Merge branch 'master' into fix/serializer-large-mapping-copy

Author: Malkiz223

.claude/settings.json

@@ -1,5 +1,49 @@
 # Changelog
 
+## 2.65.0
+
+### New Features ✨
+
+#### Huey
+
+- Set `messaging.destination.name` on consumer spans by @alexander-alderman-webb in [#6779](https://github.com/getsentry/sentry-python/pull/6779)
+- Set `messaging.destination.name` on producer spans by @alexander-alderman-webb in [#6778](https://github.com/getsentry/sentry-python/pull/6778)
+
+#### Other
+
+- (arq) Set `messaging.destination.name` on consumer spans by @alexander-alderman-webb in [#6767](https://github.com/getsentry/sentry-python/pull/6767)
+- (dramatiq) Set `messaging.destination.name` on consumer spans by @alexander-alderman-webb in [#6776](https://github.com/getsentry/sentry-python/pull/6776)
+- (rq) Set `messaging.destination.name` on consumer spans by @alexander-alderman-webb in [#6774](https://github.com/getsentry/sentry-python/pull/6774)
+
+### Bug Fixes 🐛
+
+#### Tracing
+
+- Take first sentry-trace header in case multiple are supplied by @sl0thentr0py in [#6722](https://github.com/getsentry/sentry-python/pull/6722)
+
+#### Other
+
+- (django) Avoid `ValueError` in async middleware `process_*` hooks by @r0ro in [#6698](https://github.com/getsentry/sentry-python/pull/6698)
+- (scope) Drop None user attribute values in set_user by @ericapisani in [#6692](https://github.com/getsentry/sentry-python/pull/6692)
+- (starlette) Don't overwrite user set during request in AuthenticationMiddleware by @ericapisani in [#6760](https://github.com/getsentry/sentry-python/pull/6760)
+
+### Internal Changes 🔧
+
+- (mcp) Add package to the typing group by @alexander-alderman-webb in [#6727](https://github.com/getsentry/sentry-python/pull/6727)
+- (starlette) Add package to typing group by @alexander-alderman-webb in [#6728](https://github.com/getsentry/sentry-python/pull/6728)
+- Add required `cache_write_tokens` field by @alexander-alderman-webb in [#6804](https://github.com/getsentry/sentry-python/pull/6804)
+- Pin extra test dependencies for generated test suites by @alexander-alderman-webb in [#6696](https://github.com/getsentry/sentry-python/pull/6696)
+- Add `pydantic` to the typing group by @alexander-alderman-webb in [#6730](https://github.com/getsentry/sentry-python/pull/6730)
+- Add `python_multipart` to the typing group by @alexander-alderman-webb in [#6729](https://github.com/getsentry/sentry-python/pull/6729)
+- 🤖 Update test matrix with new releases (07/06) by @github-actions in [#6753](https://github.com/getsentry/sentry-python/pull/6753)
+- Remove dependabot by @alexander-alderman-webb in [#6720](https://github.com/getsentry/sentry-python/pull/6720)
+- Update Renovate config by @alexander-alderman-webb in [#6716](https://github.com/getsentry/sentry-python/pull/6716)
+- Stop inheriting secrets for `changelog-preview` by @alexander-alderman-webb in [#6723](https://github.com/getsentry/sentry-python/pull/6723)
+- Stop inheriting secrets in tests by @alexander-alderman-webb in [#6721](https://github.com/getsentry/sentry-python/pull/6721)
+- Configure Renovate by @renovate in [#6701](https://github.com/getsentry/sentry-python/pull/6701)
+- Move conversation ID tests to their own file by @sentrivana in [#6699](https://github.com/getsentry/sentry-python/pull/6699)
+- Replace `requirements-testing.txt` with a `uv` dependency group by @alexander-alderman-webb in [#6693](https://github.com/getsentry/sentry-python/pull/6693)
+
 ## 2.64.0
 
 The SDK now extracts all `gen_ai` spans out of a transaction and sends them as v2 envelope items by default. This prevents `gen_ai` spans from being dropped when the transaction payload exceeds size limits. Because they are no longer constrained by transaction size limits, AI message data is also no longer truncated. To keep the previous behavior, set `stream_gen_ai_spans=False`.

CHANGELOG.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": []},
 )
 ```
 

README.md

@@ -31,7 +31,7 @@
 copyright = "2019-{}, Sentry Team and Contributors".format(datetime.now().year)
 author = "Sentry Team and Contributors"
 
-release = "2.64.0"
+release = "2.65.0"
 version = ".".join(release.split(".")[:2])  # The short X.Y version.
 
 

docs/conf.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 +152,59 @@ class SDKInfo(TypedDict):
         version: str
         packages: "Sequence[Mapping[str, str]]"
 
+    class KeyValueCollectionBehaviour(TypedDict):
+        mode: 'Literal["off", "denylist", "allowlist"]'
+        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 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_query_data: bool
+        queues: bool
+        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_query_data: bool
+        queues: bool
+        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/_types.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
@@ -345,11 +349,13 @@ 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 +620,19 @@ 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/client.py

@@ -45,6 +45,7 @@ class CompressionAlgo(Enum):
     from sentry_sdk._types import (
         BreadcrumbProcessor,
         ContinuousProfilerMode,
+        DataCollectionUserOptions,
         Event,
         EventProcessor,
         Hint,
@@ -86,6 +87,7 @@ class CompressionAlgo(Enum):
                 Callable[[SpanJSON, Hint], Optional[SpanJSON]]
             ],
             "suppress_asgi_chained_exceptions": Optional[bool],
+            "data_collection": Optional[DataCollectionUserOptions],
         },
         total=False,
     )
@@ -1755,7 +1757,25 @@ def __init__(
         :param stream_gen_ai_spans: When set, generative AI spans are sent in a new transport format to
             reduce downstream data loss.
 
-        :param _experiments:
+        :param _experiments: Dictionary of experimental, opt-in features that are not yet stable.
+
+            ``data_collection`` (EXPERIMENTAL): structured configuration controlling what data integrations
+            collect automatically, superseding `send_default_pii`. Passing a dict under
+            `_experiments={"data_collection": {...}}` opts into the feature; 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
+            changes nothing. Restrict collection per category (user identity, cookies, HTTP
+            headers/bodies, query params, generative AI inputs/outputs, stack frame variables, source
+            context). If `send_default_pii` is also set, `data_collection` takes precedence.
+
+            Example::
+
+                sentry_sdk.init(
+                    dsn="...",
+                    _experiments={"data_collection": {"user_info": False, "http_bodies": []}},
+                )
+
+            See https://docs.sentry.io/platforms/python/configuration/options/#data_collection for more details.
         """
         pass
 
@@ -1779,4 +1799,4 @@ def _get_default_options() -> "dict[str, Any]":
 del _get_default_options
 
 
-VERSION = "2.64.0"
+VERSION = "2.65.0"