diff --git a/sentry_sdk/consts.py b/sentry_sdk/consts.py index a82ff94c49..ae8afecf57 100644 --- a/sentry_sdk/consts.py +++ b/sentry_sdk/consts.py @@ -3,7 +3,10 @@ from typing import TYPE_CHECKING # up top to prevent circular import due to integration import -DEFAULT_MAX_VALUE_LENGTH = 1024 +# This is more or less an arbitrary large-ish value for now, so that we allow +# pretty long strings (like LLM prompts), but still have *some* upper limit +# until we verify that removing the trimming completely is safe. +DEFAULT_MAX_VALUE_LENGTH = 100_000 DEFAULT_MAX_STACK_FRAMES = 100 DEFAULT_ADD_FULL_STACK = False diff --git a/tests/integrations/bottle/test_bottle.py b/tests/integrations/bottle/test_bottle.py index 363a9167e6..1965691d6c 100644 --- a/tests/integrations/bottle/test_bottle.py +++ b/tests/integrations/bottle/test_bottle.py @@ -5,6 +5,7 @@ from io import BytesIO from bottle import Bottle, debug as set_debug, abort, redirect, HTTPResponse from sentry_sdk import capture_message +from sentry_sdk.consts import DEFAULT_MAX_VALUE_LENGTH from sentry_sdk.integrations.bottle import BottleIntegration from sentry_sdk.serializer import MAX_DATABAG_BREADTH @@ -121,9 +122,9 @@ def index(): def test_large_json_request(sentry_init, capture_events, app, get_client): - sentry_init(integrations=[BottleIntegration()]) + sentry_init(integrations=[BottleIntegration()], max_request_body_size="always") - data = {"foo": {"bar": "a" * 2000}} + data = {"foo": {"bar": "a" * (DEFAULT_MAX_VALUE_LENGTH + 10)}} @app.route("/", method="POST") def index(): @@ -144,9 +145,14 @@ def index(): (event,) = events assert event["_meta"]["request"]["data"]["foo"]["bar"] == { - "": {"len": 2000, "rem": [["!limit", "x", 1021, 1024]]} + "": { + "len": DEFAULT_MAX_VALUE_LENGTH + 10, + "rem": [ + ["!limit", "x", DEFAULT_MAX_VALUE_LENGTH - 3, DEFAULT_MAX_VALUE_LENGTH] + ], + } } - assert len(event["request"]["data"]["foo"]["bar"]) == 1024 + assert len(event["request"]["data"]["foo"]["bar"]) == DEFAULT_MAX_VALUE_LENGTH @pytest.mark.parametrize("data", [{}, []], ids=["empty-dict", "empty-list"]) @@ -174,9 +180,9 @@ def index(): def test_medium_formdata_request(sentry_init, capture_events, app, get_client): - sentry_init(integrations=[BottleIntegration()]) + sentry_init(integrations=[BottleIntegration()], max_request_body_size="always") - data = {"foo": "a" * 2000} + data = {"foo": "a" * (DEFAULT_MAX_VALUE_LENGTH + 10)} @app.route("/", method="POST") def index(): @@ -194,9 +200,14 @@ def index(): (event,) = events assert event["_meta"]["request"]["data"]["foo"] == { - "": {"len": 2000, "rem": [["!limit", "x", 1021, 1024]]} + "": { + "len": DEFAULT_MAX_VALUE_LENGTH + 10, + "rem": [ + ["!limit", "x", DEFAULT_MAX_VALUE_LENGTH - 3, DEFAULT_MAX_VALUE_LENGTH] + ], + } } - assert len(event["request"]["data"]["foo"]) == 1024 + assert len(event["request"]["data"]["foo"]) == DEFAULT_MAX_VALUE_LENGTH @pytest.mark.parametrize("input_char", ["a", b"a"]) @@ -233,7 +244,10 @@ def index(): def test_files_and_form(sentry_init, capture_events, app, get_client): sentry_init(integrations=[BottleIntegration()], max_request_body_size="always") - data = {"foo": "a" * 2000, "file": (BytesIO(b"hello"), "hello.txt")} + data = { + "foo": "a" * (DEFAULT_MAX_VALUE_LENGTH + 10), + "file": (BytesIO(b"hello"), "hello.txt"), + } @app.route("/", method="POST") def index(): @@ -253,9 +267,14 @@ def index(): (event,) = events assert event["_meta"]["request"]["data"]["foo"] == { - "": {"len": 2000, "rem": [["!limit", "x", 1021, 1024]]} + "": { + "len": DEFAULT_MAX_VALUE_LENGTH + 10, + "rem": [ + ["!limit", "x", DEFAULT_MAX_VALUE_LENGTH - 3, DEFAULT_MAX_VALUE_LENGTH] + ], + } } - assert len(event["request"]["data"]["foo"]) == 1024 + assert len(event["request"]["data"]["foo"]) == DEFAULT_MAX_VALUE_LENGTH assert event["_meta"]["request"]["data"]["file"] == { "": { diff --git a/tests/integrations/falcon/test_falcon.py b/tests/integrations/falcon/test_falcon.py index 51a1d94334..f972419092 100644 --- a/tests/integrations/falcon/test_falcon.py +++ b/tests/integrations/falcon/test_falcon.py @@ -5,6 +5,7 @@ import falcon import falcon.testing import sentry_sdk +from sentry_sdk.consts import DEFAULT_MAX_VALUE_LENGTH from sentry_sdk.integrations.falcon import FalconIntegration from sentry_sdk.integrations.logging import LoggingIntegration from sentry_sdk.utils import parse_version @@ -207,9 +208,9 @@ def on_get(self, req, resp): def test_falcon_large_json_request(sentry_init, capture_events): - sentry_init(integrations=[FalconIntegration()]) + sentry_init(integrations=[FalconIntegration()], max_request_body_size="always") - data = {"foo": {"bar": "a" * 2000}} + data = {"foo": {"bar": "a" * (DEFAULT_MAX_VALUE_LENGTH + 10)}} class Resource: def on_post(self, req, resp): @@ -228,9 +229,14 @@ def on_post(self, req, resp): (event,) = events assert event["_meta"]["request"]["data"]["foo"]["bar"] == { - "": {"len": 2000, "rem": [["!limit", "x", 1021, 1024]]} + "": { + "len": DEFAULT_MAX_VALUE_LENGTH + 10, + "rem": [ + ["!limit", "x", DEFAULT_MAX_VALUE_LENGTH - 3, DEFAULT_MAX_VALUE_LENGTH] + ], + } } - assert len(event["request"]["data"]["foo"]["bar"]) == 1024 + assert len(event["request"]["data"]["foo"]["bar"]) == DEFAULT_MAX_VALUE_LENGTH @pytest.mark.parametrize("data", [{}, []], ids=["empty-dict", "empty-list"]) diff --git a/tests/integrations/flask/test_flask.py b/tests/integrations/flask/test_flask.py index 6febb12b8b..49ee684797 100644 --- a/tests/integrations/flask/test_flask.py +++ b/tests/integrations/flask/test_flask.py @@ -27,6 +27,7 @@ capture_message, capture_exception, ) +from sentry_sdk.consts import DEFAULT_MAX_VALUE_LENGTH from sentry_sdk.integrations.logging import LoggingIntegration from sentry_sdk.serializer import MAX_DATABAG_BREADTH @@ -248,9 +249,11 @@ def login(): def test_flask_large_json_request(sentry_init, capture_events, app): - sentry_init(integrations=[flask_sentry.FlaskIntegration()]) + sentry_init( + integrations=[flask_sentry.FlaskIntegration()], max_request_body_size="always" + ) - data = {"foo": {"bar": "a" * 2000}} + data = {"foo": {"bar": "a" * (DEFAULT_MAX_VALUE_LENGTH + 10)}} @app.route("/", methods=["POST"]) def index(): @@ -268,9 +271,14 @@ def index(): (event,) = events assert event["_meta"]["request"]["data"]["foo"]["bar"] == { - "": {"len": 2000, "rem": [["!limit", "x", 1021, 1024]]} + "": { + "len": DEFAULT_MAX_VALUE_LENGTH + 10, + "rem": [ + ["!limit", "x", DEFAULT_MAX_VALUE_LENGTH - 3, DEFAULT_MAX_VALUE_LENGTH] + ], + } } - assert len(event["request"]["data"]["foo"]["bar"]) == 1024 + assert len(event["request"]["data"]["foo"]["bar"]) == DEFAULT_MAX_VALUE_LENGTH def test_flask_session_tracking(sentry_init, capture_envelopes, app): @@ -336,9 +344,11 @@ def index(): def test_flask_medium_formdata_request(sentry_init, capture_events, app): - sentry_init(integrations=[flask_sentry.FlaskIntegration()]) + sentry_init( + integrations=[flask_sentry.FlaskIntegration()], max_request_body_size="always" + ) - data = {"foo": "a" * 2000} + data = {"foo": "a" * (DEFAULT_MAX_VALUE_LENGTH + 10)} @app.route("/", methods=["POST"]) def index(): @@ -360,9 +370,14 @@ def index(): (event,) = events assert event["_meta"]["request"]["data"]["foo"] == { - "": {"len": 2000, "rem": [["!limit", "x", 1021, 1024]]} + "": { + "len": DEFAULT_MAX_VALUE_LENGTH + 10, + "rem": [ + ["!limit", "x", DEFAULT_MAX_VALUE_LENGTH - 3, DEFAULT_MAX_VALUE_LENGTH] + ], + } } - assert len(event["request"]["data"]["foo"]) == 1024 + assert len(event["request"]["data"]["foo"]) == DEFAULT_MAX_VALUE_LENGTH def test_flask_formdata_request_appear_transaction_body( @@ -441,7 +456,10 @@ def test_flask_files_and_form(sentry_init, capture_events, app): integrations=[flask_sentry.FlaskIntegration()], max_request_body_size="always" ) - data = {"foo": "a" * 2000, "file": (BytesIO(b"hello"), "hello.txt")} + data = { + "foo": "a" * (DEFAULT_MAX_VALUE_LENGTH + 10), + "file": (BytesIO(b"hello"), "hello.txt"), + } @app.route("/", methods=["POST"]) def index(): @@ -463,9 +481,14 @@ def index(): (event,) = events assert event["_meta"]["request"]["data"]["foo"] == { - "": {"len": 2000, "rem": [["!limit", "x", 1021, 1024]]} + "": { + "len": DEFAULT_MAX_VALUE_LENGTH + 10, + "rem": [ + ["!limit", "x", DEFAULT_MAX_VALUE_LENGTH - 3, DEFAULT_MAX_VALUE_LENGTH] + ], + } } - assert len(event["request"]["data"]["foo"]) == 1024 + assert len(event["request"]["data"]["foo"]) == DEFAULT_MAX_VALUE_LENGTH assert event["_meta"]["request"]["data"]["file"] == {"": {"rem": [["!raw", "x"]]}} assert not event["request"]["data"]["file"] diff --git a/tests/integrations/pyramid/test_pyramid.py b/tests/integrations/pyramid/test_pyramid.py index d42d7887c4..cd200f7f7b 100644 --- a/tests/integrations/pyramid/test_pyramid.py +++ b/tests/integrations/pyramid/test_pyramid.py @@ -9,6 +9,7 @@ from werkzeug.test import Client from sentry_sdk import capture_message, add_breadcrumb +from sentry_sdk.consts import DEFAULT_MAX_VALUE_LENGTH from sentry_sdk.integrations.pyramid import PyramidIntegration from sentry_sdk.serializer import MAX_DATABAG_BREADTH from tests.conftest import unpack_werkzeug_response @@ -156,9 +157,9 @@ def test_transaction_style( def test_large_json_request(sentry_init, capture_events, route, get_client): - sentry_init(integrations=[PyramidIntegration()]) + sentry_init(integrations=[PyramidIntegration()], max_request_body_size="always") - data = {"foo": {"bar": "a" * 2000}} + data = {"foo": {"bar": "a" * (DEFAULT_MAX_VALUE_LENGTH + 10)}} @route("/") def index(request): @@ -175,9 +176,14 @@ def index(request): (event,) = events assert event["_meta"]["request"]["data"]["foo"]["bar"] == { - "": {"len": 2000, "rem": [["!limit", "x", 1021, 1024]]} + "": { + "len": DEFAULT_MAX_VALUE_LENGTH + 10, + "rem": [ + ["!limit", "x", DEFAULT_MAX_VALUE_LENGTH - 3, DEFAULT_MAX_VALUE_LENGTH] + ], + } } - assert len(event["request"]["data"]["foo"]["bar"]) == 1024 + assert len(event["request"]["data"]["foo"]["bar"]) == DEFAULT_MAX_VALUE_LENGTH @pytest.mark.parametrize("data", [{}, []], ids=["empty-dict", "empty-list"]) @@ -230,7 +236,10 @@ def index(request): def test_files_and_form(sentry_init, capture_events, route, get_client): sentry_init(integrations=[PyramidIntegration()], max_request_body_size="always") - data = {"foo": "a" * 2000, "file": (BytesIO(b"hello"), "hello.txt")} + data = { + "foo": "a" * (DEFAULT_MAX_VALUE_LENGTH + 10), + "file": (BytesIO(b"hello"), "hello.txt"), + } @route("/") def index(request): @@ -244,9 +253,14 @@ def index(request): (event,) = events assert event["_meta"]["request"]["data"]["foo"] == { - "": {"len": 2000, "rem": [["!limit", "x", 1021, 1024]]} + "": { + "len": DEFAULT_MAX_VALUE_LENGTH + 10, + "rem": [ + ["!limit", "x", DEFAULT_MAX_VALUE_LENGTH - 3, DEFAULT_MAX_VALUE_LENGTH] + ], + } } - assert len(event["request"]["data"]["foo"]) == 1024 + assert len(event["request"]["data"]["foo"]) == DEFAULT_MAX_VALUE_LENGTH assert event["_meta"]["request"]["data"]["file"] == {"": {"rem": [["!raw", "x"]]}} assert not event["request"]["data"]["file"] diff --git a/tests/integrations/sqlalchemy/test_sqlalchemy.py b/tests/integrations/sqlalchemy/test_sqlalchemy.py index 2b95fe02d4..d2a31a55d5 100644 --- a/tests/integrations/sqlalchemy/test_sqlalchemy.py +++ b/tests/integrations/sqlalchemy/test_sqlalchemy.py @@ -275,7 +275,12 @@ def processor(event, hint): # The _meta for other truncated fields should be there as well. assert event["_meta"]["message"] == { - "": {"len": 1034, "rem": [["!limit", "x", 1021, 1024]]} + "": { + "len": DEFAULT_MAX_VALUE_LENGTH + 10, + "rem": [ + ["!limit", "x", DEFAULT_MAX_VALUE_LENGTH - 3, DEFAULT_MAX_VALUE_LENGTH] + ], + } } diff --git a/tests/test_client.py b/tests/test_client.py index 9c6dbfe740..0468fcbb7b 100644 --- a/tests/test_client.py +++ b/tests/test_client.py @@ -773,14 +773,14 @@ def test_databag_string_stripping(sentry_init, capture_events, benchmark): def inner(): del events[:] try: - a = "A" * 1000000 # noqa + a = "A" * DEFAULT_MAX_VALUE_LENGTH * 10 # noqa 1 / 0 except Exception: capture_exception() (event,) = events - assert len(json.dumps(event)) < 10000 + assert len(json.dumps(event)) < DEFAULT_MAX_VALUE_LENGTH * 10 def test_databag_breadth_stripping(sentry_init, capture_events, benchmark): @@ -1073,7 +1073,10 @@ def test_multiple_positional_args(sentry_init): "sdk_options, expected_data_length", [ ({}, DEFAULT_MAX_VALUE_LENGTH), - ({"max_value_length": 1800}, 1800), + ( + {"max_value_length": DEFAULT_MAX_VALUE_LENGTH + 1000}, + DEFAULT_MAX_VALUE_LENGTH + 1000, + ), ], ) def test_max_value_length_option( @@ -1082,7 +1085,7 @@ def test_max_value_length_option( sentry_init(sdk_options) events = capture_events() - capture_message("a" * 2000) + capture_message("a" * (DEFAULT_MAX_VALUE_LENGTH + 2000)) assert len(events[0]["message"]) == expected_data_length diff --git a/tests/test_serializer.py b/tests/test_serializer.py index 2f158097bd..2f44ba8a08 100644 --- a/tests/test_serializer.py +++ b/tests/test_serializer.py @@ -2,6 +2,7 @@ import pytest +from sentry_sdk.consts import DEFAULT_MAX_VALUE_LENGTH from sentry_sdk.serializer import MAX_DATABAG_BREADTH, MAX_DATABAG_DEPTH, serialize try: @@ -166,11 +167,11 @@ def test_no_trimming_if_max_request_body_size_is_always(body_normalizer): def test_max_value_length_default(body_normalizer): - data = {"key": "a" * 2000} + data = {"key": "a" * (DEFAULT_MAX_VALUE_LENGTH * 10)} result = body_normalizer(data) - assert len(result["key"]) == 1024 # fallback max length + assert len(result["key"]) == DEFAULT_MAX_VALUE_LENGTH # fallback max length def test_max_value_length(body_normalizer):