Span data is always be a primitive data type (#4643)

The AI Agent insights module excepts the data not to be lists, tuples,
or dicts. Make sure that we always send a string in this case.

Author: antonpirker

sentry_sdk/ai/utils.py

@@ -23,10 +23,14 @@ def _normalize_data(data):
         return list(_normalize_data(x) for x in data)
     if isinstance(data, dict):
         return {k: _normalize_data(v) for (k, v) in data.items()}
+
     return data
 
 
 def set_data_normalized(span, key, value):
     # type: (Span, str, Any) -> None
     normalized = _normalize_data(value)
-    span.set_data(key, normalized)
+    if isinstance(normalized, (int, float, bool, str)):
+        span.set_data(key, normalized)
+    else:
+        span.set_data(key, str(normalized))

tests/integrations/cohere/test_cohere.py

@@ -57,8 +57,14 @@ def test_nonstreaming_chat(
     assert span["data"][SPANDATA.AI_MODEL_ID] == "some-model"
 
     if send_default_pii and include_prompts:
-        assert "some context" in span["data"][SPANDATA.AI_INPUT_MESSAGES][0]["content"]
-        assert "hello" in span["data"][SPANDATA.AI_INPUT_MESSAGES][1]["content"]
+        assert (
+            "{'role': 'system', 'content': 'some context'}"
+            in span["data"][SPANDATA.AI_INPUT_MESSAGES]
+        )
+        assert (
+            "{'role': 'user', 'content': 'hello'}"
+            in span["data"][SPANDATA.AI_INPUT_MESSAGES]
+        )
         assert "the model response" in span["data"][SPANDATA.AI_RESPONSES]
     else:
         assert SPANDATA.AI_INPUT_MESSAGES not in span["data"]
@@ -128,8 +134,14 @@ def test_streaming_chat(sentry_init, capture_events, send_default_pii, include_p
     assert span["data"][SPANDATA.AI_MODEL_ID] == "some-model"
 
     if send_default_pii and include_prompts:
-        assert "some context" in span["data"][SPANDATA.AI_INPUT_MESSAGES][0]["content"]
-        assert "hello" in span["data"][SPANDATA.AI_INPUT_MESSAGES][1]["content"]
+        assert (
+            "{'role': 'system', 'content': 'some context'}"
+            in span["data"][SPANDATA.AI_INPUT_MESSAGES]
+        )
+        assert (
+            "{'role': 'user', 'content': 'hello'}"
+            in span["data"][SPANDATA.AI_INPUT_MESSAGES]
+        )
         assert "the model response" in span["data"][SPANDATA.AI_RESPONSES]
     else:
         assert SPANDATA.AI_INPUT_MESSAGES not in span["data"]

tests/integrations/langchain/test_langchain.py

@@ -196,15 +196,13 @@ def test_langchain_agent(
 
     if send_default_pii and include_prompts:
         assert (
-            "You are very powerful"
-            in chat_spans[0]["data"][SPANDATA.AI_INPUT_MESSAGES][0]["content"]
+            "You are very powerful" in chat_spans[0]["data"][SPANDATA.AI_INPUT_MESSAGES]
         )
         assert "5" in chat_spans[0]["data"][SPANDATA.AI_RESPONSES]
         assert "word" in tool_exec_span["data"][SPANDATA.AI_INPUT_MESSAGES]
         assert 5 == int(tool_exec_span["data"][SPANDATA.AI_RESPONSES])
         assert (
-            "You are very powerful"
-            in chat_spans[1]["data"][SPANDATA.AI_INPUT_MESSAGES][0]["content"]
+            "You are very powerful" in chat_spans[1]["data"][SPANDATA.AI_INPUT_MESSAGES]
         )
         assert "5" in chat_spans[1]["data"][SPANDATA.AI_RESPONSES]
     else:

tests/integrations/openai/test_openai.py

@@ -1,4 +1,3 @@
-import json
 import pytest
 from openai import AsyncOpenAI, OpenAI, AsyncStream, Stream, OpenAIError
 from openai.types import CompletionUsage, CreateEmbeddingResponse, Embedding
@@ -144,11 +143,8 @@ def test_nonstreaming_chat_completion(
     assert span["op"] == "gen_ai.chat"
 
     if send_default_pii and include_prompts:
-        assert "hello" in span["data"][SPANDATA.GEN_AI_REQUEST_MESSAGES]["content"]
-        assert (
-            "the model response"
-            in json.loads(span["data"][SPANDATA.GEN_AI_RESPONSE_TEXT])[0]["content"]
-        )
+        assert "hello" in span["data"][SPANDATA.GEN_AI_REQUEST_MESSAGES]
+        assert "the model response" in span["data"][SPANDATA.GEN_AI_RESPONSE_TEXT]
     else:
         assert SPANDATA.GEN_AI_REQUEST_MESSAGES not in span["data"]
         assert SPANDATA.GEN_AI_RESPONSE_TEXT not in span["data"]
@@ -189,11 +185,8 @@ async def test_nonstreaming_chat_completion_async(
     assert span["op"] == "gen_ai.chat"
 
     if send_default_pii and include_prompts:
-        assert "hello" in span["data"][SPANDATA.GEN_AI_REQUEST_MESSAGES]["content"]
-        assert (
-            "the model response"
-            in json.loads(span["data"][SPANDATA.GEN_AI_RESPONSE_TEXT])[0]["content"]
-        )
+        assert "hello" in span["data"][SPANDATA.GEN_AI_REQUEST_MESSAGES]
+        assert "the model response" in span["data"][SPANDATA.GEN_AI_RESPONSE_TEXT]
     else:
         assert SPANDATA.GEN_AI_REQUEST_MESSAGES not in span["data"]
         assert SPANDATA.GEN_AI_RESPONSE_TEXT not in span["data"]
@@ -285,7 +278,7 @@ def test_streaming_chat_completion(
     assert span["op"] == "gen_ai.chat"
 
     if send_default_pii and include_prompts:
-        assert "hello" in span["data"][SPANDATA.GEN_AI_REQUEST_MESSAGES]["content"]
+        assert "hello" in span["data"][SPANDATA.GEN_AI_REQUEST_MESSAGES]
         assert "hello world" in span["data"][SPANDATA.GEN_AI_RESPONSE_TEXT]
     else:
         assert SPANDATA.GEN_AI_REQUEST_MESSAGES not in span["data"]
@@ -381,7 +374,7 @@ async def test_streaming_chat_completion_async(
     assert span["op"] == "gen_ai.chat"
 
     if send_default_pii and include_prompts:
-        assert "hello" in span["data"][SPANDATA.GEN_AI_REQUEST_MESSAGES]["content"]
+        assert "hello" in span["data"][SPANDATA.GEN_AI_REQUEST_MESSAGES]
         assert "hello world" in span["data"][SPANDATA.GEN_AI_RESPONSE_TEXT]
     else:
         assert SPANDATA.GEN_AI_REQUEST_MESSAGES not in span["data"]