test: expect flattened metadata keys for v5 (#2001)

Co-authored-by: Cursor Agent <cursoragent@cursor.com>

Author: hassiebp

tests/e2e/test_core_sdk.py

@@ -360,13 +360,6 @@ def test_create_text_score():
     )
 
 
-@pytest.mark.xfail(
-    strict=False,
-    reason=(
-        "Needs the Langfuse platform release that adds timestamp to POST /scores "
-        "(langfuse prep-js-v6-py-v5-sdk-majors). Remove this marker once it ships."
-    ),
-)
 def test_create_score_with_custom_timestamp():
     langfuse = Langfuse()
 

tests/e2e/test_decorators.py

@@ -1114,7 +1114,7 @@ def main():
             in (trace.output or {}).get("context", {}).get("nested", "")
             and any(
                 "@@@langfuseMedia:type=application/pdf|id="
-                in observation.metadata.get("context", {}).get("nested", "")
+                in observation.metadata.get("context.nested", "")
                 for observation in trace.observations
                 if observation.metadata
             )
@@ -1133,10 +1133,10 @@ def main():
     observation = trace_data.observations[0]
     assert (
         "@@@langfuseMedia:type=application/pdf|id="
-        in observation.metadata["context"]["nested"]
+        in observation.metadata["context.nested"]
     )
     parsed_reference_string = LangfuseMedia.parse_reference_string(
-        observation.metadata["context"]["nested"]
+        observation.metadata["context.nested"]
     )
     assert parsed_reference_string["content_type"] == "application/pdf"
     assert parsed_reference_string["media_id"] is not None

tests/e2e/test_media.py

@@ -35,14 +35,14 @@ def test_replace_media_reference_string_in_object():
         is_result_ready=lambda observations: (
             re.match(
                 r"^@@@langfuseMedia:type=audio/wav\|id=.+\|source=base64_data_uri@@@$",
-                observations[0].metadata.get("context", {}).get("nested", ""),
+                observations[0].metadata.get("context.nested", ""),
             )
             is not None
         ),
     )
     assert len(fetched_observations) == 1
     fetched_observation = fetched_observations[0]
-    media_ref = fetched_observation.metadata["context"]["nested"]
+    media_ref = fetched_observation.metadata["context.nested"]
     assert re.match(
         r"^@@@langfuseMedia:type=audio/wav\|id=.+\|source=base64_data_uri@@@$",
         media_ref,
@@ -53,20 +53,20 @@ def test_replace_media_reference_string_in_object():
     )
 
     expected_base64 = f"data:audio/wav;base64,{base64_audio}"
-    assert resolved_obs["metadata"]["context"]["nested"] == expected_base64
+    assert resolved_obs["metadata"]["context.nested"] == expected_base64
 
     span2 = langfuse.start_observation(
         name=f"2-{mock_trace_name}",
-        metadata={"context": {"nested": resolved_obs["metadata"]["context"]["nested"]}},
+        metadata={"context": {"nested": resolved_obs["metadata"]["context.nested"]}},
     ).end()
 
     langfuse.flush()
 
     fetched_observations2 = wait_for_observations(
         span2.trace_id,
         is_result_ready=lambda observations: (
-            observations[0].metadata.get("context", {}).get("nested") == media_ref
+            observations[0].metadata.get("context.nested") == media_ref
         ),
     )
     assert len(fetched_observations2) == 1
-    assert fetched_observations2[0].metadata["context"]["nested"] == media_ref
+    assert fetched_observations2[0].metadata["context.nested"] == media_ref

tests/live_provider/test_openai.py

@@ -999,17 +999,13 @@ def test_structured_output_response_format_kwarg(openai):
 
     langfuse.flush()
 
-    generation = wait_for_observations(
-        name=generation_name, type="GENERATION", expand_metadata="response_format"
-    )
+    generation = wait_for_observations(name=generation_name, type="GENERATION")
 
     assert len(generation) != 0
     assert generation[0].name == generation_name
     assert generation[0].metadata["someKey"] == "someResponse"
-    assert generation[0].metadata["response_format"] == {
-        "type": "json_schema",
-        "json_schema": json_schema,
-    }
+    assert generation[0].metadata["response_format.type"] == "json_schema"
+    assert generation[0].metadata["response_format.json_schema.name"] == "math_response"
 
     assert generation[0].input == [
         {"role": "system", "content": "You are a helpful math tutor."},