fix(ai): add mapping for gen_ai message roles

sentry_sdk/ai/__init__.py

@@ -0,0 +1,7 @@
+from .utils import (
+    set_data_normalized,
+    GEN_AI_MESSAGE_ROLE_MAPPING,
+    GEN_AI_MESSAGE_ROLE_REVERSE_MAPPING,
+    normalize_message_role,
+    normalize_message_roles,
+)  # noqa: F401

sentry_sdk/ai/utils.py

@@ -10,6 +10,26 @@
 from sentry_sdk.utils import logger
 
 
+class GEN_AI_ALLOWED_MESSAGE_ROLES:
+    SYSTEM = "system"
+    USER = "user"
+    ASSISTANT = "assistant"
+    TOOL_CALL = "tool"
+
+
+GEN_AI_MESSAGE_ROLE_REVERSE_MAPPING = {
+    GEN_AI_ALLOWED_MESSAGE_ROLES.SYSTEM: ["system"],
+    GEN_AI_ALLOWED_MESSAGE_ROLES.USER: ["user", "human"],
+    GEN_AI_ALLOWED_MESSAGE_ROLES.ASSISTANT: ["assistant", "ai"],
+    GEN_AI_ALLOWED_MESSAGE_ROLES.TOOL_CALL: ["tool", "tool_call"],
+}
+
+GEN_AI_MESSAGE_ROLE_MAPPING = {}
+for target_role, source_roles in GEN_AI_MESSAGE_ROLE_REVERSE_MAPPING.items():
+    for source_role in source_roles:
+        GEN_AI_MESSAGE_ROLE_MAPPING[source_role] = target_role
+
+
 def _normalize_data(data, unpack=True):
     # type: (Any, bool) -> Any
     # convert pydantic data (e.g. OpenAI v1+) to json compatible format
@@ -40,6 +60,34 @@ def set_data_normalized(span, key, value, unpack=True):
         span.set_data(key, json.dumps(normalized))
 
 
+def normalize_message_role(role):
+    # type: (str) -> str
+    """
+    Normalize a message role to one of the 4 allowed gen_ai role values.
+    Maps "ai" -> "assistant" and keeps other standard roles unchanged.
+    """
+    return GEN_AI_MESSAGE_ROLE_MAPPING.get(role, role)
+
+
+def normalize_message_roles(messages):
+    # type: (list[dict[str, Any]]) -> list[dict[str, Any]]
+    """
+    Normalize roles in a list of messages to use standard gen_ai role values.
+    Creates a deep copy to avoid modifying the original messages.
+    """
+    normalized_messages = []
+    for message in messages:
+        if not isinstance(message, dict):
+            normalized_messages.append(message)
+            continue
+        normalized_message = message.copy()
+        if "role" in message:
+            normalized_message["role"] = normalize_message_role(message["role"])
+        normalized_messages.append(normalized_message)
+
+    return normalized_messages
+
+
 def get_start_span_function():
     # type: () -> Callable[..., Any]
     current_span = sentry_sdk.get_current_span()

sentry_sdk/integrations/anthropic.py

@@ -3,7 +3,11 @@
 
 import sentry_sdk
 from sentry_sdk.ai.monitoring import record_token_usage
-from sentry_sdk.ai.utils import set_data_normalized, get_start_span_function
+from sentry_sdk.ai.utils import (
+    set_data_normalized,
+    normalize_message_roles,
+    get_start_span_function,
+)
 from sentry_sdk.consts import OP, SPANDATA, SPANSTATUS
 from sentry_sdk.integrations import _check_minimum_version, DidNotEnable, Integration
 from sentry_sdk.scope import should_send_default_pii
@@ -140,8 +144,12 @@ def _set_input_data(span, kwargs, integration):
             else:
                 normalized_messages.append(message)
 
+        role_normalized_messages = normalize_message_roles(normalized_messages)
         set_data_normalized(
-            span, SPANDATA.GEN_AI_REQUEST_MESSAGES, normalized_messages, unpack=False
+            span,
+            SPANDATA.GEN_AI_REQUEST_MESSAGES,
+            role_normalized_messages,
+            unpack=False,
         )
 
     set_data_normalized(

sentry_sdk/integrations/langchain.py

@@ -4,7 +4,12 @@
 
 import sentry_sdk
 from sentry_sdk.ai.monitoring import set_ai_pipeline_name
-from sentry_sdk.ai.utils import set_data_normalized, get_start_span_function
+from sentry_sdk.ai.utils import (
+    GEN_AI_ALLOWED_MESSAGE_ROLES,
+    normalize_message_roles,
+    set_data_normalized,
+    get_start_span_function,
+)
 from sentry_sdk.consts import OP, SPANDATA
 from sentry_sdk.integrations import DidNotEnable, Integration
 from sentry_sdk.scope import should_send_default_pii
@@ -209,8 +214,18 @@ def on_llm_start(
             _set_tools_on_span(span, all_params.get("tools"))
 
             if should_send_default_pii() and self.include_prompts:
+                normalized_messages = [
+                    {
+                        "role": GEN_AI_ALLOWED_MESSAGE_ROLES.USER,
+                        "content": {"type": "text", "text": prompt},
+                    }
+                    for prompt in prompts
+                ]
                 set_data_normalized(
-                    span, SPANDATA.GEN_AI_REQUEST_MESSAGES, prompts, unpack=False
+                    span,
+                    SPANDATA.GEN_AI_REQUEST_MESSAGES,
+                    normalized_messages,
+                    unpack=False,
                 )
 
     def on_chat_model_start(self, serialized, messages, *, run_id, **kwargs):
@@ -262,6 +277,8 @@ def on_chat_model_start(self, serialized, messages, *, run_id, **kwargs):
                         normalized_messages.append(
                             self._normalize_langchain_message(message)
                         )
+                normalized_messages = normalize_message_roles(normalized_messages)
+
                 set_data_normalized(
                     span,
                     SPANDATA.GEN_AI_REQUEST_MESSAGES,
@@ -740,8 +757,12 @@ def new_invoke(self, *args, **kwargs):
                 and should_send_default_pii()
                 and integration.include_prompts
             ):
+                normalized_messages = normalize_message_roles([input])
                 set_data_normalized(
-                    span, SPANDATA.GEN_AI_REQUEST_MESSAGES, [input], unpack=False
+                    span,
+                    SPANDATA.GEN_AI_REQUEST_MESSAGES,
+                    normalized_messages,
+                    unpack=False,
                 )
 
             output = result.get("output")
@@ -791,8 +812,12 @@ def new_stream(self, *args, **kwargs):
             and should_send_default_pii()
             and integration.include_prompts
         ):
+            normalized_messages = normalize_message_roles([input])
             set_data_normalized(
-                span, SPANDATA.GEN_AI_REQUEST_MESSAGES, [input], unpack=False
+                span,
+                SPANDATA.GEN_AI_REQUEST_MESSAGES,
+                normalized_messages,
+                unpack=False,
             )
 
         # Run the agent

sentry_sdk/integrations/langgraph.py

@@ -2,7 +2,7 @@
 from typing import Any, Callable, List, Optional
 
 import sentry_sdk
-from sentry_sdk.ai.utils import set_data_normalized
+from sentry_sdk.ai.utils import set_data_normalized, normalize_message_roles
 from sentry_sdk.consts import OP, SPANDATA
 from sentry_sdk.integrations import DidNotEnable, Integration
 from sentry_sdk.scope import should_send_default_pii
@@ -180,10 +180,11 @@ def new_invoke(self, *args, **kwargs):
             ):
                 input_messages = _parse_langgraph_messages(args[0])
                 if input_messages:
+                    normalized_input_messages = normalize_message_roles(input_messages)
                     set_data_normalized(
                         span,
                         SPANDATA.GEN_AI_REQUEST_MESSAGES,
-                        input_messages,
+                        normalized_input_messages,
                         unpack=False,
                     )
 
@@ -230,10 +231,11 @@ async def new_ainvoke(self, *args, **kwargs):
             ):
                 input_messages = _parse_langgraph_messages(args[0])
                 if input_messages:
+                    normalized_input_messages = normalize_message_roles(input_messages)
                     set_data_normalized(
                         span,
                         SPANDATA.GEN_AI_REQUEST_MESSAGES,
-                        input_messages,
+                        normalized_input_messages,
                         unpack=False,
                     )
 

sentry_sdk/integrations/openai.py

@@ -3,7 +3,7 @@
 import sentry_sdk
 from sentry_sdk import consts
 from sentry_sdk.ai.monitoring import record_token_usage
-from sentry_sdk.ai.utils import set_data_normalized
+from sentry_sdk.ai.utils import set_data_normalized, normalize_message_roles
 from sentry_sdk.consts import SPANDATA
 from sentry_sdk.integrations import DidNotEnable, Integration
 from sentry_sdk.scope import should_send_default_pii
@@ -182,8 +182,9 @@ def _set_input_data(span, kwargs, operation, integration):
         and should_send_default_pii()
         and integration.include_prompts
     ):
+        normalized_messages = normalize_message_roles(messages)
         set_data_normalized(
-            span, SPANDATA.GEN_AI_REQUEST_MESSAGES, messages, unpack=False
+            span, SPANDATA.GEN_AI_REQUEST_MESSAGES, normalized_messages, unpack=False
         )
 
     # Input attributes: Common

sentry_sdk/integrations/openai_agents/spans/invoke_agent.py

@@ -1,5 +1,9 @@
 import sentry_sdk
-from sentry_sdk.ai.utils import get_start_span_function, set_data_normalized
+from sentry_sdk.ai.utils import (
+    get_start_span_function,
+    set_data_normalized,
+    normalize_message_roles,
+)
 from sentry_sdk.consts import OP, SPANDATA
 from sentry_sdk.scope import should_send_default_pii
 from sentry_sdk.utils import safe_serialize
@@ -56,8 +60,12 @@ def invoke_agent_span(context, agent, kwargs):
             )
 
         if len(messages) > 0:
+            normalized_messages = normalize_message_roles(messages)
             set_data_normalized(
-                span, SPANDATA.GEN_AI_REQUEST_MESSAGES, messages, unpack=False
+                span,
+                SPANDATA.GEN_AI_REQUEST_MESSAGES,
+                normalized_messages,
+                unpack=False,
             )
 
     _set_agent_data(span, agent)

sentry_sdk/integrations/openai_agents/utils.py

@@ -1,5 +1,10 @@
 import sentry_sdk
-from sentry_sdk.ai.utils import set_data_normalized
+from sentry_sdk.ai.utils import (
+    GEN_AI_ALLOWED_MESSAGE_ROLES,
+    normalize_message_roles,
+    set_data_normalized,
+    normalize_message_role,
+)
 from sentry_sdk.consts import SPANDATA, SPANSTATUS, OP
 from sentry_sdk.integrations import DidNotEnable
 from sentry_sdk.scope import should_send_default_pii
@@ -94,35 +99,47 @@ def _set_input_data(span, get_response_kwargs):
     # type: (sentry_sdk.tracing.Span, dict[str, Any]) -> None
     if not should_send_default_pii():
         return
+    request_messages = []
 
-    messages_by_role = {
-        "system": [],
-        "user": [],
-        "assistant": [],
-        "tool": [],
-    }  # type: (dict[str, list[Any]])
     system_instructions = get_response_kwargs.get("system_instructions")
     if system_instructions:
-        messages_by_role["system"].append({"type": "text", "text": system_instructions})
+        request_messages.append(
+            {
+                "role": GEN_AI_ALLOWED_MESSAGE_ROLES.SYSTEM,
+                "content": [{"type": "text", "text": system_instructions}],
+            }
+        )
 
     for message in get_response_kwargs.get("input", []):
         if "role" in message:
-            messages_by_role[message.get("role")].append(
-                {"type": "text", "text": message.get("content")}
+            normalized_role = normalize_message_role(message.get("role"))
+            request_messages.append(
+                {
+                    "role": normalized_role,
+                    "content": [{"type": "text", "text": message.get("content")}],
+                }
             )
         else:
             if message.get("type") == "function_call":
-                messages_by_role["assistant"].append(message)
+                request_messages.append(
+                    {
+                        "role": GEN_AI_ALLOWED_MESSAGE_ROLES.ASSISTANT,
+                        "content": [message],
+                    }
+                )
             elif message.get("type") == "function_call_output":
-                messages_by_role["tool"].append(message)
-
-    request_messages = []
-    for role, messages in messages_by_role.items():
-        if len(messages) > 0:
-            request_messages.append({"role": role, "content": messages})
+                request_messages.append(
+                    {
+                        "role": GEN_AI_ALLOWED_MESSAGE_ROLES.TOOL_CALL,
+                        "content": [message],
+                    }
+                )
 
     set_data_normalized(
-        span, SPANDATA.GEN_AI_REQUEST_MESSAGES, request_messages, unpack=False
+        span,
+        SPANDATA.GEN_AI_REQUEST_MESSAGES,
+        normalize_message_roles(request_messages),
+        unpack=False,
     )