airbyte-cdk 6.37.0.dev0__tar.gz → 6.37.1__tar.gz

{airbyte_cdk-6.37.0.dev0 → airbyte_cdk-6.37.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: airbyte-cdk
-Version: 6.37.0.dev0
+Version: 6.37.1
 Summary: A framework for writing Airbyte Connectors.
 Home-page: https://airbyte.com
 License: MIT
@@ -22,8 +22,8 @@ Provides-Extra: sql
 Provides-Extra: vector-db-based
 Requires-Dist: Jinja2 (>=3.1.2,<3.2.0)
 Requires-Dist: PyYAML (>=6.0.1,<7.0.0)
-Requires-Dist: Unidecode (>=1.3,<2.0)
 Requires-Dist: airbyte-protocol-models-dataclasses (>=0.14,<0.15)
+Requires-Dist: anyascii (>=0.3.2,<0.4.0)
 Requires-Dist: avro (>=1.11.2,<1.13.0) ; extra == "file-based"
 Requires-Dist: backoff
 Requires-Dist: cachetools

{airbyte_cdk-6.37.0.dev0 → airbyte_cdk-6.37.1}/airbyte_cdk/entrypoint.py

@@ -37,8 +37,8 @@ from airbyte_cdk.sources import Source
 from airbyte_cdk.sources.connector_state_manager import HashableStreamDescriptor
 from airbyte_cdk.sources.utils.schema_helpers import check_config_against_spec_or_exit, split_config
 
-from airbyte_cdk.utils import PrintBuffer, is_cloud_environment, message_utils  # add PrintBuffer back once fixed
-# from airbyte_cdk.utils import is_cloud_environment, message_utils
+# from airbyte_cdk.utils import PrintBuffer, is_cloud_environment, message_utils  # add PrintBuffer back once fixed
+from airbyte_cdk.utils import is_cloud_environment, message_utils
 from airbyte_cdk.utils.airbyte_secrets_utils import get_secrets, update_secrets
 from airbyte_cdk.utils.constants import ENV_REQUEST_CACHE_PATH
 from airbyte_cdk.utils.traced_exception import AirbyteTracedException
@@ -337,11 +337,11 @@ def launch(source: Source, args: List[str]) -> None:
     parsed_args = source_entrypoint.parse_args(args)
     # temporarily removes the PrintBuffer because we're seeing weird print behavior for concurrent syncs
     # Refer to: https://github.com/airbytehq/oncall/issues/6235
-    with PrintBuffer():
-        for message in source_entrypoint.run(parsed_args):
-            # simply printing is creating issues for concurrent CDK as Python uses different two instructions to print: one for the message and
-            # the other for the break line. Adding `\n` to the message ensure that both are printed at the same time
-            print(f"{message}\n", end="", flush=True)
+    # with PrintBuffer():
+    for message in source_entrypoint.run(parsed_args):
+        # simply printing is creating issues for concurrent CDK as Python uses different two instructions to print: one for the message and
+        # the other for the break line. Adding `\n` to the message ensure that both are printed at the same time
+        print(f"{message}\n", end="", flush=True)
 
 
 def _init_internal_request_filter() -> None:

{airbyte_cdk-6.37.0.dev0 → airbyte_cdk-6.37.1}/airbyte_cdk/sources/declarative/concurrent_declarative_source.py

@@ -31,6 +31,9 @@ from airbyte_cdk.sources.declarative.models.declarative_component_schema import
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     DatetimeBasedCursor as DatetimeBasedCursorModel,
 )
+from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
+    IncrementingCountCursor as IncrementingCountCursorModel,
+)
 from airbyte_cdk.sources.declarative.parsers.model_to_component_factory import (
     ModelToComponentFactory,
 )
@@ -222,7 +225,7 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
                     and not incremental_sync_component_definition
                 )
 
-                if self._is_datetime_incremental_without_partition_routing(
+                if self._is_concurrent_cursor_incremental_without_partition_routing(
                     declarative_stream, incremental_sync_component_definition
                 ):
                     stream_state = self._connector_state_manager.get_stream_state(
@@ -254,15 +257,26 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
                             stream_slicer=declarative_stream.retriever.stream_slicer,
                         )
                     else:
-                        cursor = (
-                            self._constructor.create_concurrent_cursor_from_datetime_based_cursor(
+                        if (
+                            incremental_sync_component_definition
+                            and incremental_sync_component_definition.get("type")
+                            == IncrementingCountCursorModel.__name__
+                        ):
+                            cursor = self._constructor.create_concurrent_cursor_from_incrementing_count_cursor(
+                                model_type=IncrementingCountCursorModel,
+                                component_definition=incremental_sync_component_definition,  # type: ignore  # Not None because of the if condition above
+                                stream_name=declarative_stream.name,
+                                stream_namespace=declarative_stream.namespace,
+                                config=config or {},
+                            )
+                        else:
+                            cursor = self._constructor.create_concurrent_cursor_from_datetime_based_cursor(
                                 model_type=DatetimeBasedCursorModel,
                                 component_definition=incremental_sync_component_definition,  # type: ignore  # Not None because of the if condition above
                                 stream_name=declarative_stream.name,
                                 stream_namespace=declarative_stream.namespace,
                                 config=config or {},
                             )
-                        )
                         partition_generator = StreamSlicerPartitionGenerator(
                             partition_factory=DeclarativePartitionFactory(
                                 declarative_stream.name,
@@ -389,7 +403,7 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
 
         return concurrent_streams, synchronous_streams
 
-    def _is_datetime_incremental_without_partition_routing(
+    def _is_concurrent_cursor_incremental_without_partition_routing(
         self,
         declarative_stream: DeclarativeStream,
         incremental_sync_component_definition: Mapping[str, Any] | None,
@@ -397,11 +411,18 @@ class ConcurrentDeclarativeSource(ManifestDeclarativeSource, Generic[TState]):
         return (
             incremental_sync_component_definition is not None
             and bool(incremental_sync_component_definition)
-            and incremental_sync_component_definition.get("type", "")
-            == DatetimeBasedCursorModel.__name__
+            and (
+                incremental_sync_component_definition.get("type", "")
+                in (DatetimeBasedCursorModel.__name__, IncrementingCountCursorModel.__name__)
+            )
             and hasattr(declarative_stream.retriever, "stream_slicer")
             and (
                 isinstance(declarative_stream.retriever.stream_slicer, DatetimeBasedCursor)
+                # IncrementingCountCursorModel is hardcoded to be of type DatetimeBasedCursor
+                # add isintance check here if we want to create a Declarative IncrementingCountCursor
+                # or isinstance(
+                #     declarative_stream.retriever.stream_slicer, IncrementingCountCursor
+                # )
                 or isinstance(declarative_stream.retriever.stream_slicer, AsyncJobPartitionRouter)
             )
         )

{airbyte_cdk-6.37.0.dev0 → airbyte_cdk-6.37.1}/airbyte_cdk/sources/declarative/datetime/datetime_parser.py

@@ -31,7 +31,8 @@ class DatetimeParser:
             return datetime.datetime.fromtimestamp(float(date), tz=datetime.timezone.utc)
         elif format == "%ms":
             return self._UNIX_EPOCH + datetime.timedelta(milliseconds=int(date))
-
+        elif "%_ms" in format:
+            format = format.replace("%_ms", "%f")
         parsed_datetime = datetime.datetime.strptime(str(date), format)
         if self._is_naive(parsed_datetime):
             return parsed_datetime.replace(tzinfo=datetime.timezone.utc)
@@ -48,6 +49,11 @@ class DatetimeParser:
         if format == "%ms":
             # timstamp() returns a float representing the number of seconds since the unix epoch
             return str(int(dt.timestamp() * 1000))
+        if "%_ms" in format:
+            _format = format.replace("%_ms", "%f")
+            milliseconds = int(dt.microsecond / 1000)
+            formatted_dt = dt.strftime(_format).replace(dt.strftime("%f"), "%03d" % milliseconds)
+            return formatted_dt
         else:
             return dt.strftime(format)
 

{airbyte_cdk-6.37.0.dev0 → airbyte_cdk-6.37.1}/airbyte_cdk/sources/declarative/declarative_component_schema.yaml

@@ -777,6 +777,44 @@ definitions:
       type:
         type: string
         enum: [LegacyToPerPartitionStateMigration]
+  IncrementingCountCursor:
+    title: Incrementing Count Cursor
+    description: Cursor that allows for incremental sync according to a continuously increasing integer.
+    type: object
+    required:
+      - type
+      - cursor_field
+    properties:
+      type:
+        type: string
+        enum: [IncrementingCountCursor]
+      cursor_field:
+        title: Cursor Field
+        description: The location of the value on a record that will be used as a bookmark during sync. To ensure no data loss, the API must return records in ascending order based on the cursor field. Nested fields are not supported, so the field must be at the top level of the record. You can use a combination of Add Field and Remove Field transformations to move the nested field to the top.
+        type: string
+        interpolation_context:
+          - config
+        examples:
+          - "created_at"
+          - "{{ config['record_cursor'] }}"
+      start_value:
+        title: Start Value
+        description: The value that determines the earliest record that should be synced.
+        anyOf:
+          - type: string
+          - type: integer
+        interpolation_context:
+          - config
+        examples:
+          - 0
+          - "{{ config['start_value'] }}"
+      start_value_option:
+        title: Inject Start Value Into Outgoing HTTP Request
+        description: Optionally configures how the start value will be sent in requests to the source API.
+        "$ref": "#/definitions/RequestOption"
+      $parameters:
+        type: object
+        additionalProperties: true
   DatetimeBasedCursor:
     title: Datetime Based Cursor
     description: Cursor to provide incremental capabilities over datetime.
@@ -844,6 +882,7 @@ definitions:
             * **%M**: Minute (zero-padded) - `00`, `01`, ..., `59`
             * **%S**: Second (zero-padded) - `00`, `01`, ..., `59`
             * **%f**: Microsecond (zero-padded to 6 digits) - `000000`
+            * **%_ms**: Millisecond (zero-padded to 3 digits) - `000`
             * **%z**: UTC offset - `(empty)`, `+0000`, `-04:00`
             * **%Z**: Time zone name - `(empty)`, `UTC`, `GMT`
             * **%j**: Day of the year (zero-padded) - `001`, `002`, ..., `366`
@@ -1318,6 +1357,7 @@ definitions:
         anyOf:
           - "$ref": "#/definitions/CustomIncrementalSync"
           - "$ref": "#/definitions/DatetimeBasedCursor"
+          - "$ref": "#/definitions/IncrementingCountCursor"
       name:
         title: Name
         description: The stream name.
@@ -1779,6 +1819,9 @@ definitions:
           - stream_interval
           - stream_partition
           - stream_slice
+          - creation_response
+          - polling_response
+          - download_target
         examples:
           - "/products"
           - "/quotes/{{ stream_partition['id'] }}/quote_line_groups"
@@ -2398,6 +2441,7 @@ definitions:
             * **%M**: Minute (zero-padded) - `00`, `01`, ..., `59`
             * **%S**: Second (zero-padded) - `00`, `01`, ..., `59`
             * **%f**: Microsecond (zero-padded to 6 digits) - `000000`, `000001`, ..., `999999`
+            * **%_ms**: Millisecond (zero-padded to 3 digits) - `000`, `001`, ..., `999`
             * **%z**: UTC offset - `(empty)`, `+0000`, `-04:00`
             * **%Z**: Time zone name - `(empty)`, `UTC`, `GMT`
             * **%j**: Day of the year (zero-padded) - `001`, `002`, ..., `366`
@@ -3223,7 +3267,7 @@ definitions:
       - polling_requester
       - download_requester
       - status_extractor
-      - urls_extractor
+      - download_target_extractor
     properties:
       type:
         type: string
@@ -3240,7 +3284,7 @@ definitions:
         anyOf:
           - "$ref": "#/definitions/CustomRecordExtractor"
           - "$ref": "#/definitions/DpathExtractor"
-      urls_extractor:
+      download_target_extractor:
         description: Responsible for fetching the final result `urls` provided by the completed / finished / ready async job.
         anyOf:
           - "$ref": "#/definitions/CustomRecordExtractor"
@@ -3261,7 +3305,7 @@ definitions:
         anyOf:
           - "$ref": "#/definitions/CustomRequester"
           - "$ref": "#/definitions/HttpRequester"
-      url_requester:
+      download_target_requester:
         description: Requester component that describes how to prepare HTTP requests to send to the source API to extract the url from polling response by the completed async job.
         anyOf:
           - "$ref": "#/definitions/CustomRequester"
@@ -3667,6 +3711,21 @@ interpolation:
             self: https://api.sendgrid.com/v3/marketing/lists?page_size=1&page_token=
             next: https://api.sendgrid.com/v3/marketing/lists?page_size=1&page_token=0236d6d2
             count: 82
+    - title: creation_response
+      description: The response received from the creation_requester in the AsyncRetriever component.
+      type: object
+      examples:
+        - id: "1234"
+    - title: polling_response
+      description: The response received from the polling_requester in the AsyncRetriever component.
+      type: object
+      examples:
+        - id: "1234"
+    - title: download_target
+      description: The `URL` received from the polling_requester in the AsyncRetriever with jobStatus as `COMPLETED`.
+      type: string
+      examples:
+        - "https://api.sendgrid.com/v3/marketing/lists?page_size=1&page_token=0236d6d2&filename=xxx_yyy_zzz.csv"
     - title: stream_interval
       description: The current stream interval being processed. The keys are defined by the incremental sync component. Default keys are `start_time` and `end_time`.
       type: object

{airbyte_cdk-6.37.0.dev0 → airbyte_cdk-6.37.1}/airbyte_cdk/sources/declarative/extractors/response_to_file_extractor.py

@@ -136,6 +136,7 @@ class ResponseToFileExtractor(RecordExtractor):
         """
 
         try:
+            # TODO: Add support for other file types, like `json`, with `pd.read_json()`
             with open(path, "r", encoding=file_encoding) as data:
                 chunks = pd.read_csv(
                     data, chunksize=chunk_size, iterator=True, dialect="unix", dtype=object

{airbyte_cdk-6.37.0.dev0 → airbyte_cdk-6.37.1}/airbyte_cdk/sources/declarative/interpolation/macros.py

@@ -173,6 +173,8 @@ def format_datetime(
     )
     if format == "%s":
         return str(int(dt_datetime.timestamp()))
+    elif format == "%ms":
+        return str(int(dt_datetime.timestamp() * 1_000_000))
     return dt_datetime.strftime(format)
 
 

{airbyte_cdk-6.37.0.dev0 → airbyte_cdk-6.37.1}/airbyte_cdk/sources/declarative/models/declarative_component_schema.py

@@ -1508,6 +1508,28 @@ class AuthFlow(BaseModel):
     oauth_config_specification: Optional[OAuthConfigSpecification] = None
 
 
+class IncrementingCountCursor(BaseModel):
+    type: Literal["IncrementingCountCursor"]
+    cursor_field: str = Field(
+        ...,
+        description="The location of the value on a record that will be used as a bookmark during sync. To ensure no data loss, the API must return records in ascending order based on the cursor field. Nested fields are not supported, so the field must be at the top level of the record. You can use a combination of Add Field and Remove Field transformations to move the nested field to the top.",
+        examples=["created_at", "{{ config['record_cursor'] }}"],
+        title="Cursor Field",
+    )
+    start_value: Optional[Union[str, int]] = Field(
+        None,
+        description="The value that determines the earliest record that should be synced.",
+        examples=[0, "{{ config['start_value'] }}"],
+        title="Start Value",
+    )
+    start_value_option: Optional[RequestOption] = Field(
+        None,
+        description="Optionally configures how the start value will be sent in requests to the source API.",
+        title="Inject Start Value Into Outgoing HTTP Request",
+    )
+    parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
+
+
 class DatetimeBasedCursor(BaseModel):
     type: Literal["DatetimeBasedCursor"]
     clamping: Optional[Clamping] = Field(
@@ -1948,7 +1970,9 @@ class DeclarativeStream(BaseModel):
         description="Component used to coordinate how records are extracted across stream slices and request pages.",
         title="Retriever",
     )
-    incremental_sync: Optional[Union[CustomIncrementalSync, DatetimeBasedCursor]] = Field(
+    incremental_sync: Optional[
+        Union[CustomIncrementalSync, DatetimeBasedCursor, IncrementingCountCursor]
+    ] = Field(
         None,
         description="Component used to fetch data incrementally based on a time field in the data.",
         title="Incremental Sync",
@@ -2263,7 +2287,7 @@ class AsyncRetriever(BaseModel):
     status_extractor: Union[CustomRecordExtractor, DpathExtractor] = Field(
         ..., description="Responsible for fetching the actual status of the async job."
     )
-    urls_extractor: Union[CustomRecordExtractor, DpathExtractor] = Field(
+    download_target_extractor: Union[CustomRecordExtractor, DpathExtractor] = Field(
         ...,
         description="Responsible for fetching the final result `urls` provided by the completed / finished / ready async job.",
     )
@@ -2278,7 +2302,7 @@ class AsyncRetriever(BaseModel):
         ...,
         description="Requester component that describes how to prepare HTTP requests to send to the source API to fetch the status of the running async job.",
     )
-    url_requester: Optional[Union[CustomRequester, HttpRequester]] = Field(
+    download_target_requester: Optional[Union[CustomRequester, HttpRequester]] = Field(
         None,
         description="Requester component that describes how to prepare HTTP requests to send to the source API to extract the url from polling response by the completed async job.",
     )

{airbyte_cdk-6.37.0.dev0 → airbyte_cdk-6.37.1}/airbyte_cdk/sources/declarative/parsers/custom_code_compiler.py

@@ -45,7 +45,7 @@ class AirbyteCustomCodeNotPermittedError(Exception):
 def _hash_text(input_text: str, hash_type: str = "md5") -> str:
     """Return the hash of the input text using the specified hash type."""
     if not input_text:
-        raise ValueError("Input text cannot be empty.")
+        raise ValueError("Hash input text cannot be empty.")
 
     hash_object = CHECKSUM_FUNCTIONS[hash_type]()
     hash_object.update(input_text.encode())
@@ -68,6 +68,10 @@ def validate_python_code(
 
     Currently we fail if no checksums are provided, although this may change in the future.
     """
+    if not code_text:
+        # No code provided, nothing to validate.
+        return
+
     if not checksums:
         raise ValueError(f"A checksum is required to validate the code. Received: {checksums}")
 
@@ -77,8 +81,18 @@ def validate_python_code(
                 f"Unsupported checksum type: {checksum_type}. Supported checksum types are: {CHECKSUM_FUNCTIONS.keys()}"
             )
 
-        if _hash_text(code_text, checksum_type) != checksum:
-            raise AirbyteCodeTamperedError(f"{checksum_type} checksum does not match.")
+        calculated_checksum = _hash_text(code_text, checksum_type)
+        if calculated_checksum != checksum:
+            raise AirbyteCodeTamperedError(
+                f"{checksum_type} checksum does not match."
+                + str(
+                    {
+                        "expected_checksum": checksum,
+                        "actual_checksum": calculated_checksum,
+                        "code_text": code_text,
+                    }
+                ),
+            )
 
 
 def get_registered_components_module(
@@ -94,7 +108,7 @@ def get_registered_components_module(
 
     Returns `None` if no components is provided and the `components` module is not found.
     """
-    if config and INJECTED_COMPONENTS_PY in config:
+    if config and config.get(INJECTED_COMPONENTS_PY, None):
         if not custom_code_execution_permitted():
             raise AirbyteCustomCodeNotPermittedError
 

{airbyte_cdk-6.37.0.dev0 → airbyte_cdk-6.37.1}/airbyte_cdk/sources/declarative/parsers/model_to_component_factory.py

@@ -245,6 +245,9 @@ from airbyte_cdk.sources.declarative.models.declarative_component_schema import
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     HttpResponseFilter as HttpResponseFilterModel,
 )
+from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
+    IncrementingCountCursor as IncrementingCountCursorModel,
+)
 from airbyte_cdk.sources.declarative.models.declarative_component_schema import (
     InlineSchemaLoader as InlineSchemaLoaderModel,
 )
@@ -496,6 +499,9 @@ from airbyte_cdk.sources.streams.concurrent.state_converters.datetime_stream_sta
     CustomFormatConcurrentStreamStateConverter,
     DateTimeStreamStateConverter,
 )
+from airbyte_cdk.sources.streams.concurrent.state_converters.incrementing_count_stream_state_converter import (
+    IncrementingCountStreamStateConverter,
+)
 from airbyte_cdk.sources.streams.http.error_handlers.response_models import ResponseAction
 from airbyte_cdk.sources.types import Config
 from airbyte_cdk.sources.utils.transform import TransformConfig, TypeTransformer
@@ -584,6 +590,7 @@ class ModelToComponentFactory:
             FlattenFieldsModel: self.create_flatten_fields,
             DpathFlattenFieldsModel: self.create_dpath_flatten_fields,
             IterableDecoderModel: self.create_iterable_decoder,
+            IncrementingCountCursorModel: self.create_incrementing_count_cursor,
             XmlDecoderModel: self.create_xml_decoder,
             JsonFileSchemaLoaderModel: self.create_json_file_schema_loader,
             DynamicSchemaLoaderModel: self.create_dynamic_schema_loader,
@@ -1189,6 +1196,70 @@ class ModelToComponentFactory:
             clamping_strategy=clamping_strategy,
         )
 
+    def create_concurrent_cursor_from_incrementing_count_cursor(
+        self,
+        model_type: Type[BaseModel],
+        component_definition: ComponentDefinition,
+        stream_name: str,
+        stream_namespace: Optional[str],
+        config: Config,
+        message_repository: Optional[MessageRepository] = None,
+        **kwargs: Any,
+    ) -> ConcurrentCursor:
+        # Per-partition incremental streams can dynamically create child cursors which will pass their current
+        # state via the stream_state keyword argument. Incremental syncs without parent streams use the
+        # incoming state and connector_state_manager that is initialized when the component factory is created
+        stream_state = (
+            self._connector_state_manager.get_stream_state(stream_name, stream_namespace)
+            if "stream_state" not in kwargs
+            else kwargs["stream_state"]
+        )
+
+        component_type = component_definition.get("type")
+        if component_definition.get("type") != model_type.__name__:
+            raise ValueError(
+                f"Expected manifest component of type {model_type.__name__}, but received {component_type} instead"
+            )
+
+        incrementing_count_cursor_model = model_type.parse_obj(component_definition)
+
+        if not isinstance(incrementing_count_cursor_model, IncrementingCountCursorModel):
+            raise ValueError(
+                f"Expected {model_type.__name__} component, but received {incrementing_count_cursor_model.__class__.__name__}"
+            )
+
+        interpolated_start_value = (
+            InterpolatedString.create(
+                incrementing_count_cursor_model.start_value,  # type: ignore
+                parameters=incrementing_count_cursor_model.parameters or {},
+            )
+            if incrementing_count_cursor_model.start_value
+            else 0
+        )
+
+        interpolated_cursor_field = InterpolatedString.create(
+            incrementing_count_cursor_model.cursor_field,
+            parameters=incrementing_count_cursor_model.parameters or {},
+        )
+        cursor_field = CursorField(interpolated_cursor_field.eval(config=config))
+
+        connector_state_converter = IncrementingCountStreamStateConverter(
+            is_sequential_state=True,  # ConcurrentPerPartitionCursor only works with sequential state
+        )
+
+        return ConcurrentCursor(
+            stream_name=stream_name,
+            stream_namespace=stream_namespace,
+            stream_state=stream_state,
+            message_repository=message_repository or self._message_repository,
+            connector_state_manager=self._connector_state_manager,
+            connector_state_converter=connector_state_converter,
+            cursor_field=cursor_field,
+            slice_boundary_fields=None,
+            start=interpolated_start_value,  # type: ignore  # Having issues w/ inspection for GapType and CursorValueType as shown in existing tests. Confirmed functionality is working in practice
+            end_provider=connector_state_converter.get_end_provider(),  # type: ignore  # Having issues w/ inspection for GapType and CursorValueType as shown in existing tests. Confirmed functionality is working in practice
+        )
+
     def _assemble_weekday(self, weekday: str) -> Weekday:
         match weekday:
             case "MONDAY":
@@ -1622,6 +1693,31 @@ class ModelToComponentFactory:
                 config=config,
                 parameters=model.parameters or {},
             )
+        elif model.incremental_sync and isinstance(
+            model.incremental_sync, IncrementingCountCursorModel
+        ):
+            cursor_model: IncrementingCountCursorModel = model.incremental_sync  # type: ignore
+
+            start_time_option = (
+                self._create_component_from_model(
+                    cursor_model.start_value_option,  # type: ignore # mypy still thinks cursor_model of type DatetimeBasedCursor
+                    config,
+                    parameters=cursor_model.parameters or {},
+                )
+                if cursor_model.start_value_option  # type: ignore # mypy still thinks cursor_model of type DatetimeBasedCursor
+                else None
+            )
+
+            # The concurrent engine defaults the start/end fields on the slice to "start" and "end", but
+            # the default DatetimeBasedRequestOptionsProvider() sets them to start_time/end_time
+            partition_field_start = "start"
+
+            request_options_provider = DatetimeBasedRequestOptionsProvider(
+                start_time_option=start_time_option,
+                partition_field_start=partition_field_start,
+                config=config,
+                parameters=model.parameters or {},
+            )
         else:
             request_options_provider = None
 
@@ -2111,6 +2207,22 @@ class ModelToComponentFactory:
             stream_response=False if self._emit_connector_builder_messages else True,
         )
 
+    @staticmethod
+    def create_incrementing_count_cursor(
+        model: IncrementingCountCursorModel, config: Config, **kwargs: Any
+    ) -> DatetimeBasedCursor:
+        # This should not actually get used anywhere at runtime, but needed to add this to pass checks since
+        # we still parse models into components. The issue is that there's no runtime implementation of a
+        # IncrementingCountCursor.
+        # A known and expected issue with this stub is running a check with the declared IncrementingCountCursor because it is run without ConcurrentCursor.
+        return DatetimeBasedCursor(
+            cursor_field=model.cursor_field,
+            datetime_format="%Y-%m-%d",
+            start_datetime="2024-12-12",
+            config=config,
+            parameters={},
+        )
+
     @staticmethod
     def create_iterable_decoder(
         model: IterableDecoderModel, config: Config, **kwargs: Any
@@ -2744,32 +2856,32 @@ class ModelToComponentFactory:
             if model.delete_requester
             else None
         )
-        url_requester = (
+        download_target_requester = (
             self._create_component_from_model(
-                model=model.url_requester,
+                model=model.download_target_requester,
                 decoder=decoder,
                 config=config,
                 name=f"job extract_url - {name}",
             )
-            if model.url_requester
+            if model.download_target_requester
             else None
         )
         status_extractor = self._create_component_from_model(
             model=model.status_extractor, decoder=decoder, config=config, name=name
         )
-        urls_extractor = self._create_component_from_model(
-            model=model.urls_extractor, decoder=decoder, config=config, name=name
+        download_target_extractor = self._create_component_from_model(
+            model=model.download_target_extractor, decoder=decoder, config=config, name=name
         )
         job_repository: AsyncJobRepository = AsyncHttpJobRepository(
             creation_requester=creation_requester,
             polling_requester=polling_requester,
             download_retriever=download_retriever,
-            url_requester=url_requester,
+            download_target_requester=download_target_requester,
             abort_requester=abort_requester,
             delete_requester=delete_requester,
             status_extractor=status_extractor,
             status_mapping=self._create_async_job_status_mapping(model.status_mapping, config),
-            urls_extractor=urls_extractor,
+            download_target_extractor=download_target_extractor,
         )
 
         async_job_partition_router = AsyncJobPartitionRouter(

{airbyte_cdk-6.37.0.dev0 → airbyte_cdk-6.37.1}/airbyte_cdk/sources/declarative/requesters/README.md

@@ -1,8 +1,8 @@
 # AsyncHttpJobRepository sequence diagram
 
 - Components marked as optional are not required and can be ignored.
-- if `url_requester` is not provided, `urls_extractor` will get urls from the `polling_job_response`
-- interpolation_context, e.g. `create_job_response` or `polling_job_response` can be obtained from stream_slice
+- if `download_target_requester` is not provided, `download_target_extractor` will get urls from the `polling_response`
+- interpolation_context, e.g. `creation_response` or `polling_response` can be obtained from stream_slice
 
 ```mermaid
 ---
@@ -12,7 +12,7 @@ sequenceDiagram
     participant AsyncHttpJobRepository as AsyncOrchestrator
     participant CreationRequester as creation_requester
     participant PollingRequester as polling_requester
-    participant UrlRequester as url_requester (Optional)
+    participant UrlRequester as download_target_requester (Optional)
     participant DownloadRetriever as download_retriever
     participant AbortRequester as abort_requester (Optional)
     participant DeleteRequester as delete_requester (Optional)
@@ -25,14 +25,14 @@ sequenceDiagram
 
     loop Poll for job status
         AsyncHttpJobRepository ->> PollingRequester: Check job status
-        PollingRequester ->> Reporting Server: Status request (interpolation_context: `create_job_response`)
+        PollingRequester ->> Reporting Server: Status request (interpolation_context: `creation_response`)
         Reporting Server -->> PollingRequester: Status response
         PollingRequester -->> AsyncHttpJobRepository: Job status
     end
 
     alt Status: Ready
         AsyncHttpJobRepository ->> UrlRequester: Request download URLs (if applicable)
-        UrlRequester ->> Reporting Server: URL request (interpolation_context: `polling_job_response`)
+        UrlRequester ->> Reporting Server: URL request (interpolation_context: `polling_response`)
         Reporting Server -->> UrlRequester: Download URLs
         UrlRequester -->> AsyncHttpJobRepository: Download URLs