From d322e772f0d4625da563699f1447e69b13ca0f3c Mon Sep 17 00:00:00 2001
From: "Jugal D. Bhatt" <55304795+jugaldb@users.noreply.github.com>
Date: Wed, 2 Jul 2025 09:12:36 +0530
Subject: [PATCH] Litellm add sentry scrubbing (#12210)

* add sentry scrubbing

* add new constants

* remove_unused_import

* sentry scrubbing test

* added unit test
---
 litellm/constants.py                          | 26 ++++++++++++++
 litellm/litellm_core_utils/litellm_logging.py | 11 ++++++
 .../test_litellm_logging.py                   | 35 +++++++++++++++++++
 3 files changed, 72 insertions(+)

diff --git a/litellm/constants.py b/litellm/constants.py
index 4ee28adff93..c883336274d 100644
--- a/litellm/constants.py
+++ b/litellm/constants.py
@@ -803,3 +803,29 @@ SPECIAL_LITELLM_AUTH_TOKEN = ["ui-token"]
 DEFAULT_MANAGEMENT_OBJECT_IN_MEMORY_CACHE_TTL = int(
     os.getenv("DEFAULT_MANAGEMENT_OBJECT_IN_MEMORY_CACHE_TTL", 60)
 )
+
+# Sentry Scrubbing Configuration
+SENTRY_DENYLIST = [
+    # API Keys and Tokens
+    "api_key", "token", "key", "secret", "password", "auth", "credential",
+    "OPENAI_API_KEY", "ANTHROPIC_API_KEY", "AZURE_API_KEY", "COHERE_API_KEY",
+    "REPLICATE_API_KEY", "HUGGINGFACE_API_KEY", "TOGETHERAI_API_KEY",
+    "CLOUDFLARE_API_KEY", "BASETEN_KEY", "OPENROUTER_KEY", "DATAROBOT_API_TOKEN",
+    "FIREWORKS_API_KEY", "FIREWORKS_AI_API_KEY", "FIREWORKSAI_API_KEY",
+    # Database and Connection Strings
+    "database_url", "redis_url", "connection_string",
+    # Authentication and Security
+    "master_key", "LITELLM_MASTER_KEY", "auth_token", "jwt_token", "private_key",
+    "SLACK_WEBHOOK_URL", "webhook_url", "LANGFUSE_SECRET_KEY",
+    # Email Configuration
+    "SMTP_PASSWORD", "SMTP_USERNAME", "email_password",
+    # Cloud Provider Credentials
+    "aws_access_key", "aws_secret_key", "gcp_credentials",
+    "azure_credentials", "HCP_VAULT_TOKEN", "CIRCLE_OIDC_TOKEN",
+    # Proxy and Environment Settings
+    "proxy_url", "proxy_key", "environment_variables"
+]
+SENTRY_PII_DENYLIST = [
+    "user_id", "email", "phone", "address", "ip_address",
+    "SMTP_SENDER_EMAIL", "TEST_EMAIL_ADDRESS"
+]
\ No newline at end of file
diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py
index 88c39a665aa..f7be8b1bb5c 100644
--- a/litellm/litellm_core_utils/litellm_logging.py
+++ b/litellm/litellm_core_utils/litellm_logging.py
@@ -44,6 +44,8 @@ from litellm.caching.caching_handler import LLMCachingHandler
 from litellm.constants import (
     DEFAULT_MOCK_RESPONSE_COMPLETION_TOKEN_COUNT,
     DEFAULT_MOCK_RESPONSE_PROMPT_TOKEN_COUNT,
+    SENTRY_DENYLIST,
+    SENTRY_PII_DENYLIST,
 )
 from litellm.cost_calculator import (
     RealtimeAPITokenUsageProcessor,
@@ -2949,6 +2951,10 @@ def set_callbacks(callback_list, function_id=None):  # noqa: PLR0915
                         [sys.executable, "-m", "pip", "install", "sentry_sdk"]
                     )
                     import sentry_sdk
+                from sentry_sdk.scrubber import EventScrubber
+
+                
+
                 sentry_sdk_instance = sentry_sdk
                 sentry_trace_rate = (
                     os.environ.get("SENTRY_API_TRACE_RATE")
@@ -2966,6 +2972,11 @@ def set_callbacks(callback_list, function_id=None):  # noqa: PLR0915
                     sample_rate=float(
                         sentry_sample_rate if sentry_sample_rate else 1.0
                     ),
+                    send_default_pii=False,  # Prevent sending Personal Identifiable Information
+                    event_scrubber=EventScrubber(
+                        denylist=SENTRY_DENYLIST,
+                        pii_denylist=SENTRY_PII_DENYLIST
+                    ),
                 )
                 capture_exception = sentry_sdk_instance.capture_exception
                 add_breadcrumb = sentry_sdk_instance.add_breadcrumb
diff --git a/tests/test_litellm/litellm_core_utils/test_litellm_logging.py b/tests/test_litellm/litellm_core_utils/test_litellm_logging.py
index be51a1cce7a..d4512b16714 100644
--- a/tests/test_litellm/litellm_core_utils/test_litellm_logging.py
+++ b/tests/test_litellm/litellm_core_utils/test_litellm_logging.py
@@ -13,6 +13,7 @@ import time
 
 from litellm.litellm_core_utils.litellm_logging import Logging as LitellmLogging
 from litellm.litellm_core_utils.litellm_logging import set_callbacks
+from litellm.constants import SENTRY_DENYLIST, SENTRY_PII_DENYLIST
 
 
 @pytest.fixture
@@ -309,3 +310,37 @@ def test_response_cost_calculator_with_response_cost_in_hidden_params(logging_ob
 
     assert response_cost is not None
     assert response_cost > 100
+
+
+def test_sentry_event_scrubber_initialization(monkeypatch):
+    # Step 1: Create a fake sentry_sdk.scrubber module
+    mock_event_scrubber_instance = MagicMock()
+    mock_event_scrubber_cls = MagicMock(return_value=mock_event_scrubber_instance)
+
+    mock_scrubber_module = MagicMock()
+    mock_scrubber_module.EventScrubber = mock_event_scrubber_cls
+
+    # Step 2: Create a fake sentry_sdk module and insert into sys.modules
+    mock_sentry_sdk = MagicMock()
+    mock_sentry_sdk.scrubber = mock_scrubber_module
+    mock_init = MagicMock()
+    mock_sentry_sdk.init = mock_init
+
+    # Step 3: Inject both into sys.modules BEFORE import occurs
+    sys.modules["sentry_sdk"] = mock_sentry_sdk
+    sys.modules["sentry_sdk.scrubber"] = mock_scrubber_module
+
+    # Step 4: Run the actual sentry setup code
+    set_callbacks(["sentry"])
+
+    # Step 5: Assert the EventScrubber was constructed correctly
+    mock_event_scrubber_cls.assert_called_once_with(
+        denylist=SENTRY_DENYLIST,
+        pii_denylist=SENTRY_PII_DENYLIST,
+    )
+
+    # Step 6: Assert the event_scrubber and PII args were passed
+    mock_init.assert_called_once()
+    call_args = mock_init.call_args[1]
+    assert call_args["event_scrubber"] == mock_event_scrubber_instance
+    assert call_args["send_default_pii"] is False
\ No newline at end of file