resolve

Mantisus · Mantisus · commit bb84523ab6bc · 2025-09-18T18:07:26.000Z
diff --git a/src/crawlee/_request.py b/src/crawlee/_request.py
@@ -163,7 +163,7 @@ class Request(BaseModel):
     ```
     """
 
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
     unique_key: Annotated[str, Field(alias='uniqueKey')]
     """A unique key identifying the request. Two requests with the same `unique_key` are considered as pointing
diff --git a/src/crawlee/_types.py b/src/crawlee/_types.py
@@ -69,7 +69,7 @@ def _normalize_headers(headers: Mapping[str, str]) -> dict[str, str]:
 class HttpHeaders(RootModel, Mapping[str, str]):
     """A dictionary-like object representing HTTP headers."""
 
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
     root: Annotated[
         dict[str, str],
diff --git a/src/crawlee/_utils/system.py b/src/crawlee/_utils/system.py
@@ -36,7 +36,7 @@ def _get_used_memory(process: psutil.Process) -> int:
 class CpuInfo(BaseModel):
     """Information about the CPU usage."""
 
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
     used_ratio: Annotated[float, Field(alias='usedRatio')]
     """The ratio of CPU currently in use, represented as a float between 0 and 1."""
@@ -51,7 +51,7 @@ class CpuInfo(BaseModel):
 class MemoryUsageInfo(BaseModel):
     """Information about the memory usage."""
 
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
     current_size: Annotated[
         ByteSize,
@@ -71,7 +71,7 @@ class MemoryUsageInfo(BaseModel):
 class MemoryInfo(MemoryUsageInfo):
     """Information about system memory."""
 
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
     total_size: Annotated[
         ByteSize, PlainValidator(ByteSize.validate), PlainSerializer(lambda size: size.bytes), Field(alias='totalSize')
diff --git a/src/crawlee/crawlers/_adaptive_playwright/_adaptive_playwright_crawler_statistics.py b/src/crawlee/crawlers/_adaptive_playwright/_adaptive_playwright_crawler_statistics.py
@@ -12,7 +12,7 @@
 class AdaptivePlaywrightCrawlerStatisticState(StatisticsState):
     """Statistic data about a crawler run with additional information related to adaptive crawling."""
 
-    model_config = ConfigDict(populate_by_name=True, ser_json_inf_nan='constants')
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True, ser_json_inf_nan='constants')
 
     http_only_request_handler_runs: Annotated[int, Field(alias='http_only_request_handler_runs')] = 0
     """Number representing how many times static http based crawling was used."""
diff --git a/src/crawlee/crawlers/_adaptive_playwright/_rendering_type_predictor.py b/src/crawlee/crawlers/_adaptive_playwright/_rendering_type_predictor.py
@@ -32,7 +32,7 @@
 
 
 class RenderingTypePredictorState(BaseModel):
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
     model: Annotated[
         LogisticRegression,
diff --git a/src/crawlee/events/_types.py b/src/crawlee/events/_types.py
@@ -40,7 +40,7 @@ class Event(str, Enum):
 class EventPersistStateData(BaseModel):
     """Data for the persist state event."""
 
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
     is_migrating: Annotated[bool, Field(alias='isMigrating')]
 
@@ -49,7 +49,7 @@ class EventPersistStateData(BaseModel):
 class EventSystemInfoData(BaseModel):
     """Data for the system info event."""
 
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
     cpu_info: Annotated[CpuInfo, Field(alias='cpuInfo')]
     memory_info: Annotated[
@@ -62,7 +62,7 @@ class EventSystemInfoData(BaseModel):
 class EventMigratingData(BaseModel):
     """Data for the migrating event."""
 
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
     # The remaining time in seconds before the migration is forced and the process is killed
     # Optional because it's not present when the event handler is called manually
@@ -73,21 +73,21 @@ class EventMigratingData(BaseModel):
 class EventAbortingData(BaseModel):
     """Data for the aborting event."""
 
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
 
 @docs_group('Event data')
 class EventExitData(BaseModel):
     """Data for the exit event."""
 
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
 
 @docs_group('Event data')
 class EventCrawlerStatusData(BaseModel):
     """Data for the crawler status event."""
 
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
     message: str
     """A message describing the current status of the crawler."""
diff --git a/src/crawlee/fingerprint_suite/_types.py b/src/crawlee/fingerprint_suite/_types.py
@@ -11,7 +11,7 @@
 
 
 class ScreenOptions(BaseModel):
-    model_config = ConfigDict(extra='forbid', populate_by_name=True)
+    model_config = ConfigDict(extra='forbid', validate_by_name=True, validate_by_alias=True)
 
     """Defines the screen constrains for the fingerprint generator."""
 
@@ -31,7 +31,7 @@ class ScreenOptions(BaseModel):
 class HeaderGeneratorOptions(BaseModel):
     """Collection of header related attributes that can be used by the fingerprint generator."""
 
-    model_config = ConfigDict(extra='forbid', populate_by_name=True)
+    model_config = ConfigDict(extra='forbid', validate_by_name=True, validate_by_alias=True)
 
     browsers: list[SupportedBrowserType] | None = None
     """List of BrowserSpecifications to generate the headers for."""
diff --git a/src/crawlee/request_loaders/_request_list.py b/src/crawlee/request_loaders/_request_list.py
@@ -17,7 +17,7 @@
 
 
 class RequestListState(BaseModel):
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
     next_index: Annotated[int, Field(alias='nextIndex')] = 0
     next_unique_key: Annotated[str | None, Field(alias='nextUniqueKey')] = None
diff --git a/src/crawlee/request_loaders/_sitemap_request_loader.py b/src/crawlee/request_loaders/_sitemap_request_loader.py
@@ -56,7 +56,7 @@ class SitemapRequestLoaderState(BaseModel):
     `in_progress` is cleared.
     """
 
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
     url_queue: Annotated[deque[str], Field(alias='urlQueue')]
     """Queue of URLs extracted from sitemaps and ready for processing."""
diff --git a/src/crawlee/sessions/_models.py b/src/crawlee/sessions/_models.py
@@ -20,7 +20,7 @@
 class SessionModel(BaseModel):
     """Model for a Session object."""
 
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
     id: Annotated[str, Field(alias='id')]
     max_age: Annotated[timedelta, Field(alias='maxAge')]
@@ -38,7 +38,7 @@ class SessionModel(BaseModel):
 class SessionPoolModel(BaseModel):
     """Model for a SessionPool object."""
 
-    model_config = ConfigDict(populate_by_name=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
     max_pool_size: Annotated[int, Field(alias='maxPoolSize')]
 
diff --git a/src/crawlee/statistics/_models.py b/src/crawlee/statistics/_models.py
@@ -57,7 +57,7 @@ def __str__(self) -> str:
 class StatisticsState(BaseModel):
     """Statistic data about a crawler run."""
 
-    model_config = ConfigDict(populate_by_name=True, ser_json_inf_nan='constants')
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True, ser_json_inf_nan='constants')
     stats_id: Annotated[int | None, Field(alias='statsId')] = None
 
     requests_finished: Annotated[int, Field(alias='requestsFinished')] = 0
diff --git a/src/crawlee/storage_clients/models.py b/src/crawlee/storage_clients/models.py
@@ -20,7 +20,7 @@ class StorageMetadata(BaseModel):
     It contains common fields shared across all specific storage types.
     """
 
-    model_config = ConfigDict(populate_by_name=True, extra='allow', from_attributes=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True, extra='allow', from_attributes=True)
 
     id: Annotated[str, Field(alias='id')]
     """The unique identifier of the storage."""
@@ -42,7 +42,7 @@ class StorageMetadata(BaseModel):
 class DatasetMetadata(StorageMetadata):
     """Model for a dataset metadata."""
 
-    model_config = ConfigDict(populate_by_name=True, from_attributes=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True, from_attributes=True)
 
     item_count: Annotated[int, Field(alias='itemCount')]
     """The number of items in the dataset."""
@@ -52,14 +52,14 @@ class DatasetMetadata(StorageMetadata):
 class KeyValueStoreMetadata(StorageMetadata):
     """Model for a key-value store metadata."""
 
-    model_config = ConfigDict(populate_by_name=True, from_attributes=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True, from_attributes=True)
 
 
 @docs_group('Storage data')
 class RequestQueueMetadata(StorageMetadata):
     """Model for a request queue metadata."""
 
-    model_config = ConfigDict(populate_by_name=True, from_attributes=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True, from_attributes=True)
 
     had_multiple_clients: Annotated[bool, Field(alias='hadMultipleClients')]
     """Indicates whether the queue has been accessed by multiple clients (consumers)."""
@@ -78,7 +78,7 @@ class RequestQueueMetadata(StorageMetadata):
 class KeyValueStoreRecordMetadata(BaseModel):
     """Model for a key-value store record metadata."""
 
-    model_config = ConfigDict(populate_by_name=True, from_attributes=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True, from_attributes=True)
 
     key: Annotated[str, Field(alias='key')]
     """The key of the record.
@@ -100,7 +100,7 @@ class KeyValueStoreRecordMetadata(BaseModel):
 class KeyValueStoreRecord(KeyValueStoreRecordMetadata, Generic[KvsValueType]):
     """Model for a key-value store record."""
 
-    model_config = ConfigDict(populate_by_name=True, from_attributes=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True, from_attributes=True)
 
     value: Annotated[KvsValueType, Field(alias='value')]
     """The value of the record."""
@@ -110,7 +110,7 @@ class KeyValueStoreRecord(KeyValueStoreRecordMetadata, Generic[KvsValueType]):
 class DatasetItemsListPage(BaseModel):
     """Model for a single page of dataset items returned from a collection list method."""
 
-    model_config = ConfigDict(populate_by_name=True, from_attributes=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True, from_attributes=True)
 
     count: Annotated[int, Field(default=0)]
     """The number of objects returned on this page."""
@@ -135,7 +135,7 @@ class DatasetItemsListPage(BaseModel):
 class ProcessedRequest(BaseModel):
     """Represents a processed request."""
 
-    model_config = ConfigDict(populate_by_name=True, from_attributes=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True, from_attributes=True)
 
     id: Annotated[str | None, Field(alias='requestId', default=None)] = None
     """Internal representation of the request by the storage client. Only some clients use id."""
@@ -149,7 +149,7 @@ class ProcessedRequest(BaseModel):
 class UnprocessedRequest(BaseModel):
     """Represents an unprocessed request."""
 
-    model_config = ConfigDict(populate_by_name=True, from_attributes=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True, from_attributes=True)
 
     unique_key: Annotated[str, Field(alias='uniqueKey')]
     url: Annotated[str, BeforeValidator(validate_http_url), Field()]
@@ -165,7 +165,7 @@ class AddRequestsResponse(BaseModel):
     encountered issues during processing.
     """
 
-    model_config = ConfigDict(populate_by_name=True, from_attributes=True)
+    model_config = ConfigDict(validate_by_name=True, validate_by_alias=True, from_attributes=True)
 
     processed_requests: Annotated[list[ProcessedRequest], Field(alias='processedRequests')]
     """Successfully processed requests, including information about whether they were
diff --git a/src/crawlee/storages/_storage_instance_manager.py b/src/crawlee/storages/_storage_instance_manager.py
@@ -158,18 +158,22 @@ async def open_storage_instance(
             instance = cls(client, metadata.id, metadata.name)  # type: ignore[call-arg]
             instance_name = getattr(instance, 'name', None)
 
-            # Cache the instance. Always cache by id and cache named or unnamed (alias).
+            # Cache the instance.
+            # Always cache by id.
             self._cache_by_storage_client[storage_client_type].by_id[cls][instance.id][additional_cache_key] = instance
+
+            # Cache named storage.
             if instance_name is not None:
                 self._cache_by_storage_client[storage_client_type].by_name[cls][instance_name][additional_cache_key] = (
                     instance
                 )
-            elif alias is not None:
+
+            # Cache unnamed storage.
+            if alias is not None:
                 self._cache_by_storage_client[storage_client_type].by_alias[cls][alias][additional_cache_key] = instance
-            else:
-                raise RuntimeError('Storage instance must have either a name or an alias.')
 
             return instance
+
         finally:
             # Make sure the client opener is closed.
             # If it was awaited, then closing is no operation, if it was not awaited, this is the cleanup.
diff --git a/tests/unit/storages/test_storage_instance_manager.py b/tests/unit/storages/test_storage_instance_manager.py
@@ -128,3 +128,16 @@ async def test_identical_storage_remove_from_cache(storage_type: type[Storage])
     service_locator.storage_instance_manager.remove_from_cache(storage_1)
     storage_2 = await storage_type.open()
     assert storage_1 is not storage_2
+
+
+async def test_preexisting_unnamed_storage_open_by_id(storage_type: type[Storage]) -> None:
+    """Test that persisted pre-existing unnamed storage can be opened by ID."""
+    storage_client = FileSystemStorageClient()
+    storage_1 = await storage_type.open(alias='custom_name', storage_client=storage_client)
+
+    # Make service_locator unaware of this storage
+    service_locator.storage_instance_manager.clear_cache()
+
+    storage_1_again = await storage_type.open(id=storage_1.id, storage_client=storage_client)
+
+    assert storage_1.id == storage_1_again.id
diff --git a/website/package.json b/website/package.json
@@ -21,8 +21,8 @@
         "@docusaurus/module-type-aliases": "3.8.1",
         "@docusaurus/types": "3.8.1",
         "@types/react": "^19.0.0",
-        "@typescript-eslint/eslint-plugin": "8.42.0",
-        "@typescript-eslint/parser": "8.42.0",
+        "@typescript-eslint/eslint-plugin": "8.44.0",
+        "@typescript-eslint/parser": "8.44.0",
         "eslint": "8.57.0",
         "eslint-plugin-react": "7.37.5",
         "eslint-plugin-react-hooks": "5.2.0",
diff --git a/website/yarn.lock b/website/yarn.lock
