Merge branch 'main' into aiothttp-server-attributes-for-sampling

Author: xrmx

CHANGELOG.md

@@ -29,18 +29,32 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   ([#3819](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3819))
 - `opentelemetry-instrumentation-system-metrics`: Add support for the `OTEL_PYTHON_SYSTEM_METRICS_EXCLUDED_METRICS` environment variable
   ([#3959](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3959))
-- `opentelemetry-instrumentation-httpx`: add ability to capture custom headers 
+- `opentelemetry-instrumentation-httpx`: add ability to capture custom headers
   ([#4047](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/4047))
 - `opentelemetry-instrumentation-urllib3`: add ability to capture custom headers
   ([#4050](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/4050))
 - `opentelemetry-instrumentation-urllib`: add ability to capture custom headers
   ([#4051](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/4051))
+- `opentelemetry-instrumentation-confluent-kafka`: Increase confluent-kafka upper bound to support newer versions (2.13.0)
+  ([#4099](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/4099))
 - `opentelemetry-instrumentation-aiohttp-server` Implement new semantic convention opt-in migration
   ([#3980](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3980))
+- `opentelemetry-instrumentation-falcon`: pass request attributes at span creation
+  ([#4119](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/4119))
 - `opentelemetry-instrumentation`: add database stability attribute setters in `_semconv` utilities
   ([#4108](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/4108))
 - `opentelemetry-instrumentation-aiohttp-server`: pass request attributes at span creation
   ([#4118](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/4118))
+- `opentelemetry-instrumentation-tornado`: Implement new semantic convention opt-in migration
+  ([#3993](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3993))
+- `opentelemetry-instrumentation-tornado`: pass request attributes at span creation
+  ([#4140](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/4140))
+- `opentelemetry-instrumentation-pyramid` Implement new semantic convention opt-in migration
+  ([#3982](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3982))
+- `opentelemetry-instrumentation-tortoiseorm` Add unit tests for Tortoise ORM instrumentation
+  ([#4141](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/4141))
+- `opentelemetry-instrumentation-pyramid`: pass request attributes at span creation
+  ([#4139](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/4139))
 
 ### Fixed
 
@@ -84,9 +98,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   ([#4081](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/4081))
 - `opentelemetry-instrumentation-system-metrics`: Use proper numeric `cpython.gc.generation` attribute in CPython metrics, out of spec `generation` attribute is deprecated and will be removed in the future
   ([#4092](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/4092))
+- `opentelemetry-instrumentation-dbapi`: Fix sqlcomment calculation of mysql_client_version field if connection reassignment, with "unknown" fallback
+  ([#3729](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3729))
+- `opentelemetry-instrumentation-confluent-kafka`: Fix incorrect number of argument to `_inner_wrap_close`
+  ([#3922](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3922))
 
 ### Breaking changes
 
+- `opentelemetry-instrumentation-logging`: Inject span context attributes into logging LogRecord only if configured to do so
+  ([#4112](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/4112))
 - `opentelemetry-instrumentation-django`: Drop support for Django < 2.0
   ([#3848](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/4083))
 

CONTRIBUTING.md

@@ -122,6 +122,12 @@ Some packages may require additional system-wide dependencies to be installed. F
 
 For `docs` building, you may need to install `mysql-client` and other required dependencies as necessary. Ensure the Python version used in your local setup matches the version used in the [CI](./.github/workflows/) to maintain compatibility when building the documentation.
 
+If you are using `tox-uv` for tests and have issues with resolving OpenTelemetry dependencies try:
+
+```sh
+uv sync --refresh
+```
+
 ### Benchmarks
 
 Some packages have benchmark tests. To run them, run `tox -f benchmark`. Benchmark tests use `pytest-benchmark` and they output a table with results to the console.

docs-requirements.txt

@@ -24,7 +24,7 @@ botocore~=1.0
 boto3~=1.0
 cassandra-driver~=3.25
 celery>=4.0
-confluent-kafka>= 1.8.2,<= 2.11.0
+confluent-kafka>= 1.8.2,<= 2.13.0
 elasticsearch>=6.0,<9.0
 flask~=2.0
 falcon~=2.0

instrumentation-genai/opentelemetry-instrumentation-google-genai/CHANGELOG.md

@@ -8,6 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## Unreleased
 
 - Enable the addition of custom attributes to the `generate_content {model.name}` span via the Context API. ([#3961](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/3961)).
+- Enable the addition of custom attributes to `gen_ai.client.inference.operation.details` log events ([#4103](https://github.com/open-telemetry/opentelemetry-python-contrib/pull/4103)).
 
 ## Version 0.5b0 (2025-12-11)
 

instrumentation-genai/opentelemetry-instrumentation-google-genai/src/opentelemetry/instrumentation/google_genai/generate_content.py

@@ -25,7 +25,6 @@
     AsyncIterator,
     Awaitable,
     Iterator,
-    Mapping,
     Optional,
     Union,
 )
@@ -189,7 +188,7 @@ def _to_dict(value: object):
 def _create_request_attributes(
     config: Optional[GenerateContentConfigOrDict],
     allow_list: AllowList,
-) -> dict[str, Any]:
+) -> dict[str, AttributeValue]:
     if not config:
         return {}
     config = _to_dict(config)
@@ -291,8 +290,8 @@ def _create_completion_details_attributes(
     output_messages: list[OutputMessage],
     system_instructions: list[MessagePart],
     as_str: bool = False,
-) -> dict[str, Any]:
-    attributes: dict[str, Any] = {
+) -> dict[str, AttributeValue]:
+    attributes: dict[str, AttributeValue] = {
         gen_ai_attributes.GEN_AI_INPUT_MESSAGES: [
             dataclasses.asdict(input_message)
             for input_message in input_messages
@@ -310,10 +309,11 @@ def _create_completion_details_attributes(
     return attributes
 
 
-def _get_extra_generate_content_attributes() -> Optional[
-    Mapping[str, AttributeValue]
-]:
-    return context_api.get_value(GENERATE_CONTENT_EXTRA_ATTRIBUTES_CONTEXT_KEY)
+def _get_extra_generate_content_attributes() -> dict[str, AttributeValue]:
+    attrs = context_api.get_value(
+        GENERATE_CONTENT_EXTRA_ATTRIBUTES_CONTEXT_KEY
+    )
+    return dict(attrs or {})
 
 
 class _GenerateContentInstrumentationHelper:
@@ -371,7 +371,7 @@ def start_span_as_current_span(
             end_on_exit=end_on_exit,
         )
 
-    def create_final_attributes(self) -> dict[str, Any]:
+    def create_final_attributes(self) -> dict[str, AttributeValue]:
         final_attributes = {
             gen_ai_attributes.GEN_AI_USAGE_INPUT_TOKENS: self._input_tokens,
             gen_ai_attributes.GEN_AI_USAGE_OUTPUT_TOKENS: self._output_tokens,
@@ -463,8 +463,9 @@ def _maybe_update_error_type(self, response: GenerateContentResponse):
 
     def _maybe_log_completion_details(
         self,
-        request_attributes: dict[str, Any],
-        final_attributes: dict[str, Any],
+        extra_attributes: dict[str, AttributeValue],
+        request_attributes: dict[str, AttributeValue],
+        final_attributes: dict[str, AttributeValue],
         request: Union[ContentListUnion, ContentListUnionDict],
         candidates: list[Candidate],
         config: Optional[GenerateContentConfigOrDict] = None,
@@ -487,7 +488,9 @@ def _maybe_log_completion_details(
         span = trace.get_current_span()
         event = LogRecord(
             event_name="gen_ai.client.inference.operation.details",
-            attributes=request_attributes | final_attributes,
+            attributes=extra_attributes
+            | request_attributes
+            | final_attributes,
         )
         self.completion_hook.on_completion(
             inputs=input_messages,
@@ -742,9 +745,8 @@ def instrumented_generate_content(
         with helper.start_span_as_current_span(
             model, "google.genai.Models.generate_content"
         ) as span:
-            if extra_attributes := _get_extra_generate_content_attributes():
-                span.set_attributes(extra_attributes)
-            span.set_attributes(request_attributes)
+            extra_attributes = _get_extra_generate_content_attributes()
+            span.set_attributes(extra_attributes | request_attributes)
             if helper.sem_conv_opt_in_mode == _StabilityMode.DEFAULT:
                 helper.process_request(contents, config, span)
             try:
@@ -773,6 +775,7 @@ def instrumented_generate_content(
                 final_attributes = helper.create_final_attributes()
                 span.set_attributes(final_attributes)
                 helper._maybe_log_completion_details(
+                    extra_attributes,
                     request_attributes,
                     final_attributes,
                     contents,
@@ -817,9 +820,8 @@ def instrumented_generate_content_stream(
         with helper.start_span_as_current_span(
             model, "google.genai.Models.generate_content_stream"
         ) as span:
-            if extra_attributes := _get_extra_generate_content_attributes():
-                span.set_attributes(extra_attributes)
-            span.set_attributes(request_attributes)
+            extra_attributes = _get_extra_generate_content_attributes()
+            span.set_attributes(extra_attributes | request_attributes)
             if helper.sem_conv_opt_in_mode == _StabilityMode.DEFAULT:
                 helper.process_request(contents, config, span)
             try:
@@ -848,6 +850,7 @@ def instrumented_generate_content_stream(
                 final_attributes = helper.create_final_attributes()
                 span.set_attributes(final_attributes)
                 helper._maybe_log_completion_details(
+                    extra_attributes,
                     request_attributes,
                     final_attributes,
                     contents,
@@ -892,9 +895,8 @@ async def instrumented_generate_content(
         with helper.start_span_as_current_span(
             model, "google.genai.AsyncModels.generate_content"
         ) as span:
-            if extra_attributes := _get_extra_generate_content_attributes():
-                span.set_attributes(extra_attributes)
-            span.set_attributes(request_attributes)
+            extra_attributes = _get_extra_generate_content_attributes()
+            span.set_attributes(extra_attributes | request_attributes)
             if helper.sem_conv_opt_in_mode == _StabilityMode.DEFAULT:
                 helper.process_request(contents, config, span)
             try:
@@ -922,6 +924,7 @@ async def instrumented_generate_content(
                 final_attributes = helper.create_final_attributes()
                 span.set_attributes(final_attributes)
                 helper._maybe_log_completion_details(
+                    extra_attributes,
                     request_attributes,
                     final_attributes,
                     contents,
@@ -968,9 +971,8 @@ async def instrumented_generate_content_stream(
             "google.genai.AsyncModels.generate_content_stream",
             end_on_exit=False,
         ) as span:
-            if extra_attributes := _get_extra_generate_content_attributes():
-                span.set_attributes(extra_attributes)
-            span.set_attributes(request_attributes)
+            extra_attributes = _get_extra_generate_content_attributes()
+            span.set_attributes(extra_attributes | request_attributes)
             if (
                 not helper.sem_conv_opt_in_mode
                 == _StabilityMode.GEN_AI_LATEST_EXPERIMENTAL
@@ -990,6 +992,7 @@ async def instrumented_generate_content_stream(
                 final_attributes = helper.create_final_attributes()
                 span.set_attributes(final_attributes)
                 helper._maybe_log_completion_details(
+                    extra_attributes,
                     request_attributes,
                     final_attributes,
                     contents,
@@ -1023,6 +1026,7 @@ async def _response_async_generator_wrapper():
                         final_attributes = helper.create_final_attributes()
                         span.set_attributes(final_attributes)
                         helper._maybe_log_completion_details(
+                            extra_attributes,
                             request_attributes,
                             final_attributes,
                             contents,

instrumentation-genai/opentelemetry-instrumentation-google-genai/tests/generate_content/nonstreaming_base.py

@@ -520,6 +520,46 @@ def test_new_semconv_record_completion_in_span(self):
 
                 self.tearDown()
 
+    def test_new_semconv_log_has_extra_genai_attributes(self):
+        patched_environ = patch.dict(
+            "os.environ",
+            {
+                "OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT": "EVENT_ONLY",
+                "OTEL_SEMCONV_STABILITY_OPT_IN": "gen_ai_latest_experimental",
+            },
+        )
+        patched_otel_mapping = patch.dict(
+            _OpenTelemetrySemanticConventionStability._OTEL_SEMCONV_STABILITY_SIGNAL_MAPPING,
+            {
+                _OpenTelemetryStabilitySignalType.GEN_AI: _StabilityMode.GEN_AI_LATEST_EXPERIMENTAL
+            },
+        )
+        with patched_environ, patched_otel_mapping:
+            self.configure_valid_response(text="Yep, it works!")
+            tok = context_api.attach(
+                context_api.set_value(
+                    GENERATE_CONTENT_EXTRA_ATTRIBUTES_CONTEXT_KEY,
+                    {"extra_attribute_key": "extra_attribute_value"},
+                )
+            )
+            try:
+                self.generate_content(
+                    model="gemini-2.0-flash",
+                    contents="Does this work?",
+                )
+                self.otel.assert_has_event_named(
+                    "gen_ai.client.inference.operation.details"
+                )
+                event = self.otel.get_event_named(
+                    "gen_ai.client.inference.operation.details"
+                )
+                assert (
+                    event.attributes["extra_attribute_key"]
+                    == "extra_attribute_value"
+                )
+            finally:
+                context_api.detach(tok)
+
     def test_records_metrics_data(self):
         self.configure_valid_response()
         self.generate_content(model="gemini-2.0-flash", contents="Some input")

instrumentation-genai/opentelemetry-instrumentation-google-genai/tests/generate_content/streaming_base.py

@@ -13,8 +13,14 @@
 # limitations under the License.
 
 import unittest
+from unittest.mock import patch
 
 from opentelemetry import context as context_api
+from opentelemetry.instrumentation._semconv import (
+    _OpenTelemetrySemanticConventionStability,
+    _OpenTelemetryStabilitySignalType,
+    _StabilityMode,
+)
 from opentelemetry.instrumentation.google_genai import (
     GENERATE_CONTENT_EXTRA_ATTRIBUTES_CONTEXT_KEY,
 )
@@ -99,3 +105,43 @@ def test_includes_token_counts_in_span_aggregated_from_responses(self):
         span = self.otel.get_span_named("generate_content gemini-2.0-flash")
         self.assertEqual(span.attributes["gen_ai.usage.input_tokens"], 9)
         self.assertEqual(span.attributes["gen_ai.usage.output_tokens"], 12)
+
+    def test_new_semconv_log_has_extra_genai_attributes(self):
+        patched_environ = patch.dict(
+            "os.environ",
+            {
+                "OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT": "EVENT_ONLY",
+                "OTEL_SEMCONV_STABILITY_OPT_IN": "gen_ai_latest_experimental",
+            },
+        )
+        patched_otel_mapping = patch.dict(
+            _OpenTelemetrySemanticConventionStability._OTEL_SEMCONV_STABILITY_SIGNAL_MAPPING,
+            {
+                _OpenTelemetryStabilitySignalType.GEN_AI: _StabilityMode.GEN_AI_LATEST_EXPERIMENTAL
+            },
+        )
+        with patched_environ, patched_otel_mapping:
+            self.configure_valid_response(text="Yep, it works!")
+            tok = context_api.attach(
+                context_api.set_value(
+                    GENERATE_CONTENT_EXTRA_ATTRIBUTES_CONTEXT_KEY,
+                    {"extra_attribute_key": "extra_attribute_value"},
+                )
+            )
+            try:
+                self.generate_content(
+                    model="gemini-2.0-flash",
+                    contents="Does this work?",
+                )
+                self.otel.assert_has_event_named(
+                    "gen_ai.client.inference.operation.details"
+                )
+                event = self.otel.get_event_named(
+                    "gen_ai.client.inference.operation.details"
+                )
+                assert (
+                    event.attributes["extra_attribute_key"]
+                    == "extra_attribute_value"
+                )
+            finally:
+                context_api.detach(tok)

instrumentation-genai/opentelemetry-instrumentation-langchain/src/opentelemetry/instrumentation/langchain/span_manager.py

@@ -20,7 +20,7 @@
     gen_ai_attributes as GenAI,
 )
 from opentelemetry.semconv.attributes import (
-    error_attributes as ErrorAttributes,
+    error_attributes,
 )
 from opentelemetry.trace import Span, SpanKind, Tracer, set_span_in_context
 from opentelemetry.trace.status import Status, StatusCode
@@ -112,6 +112,6 @@ def handle_error(self, error: BaseException, run_id: UUID):
             return
         span.set_status(Status(StatusCode.ERROR, str(error)))
         span.set_attribute(
-            ErrorAttributes.ERROR_TYPE, type(error).__qualname__
+            error_attributes.ERROR_TYPE, type(error).__qualname__
         )
         self.end_span(run_id)