feat(data-collection): create DataCollection option in client

CHANGELOG.md

@@ -66,7 +66,6 @@ Self-hosted Sentry users should opt out with `stream_gen_ai_spans=False`, since
 
 - (test): exclude django 6.1 alphas and betas from tox by @ericapisani in [#6690](https://github.com/getsentry/sentry-python/pull/6690)
 - (test): need to include the alpha tag for mcp package inclusion by @ericapisani in [#6688](https://github.com/getsentry/sentry-python/pull/6688)
-
 ## 2.63.0
 
 ### Bug Fixes 🐛

README.md

@@ -49,6 +49,11 @@ sentry_sdk.init(
     # Set traces_sample_rate to 1.0 to capture 100%
     # of traces for performance monitoring.
     traces_sample_rate=1.0,
+
+    # To disable sending user data and HTTP request/response bodies, uncomment
+    # the line below. For more info visit:
+    # https://docs.sentry.io/platforms/python/configuration/options/#data_collection
+    # data_collection={"user_info": False, "http_bodies": []},
 )
 ```
 

sentry_sdk/_types.py

@@ -141,7 +141,7 @@ def substituted_because_contains_sensitive_data(cls) -> "AnnotatedValue":
     from collections.abc import Container, MutableMapping, Sequence
     from datetime import datetime
     from types import TracebackType
-    from typing import Any, Callable, Dict, Mapping, NotRequired, Optional, Type
+    from typing import Any, Callable, Dict, List, Mapping, NotRequired, Optional, Type
 
     from typing_extensions import Literal, TypedDict
 
@@ -152,6 +152,63 @@ class SDKInfo(TypedDict):
         version: str
         packages: "Sequence[Mapping[str, str]]"
 
+    class KeyValueCollectionBehaviour(TypedDict):
+        mode: 'Literal["off", "deny_list", "allow_list"]'
+        terms: "NotRequired[List[str]]"
+
+    class GenAICollectionUserOptions(TypedDict, total=False):
+        inputs: bool
+        outputs: bool
+
+    class GenAICollectionBehaviour(TypedDict):
+        inputs: bool
+        outputs: bool
+
+    class GraphQLCollectionUserOptions(TypedDict, total=False):
+        document: bool
+        variables: bool
+
+    class GraphQLCollectionBehaviour(TypedDict):
+        document: bool
+        variables: bool
+
+    class DatabaseCollectionUserOptions(TypedDict, total=False):
+        query_params: bool
+
+    class DatabaseCollectionBehaviour(TypedDict):
+        query_params: bool
+
+    class HttpHeadersCollectionUserOptions(TypedDict, total=False):
+        request: "KeyValueCollectionBehaviour"
+
+    class HttpHeadersCollectionBehaviour(TypedDict):
+        request: "KeyValueCollectionBehaviour"
+
+    class DataCollectionUserOptions(TypedDict, total=False):
+        user_info: bool
+        cookies: "KeyValueCollectionBehaviour"
+        http_headers: "HttpHeadersCollectionUserOptions"
+        http_bodies: "List[str]"
+        query_params: "KeyValueCollectionBehaviour"
+        graphql: "GraphQLCollectionUserOptions"
+        gen_ai: "GenAICollectionUserOptions"
+        database: "DatabaseCollectionUserOptions"
+        stack_frame_variables: bool
+        frame_context_lines: int
+
+    class DataCollection(TypedDict):
+        provided_by_user: bool
+        user_info: bool
+        cookies: "KeyValueCollectionBehaviour"
+        http_headers: "HttpHeadersCollectionBehaviour"
+        http_bodies: "List[str]"
+        query_params: "KeyValueCollectionBehaviour"
+        graphql: "GraphQLCollectionBehaviour"
+        gen_ai: "GenAICollectionBehaviour"
+        database: "DatabaseCollectionBehaviour"
+        stack_frame_variables: bool
+        frame_context_lines: int
+
     # "critical" is an alias of "fatal" recognized by Relay
     LogLevelStr = Literal["fatal", "critical", "error", "warning", "info", "debug"]
 

sentry_sdk/client.py

@@ -23,6 +23,10 @@
     VERSION,
     ClientConstructor,
 )
+from sentry_sdk.data_collection import (
+    _map_from_send_default_pii,
+    _resolve_data_collection,
+)
 from sentry_sdk.envelope import Envelope, Item, PayloadRef
 from sentry_sdk.integrations import _DEFAULT_INTEGRATIONS, setup_integrations
 from sentry_sdk.integrations.dedupe import DedupeIntegration
@@ -70,6 +74,7 @@
     from sentry_sdk._log_batcher import LogBatcher
     from sentry_sdk._metrics_batcher import MetricsBatcher
     from sentry_sdk._types import (
+        DataCollection,
         Event,
         EventDataCategory,
         Hint,
@@ -345,11 +350,13 @@ def _get_options(*args: "Optional[str]", **kwargs: "Any") -> "Dict[str, Any]":
     if rv["enable_tracing"] is True and rv["traces_sample_rate"] is None:
         rv["traces_sample_rate"] = 1.0
 
+    rv["data_collection"] = _resolve_data_collection(rv)
+
     if rv["event_scrubber"] is None:
         rv["event_scrubber"] = EventScrubber(
-            send_default_pii=(
-                False if rv["send_default_pii"] is None else rv["send_default_pii"]
-            )
+            send_default_pii=False
+            if rv["send_default_pii"] is None
+            else rv["send_default_pii"]
         )
 
     if rv["socket_options"] and not isinstance(rv["socket_options"], list):
@@ -614,6 +621,19 @@ def _record_lost_event(
                 self.options["error_sampler"] = sample_all
                 self.options["traces_sampler"] = sample_all
                 self.options["profiles_sampler"] = sample_all
+                # data_collection was resolved in _get_options() before this
+                # spotlight override flipped send_default_pii on. Re-derive it so
+                # data_collection agrees with should_send_default_pii() in
+                # DSN-less spotlight mode (only when the user did not set
+                # data_collection explicitly).
+                if not self.options["data_collection"]["provided_by_user"]:
+                    self.options["data_collection"] = _map_from_send_default_pii(
+                        send_default_pii=True,
+                        include_local_variables=self.options["include_local_variables"]
+                        is not False,
+                        include_source_context=self.options["include_source_context"]
+                        is not False,
+                    )
 
             self.session_flusher = SessionFlusher(capture_func=_capture_envelope)
 

sentry_sdk/consts.py

@@ -45,6 +45,7 @@ class CompressionAlgo(Enum):
     from sentry_sdk._types import (
         BreadcrumbProcessor,
         ContinuousProfilerMode,
+        DataCollectionUserOptions,
         Event,
         EventProcessor,
         Hint,
@@ -1278,6 +1279,7 @@ def __init__(
         transport_queue_size: int = DEFAULT_QUEUE_SIZE,
         sample_rate: float = 1.0,
         send_default_pii: "Optional[bool]" = None,
+        data_collection: "Optional[DataCollectionUserOptions]" = None,
         http_proxy: "Optional[str]" = None,
         https_proxy: "Optional[str]" = None,
         ignore_errors: "Sequence[Union[type, str]]" = [],  # noqa: B006
@@ -1432,6 +1434,23 @@ def __init__(
             If you enable this option, be sure to manually remove what you don't want to send using our features for
             managing `Sensitive Data <https://docs.sentry.io/data-management/sensitive-data/>`_.
 
+        :param data_collection: (EXPERIMENTAL) Structured configuration controlling what data integrations collect automatically,
+            superseding `send_default_pii`. Pass a dict to enable or
+            restrict collection per category (user identity, cookies, HTTP headers/bodies, query params, generative AI
+            inputs/outputs, stack frame variables, source context).
+
+            When `data_collection` is set, omitted fields use their defaults (most categories are collected, with the
+            sensitive denylist scrubbing values). When it is not set, the SDK derives behaviour from `send_default_pii`
+            so that upgrading without configuring `data_collection` changes nothing. If both are set, `data_collection`
+            takes precedence.
+
+            Example::
+
+                sentry_sdk.init(
+                    dsn="...",
+                    data_collection={"user_info": False, "http_bodies": []},
+                )
+
         :param event_scrubber: Scrubs the event payload for sensitive information such as cookies, sessions, and
             passwords from a `denylist`.