airbyte-cdk 6.37.0.dev1__py3-none-any.whl → 6.37.2__py3-none-any.whl

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.
@@ -1490,7 +1530,11 @@ definitions:
       limit:
         title: Limit
         description: The maximum number of calls allowed within the interval.
-        type: integer
+        anyOf:
+          - type: integer
+          - type: string
+        interpolation_context:
+          - config
       interval:
         title: Interval
         description: The time interval for the rate limit.
@@ -1750,7 +1794,6 @@ definitions:
     type: object
     required:
       - type
-      - path
       - url_base
     properties:
       type:
@@ -1762,9 +1805,18 @@ definitions:
         type: string
         interpolation_context:
           - config
+          - next_page_token
+          - stream_interval
+          - stream_partition
+          - stream_slice
+          - creation_response
+          - polling_response
+          - download_target
         examples:
           - "https://connect.squareup.com/v2"
-          - "{{ config['base_url'] or 'https://app.posthog.com'}}/api/"
+          - "{{ config['base_url'] or 'https://app.posthog.com'}}/api"
+          - "https://connect.squareup.com/v2/quotes/{{ stream_partition['id'] }}/quote_line_groups"
+          - "https://example.com/api/v1/resource/{{ next_page_token['id'] }}"
       path:
         title: URL Path
         description: Path the specific API endpoint that this stream represents. Do not put sensitive information (e.g. API tokens) into this field - Use the Authentication component for this.
@@ -1775,6 +1827,9 @@ definitions:
           - stream_interval
           - stream_partition
           - stream_slice
+          - creation_response
+          - polling_response
+          - download_target
         examples:
           - "/products"
           - "/quotes/{{ stream_partition['id'] }}/quote_line_groups"
@@ -2394,6 +2449,7 @@ 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`
@@ -3130,14 +3186,12 @@ definitions:
           - "$ref": "#/definitions/CustomPartitionRouter"
           - "$ref": "#/definitions/ListPartitionRouter"
           - "$ref": "#/definitions/SubstreamPartitionRouter"
-          - "$ref": "#/definitions/GroupingPartitionRouter"
           - type: array
             items:
               anyOf:
                 - "$ref": "#/definitions/CustomPartitionRouter"
                 - "$ref": "#/definitions/ListPartitionRouter"
                 - "$ref": "#/definitions/SubstreamPartitionRouter"
-                - "$ref": "#/definitions/GroupingPartitionRouter"
       decoder:
         title: Decoder
         description: Component decoding the response so records can be extracted.
@@ -3221,7 +3275,7 @@ definitions:
       - polling_requester
       - download_requester
       - status_extractor
-      - urls_extractor
+      - download_target_extractor
     properties:
       type:
         type: string
@@ -3238,7 +3292,7 @@ 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:
           - "$ref": "#/definitions/CustomRecordExtractor"
@@ -3259,7 +3313,7 @@ definitions:
         anyOf:
           - "$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"
@@ -3292,14 +3346,12 @@ definitions:
           - "$ref": "#/definitions/CustomPartitionRouter"
           - "$ref": "#/definitions/ListPartitionRouter"
           - "$ref": "#/definitions/SubstreamPartitionRouter"
-          - "$ref": "#/definitions/GroupingPartitionRouter"
           - type: array
             items:
               anyOf:
                 - "$ref": "#/definitions/CustomPartitionRouter"
                 - "$ref": "#/definitions/ListPartitionRouter"
                 - "$ref": "#/definitions/SubstreamPartitionRouter"
-                - "$ref": "#/definitions/GroupingPartitionRouter"
       decoder:
         title: Decoder
         description: Component decoding the response so records can be extracted.
@@ -3416,44 +3468,6 @@ definitions:
       $parameters:
         type: object
         additionalProperties: true
-  GroupingPartitionRouter:
-    title: Grouping Partition Router
-    description: >
-      A decorator on top of a partition router that groups partitions into batches of a specified size.
-      This is useful for APIs that support filtering by multiple partition keys in a single request.
-      Note that per-partition incremental syncs may not work as expected because the grouping
-      of partitions might change between syncs, potentially leading to inconsistent state tracking.
-    type: object
-    required:
-      - type
-      - group_size
-      - underlying_partition_router
-    properties:
-      type:
-        type: string
-        enum: [GroupingPartitionRouter]
-      group_size:
-        title: Group Size
-        description: The number of partitions to include in each group. This determines how many partition values are batched together in a single slice.
-        type: integer
-        examples:
-          - 10
-          - 50
-      underlying_partition_router:
-        title: Underlying Partition Router
-        description: The partition router whose output will be grouped. This can be any valid partition router component.
-        anyOf:
-          - "$ref": "#/definitions/CustomPartitionRouter"
-          - "$ref": "#/definitions/ListPartitionRouter"
-          - "$ref": "#/definitions/SubstreamPartitionRouter"
-      deduplicate:
-        title: Deduplicate Partitions
-        description: If true, ensures that partitions are unique within each group by removing duplicates based on the partition key.
-        type: boolean
-        default: true
-      $parameters:
-        type: object
-        additionalProperties: true
   WaitUntilTimeFromHeader:
     title: Wait Until Time Defined In Response Header
     description: Extract time at which we can retry the request from response header and wait for the difference between now and that time.
@@ -3705,6 +3719,21 @@ 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/sources/declarative/decoders/composite_raw_decoder.py

@@ -107,6 +107,16 @@ class CsvParser(Parser):
     encoding: Optional[str] = "utf-8"
     delimiter: Optional[str] = ","
 
+    def _get_delimiter(self) -> Optional[str]:
+        """
+        Get delimiter from the configuration. Check for the escape character and decode it.
+        """
+        if self.delimiter is not None:
+            if self.delimiter.startswith("\\"):
+                self.delimiter = self.delimiter.encode("utf-8").decode("unicode_escape")
+
+        return self.delimiter
+
     def parse(
         self,
         data: BufferedIOBase,
@@ -115,8 +125,9 @@ class CsvParser(Parser):
         Parse CSV data from decompressed bytes.
         """
         text_data = TextIOWrapper(data, encoding=self.encoding)  # type: ignore
-        reader = csv.DictReader(text_data, delimiter=self.delimiter or ",")
-        yield from reader
+        reader = csv.DictReader(text_data, delimiter=self._get_delimiter() or ",")
+        for row in reader:
+            yield row
 
 
 @dataclass

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/sources/declarative/incremental/concurrent_partition_cursor.py

@@ -95,6 +95,10 @@ class ConcurrentPerPartitionCursor(Cursor):
         # the oldest partitions can be efficiently removed, maintaining the most recent partitions.
         self._cursor_per_partition: OrderedDict[str, ConcurrentCursor] = OrderedDict()
         self._semaphore_per_partition: OrderedDict[str, threading.Semaphore] = OrderedDict()
+
+        # Parent-state tracking: store each partition’s parent state in creation order
+        self._partition_parent_state_map: OrderedDict[str, Mapping[str, Any]] = OrderedDict()
+
         self._finished_partitions: set[str] = set()
         self._lock = threading.Lock()
         self._timer = Timer()
@@ -155,11 +159,62 @@ class ConcurrentPerPartitionCursor(Cursor):
                     and self._semaphore_per_partition[partition_key]._value == 0
                 ):
                     self._update_global_cursor(cursor.state[self.cursor_field.cursor_field_key])
-                self._emit_state_message()
+
+            self._check_and_update_parent_state()
+
+            self._emit_state_message()
+
+    def _check_and_update_parent_state(self) -> None:
+        """
+        Pop the leftmost partition state from _partition_parent_state_map only if
+        *all partitions* up to (and including) that partition key in _semaphore_per_partition
+        are fully finished (i.e. in _finished_partitions and semaphore._value == 0).
+        Additionally, delete finished semaphores with a value of 0 to free up memory,
+        as they are only needed to track errors and completion status.
+        """
+        last_closed_state = None
+
+        while self._partition_parent_state_map:
+            # Look at the earliest partition key in creation order
+            earliest_key = next(iter(self._partition_parent_state_map))
+
+            # Verify ALL partitions from the left up to earliest_key are finished
+            all_left_finished = True
+            for p_key, sem in list(
+                self._semaphore_per_partition.items()
+            ):  # Use list to allow modification during iteration
+                # If any earlier partition is still not finished, we must stop
+                if p_key not in self._finished_partitions or sem._value != 0:
+                    all_left_finished = False
+                    break
+                # Once we've reached earliest_key in the semaphore order, we can stop checking
+                if p_key == earliest_key:
+                    break
+
+            # If the partitions up to earliest_key are not all finished, break the while-loop
+            if not all_left_finished:
+                break
+
+            # Pop the leftmost entry from parent-state map
+            _, closed_parent_state = self._partition_parent_state_map.popitem(last=False)
+            last_closed_state = closed_parent_state
+
+            # Clean up finished semaphores with value 0 up to and including earliest_key
+            for p_key in list(self._semaphore_per_partition.keys()):
+                sem = self._semaphore_per_partition[p_key]
+                if p_key in self._finished_partitions and sem._value == 0:
+                    del self._semaphore_per_partition[p_key]
+                    logger.debug(f"Deleted finished semaphore for partition {p_key} with value 0")
+                if p_key == earliest_key:
+                    break
+
+        # Update _parent_state if we popped at least one partition
+        if last_closed_state is not None:
+            self._parent_state = last_closed_state
 
     def ensure_at_least_one_state_emitted(self) -> None:
         """
-        The platform expect to have at least one state message on successful syncs. Hence, whatever happens, we expect this method to be
+        The platform expects at least one state message on successful syncs. Hence, whatever happens, we expect this method to be
         called.
         """
         if not any(
@@ -201,13 +256,19 @@ class ConcurrentPerPartitionCursor(Cursor):
 
         slices = self._partition_router.stream_slices()
         self._timer.start()
-        for partition in slices:
-            yield from self._generate_slices_from_partition(partition)
+        for partition, last, parent_state in iterate_with_last_flag_and_state(
+            slices, self._partition_router.get_stream_state
+        ):
+            yield from self._generate_slices_from_partition(partition, parent_state)
 
-    def _generate_slices_from_partition(self, partition: StreamSlice) -> Iterable[StreamSlice]:
+    def _generate_slices_from_partition(
+        self, partition: StreamSlice, parent_state: Mapping[str, Any]
+    ) -> Iterable[StreamSlice]:
         # Ensure the maximum number of partitions is not exceeded
         self._ensure_partition_limit()
 
+        partition_key = self._to_partition_key(partition.partition)
+
         cursor = self._cursor_per_partition.get(self._to_partition_key(partition.partition))
         if not cursor:
             cursor = self._create_cursor(
@@ -216,18 +277,26 @@ class ConcurrentPerPartitionCursor(Cursor):
             )
             with self._lock:
                 self._number_of_partitions += 1
-                self._cursor_per_partition[self._to_partition_key(partition.partition)] = cursor
-            self._semaphore_per_partition[self._to_partition_key(partition.partition)] = (
-                threading.Semaphore(0)
-            )
+                self._cursor_per_partition[partition_key] = cursor
+        self._semaphore_per_partition[partition_key] = threading.Semaphore(0)
+
+        with self._lock:
+            if (
+                len(self._partition_parent_state_map) == 0
+                or self._partition_parent_state_map[
+                    next(reversed(self._partition_parent_state_map))
+                ]
+                != parent_state
+            ):
+                self._partition_parent_state_map[partition_key] = deepcopy(parent_state)
 
         for cursor_slice, is_last_slice, _ in iterate_with_last_flag_and_state(
             cursor.stream_slices(),
             lambda: None,
         ):
-            self._semaphore_per_partition[self._to_partition_key(partition.partition)].release()
+            self._semaphore_per_partition[partition_key].release()
             if is_last_slice:
-                self._finished_partitions.add(self._to_partition_key(partition.partition))
+                self._finished_partitions.add(partition_key)
             yield StreamSlice(
                 partition=partition, cursor_slice=cursor_slice, extra_fields=partition.extra_fields
             )
@@ -257,9 +326,9 @@ class ConcurrentPerPartitionCursor(Cursor):
             while len(self._cursor_per_partition) > self.DEFAULT_MAX_PARTITIONS_NUMBER - 1:
                 # Try removing finished partitions first
                 for partition_key in list(self._cursor_per_partition.keys()):
-                    if (
-                        partition_key in self._finished_partitions
-                        and self._semaphore_per_partition[partition_key]._value == 0
+                    if partition_key in self._finished_partitions and (
+                        partition_key not in self._semaphore_per_partition
+                        or self._semaphore_per_partition[partition_key]._value == 0
                     ):
                         oldest_partition = self._cursor_per_partition.pop(
                             partition_key
@@ -338,9 +407,6 @@ class ConcurrentPerPartitionCursor(Cursor):
                 self._cursor_per_partition[self._to_partition_key(state["partition"])] = (
                     self._create_cursor(state["cursor"])
                 )
-                self._semaphore_per_partition[self._to_partition_key(state["partition"])] = (
-                    threading.Semaphore(0)
-                )
 
             # set default state for missing partitions if it is per partition with fallback to global
             if self._GLOBAL_STATE_KEY in stream_state:

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/sources/declarative/models/declarative_component_schema.py

@@ -646,7 +646,7 @@ class Rate(BaseModel):
     class Config:
         extra = Extra.allow
 
-    limit: int = Field(
+    limit: Union[int, str] = Field(
         ...,
         description="The maximum number of calls allowed within the interval.",
         title="Limit",
@@ -939,7 +939,7 @@ class MinMaxDatetime(BaseModel):
     )
     datetime_format: Optional[str] = Field(
         "",
-        description='Format of the datetime value. Defaults to "%Y-%m-%dT%H:%M:%S.%f%z" if left empty. Use placeholders starting with "%" to describe the format the API is using. The following placeholders are available:\n  * **%s**: Epoch unix timestamp - `1686218963`\n  * **%s_as_float**: Epoch unix timestamp in seconds as float with microsecond precision - `1686218963.123456`\n  * **%ms**: Epoch unix timestamp - `1686218963123`\n  * **%a**: Weekday (abbreviated) - `Sun`\n  * **%A**: Weekday (full) - `Sunday`\n  * **%w**: Weekday (decimal) - `0` (Sunday), `6` (Saturday)\n  * **%d**: Day of the month (zero-padded) - `01`, `02`, ..., `31`\n  * **%b**: Month (abbreviated) - `Jan`\n  * **%B**: Month (full) - `January`\n  * **%m**: Month (zero-padded) - `01`, `02`, ..., `12`\n  * **%y**: Year (without century, zero-padded) - `00`, `01`, ..., `99`\n  * **%Y**: Year (with century) - `0001`, `0002`, ..., `9999`\n  * **%H**: Hour (24-hour, zero-padded) - `00`, `01`, ..., `23`\n  * **%I**: Hour (12-hour, zero-padded) - `01`, `02`, ..., `12`\n  * **%p**: AM/PM indicator\n  * **%M**: Minute (zero-padded) - `00`, `01`, ..., `59`\n  * **%S**: Second (zero-padded) - `00`, `01`, ..., `59`\n  * **%f**: Microsecond (zero-padded to 6 digits) - `000000`, `000001`, ..., `999999`\n  * **%z**: UTC offset - `(empty)`, `+0000`, `-04:00`\n  * **%Z**: Time zone name - `(empty)`, `UTC`, `GMT`\n  * **%j**: Day of the year (zero-padded) - `001`, `002`, ..., `366`\n  * **%U**: Week number of the year (Sunday as first day) - `00`, `01`, ..., `53`\n  * **%W**: Week number of the year (Monday as first day) - `00`, `01`, ..., `53`\n  * **%c**: Date and time representation - `Tue Aug 16 21:30:00 1988`\n  * **%x**: Date representation - `08/16/1988`\n  * **%X**: Time representation - `21:30:00`\n  * **%%**: Literal \'%\' character\n\n  Some placeholders depend on the locale of the underlying system - in most cases this locale is configured as en/US. For more information see the [Python documentation](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes).\n',
+        description='Format of the datetime value. Defaults to "%Y-%m-%dT%H:%M:%S.%f%z" if left empty. Use placeholders starting with "%" to describe the format the API is using. The following placeholders are available:\n  * **%s**: Epoch unix timestamp - `1686218963`\n  * **%s_as_float**: Epoch unix timestamp in seconds as float with microsecond precision - `1686218963.123456`\n  * **%ms**: Epoch unix timestamp - `1686218963123`\n  * **%a**: Weekday (abbreviated) - `Sun`\n  * **%A**: Weekday (full) - `Sunday`\n  * **%w**: Weekday (decimal) - `0` (Sunday), `6` (Saturday)\n  * **%d**: Day of the month (zero-padded) - `01`, `02`, ..., `31`\n  * **%b**: Month (abbreviated) - `Jan`\n  * **%B**: Month (full) - `January`\n  * **%m**: Month (zero-padded) - `01`, `02`, ..., `12`\n  * **%y**: Year (without century, zero-padded) - `00`, `01`, ..., `99`\n  * **%Y**: Year (with century) - `0001`, `0002`, ..., `9999`\n  * **%H**: Hour (24-hour, zero-padded) - `00`, `01`, ..., `23`\n  * **%I**: Hour (12-hour, zero-padded) - `01`, `02`, ..., `12`\n  * **%p**: AM/PM indicator\n  * **%M**: Minute (zero-padded) - `00`, `01`, ..., `59`\n  * **%S**: Second (zero-padded) - `00`, `01`, ..., `59`\n  * **%f**: Microsecond (zero-padded to 6 digits) - `000000`, `000001`, ..., `999999`\n  * **%_ms**: Millisecond (zero-padded to 3 digits) - `000`, `001`, ..., `999`\n  * **%z**: UTC offset - `(empty)`, `+0000`, `-04:00`\n  * **%Z**: Time zone name - `(empty)`, `UTC`, `GMT`\n  * **%j**: Day of the year (zero-padded) - `001`, `002`, ..., `366`\n  * **%U**: Week number of the year (Sunday as first day) - `00`, `01`, ..., `53`\n  * **%W**: Week number of the year (Monday as first day) - `00`, `01`, ..., `53`\n  * **%c**: Date and time representation - `Tue Aug 16 21:30:00 1988`\n  * **%x**: Date representation - `08/16/1988`\n  * **%X**: Time representation - `21:30:00`\n  * **%%**: Literal \'%\' character\n\n  Some placeholders depend on the locale of the underlying system - in most cases this locale is configured as en/US. For more information see the [Python documentation](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes).\n',
         examples=["%Y-%m-%dT%H:%M:%S.%f%z", "%Y-%m-%d", "%s"],
         title="Datetime Format",
     )
@@ -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(
@@ -1523,7 +1545,7 @@ class DatetimeBasedCursor(BaseModel):
     )
     datetime_format: str = Field(
         ...,
-        description="The datetime format used to format the datetime values that are sent in outgoing requests to the API. Use placeholders starting with \"%\" to describe the format the API is using. The following placeholders are available:\n  * **%s**: Epoch unix timestamp - `1686218963`\n  * **%s_as_float**: Epoch unix timestamp in seconds as float with microsecond precision - `1686218963.123456`\n  * **%ms**: Epoch unix timestamp (milliseconds) - `1686218963123`\n  * **%a**: Weekday (abbreviated) - `Sun`\n  * **%A**: Weekday (full) - `Sunday`\n  * **%w**: Weekday (decimal) - `0` (Sunday), `6` (Saturday)\n  * **%d**: Day of the month (zero-padded) - `01`, `02`, ..., `31`\n  * **%b**: Month (abbreviated) - `Jan`\n  * **%B**: Month (full) - `January`\n  * **%m**: Month (zero-padded) - `01`, `02`, ..., `12`\n  * **%y**: Year (without century, zero-padded) - `00`, `01`, ..., `99`\n  * **%Y**: Year (with century) - `0001`, `0002`, ..., `9999`\n  * **%H**: Hour (24-hour, zero-padded) - `00`, `01`, ..., `23`\n  * **%I**: Hour (12-hour, zero-padded) - `01`, `02`, ..., `12`\n  * **%p**: AM/PM indicator\n  * **%M**: Minute (zero-padded) - `00`, `01`, ..., `59`\n  * **%S**: Second (zero-padded) - `00`, `01`, ..., `59`\n  * **%f**: Microsecond (zero-padded to 6 digits) - `000000`\n  * **%z**: UTC offset - `(empty)`, `+0000`, `-04:00`\n  * **%Z**: Time zone name - `(empty)`, `UTC`, `GMT`\n  * **%j**: Day of the year (zero-padded) - `001`, `002`, ..., `366`\n  * **%U**: Week number of the year (starting Sunday) - `00`, ..., `53`\n  * **%W**: Week number of the year (starting Monday) - `00`, ..., `53`\n  * **%c**: Date and time - `Tue Aug 16 21:30:00 1988`\n  * **%x**: Date standard format - `08/16/1988`\n  * **%X**: Time standard format - `21:30:00`\n  * **%%**: Literal '%' character\n\n  Some placeholders depend on the locale of the underlying system - in most cases this locale is configured as en/US. For more information see the [Python documentation](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes).\n",
+        description="The datetime format used to format the datetime values that are sent in outgoing requests to the API. Use placeholders starting with \"%\" to describe the format the API is using. The following placeholders are available:\n  * **%s**: Epoch unix timestamp - `1686218963`\n  * **%s_as_float**: Epoch unix timestamp in seconds as float with microsecond precision - `1686218963.123456`\n  * **%ms**: Epoch unix timestamp (milliseconds) - `1686218963123`\n  * **%a**: Weekday (abbreviated) - `Sun`\n  * **%A**: Weekday (full) - `Sunday`\n  * **%w**: Weekday (decimal) - `0` (Sunday), `6` (Saturday)\n  * **%d**: Day of the month (zero-padded) - `01`, `02`, ..., `31`\n  * **%b**: Month (abbreviated) - `Jan`\n  * **%B**: Month (full) - `January`\n  * **%m**: Month (zero-padded) - `01`, `02`, ..., `12`\n  * **%y**: Year (without century, zero-padded) - `00`, `01`, ..., `99`\n  * **%Y**: Year (with century) - `0001`, `0002`, ..., `9999`\n  * **%H**: Hour (24-hour, zero-padded) - `00`, `01`, ..., `23`\n  * **%I**: Hour (12-hour, zero-padded) - `01`, `02`, ..., `12`\n  * **%p**: AM/PM indicator\n  * **%M**: Minute (zero-padded) - `00`, `01`, ..., `59`\n  * **%S**: Second (zero-padded) - `00`, `01`, ..., `59`\n  * **%f**: Microsecond (zero-padded to 6 digits) - `000000`\n  * **%_ms**: Millisecond (zero-padded to 3 digits) - `000`\n  * **%z**: UTC offset - `(empty)`, `+0000`, `-04:00`\n  * **%Z**: Time zone name - `(empty)`, `UTC`, `GMT`\n  * **%j**: Day of the year (zero-padded) - `001`, `002`, ..., `366`\n  * **%U**: Week number of the year (starting Sunday) - `00`, ..., `53`\n  * **%W**: Week number of the year (starting Monday) - `00`, ..., `53`\n  * **%c**: Date and time - `Tue Aug 16 21:30:00 1988`\n  * **%x**: Date standard format - `08/16/1988`\n  * **%X**: Time standard format - `21:30:00`\n  * **%%**: Literal '%' character\n\n  Some placeholders depend on the locale of the underlying system - in most cases this locale is configured as en/US. For more information see the [Python documentation](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes).\n",
         examples=["%Y-%m-%dT%H:%M:%S.%f%z", "%Y-%m-%d", "%s", "%ms", "%s_as_float"],
         title="Outgoing Datetime Format",
     )
@@ -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",
@@ -2048,12 +2072,14 @@ class HttpRequester(BaseModel):
         description="Base URL of the API source. Do not put sensitive information (e.g. API tokens) into this field - Use the Authentication component for this.",
         examples=[
             "https://connect.squareup.com/v2",
-            "{{ config['base_url'] or 'https://app.posthog.com'}}/api/",
+            "{{ config['base_url'] or 'https://app.posthog.com'}}/api",
+            "https://connect.squareup.com/v2/quotes/{{ stream_partition['id'] }}/quote_line_groups",
+            "https://example.com/api/v1/resource/{{ next_page_token['id'] }}",
         ],
         title="API Base URL",
     )
-    path: str = Field(
-        ...,
+    path: Optional[str] = Field(
+        None,
         description="Path the specific API endpoint that this stream represents. Do not put sensitive information (e.g. API tokens) into this field - Use the Authentication component for this.",
         examples=[
             "/products",
@@ -2225,15 +2251,7 @@ class SimpleRetriever(BaseModel):
             CustomPartitionRouter,
             ListPartitionRouter,
             SubstreamPartitionRouter,
-            GroupingPartitionRouter,
-            List[
-                Union[
-                    CustomPartitionRouter,
-                    ListPartitionRouter,
-                    SubstreamPartitionRouter,
-                    GroupingPartitionRouter,
-                ]
-            ],
+            List[Union[CustomPartitionRouter, ListPartitionRouter, SubstreamPartitionRouter]],
         ]
     ] = Field(
         [],
@@ -2271,7 +2289,7 @@ 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.",
     )
@@ -2286,7 +2304,7 @@ 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.",
     )
@@ -2311,15 +2329,7 @@ class AsyncRetriever(BaseModel):
             CustomPartitionRouter,
             ListPartitionRouter,
             SubstreamPartitionRouter,
-            GroupingPartitionRouter,
-            List[
-                Union[
-                    CustomPartitionRouter,
-                    ListPartitionRouter,
-                    SubstreamPartitionRouter,
-                    GroupingPartitionRouter,
-                ]
-            ],
+            List[Union[CustomPartitionRouter, ListPartitionRouter, SubstreamPartitionRouter]],
         ]
     ] = Field(
         [],
@@ -2371,29 +2381,6 @@ class SubstreamPartitionRouter(BaseModel):
     parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
 
 
-class GroupingPartitionRouter(BaseModel):
-    type: Literal["GroupingPartitionRouter"]
-    group_size: int = Field(
-        ...,
-        description="The number of partitions to include in each group. This determines how many partition values are batched together in a single slice.",
-        examples=[10, 50],
-        title="Group Size",
-    )
-    underlying_partition_router: Union[
-        CustomPartitionRouter, ListPartitionRouter, SubstreamPartitionRouter
-    ] = Field(
-        ...,
-        description="The partition router whose output will be grouped. This can be any valid partition router component.",
-        title="Underlying Partition Router",
-    )
-    deduplicate: Optional[bool] = Field(
-        True,
-        description="If true, ensures that partitions are unique within each group by removing duplicates based on the partition key.",
-        title="Deduplicate Partitions",
-    )
-    parameters: Optional[Dict[str, Any]] = Field(None, alias="$parameters")
-
-
 class HttpComponentsResolver(BaseModel):
     type: Literal["HttpComponentsResolver"]
     retriever: Union[AsyncRetriever, CustomRetriever, SimpleRetriever] = Field(