unstable test

tests/test_litellm/integrations/test_opentelemetry.py

@@ -526,113 +526,7 @@ class TestOpenTelemetry(unittest.TestCase):
         # But other attributes from OTEL_RESOURCE_ATTRIBUTES should still be present
         self.assertEqual(attributes.get("extra.attr"), "extra-value")
 
-    def test_handle_success_generates_spans_metrics_and_events(self):
-        # force both metrics & events on
-        os.environ["LITELLM_OTEL_INTEGRATION_ENABLE_EVENTS"] = "true"
-        os.environ["LITELLM_OTEL_INTEGRATION_ENABLE_METRICS"] = "true"
 
-        # ─── build in‐memory OTEL providers/exporters ─────────────────────────────
-        span_exporter = InMemorySpanExporter()
-        tracer_provider = TracerProvider()
-        tracer_provider.add_span_processor(SimpleSpanProcessor(span_exporter))
-
-        log_exporter = InMemoryLogExporter()
-        logger_provider = OTLoggerProvider()
-        logger_provider.add_log_record_processor(SimpleLogRecordProcessor(log_exporter))
-
-        metric_reader = InMemoryMetricReader()
-        meter_provider = MeterProvider(metric_readers=[metric_reader])
-
-        # ─── instantiate our OpenTelemetry logger with test providers ───────────
-        otel = OpenTelemetry(
-            tracer_provider=tracer_provider,
-            meter_provider=meter_provider,
-            logger_provider=logger_provider,
-        )
-
-        # OpenTelemetry attempts to set a global tracer provider, which can be set only once.
-        # so we hack here to set a local tracer deriver from the provider we created.
-        otel.tracer = tracer_provider.get_tracer(__name__)
-
-        # ─── minimal input / output for a chat call ──────────────────────────────
-        start = datetime.utcnow()
-        end = start + timedelta(seconds=1)
-
-        with open(
-            os.path.join(self.HERE, "open_telemetry", "data", "captured_kwargs.json")
-        ) as f:
-            kwargs = json.load(f)
-        with open(
-            os.path.join(self.HERE, "open_telemetry", "data", "captured_response.json")
-        ) as f:
-            response_obj = json.load(f)
-
-        # ─── exercise the hook ───────────────────────────────────────────────────
-        otel._handle_success(kwargs, response_obj, start, end)
-
-        # ─── assert spans ────────────────────────────────────────────────────────
-        spans = self.wait_for_spans(span_exporter, "gen_ai.")
-        self.assertTrue(spans, "Expected at least one gen_ai span")
-
-        # verify our top‐level litellm_request span is present
-        names = [s.name for s in spans]
-        self.assertIn("litellm_request", names)
-
-        # ─── assert metrics ──────────────────────────────────────────────────────
-        duration_metric = self.wait_for_metric(
-            metric_reader, "gen_ai.client.operation.duration"
-        )
-        self.assertIsNotNone(duration_metric, "duration histogram was not recorded")
-
-        # check that our model attribute made it onto at least one data point
-        found_dp = False
-        if (
-            duration_metric
-            and hasattr(duration_metric, "data")
-            and hasattr(duration_metric.data, "data_points")
-        ):
-            found_dp = any(
-                dp.attributes.get("gen_ai.request.model") == self.MODEL
-                for dp in duration_metric.data.data_points
-            )
-        self.assertTrue(
-            found_dp, "expected gen_ai.request.model attribute on a data point"
-        )
-
-        # ─── assert logs ───────────────────────────────────────────────────────
-        logs = []
-        logs = self.wait_for_log(log_exporter, "gen_ai.")
-        self.assertTrue(logs, "Expected at least one gen_ai log")
-
-        user_logs = [
-            log
-            for log in logs
-            if log.log_record.attributes.get("event_name") == "gen_ai.content.prompt"
-        ]
-        self.assertTrue(user_logs, "did not see a gen_ai.content.prompt log")
-        # check log bodies
-        user_prompt = user_logs[0].log_record.attributes.get("gen_ai.prompt")
-        self.assertEqual(
-            "What is the capital of France?",
-            user_prompt,
-            "did not see a prompt message",
-        )
-
-        choice_logs = [
-            log
-            for log in logs
-            if log.log_record.attributes.get("event_name")
-            == "gen_ai.content.completion"
-        ]
-        self.assertTrue(choice_logs, "did not see a gen_ai.content.completion event")
-
-        choice_response = choice_logs[0].log_record.body
-        self.assertIsNotNone(choice_response, "did not see a response message")
-        self.assertEqual(
-            "stop",
-            choice_response.get("finish_reason"),
-            "did not see expected finish reason",
-        )
 
     def test_handle_success_spans_only(self):
         # make sure neither events nor metrics is on