Merge branch 'potel-base' into potel-base-run-all-tests

Author: sentrivana

MIGRATION_GUIDE.md

@@ -21,6 +21,16 @@ Looking to upgrade from Sentry SDK 2.x to 3.x? Here's a comprehensive list of wh
 - clickhouse-driver integration: The query is now available under the `db.query.text` span attribute (only if `send_default_pii` is `True`).
 - `sentry_sdk.init` now returns `None` instead of a context manager.
 - The `sampling_context` argument of `traces_sampler` now additionally contains all span attributes known at span start.
+- If you're using the Celery integration, the `sampling_context` argument of `traces_sampler` doesn't contain the `celery_job` dictionary anymore. Instead, the individual keys are now available as:
+
+  | Dictionary keys        | Sampling context key |
+  | ---------------------- | -------------------- |
+  | `celery_job["args"]`   | `celery.job.args`    |
+  | `celery_job["kwargs"]` | `celery.job.kwargs`  |
+  | `celery_job["task"]`   | `celery.job.task`    |
+
+  Note that all of these are serialized, i.e., not the original `args` and `kwargs` but rather OpenTelemetry-friendly span attributes.
+
 - If you're using the AIOHTTP integration, the `sampling_context` argument of `traces_sampler` doesn't contain the `aiohttp_request` object anymore. Instead, some of the individual properties of the request are accessible, if available, as follows:
 
   | Request property | Sampling context key(s)         |
@@ -71,18 +81,30 @@ Looking to upgrade from Sentry SDK 2.x to 3.x? Here's a comprehensive list of wh
   | `client`       | `client.address`, `client.port` |
   | full URL       | `url.full`                      |
 
-- If you're using the RQ integration, the `sampling_context` argument of `traces_sampler` doesn't contain the `rq_job` object anymore. Instead, the individual properties of the scope, if available, are accessible as follows:
+- If you're using the RQ integration, the `sampling_context` argument of `traces_sampler` doesn't contain the `rq_job` object anymore. Instead, the individual properties of the job and the queue, if available, are accessible as follows:
 
   | RQ property     | Sampling context key(s)      |
   | --------------- | ---------------------------- |
   | `rq_job.args`   | `rq.job.args`                |
   | `rq_job.kwargs` | `rq.job.kwargs`              |
   | `rq_job.func`   | `rq.job.func`                |
   | `queue.name`    | `messaging.destination.name` |
-  | `job.id`        | `messaging.message.id`       |
+  | `rq_job.id`     | `messaging.message.id`       |
 
   Note that `rq.job.args`, `rq.job.kwargs`, and `rq.job.func` are serialized and not the actual objects on the job.
 
+- If you're using the AWS Lambda integration, the `sampling_context` argument of `traces_sampler` doesn't contain the `aws_event` and `aws_context` objects anymore. Instead, the following, if available, is accessible:
+
+  | AWS property                                | Sampling context key(s) |
+  | ------------------------------------------- | ----------------------- |
+  | `aws_event["httpMethod"]`                   | `http.request.method`   |
+  | `aws_event["queryStringParameters"]`        | `url.query`             |
+  | `aws_event["path"]`                         | `url.path`              |
+  | full URL                                    | `url.full`              |
+  | `aws_event["headers"]["X-Forwarded-Proto"]` | `network.protocol.name` |
+  | `aws_event["headers"]["Host"]`              | `server.address`        |
+  | `aws_context["function_name"]`              | `faas.name`             |
+
 ### Removed
 
 - Spans no longer have a `description`. Use `name` instead.

sentry_sdk/integrations/aws_lambda.py

@@ -39,6 +39,17 @@
 MILLIS_TO_SECONDS = 1000.0
 
 
+EVENT_TO_ATTRIBUTES = {
+    "httpMethod": "http.request.method",
+    "queryStringParameters": "url.query",
+    "path": "url.path",
+}
+
+CONTEXT_TO_ATTRIBUTES = {
+    "function_name": "faas.name",
+}
+
+
 def _wrap_init_error(init_error):
     # type: (F) -> F
     @ensure_integration_enabled(AwsLambdaIntegration, init_error)
@@ -151,10 +162,7 @@ def sentry_handler(aws_event, aws_context, *args, **kwargs):
                     name=aws_context.function_name,
                     source=TRANSACTION_SOURCE_COMPONENT,
                     origin=AwsLambdaIntegration.origin,
-                    custom_sampling_context={
-                        "aws_event": aws_event,
-                        "aws_context": aws_context,
-                    },
+                    attributes=_prepopulate_attributes(aws_event, aws_context),
                 ):
                     try:
                         return handler(aws_event, aws_context, *args, **kwargs)
@@ -457,3 +465,29 @@ def _event_from_error_json(error_json):
     }  # type: Event
 
     return event
+
+
+def _prepopulate_attributes(aws_event, aws_context):
+    attributes = {}
+
+    for prop, attr in EVENT_TO_ATTRIBUTES.items():
+        if aws_event.get(prop) is not None:
+            attributes[attr] = aws_event[prop]
+
+    for prop, attr in CONTEXT_TO_ATTRIBUTES.items():
+        if getattr(aws_context, prop, None) is not None:
+            attributes[attr] = getattr(aws_context, prop)
+
+    url = _get_url(aws_event, aws_context)
+    if url:
+        if aws_event.get("queryStringParameters"):
+            url += f"?{aws_event['queryStringParameters']}"
+        attributes["url.full"] = url
+
+    headers = aws_event.get("headers") or {}
+    if headers.get("X-Forwarded-Proto"):
+        attributes["network.protocol.name"] = headers["X-Forwarded-Proto"]
+    if headers.get("Host"):
+        attributes["server.address"] = headers["Host"]
+
+    return attributes

sentry_sdk/integrations/celery/__init__.py

@@ -20,6 +20,7 @@
     ensure_integration_enabled,
     event_from_exception,
     reraise,
+    _serialize_span_attribute,
 )
 
 from typing import TYPE_CHECKING
@@ -318,15 +319,9 @@ def _inner(*args, **kwargs):
                     name=task.name,
                     source=TRANSACTION_SOURCE_TASK,
                     origin=CeleryIntegration.origin,
-                    custom_sampling_context={
-                        "celery_job": {
-                            "task": task.name,
-                            # for some reason, args[1] is a list if non-empty but a
-                            # tuple if empty
-                            "args": list(args[1]),
-                            "kwargs": args[2],
-                        }
-                    },
+                    # for some reason, args[1] is a list if non-empty but a
+                    # tuple if empty
+                    attributes=_prepopulate_attributes(task, list(args[1]), args[2]),
                 ) as transaction:
                     transaction.set_status(SPANSTATUS.OK)
                     return f(*args, **kwargs)
@@ -516,3 +511,12 @@ def sentry_publish(self, *args, **kwargs):
             return original_publish(self, *args, **kwargs)
 
     Producer.publish = sentry_publish
+
+
+def _prepopulate_attributes(task, args, kwargs):
+    attributes = {
+        "celery.job.task": task.name,
+        "celery.job.args": _serialize_span_attribute(args),
+        "celery.job.kwargs": _serialize_span_attribute(kwargs),
+    }
+    return attributes

tests/integrations/asyncio/test_asyncio.py

@@ -74,7 +74,7 @@ async def test_create_task(
 
     events = capture_events()
 
-    with sentry_sdk.start_transaction(name="test_transaction_for_create_task"):
+    with sentry_sdk.start_span(name="test_transaction_for_create_task"):
         with sentry_sdk.start_span(op="root", name="not so important"):
             tasks = [event_loop.create_task(foo()), event_loop.create_task(bar())]
             await asyncio.wait(tasks, return_when=asyncio.FIRST_EXCEPTION)
@@ -117,7 +117,7 @@ async def test_gather(
 
     events = capture_events()
 
-    with sentry_sdk.start_transaction(name="test_transaction_for_gather"):
+    with sentry_sdk.start_span(name="test_transaction_for_gather"):
         with sentry_sdk.start_span(op="root", name="not so important"):
             await asyncio.gather(foo(), bar(), return_exceptions=True)
 
@@ -160,7 +160,8 @@ async def test_exception(
 
     events = capture_events()
 
-    with sentry_sdk.start_transaction(name="test_exception"):
+    with sentry_sdk.start_span(name="test_exception"):
+        sentry_sdk.get_isolation_scope().set_transaction_name("test_exception")
         with sentry_sdk.start_span(op="root", name="not so important"):
             tasks = [event_loop.create_task(boom()), event_loop.create_task(bar())]
             await asyncio.wait(tasks, return_when=asyncio.FIRST_EXCEPTION)
@@ -375,7 +376,7 @@ async def test_span_origin(
 
     events = capture_events()
 
-    with sentry_sdk.start_transaction(name="something"):
+    with sentry_sdk.start_span(name="something"):
         tasks = [
             event_loop.create_task(foo()),
         ]

tests/integrations/aws_lambda/test_aws.py

@@ -619,18 +619,12 @@ def test_handler(event, context):
                     traces_sampler.assert_any_call(
                         DictionaryContaining(
                             {
-                                "aws_event": DictionaryContaining({
-                                    "httpMethod": "GET",
-                                    "path": "/sit/stay/rollover",
-                                    "headers": {"Host": "x.io", "X-Forwarded-Proto": "http"},
-                                }),
-                                "aws_context": ObjectDescribedBy(
-                                    type=get_lambda_bootstrap().LambdaContext,
-                                    attrs={
-                                        'function_name': StringContaining("test_"),
-                                        'function_version': '$LATEST',
-                                    }
-                                )
+                                "http.request.method": "GET",
+                                "url.path": "/sit/stay/rollover",
+                                "url.query": "repeat=again",
+                                "url.full": "http://x.io/sit/stay/rollover?repeat=twice",
+                                "network.protocol.name": "http",
+                                "server.address": "x.io",
                             }
                         )
                     )
@@ -649,7 +643,7 @@ def test_handler(event, context):
             )
         """
         ),
-        b'{"httpMethod": "GET", "path": "/sit/stay/rollover", "headers": {"Host": "x.io", "X-Forwarded-Proto": "http"}}',
+        b'{"httpMethod": "GET", "path": "/sit/stay/rollover", "query_string": {"repeat": "again"}, "headers": {"Host": "x.io", "X-Forwarded-Proto": "http"}}',
     )
 
     assert response["Payload"]["AssertionError raised"] is False

tests/integrations/celery/test_celery.py

@@ -13,6 +13,7 @@
     _wrap_task_run,
 )
 from sentry_sdk.integrations.celery.beat import _get_headers
+from sentry_sdk.utils import _serialize_span_attribute
 from tests.conftest import ApproxDict
 
 
@@ -430,7 +431,7 @@ def dummy_task(self, x, y):
 
 
 def test_traces_sampler_gets_task_info_in_sampling_context(
-    init_celery, celery_invocation, DictionaryContaining  # noqa:N803
+    init_celery, celery_invocation
 ):
     traces_sampler = mock.Mock()
     celery = init_celery(traces_sampler=traces_sampler)
@@ -445,10 +446,13 @@ def walk_dogs(x, y):
         walk_dogs, [["Maisey", "Charlie", "Bodhi", "Cory"], "Dog park round trip"], 1
     )
 
-    traces_sampler.assert_any_call(
-        # depending on the iteration of celery_invocation, the data might be
-        # passed as args or as kwargs, so make this generic
-        DictionaryContaining({"celery_job": dict(task="dog_walk", **args_kwargs)})
+    sampling_context = traces_sampler.call_args_list[1][0][0]
+    assert sampling_context["celery.job.task"] == "dog_walk"
+    assert sampling_context["celery.job.args"] == _serialize_span_attribute(
+        args_kwargs["args"]
+    )
+    assert sampling_context["celery.job.kwargs"] == _serialize_span_attribute(
+        args_kwargs["kwargs"]
     )
 
 

tests/integrations/httpx/test_httpx.py

@@ -6,7 +6,7 @@
 import responses
 
 import sentry_sdk
-from sentry_sdk import capture_message, start_transaction
+from sentry_sdk import capture_message, start_span
 from sentry_sdk.consts import MATCH_ALL, SPANDATA
 from sentry_sdk.integrations.httpx import HttpxIntegration
 from tests.conftest import ApproxDict
@@ -26,7 +26,7 @@ def before_breadcrumb(crumb, hint):
     url = "http://example.com/"
     responses.add(responses.GET, url, status=200)
 
-    with start_transaction():
+    with start_span():
         events = capture_events()
 
         if asyncio.iscoroutinefunction(httpx_client.get):
@@ -72,11 +72,10 @@ def test_outgoing_trace_headers(sentry_init, httpx_client, capture_envelopes):
     url = "http://example.com/"
     responses.add(responses.GET, url, status=200)
 
-    with start_transaction(
+    with start_span(
         name="/interactions/other-dogs/new-dog",
         op="greeting.sniff",
-        trace_id="01234567890123456789012345678901",
-    ) as transaction:
+    ) as span:
         if asyncio.iscoroutinefunction(httpx_client.get):
             response = asyncio.get_event_loop().run_until_complete(
                 httpx_client.get(url)
@@ -102,7 +101,7 @@ def test_outgoing_trace_headers(sentry_init, httpx_client, capture_envelopes):
     (httpx.Client(), httpx.AsyncClient()),
 )
 def test_outgoing_trace_headers_append_to_baggage(
-    sentry_init, httpx_client, capture_envelopes
+    sentry_init, httpx_client, capture_envelopes, SortedBaggage,  # noqa: N803
 ):
     sentry_init(
         traces_sample_rate=1.0,
@@ -115,11 +114,10 @@ def test_outgoing_trace_headers_append_to_baggage(
     url = "http://example.com/"
     responses.add(responses.GET, url, status=200)
 
-    with start_transaction(
+    with start_span(
         name="/interactions/other-dogs/new-dog",
         op="greeting.sniff",
-        trace_id="01234567890123456789012345678901",
-    ) as transaction:
+    ):
         if asyncio.iscoroutinefunction(httpx_client.get):
             response = asyncio.get_event_loop().run_until_complete(
                 httpx_client.get(url, headers={"baGGage": "custom=data"})
@@ -130,17 +128,18 @@ def test_outgoing_trace_headers_append_to_baggage(
     (envelope,) = envelopes
     transaction = envelope.get_transaction_event()
     request_span = transaction["spans"][-1]
+    trace_id = transaction["contexts"]["trace"]["trace_id"]
 
     assert response.request.headers[
         "sentry-trace"
     ] == "{trace_id}-{parent_span_id}-{sampled}".format(
-        trace_id=transaction["contexts"]["trace"]["trace_id"],
+        trace_id=trace_id,
         parent_span_id=request_span["span_id"],
         sampled=1,
     )
     assert (
         response.request.headers["baggage"]
-        == "custom=data,sentry-trace_id=01234567890123456789012345678901,sentry-environment=production,sentry-release=d08ebdb9309e1b004c6f52202de58a09c2268e42,sentry-transaction=/interactions/other-dogs/new-dog,sentry-sample_rate=1.0,sentry-sampled=true"
+        == SortedBaggage(f"custom=data,sentry-trace_id={trace_id},sentry-environment=production,sentry-release=d08ebdb9309e1b004c6f52202de58a09c2268e42,sentry-transaction=/interactions/other-dogs/new-dog,sentry-sample_rate=1.0,sentry-sampled=true")
     )
 
 
@@ -274,7 +273,7 @@ def test_option_trace_propagation_targets(
         integrations=[HttpxIntegration()],
     )
 
-    with sentry_sdk.start_transaction():  # Must be in a transaction to propagate headers
+    with sentry_sdk.start_span():  # Must be in a root span to propagate headers
         if asyncio.iscoroutinefunction(httpx_client.get):
             asyncio.get_event_loop().run_until_complete(httpx_client.get(url))
         else:
@@ -288,7 +287,7 @@ def test_option_trace_propagation_targets(
         assert "sentry-trace" not in request_headers
 
 
-def test_do_not_propagate_outside_transaction(sentry_init, httpx_mock):
+def test_propagates_twp_outside_root_span(sentry_init, httpx_mock):
     httpx_mock.add_response()
 
     sentry_init(
@@ -301,7 +300,8 @@ def test_do_not_propagate_outside_transaction(sentry_init, httpx_mock):
     httpx_client.get("http://example.com/")
 
     request_headers = httpx_mock.get_request().headers
-    assert "sentry-trace" not in request_headers
+    assert "sentry-trace" in request_headers
+    assert request_headers["sentry-trace"] == sentry_sdk.get_traceparent()
 
 
 @pytest.mark.tests_internal_exceptions
@@ -352,7 +352,7 @@ def test_span_origin(sentry_init, capture_events, httpx_client):
     url = "http://example.com/"
     responses.add(responses.GET, url, status=200)
 
-    with start_transaction(name="test_transaction"):
+    with start_span(name="test_root_span"):
         if asyncio.iscoroutinefunction(httpx_client.get):
             asyncio.get_event_loop().run_until_complete(httpx_client.get(url))
         else: