Skip to content

ref(tornado): Drop send_default_pii support #7705

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
pabloDeputter wants to merge 2 commits into
base: major/3.0
Choose a base branch
from
+70 −138
Open

ref(tornado): Drop send_default_pii support #7705

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b5d5d3d
ref(tornado): Drop `send_default_pii` support
pabloDeputter Sep 24, 2026
ce25a48
tests
pabloDeputter Sep 24, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
97 changes: 28 additions & 69 deletions sentry_sdk/integrations/tornado.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,14 +12,12 @@
request_body_within_bounds,
)
from sentry_sdk.integrations.logging import ignore_logger_for_events
from sentry_sdk.scope import should_send_default_pii
from sentry_sdk.traces import SegmentNameSource
from sentry_sdk.utils import (
AnnotatedValue,
capture_internal_exceptions,
ensure_integration_enabled,
event_from_exception,
has_data_collection_enabled,
parse_url,
transaction_from_function,
)
Expand Down Expand Up @@ -98,14 +96,8 @@ def _handle_request_impl(self: "RequestHandler") -> "Generator[None, None, None]
sentry_sdk.continue_trace(dict(headers))
scope.set_custom_sampling_context({"tornado_request": self.request})

if self.request.remote_ip:
if has_data_collection_enabled(client.options):
if client.options["data_collection"]["user_info"]:
scope.set_attribute(
SPANDATA.USER_IP_ADDRESS, self.request.remote_ip
)
elif should_send_default_pii():
scope.set_attribute(SPANDATA.USER_IP_ADDRESS, self.request.remote_ip)
if self.request.remote_ip and client.options["data_collection"]["user_info"]:
scope.set_attribute(SPANDATA.USER_IP_ADDRESS, self.request.remote_ip)

with sentry_sdk.start_span(
name=_DEFAULT_ROOT_SPAN_NAME,
Expand Down Expand Up @@ -151,47 +143,31 @@ def _get_request_attributes(request: "Any") -> "Dict[str, Any]":
for header, value in headers.items():
attributes[f"{SPANDATA.HTTP_REQUEST_HEADER}.{header.lower()}"] = value

if has_data_collection_enabled(client_options):
attributes["url.path"] = request.path
attributes["url.path"] = request.path

filtered_query = None
if request.query:
filtered_query = _apply_data_collection_filtering_to_query_string(
query_string=request.query,
behaviour=client_options["data_collection"]["url_query_params"],
)
if filtered_query:
attributes[SPANDATA.URL_QUERY] = filtered_query

parsed_url = parse_url(request.full_url())
attributes[SPANDATA.URL_FULL] = (
f"{parsed_url.url}?{filtered_query}" if filtered_query else parsed_url.url
filtered_query = None
if request.query:
filtered_query = _apply_data_collection_filtering_to_query_string(
query_string=request.query,
behaviour=client_options["data_collection"]["url_query_params"],
)
if filtered_query:
attributes[SPANDATA.URL_QUERY] = filtered_query

if request.remote_ip:
if client_options["data_collection"]["user_info"]:
attributes[SPANDATA.CLIENT_ADDRESS] = request.remote_ip

elif should_send_default_pii():
attributes[SPANDATA.URL_FULL] = request.full_url()
attributes["url.path"] = request.path

if request.query:
attributes[SPANDATA.URL_QUERY] = request.query
parsed_url = parse_url(request.full_url())
attributes[SPANDATA.URL_FULL] = (
f"{parsed_url.url}?{filtered_query}" if filtered_query else parsed_url.url
)

if request.remote_ip:
attributes[SPANDATA.CLIENT_ADDRESS] = request.remote_ip
if request.remote_ip and client_options["data_collection"]["user_info"]:
attributes[SPANDATA.CLIENT_ADDRESS] = request.remote_ip

if request.protocol:
attributes[SPANDATA.NETWORK_PROTOCOL_NAME] = request.protocol

# The request data was unconditionally set pre-data collection which is
# why we're defaulting to True
record_incoming_request_data = True
if has_data_collection_enabled(client_options):
record_incoming_request_data = (
"incoming_request" in client_options["data_collection"]["http_bodies"]
)
record_incoming_request_data = (
"incoming_request" in client_options["data_collection"]["http_bodies"]
)

if record_incoming_request_data:
with capture_internal_exceptions():
Expand Down Expand Up @@ -260,38 +236,21 @@ def tornado_processor(event: "Event", hint: "dict[str, Any]") -> "Event":
request.path,
)

if has_data_collection_enabled(client_options):
if request.query:
filtered_query = _apply_data_collection_filtering_to_query_string(
query_string=request.query,
behaviour=client_options["data_collection"]["url_query_params"],
)
if filtered_query:
request_info["query_string"] = filtered_query
else:
request_info["query_string"] = request.query
if request.query:
filtered_query = _apply_data_collection_filtering_to_query_string(
query_string=request.query,
behaviour=client_options["data_collection"]["url_query_params"],
)
if filtered_query:
request_info["query_string"] = filtered_query

request_info["method"] = request.method

# REMOTE_ADDR was unconditionally set pre-data collection, so it
# continues to be set when data collection is not enabled.
if (
not has_data_collection_enabled(client_options)
or client_options["data_collection"]["user_info"]
):
if client_options["data_collection"]["user_info"]:
request_info["env"] = {"REMOTE_ADDR": request.remote_ip}
request_info["headers"] = _filter_headers(dict(request.headers))

if has_data_collection_enabled(client_options):
if client_options["data_collection"]["user_info"]:
try:
current_user = handler.current_user
except Exception:
current_user = None

if current_user:
event.setdefault("user", {}).setdefault("is_authenticated", True)
elif should_send_default_pii():
if client_options["data_collection"]["user_info"]:
try:
current_user = handler.current_user
except Exception:
Expand Down
111 changes: 42 additions & 69 deletions tests/integrations/tornado/test_tornado.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,24 +87,24 @@ def get(self):
"init_kwargs, expected_cookies",
[
pytest.param(
{"send_default_pii": True},
{"data_collection": {}},

@sentrivana sentrivana Sep 24, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Totally optional, but we could clean this up more now that it's not really init_kwargs anymore, but just the data_collection definition: you can remove the outer {"data_collection": } dict from the first param everywhere, and rename the param init_kwargs -> data_collection, and then just provide it in the sentry_init as data_collection=data_collection.

{
"jwt": "tokenval",
"jwt": SENSITIVE_DATA_SUBSTITUTE,
"theme": "dark",
"lang": "en",
"identity": "alice",
"identity": SENSITIVE_DATA_SUBSTITUTE,
},
id="send_default_pii_true",
id="data_collection_default",
),
pytest.param(
{"send_default_pii": False},
None,
id="send_default_pii_false",
),
pytest.param(
{},
None,
id="defaults",
{"data_collection": {"cookies": {"mode": "denylist", "terms": []}}},
{
"jwt": SENSITIVE_DATA_SUBSTITUTE,
"theme": "dark",
"lang": "en",
"identity": SENSITIVE_DATA_SUBSTITUTE,
},
id="data_collection_denylist_empty_terms",
),
pytest.param(
{"data_collection": {"cookies": {"mode": "off"}}},
Expand Down Expand Up @@ -155,19 +155,6 @@ def get(self):
},
id="data_collection_allowlist_sensitive_term",
),
pytest.param(
{
"send_default_pii": False,
"data_collection": {"cookies": {"mode": "denylist"}},
},
{
"jwt": SENSITIVE_DATA_SUBSTITUTE,
"theme": "dark",
"lang": "en",
"identity": SENSITIVE_DATA_SUBSTITUTE,
},
id="data_collection_wins_over_send_default_pii",
),
],
)
def test_cookie_data_collection(
Expand All @@ -194,19 +181,14 @@ async def get(self):

_QUERY_PARAM_DATA_COLLECTION_CASES = [
pytest.param(
{"send_default_pii": True},
"toy=tennisball&color=red&auth=secret",
id="send_default_pii_true",
),
pytest.param(
{"send_default_pii": False},
None,
id="send_default_pii_false",
{"data_collection": {"url_query_params": {"mode": "denylist", "terms": []}}},
"toy=tennisball&color=red&auth=%5BFiltered%5D",
id="data_collection_denylist_empty_terms",
),
pytest.param(
{},
{"data_collection": {"url_query_params": {"mode": "off"}}},
None,
id="defaults",
id="data_collection_off",
),
pytest.param(
{"data_collection": {}},
Expand Down Expand Up @@ -240,19 +222,6 @@ async def get(self):
"toy=%5BFiltered%5D&color=%5BFiltered%5D&auth=%5BFiltered%5D",
id="data_collection_allowlist_sensitive_term",
),
pytest.param(
{"data_collection": {"url_query_params": {"mode": "off"}}},
None,
id="data_collection_off",
),
pytest.param(
{
"send_default_pii": True,
"data_collection": {"url_query_params": {"mode": "off"}},
},
None,
id="data_collection_wins_over_send_default_pii",
),
]


Expand All @@ -279,19 +248,10 @@ def test_url_query_data_collection(

(server_span,) = [item.payload for item in items]

data_collection_enabled = "data_collection" in init_kwargs
url_attrs_expected = data_collection_enabled or init_kwargs.get(
"send_default_pii", False
)

if expected_query is None:
assert "url.query" not in server_span["attributes"]
if url_attrs_expected:
assert server_span["attributes"]["url.full"].endswith("/hi")
assert server_span["attributes"]["url.path"] == "/hi"
else:
assert "url.full" not in server_span["attributes"]
assert "url.path" not in server_span["attributes"]
assert server_span["attributes"]["url.full"].endswith("/hi")
assert server_span["attributes"]["url.path"] == "/hi"
else:
assert server_span["attributes"]["url.query"] == expected_query
assert server_span["attributes"]["url.full"].endswith(f"/hi?{expected_query}")
Expand Down Expand Up @@ -465,7 +425,17 @@ def test_request_body_data_collection_event_processor(
assert "data" not in event["request"]


@pytest.mark.parametrize("send_pii", [True, False])
@pytest.mark.parametrize(
"data_collection, expect_query",
[
pytest.param({}, True, id="data_collection_default"),
pytest.param(
{"url_query_params": {"mode": "off"}},
False,
id="data_collection_url_query_params_off",
),
],
)
@pytest.mark.parametrize(
"handler,code",
[
Expand All @@ -480,12 +450,13 @@ def test_transactions(
capture_items,
handler,
code,
send_pii,
data_collection,
expect_query,
):
sentry_init(
integrations=[TornadoIntegration()],
traces_sample_rate=1.0,
send_default_pii=send_pii,
data_collection=data_collection,
)

items = capture_items("event", "span")
Expand Down Expand Up @@ -533,15 +504,14 @@ def test_transactions(
assert server_segment["status"] == ("ok" if code == 200 else "error")
assert client_segment["trace_id"] == server_segment["trace_id"]

if send_pii:
assert server_segment["attributes"]["url.path"] == "/hi"
if expect_query:
assert server_segment["attributes"]["url.query"] == "foo=bar"
assert server_segment["attributes"]["url.full"].endswith("/hi?foo=bar")
assert server_segment["attributes"]["url.full"].startswith("http://")
assert server_segment["attributes"]["url.path"] == "/hi"
else:
assert "url.query" not in server_segment["attributes"]
assert "url.full" not in server_segment["attributes"]
assert "url.path" not in server_segment["attributes"]
assert server_segment["attributes"]["url.full"].endswith("/hi")


def test_400_not_logged(tornado_testcase, sentry_init, capture_events):
Expand All @@ -561,7 +531,10 @@ def get(self):


def test_user_auth(tornado_testcase, sentry_init, capture_events):
sentry_init(integrations=[TornadoIntegration()], send_default_pii=True)
sentry_init(
integrations=[TornadoIntegration()],
data_collection={"user_info": True},
)
events = capture_events()

class UserHandler(RequestHandler):
Expand Down Expand Up @@ -629,7 +602,7 @@ def get_current_user(self):


def test_formdata(tornado_testcase, sentry_init, capture_events):
sentry_init(integrations=[TornadoIntegration()], send_default_pii=True)
sentry_init(integrations=[TornadoIntegration()], data_collection={})
events = capture_events()

class FormdataHandler(RequestHandler):
Expand All @@ -654,7 +627,7 @@ def post(self):


def test_json(tornado_testcase, sentry_init, capture_events):
sentry_init(integrations=[TornadoIntegration()], send_default_pii=True)
sentry_init(integrations=[TornadoIntegration()], data_collection={})
events = capture_events()

class FormdataHandler(RequestHandler):
Expand Down
Loading