Format span attributes in AI integrations

sentry_sdk/ai/utils.py

@@ -1,30 +1,33 @@
+import json
+
 from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
     from typing import Any
+    from sentry_sdk.tracing import Span
 
-from sentry_sdk.tracing import Span
 from sentry_sdk.utils import logger
 
 
 def _normalize_data(data, unpack=True):
     # type: (Any, bool) -> Any
-
     # convert pydantic data (e.g. OpenAI v1+) to json compatible format
     if hasattr(data, "model_dump"):
         try:
-            return data.model_dump()
+            return _normalize_data(data.model_dump(), unpack=unpack)
         except Exception as e:
             logger.warning("Could not convert pydantic data to JSON: %s", e)
-            return data
+            return data if isinstance(data, (int, float, bool, str)) else str(data)
+
     if isinstance(data, list):
         if unpack and len(data) == 1:
             return _normalize_data(data[0], unpack=unpack)  # remove empty dimensions
         return list(_normalize_data(x, unpack=unpack) for x in data)
+
     if isinstance(data, dict):
         return {k: _normalize_data(v, unpack=unpack) for (k, v) in data.items()}
 
-    return data
+    return data if isinstance(data, (int, float, bool, str)) else str(data)
 
 
 def set_data_normalized(span, key, value, unpack=True):
@@ -33,4 +36,4 @@ def set_data_normalized(span, key, value, unpack=True):
     if isinstance(normalized, (int, float, bool, str)):
         span.set_data(key, normalized)
     else:
-        span.set_data(key, str(normalized))
+        span.set_data(key, json.dumps(normalized))

tests/integrations/cohere/test_cohere.py

@@ -58,11 +58,11 @@ def test_nonstreaming_chat(
 
     if send_default_pii and include_prompts:
         assert (
-            "{'role': 'system', 'content': 'some context'}"
+            '{"role": "system", "content": "some context"}'
             in span["data"][SPANDATA.AI_INPUT_MESSAGES]
         )
         assert (
-            "{'role': 'user', 'content': 'hello'}"
+            '{"role": "user", "content": "hello"}'
             in span["data"][SPANDATA.AI_INPUT_MESSAGES]
         )
         assert "the model response" in span["data"][SPANDATA.AI_RESPONSES]
@@ -135,11 +135,11 @@ def test_streaming_chat(sentry_init, capture_events, send_default_pii, include_p
 
     if send_default_pii and include_prompts:
         assert (
-            "{'role': 'system', 'content': 'some context'}"
+            '{"role": "system", "content": "some context"}'
             in span["data"][SPANDATA.AI_INPUT_MESSAGES]
         )
         assert (
-            "{'role': 'user', 'content': 'hello'}"
+            '{"role": "user", "content": "hello"}'
             in span["data"][SPANDATA.AI_INPUT_MESSAGES]
         )
         assert "the model response" in span["data"][SPANDATA.AI_RESPONSES]