apify/apify-sdk-python/commit/50c4b6ce80b45da5348a74c559b8790edbeae04a)) by [@Mantisus](https://github.com/Mantisus), closes [#705](https://github.com/apify/apify-sdk-python/issues/705), [#760](https://github.com/apify/apify-sdk-python/issues/760)
 
 
-<!-- git-cliff-unreleased-end -->
 ## [3.3.0](https://github.com/apify/apify-sdk-python/releases/tag/v3.3.0) (2026-02-25)
 
 ### 🚀 Features

{apify-3.3.1b6 → apify-3.3.2b2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: apify
-Version: 3.3.1b6
+Version: 3.3.2b2
 Summary: Apify SDK for Python
 Project-URL: Apify Homepage, https://apify.com
 Project-URL: Changelog, https://docs.apify.com/sdk/python/docs/changelog

{apify-3.3.1b6 → apify-3.3.2b2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "apify"
-version = "3.3.1b6"
+version = "3.3.2b2"
 description = "Apify SDK for Python"
 authors = [{ name = "Apify Technologies s.r.o.", email = "support@apify.com" }]
 license = { file = "LICENSE" }
@@ -99,6 +99,9 @@ allow-direct-references = true
 [tool.ruff]
 line-length = 120
 include = ["src/**/*.py", "tests/**/*.py", "docs/**/*.py", "website/**/*.py"]
+exclude = [
+    "website/versioned_docs/**",
+]
 
 [tool.ruff.lint]
 select = ["ALL"]
@@ -201,6 +204,7 @@ python-version = "3.10"
 
 [tool.ty.src]
 include = ["src", "tests", "scripts", "docs", "website"]
+exclude = ["website/versioned_docs"]
 
 [[tool.ty.overrides]]
 include = [

{apify-3.3.1b6 → apify-3.3.2b2}/src/apify/scrapy/requests.py

@@ -10,6 +10,7 @@ from scrapy import Spider
 from scrapy.http.headers import Headers
 from scrapy.utils.request import request_from_dict
 
+from crawlee._request import UserData
 from crawlee._types import HttpHeaders
 
 from apify import Request as ApifyRequest
@@ -52,7 +53,19 @@ def to_apify_request(scrapy_request: ScrapyRequest, spider: Spider) -> ApifyRequ
             if scrapy_request.meta.get('apify_request_id'):
                 request_kwargs['id'] = scrapy_request.meta['apify_request_id']
 
-        request_kwargs['user_data'] = scrapy_request.meta.get('userData', {})
+        user_data = scrapy_request.meta.get('userData', {})
+
+        # Convert UserData Pydantic model to a plain dict to prevent CrawleeRequestData objects
+        # from leaking into Request.from_url() during Scrapy-Apify roundtrips.
+        if isinstance(user_data, UserData):
+            user_data = user_data.model_dump(by_alias=True)
+
+        # Remove internal Crawlee data since it's managed by Request.from_url() and values
+        # from previous roundtrips cause incorrect state.
+        if isinstance(user_data, dict):
+            user_data.pop('__crawlee', None)
+
+        request_kwargs['user_data'] = user_data if isinstance(user_data, dict) else {}
 
         # Convert Scrapy's headers to a HttpHeaders and store them in the apify_request
         if isinstance(scrapy_request.headers, Headers):

{apify-3.3.1b6 → apify-3.3.2b2}/src/apify/storage_clients/_apify/_alias_resolving.py

@@ -76,7 +76,7 @@ async def open_by_alias(
     The alias mapping is stored in the default key-value store for persistence across Actor runs.
 
     Args:
-        alias: The alias name for the storage (e.g., '__default__', 'my-storage').
+        alias: The alias name for the storage (e.g., 'my-storage').
         storage_type: The type of storage to open.
         collection_client: The Apify API collection client for the storage type.
         get_resource_client_by_id: A callable that takes a storage ID and returns the resource client.
@@ -131,6 +131,8 @@ class AliasResolver:
     _alias_init_lock: Lock | None = None
     """Lock for creating alias storages. Only one alias storage can be created at the time. Global for all instances."""
 
+    default_storage_key: ClassVar[str] = '__default__'
+
     def __init__(
         self,
         storage_type: Literal['Dataset', 'KeyValueStore', 'RequestQueue'],
@@ -195,7 +197,7 @@ class AliasResolver:
         """
         # First try to find the alias in the configuration mapping to avoid any API calls.
         # This mapping is maintained by the Apify platform and does not have to be maintained in the default KVS.
-        if self._configuration.actor_storages and self._alias != 'default':
+        if self._configuration.actor_storages:
             storage_maps = {
                 'Dataset': self._configuration.actor_storages['datasets'],
                 'KeyValueStore': self._configuration.actor_storages['key_value_stores'],

{apify-3.3.1b6 → apify-3.3.2b2}/src/apify/storage_clients/_apify/_api_client_creation.py

@@ -5,7 +5,7 @@ from typing import TYPE_CHECKING, Literal, overload
 from apify_client import ApifyClientAsync
 from crawlee._utils.crypto import crypto_random_object_id
 
-from apify.storage_clients._apify._alias_resolving import open_by_alias
+from apify.storage_clients._apify._alias_resolving import AliasResolver, open_by_alias
 
 if TYPE_CHECKING:
     from apify_client.clients import DatasetClientAsync, KeyValueStoreClientAsync, RequestQueueClientAsync
@@ -113,7 +113,7 @@ async def create_storage_api_client(
         # Normalize unnamed default storage to unnamed storage aliased as `__default__`.
         case (None, None, None, None):
             return await open_by_alias(
-                alias='__default__',
+                alias=AliasResolver.default_storage_key,
                 storage_type=storage_type,
                 collection_client=collection_client,
                 get_resource_client_by_id=get_resource_client,

{apify-3.3.1b6 → apify-3.3.2b2}/tests/e2e/test_schema_storages/actor_source/main.py

@@ -7,3 +7,7 @@ async def main() -> None:
         dataset = await Actor.open_dataset(alias='custom')
         expected_id = Actor.configuration.actor_storages['datasets']['custom']
         assert dataset.id == expected_id
+
+        implicit_default_dataset = await Actor.open_dataset()
+        explicit_default_dataset = await Actor.open_dataset(alias='default')
+        assert implicit_default_dataset.id == explicit_default_dataset.id

{apify-3.3.1b6 → apify-3.3.2b2}/tests/integration/_utils.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import asyncio
-from typing import TYPE_CHECKING, TypeVar
+from typing import TYPE_CHECKING, Literal, TypeVar
 
 from crawlee._utils.crypto import crypto_random_object_id
 
@@ -13,26 +13,39 @@ if TYPE_CHECKING:
 T = TypeVar('T')
 
 
-async def call_with_exp_backoff(fn: Callable[[], Awaitable[T]], *, max_retries: int = 3) -> T | None:
+async def call_with_exp_backoff(
+    fn: Callable[[], Awaitable[T]],
+    *,
+    rq_access_mode: Literal['single', 'shared'],
+    max_retries: int = 3,
+) -> T | None:
     """Call an async callable with exponential backoff retries until it returns a truthy value.
 
     In shared request queue mode, there is a propagation delay before newly added, reclaimed, or handled requests
     become visible in the API (see https://github.com/apify/apify-sdk-python/issues/808). This helper retries with
     exponential backoff to handle that delay in integration tests.
+
+    When `rq_access_mode` is `'single'`, the function is called once without retries.
     """
-    result = None
+    if rq_access_mode == 'single':
+        return await fn()
+
+    if rq_access_mode == 'shared':
+        result = None
+
+        for attempt in range(max_retries):
+            result = await fn()
 
-    for attempt in range(max_retries):
-        result = await fn()
+            if result:
+                return result
 
-        if result:
-            return result
+            delay = 2**attempt
+            Actor.log.info(f'{fn} returned {result!r}, retrying in {delay}s (attempt {attempt + 1}/{max_retries})')
+            await asyncio.sleep(delay)
 
-        delay = 2**attempt
-        Actor.log.info(f'{fn} returned {result!r}, retrying in {delay}s (attempt {attempt + 1}/{max_retries})')
-        await asyncio.sleep(delay)
+        return result
 
-    return result
+    raise ValueError(f'Invalid rq_access_mode: {rq_access_mode}')
 
 
 def generate_unique_resource_name(label: str) -> str: