feat(data-collection): add data_collection option, resolution, and accessors

Author: ericapisani

CHANGELOG.md

@@ -1,5 +1,14 @@
 # Changelog
 
+## Unreleased
+
+### Features
+
+- Add the `data_collection` option, a structured configuration that supersedes `send_default_pii` for controlling what data integrations collect automatically (user identity, cookies, HTTP headers, query params, HTTP bodies, generative AI inputs/outputs, stack frame variables, source context). See the [Data Collection spec](https://develop.sentry.dev/sdk/foundations/client/data-collection/).
+  - Adds `sentry_sdk.DataCollection`, `KeyValueCollectionBehavior`, `HttpHeadersCollection`, and `GenAICollection`.
+  - When `data_collection` is not set, behavior is derived from `send_default_pii` (now deprecated), so upgrading without configuring `data_collection` changes nothing.
+  - `frame_context_lines` is now configurable (previously hardcoded to 5); AI integrations' `include_prompts` becomes a per-integration override of `data_collection.gen_ai`.
+
 ## 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=sentry_sdk.DataCollection(user_info=False, http_bodies=[]),
 )
 ```
 

sentry_sdk/__init__.py

@@ -2,6 +2,12 @@
 
 from sentry_sdk.scope import Scope  # isort: skip
 from sentry_sdk.client import Client  # isort: skip
+from sentry_sdk.data_collection import (  # isort: skip
+    DataCollection,
+    GenAICollection,
+    HttpHeadersCollection,
+    KeyValueCollectionBehavior,
+)
 from sentry_sdk.consts import VERSION
 from sentry_sdk.transport import HttpTransport, Transport
 
@@ -11,6 +17,10 @@
     "Hub",
     "Scope",
     "Client",
+    "DataCollection",
+    "GenAICollection",
+    "HttpHeadersCollection",
+    "KeyValueCollectionBehavior",
     "Transport",
     "HttpTransport",
     "VERSION",

sentry_sdk/client.py

@@ -23,6 +23,12 @@
     VERSION,
     ClientConstructor,
 )
+from sentry_sdk.data_collection import (
+    OFF_DATA_COLLECTION,
+    DataCollection,
+    _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
@@ -345,11 +351,11 @@ 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=rv["data_collection"].user_info
         )
 
     if rv["socket_options"] and not isinstance(rv["socket_options"], list):
@@ -425,6 +431,23 @@ def parsed_dsn(self) -> "Optional[Dsn]":
     def should_send_default_pii(self) -> bool:
         return False
 
+    @property
+    def data_collection(self) -> "DataCollection":
+        return OFF_DATA_COLLECTION
+
+    def should_collect_user_info(self) -> bool:
+        return False
+
+    def should_collect_gen_ai_inputs(
+        self, include_prompts: "Optional[bool]" = None
+    ) -> bool:
+        return False
+
+    def should_collect_gen_ai_outputs(
+        self, include_prompts: "Optional[bool]" = None
+    ) -> bool:
+        return False
+
     def is_active(self) -> bool:
         """
         .. versionadded:: 2.0.0
@@ -614,6 +637,17 @@ 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
+                # the should_collect_* accessors agree 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"].explicit:
+                    self.options["data_collection"] = _map_from_send_default_pii(
+                        True,
+                        self.options["include_local_variables"] is not False,
+                        self.options["include_source_context"] is not False,
+                    )
 
             self.session_flusher = SessionFlusher(capture_func=_capture_envelope)
 
@@ -724,6 +758,59 @@ def should_send_default_pii(self) -> bool:
         """
         return self.options.get("send_default_pii") or False
 
+    @property
+    def data_collection(self) -> "DataCollection":
+        """
+        Returns the resolved :class:`~sentry_sdk.data_collection.DataCollection`
+        config for this client.
+        """
+        dc = self.options.get("data_collection")
+        return dc if dc is not None else OFF_DATA_COLLECTION
+
+    def should_collect_user_info(self) -> bool:
+        """
+        Returns whether the SDK should automatically populate ``user.*`` fields
+        (id, email, username, ip_address) from instrumentation.
+        """
+        return bool(self.data_collection.user_info)
+
+    def should_collect_gen_ai_inputs(
+        self, include_prompts: "Optional[bool]" = None
+    ) -> bool:
+        """
+        Returns whether the SDK should collect generative AI input content.
+
+        ``include_prompts`` is the integration-level override (if set, it takes
+        precedence over the global ``data_collection.gen_ai.inputs`` setting).
+        """
+        return self._should_collect_gen_ai_content("inputs", include_prompts)
+
+    def should_collect_gen_ai_outputs(
+        self, include_prompts: "Optional[bool]" = None
+    ) -> bool:
+        """
+        Returns whether the SDK should collect generative AI output content.
+
+        ``include_prompts`` is the integration-level override (if set, it takes
+        precedence over the global ``data_collection.gen_ai.outputs`` setting).
+        """
+        return self._should_collect_gen_ai_content("outputs", include_prompts)
+
+    def _should_collect_gen_ai_content(
+        self, direction: str, include_prompts: "Optional[bool]"
+    ) -> bool:
+        dc = self.data_collection
+        if dc.explicit:
+            # Integration-level override wins over the global gen_ai setting.
+            if include_prompts is not None:
+                return include_prompts
+            return bool(getattr(dc.gen_ai, direction))
+        # Legacy (data_collection not set): preserve the historical gate
+        # `should_send_default_pii() and integration.include_prompts`.
+        # `include_prompts is None` means "no integration-level override", which
+        # falls back to the legacy default of True (collect when PII is on).
+        return self.should_send_default_pii() and (include_prompts is not False)
+
     @property
     def dsn(self) -> "Optional[str]":
         """Returns the configured DSN as string."""

sentry_sdk/consts.py

@@ -56,6 +56,7 @@ class CompressionAlgo(Enum):
         TracesSampler,
         TransactionProcessor,
     )
+    from sentry_sdk.data_collection import DataCollection
 
     # Experiments are feature flags to enable and disable certain unstable SDK
     # functionality. Changing them from the defaults (`None`) in production
@@ -1272,6 +1273,7 @@ def __init__(
         transport_queue_size: int = DEFAULT_QUEUE_SIZE,
         sample_rate: float = 1.0,
         send_default_pii: "Optional[bool]" = None,
+        data_collection: "Optional[Union[DataCollection, Dict[str, Any]]]" = None,
         http_proxy: "Optional[str]" = None,
         https_proxy: "Optional[str]" = None,
         ignore_errors: "Sequence[Union[type, str]]" = [],  # noqa: B006
@@ -1426,6 +1428,26 @@ 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/>`_.
 
+            .. deprecated::
+                Use `data_collection` instead. `send_default_pii` is still honored when `data_collection` is not set.
+
+        :param data_collection: Structured configuration controlling what data integrations collect automatically,
+            superseding `send_default_pii`. Pass a dict or a :class:`sentry_sdk.DataCollection` instance 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 behavior 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`.