[OPIK-571] error tracking sdk add e 2 e tests for traces spans with e…

…rrors (#907)

* Implement e2e tests for error_info

* Fix lint errors

sdks/python/tests/e2e/test_tracing.py

@@ -7,6 +7,8 @@
 from . import verifiers
 from .conftest import OPIK_E2E_TESTS_PROJECT_NAME
 
+from ..testlib import ANY_STRING
+
 
 @pytest.mark.parametrize(
     "project_name",
@@ -85,6 +87,142 @@ def f_inner(y):
     )
 
 
+def test_tracked_function__error_inside_inner_function__caugth_in_top_level_span__inner_span_has_error_info(
+    opik_client,
+):
+    # Setup
+    ID_STORAGE = {}
+
+    @opik.track
+    def f_inner(y):
+        ID_STORAGE["f_inner-span-id"] = opik_context.get_current_span_data().id
+        raise ValueError("inner span error message")
+
+    @opik.track
+    def f_outer(x):
+        ID_STORAGE["f_outer-trace-id"] = opik_context.get_current_trace_data().id
+        ID_STORAGE["f_outer-span-id"] = opik_context.get_current_span_data().id
+
+        try:
+            f_inner("inner-input")
+        except Exception:
+            pass
+
+        return "outer-output"
+
+    # Call
+    f_outer("outer-input")
+    opik.flush_tracker()
+
+    # Verify trace
+    verifiers.verify_trace(
+        opik_client=opik_client,
+        trace_id=ID_STORAGE["f_outer-trace-id"],
+        name="f_outer",
+        input={"x": "outer-input"},
+        output={"output": "outer-output"},
+        error_info=None,
+    )
+
+    # Verify top level span
+    verifiers.verify_span(
+        opik_client=opik_client,
+        span_id=ID_STORAGE["f_outer-span-id"],
+        parent_span_id=None,
+        trace_id=ID_STORAGE["f_outer-trace-id"],
+        name="f_outer",
+        input={"x": "outer-input"},
+        output={"output": "outer-output"},
+    )
+
+    # Verify nested span
+    verifiers.verify_span(
+        opik_client=opik_client,
+        span_id=ID_STORAGE["f_inner-span-id"],
+        parent_span_id=ID_STORAGE["f_outer-span-id"],
+        trace_id=ID_STORAGE["f_outer-trace-id"],
+        name="f_inner",
+        input={"y": "inner-input"},
+        output=None,
+        error_info={
+            "exception_type": "ValueError",
+            "message": "inner span error message",
+            "traceback": ANY_STRING(),
+        },
+    )
+
+
+def test_tracked_function__error_inside_inner_function__error_not_caugth__trace_and_its_spans_have_error_info(
+    opik_client,
+):
+    # Setup
+    ID_STORAGE = {}
+
+    @opik.track
+    def f_inner(y):
+        ID_STORAGE["f_inner-span-id"] = opik_context.get_current_span_data().id
+        raise ValueError("inner span error message")
+
+    @opik.track
+    def f_outer(x):
+        ID_STORAGE["f_outer-trace-id"] = opik_context.get_current_trace_data().id
+        ID_STORAGE["f_outer-span-id"] = opik_context.get_current_span_data().id
+
+        f_inner("inner-input")
+
+    # Call
+    with pytest.raises(ValueError):
+        f_outer("outer-input")
+
+    opik.flush_tracker()
+
+    # Verify trace
+    verifiers.verify_trace(
+        opik_client=opik_client,
+        trace_id=ID_STORAGE["f_outer-trace-id"],
+        name="f_outer",
+        input={"x": "outer-input"},
+        output=None,
+        error_info={
+            "exception_type": "ValueError",
+            "message": "inner span error message",
+            "traceback": ANY_STRING(),
+        },
+    )
+
+    # Verify top level span
+    verifiers.verify_span(
+        opik_client=opik_client,
+        span_id=ID_STORAGE["f_outer-span-id"],
+        parent_span_id=None,
+        trace_id=ID_STORAGE["f_outer-trace-id"],
+        name="f_outer",
+        input={"x": "outer-input"},
+        output=None,
+        error_info={
+            "exception_type": "ValueError",
+            "message": "inner span error message",
+            "traceback": ANY_STRING(),
+        },
+    )
+
+    # Verify nested span
+    verifiers.verify_span(
+        opik_client=opik_client,
+        span_id=ID_STORAGE["f_inner-span-id"],
+        parent_span_id=ID_STORAGE["f_outer-span-id"],
+        trace_id=ID_STORAGE["f_outer-trace-id"],
+        name="f_inner",
+        input={"y": "inner-input"},
+        output=None,
+        error_info={
+            "exception_type": "ValueError",
+            "message": "inner span error message",
+            "traceback": ANY_STRING(),
+        },
+    )
+
+
 def test_tracked_function__two_traces_and_two_spans__happyflow(opik_client):
     # Setup
     project_name = "e2e-tests-batching-messages"

sdks/python/tests/e2e/verifiers.py

@@ -3,14 +3,21 @@
 import json
 
 from opik.rest_api import ExperimentPublic
-from opik.types import FeedbackScoreDict
+from opik.types import FeedbackScoreDict, ErrorInfoDict
 from opik.api_objects.dataset import dataset_item
 from opik import Prompt, synchronization
 
 from .. import testlib
 import mock
 
 
+def _try_get__dict__(instance: Any) -> Optional[Dict[str, Any]]:
+    if instance is None:
+        return None
+
+    return instance.__dict__
+
+
 def verify_trace(
     opik_client: opik.Opik,
     trace_id: str,
@@ -20,7 +27,8 @@ def verify_trace(
     output: Dict[str, Any] = mock.ANY,  # type: ignore
     tags: List[str] = mock.ANY,  # type: ignore
     feedback_scores: List[FeedbackScoreDict] = mock.ANY,  # type: ignore
-    project_name: Optional[str] = mock.ANY,
+    project_name: Optional[str] = mock.ANY,  # type: ignore
+    error_info: Optional[ErrorInfoDict] = mock.ANY,  # type: ignore
 ):
     if not synchronization.until(
         lambda: (opik_client.get_trace_content(id=trace_id) is not None),
@@ -39,6 +47,9 @@ def verify_trace(
         trace.metadata, metadata
     )
     assert trace.tags == tags, testlib.prepare_difference_report(trace.tags, tags)
+    assert (
+        _try_get__dict__(trace.error_info) == error_info
+    ), testlib.prepare_difference_report(trace.error_info, error_info)
 
     if project_name is not mock.ANY:
         trace_project = opik_client.get_project(trace.project_id)
@@ -88,8 +99,9 @@ def verify_span(
     type: str = mock.ANY,  # type: ignore
     feedback_scores: List[FeedbackScoreDict] = mock.ANY,  # type: ignore
     project_name: Optional[str] = mock.ANY,
-    model: Optional[str] = None,
-    provider: Optional[str] = None,
+    model: Optional[str] = mock.ANY,  # type: ignore
+    provider: Optional[str] = mock.ANY,  # type: ignore
+    error_info: Optional[ErrorInfoDict] = mock.ANY,  # type: ignore
 ):
     if not synchronization.until(
         lambda: (opik_client.get_span_content(id=span_id) is not None),
@@ -117,6 +129,9 @@ def verify_span(
         span.metadata, metadata
     )
     assert span.tags == tags, testlib.prepare_difference_report(span.tags, tags)
+    assert (
+        _try_get__dict__(span.error_info) == error_info
+    ), testlib.prepare_difference_report(span.error_info, error_info)
     assert span.model == model
     assert span.provider == provider