chore(deps): Upgrade pydantic-settings to v2.12 (#1549)

### Description

Upgrade `pydantic-settings` to v2.12. This release fixes the issue where
environment variables were taking precedence over explicitly provided
field values during model instantiation.

### Issues

- Closes: #146

Author: Mantisus

pyproject.toml

@@ -39,7 +39,7 @@ dependencies = [
     "more-itertools>=10.2.0",
     "protego>=0.5.0",
     "psutil>=6.0.0",
-    "pydantic-settings>=2.2.0,!=2.7.0,!=2.7.1,!=2.8.0",
+    "pydantic-settings>=2.12.0",
     "pydantic>=2.11.0",
     "pyee>=9.0.0",
     "tldextract>=5.1.0",

src/crawlee/configuration.py

@@ -28,7 +28,9 @@ class Configuration(BaseSettings):
     Settings can also be configured via environment variables, prefixed with `CRAWLEE_`.
     """
 
-    model_config = SettingsConfigDict(validate_by_name=True, validate_by_alias=True)
+    # TODO: https://github.com/pydantic/pydantic-settings/issues/706
+    # Use `SettingsConfigDict(validate_by_name=True, validate_by_alias=True)` when issue is resolved.
+    model_config = SettingsConfigDict(populate_by_name=True)
 
     internal_timeout: Annotated[timedelta | None, Field(alias='crawlee_internal_timeout')] = None
     """Timeout for the internal asynchronous operations."""

tests/unit/conftest.py

@@ -1,6 +1,3 @@
-# TODO: Update crawlee_storage_dir args once the Pydantic bug is fixed
-# https://github.com/apify/crawlee-python/issues/146
-
 from __future__ import annotations
 
 import logging

tests/unit/crawlers/_basic/test_basic_crawler.py

@@ -1102,7 +1102,7 @@ async def test_services_crawlers_can_use_different_services() -> None:
 
 async def test_crawler_uses_default_storages(tmp_path: Path) -> None:
     configuration = Configuration(
-        crawlee_storage_dir=str(tmp_path),  # type: ignore[call-arg]
+        storage_dir=str(tmp_path),
         purge_on_start=True,
     )
     service_locator.set_configuration(configuration)
@@ -1120,7 +1120,7 @@ async def test_crawler_uses_default_storages(tmp_path: Path) -> None:
 
 async def test_crawler_can_use_other_storages(tmp_path: Path) -> None:
     configuration = Configuration(
-        crawlee_storage_dir=str(tmp_path),  # type: ignore[call-arg]
+        storage_dir=str(tmp_path),
         purge_on_start=True,
     )
     service_locator.set_configuration(configuration)
@@ -1148,11 +1148,11 @@ async def test_crawler_can_use_other_storages_of_same_type(tmp_path: Path) -> No
     }
 
     configuration_a = Configuration(
-        crawlee_storage_dir=str(a_path),  # type: ignore[call-arg]
+        storage_dir=str(a_path),
         purge_on_start=True,
     )
     configuration_b = Configuration(
-        crawlee_storage_dir=str(b_path),  # type: ignore[call-arg]
+        storage_dir=str(b_path),
         purge_on_start=True,
     )
 
@@ -1652,7 +1652,7 @@ async def _run_crawler(requests: list[str], storage_dir: str) -> StatisticsState
     Must be defined like this to be pickable for ProcessPoolExecutor."""
     service_locator.set_configuration(
         Configuration(
-            crawlee_storage_dir=storage_dir,  # type: ignore[call-arg]
+            storage_dir=storage_dir,
             purge_on_start=False,
         )
     )

tests/unit/storage_clients/_file_system/test_fs_dataset_client.py

@@ -20,7 +20,7 @@
 @pytest.fixture
 def configuration(tmp_path: Path) -> Configuration:
     return Configuration(
-        crawlee_storage_dir=str(tmp_path),  # type: ignore[call-arg]
+        storage_dir=str(tmp_path),
     )
 
 

tests/unit/storage_clients/_file_system/test_fs_kvs_client.py

@@ -20,7 +20,7 @@
 @pytest.fixture
 def configuration(tmp_path: Path) -> Configuration:
     return Configuration(
-        crawlee_storage_dir=str(tmp_path),  # type: ignore[call-arg]
+        storage_dir=str(tmp_path),
     )
 
 

tests/unit/storage_clients/_file_system/test_fs_rq_client.py

@@ -20,7 +20,7 @@
 @pytest.fixture
 def configuration(tmp_path: Path) -> Configuration:
     return Configuration(
-        crawlee_storage_dir=str(tmp_path),  # type: ignore[call-arg]
+        storage_dir=str(tmp_path),
     )
 
 

tests/unit/storage_clients/_sql/test_sql_dataset_client.py

@@ -25,7 +25,7 @@
 def configuration(tmp_path: Path) -> Configuration:
     """Temporary configuration for tests."""
     return Configuration(
-        crawlee_storage_dir=str(tmp_path),  # type: ignore[call-arg]
+        storage_dir=str(tmp_path),
     )
 
 

tests/unit/storage_clients/_sql/test_sql_kvs_client.py

@@ -27,7 +27,7 @@
 def configuration(tmp_path: Path) -> Configuration:
     """Temporary configuration for tests."""
     return Configuration(
-        crawlee_storage_dir=str(tmp_path),  # type: ignore[call-arg]
+        storage_dir=str(tmp_path),
     )
 
 

tests/unit/storage_clients/_sql/test_sql_rq_client.py

@@ -28,7 +28,7 @@
 def configuration(tmp_path: Path) -> Configuration:
     """Temporary configuration for tests."""
     return Configuration(
-        crawlee_storage_dir=str(tmp_path),  # type: ignore[call-arg]
+        storage_dir=str(tmp_path),
     )