merge master

Author: alexander-alderman-webb

CHANGELOG.md

@@ -1,5 +1,82 @@
 # Changelog
 
+## 2.55.0
+
+### New Features ✨
+
+#### Anthropic
+
+- Record finish reasons in AI monitoring spans by @ericapisani in [#5678](https://github.com/getsentry/sentry-python/pull/5678)
+- Emit `gen_ai.chat` spans for asynchronous `messages.stream()` by @alexander-alderman-webb in [#5572](https://github.com/getsentry/sentry-python/pull/5572)
+- Emit AI Client Spans for synchronous `messages.stream()` by @alexander-alderman-webb in [#5565](https://github.com/getsentry/sentry-python/pull/5565)
+- Set gen_ai.response.id span attribute by @ericapisani in [#5662](https://github.com/getsentry/sentry-python/pull/5662)
+- Add `gen_ai.system` attribute to spans by @ericapisani in [#5661](https://github.com/getsentry/sentry-python/pull/5661)
+
+#### Pydantic Ai
+
+- Support ImageUrl content type in span instrumentation by @ericapisani in [#5629](https://github.com/getsentry/sentry-python/pull/5629)
+- Add tool description to execute_tool spans by @ericapisani in [#5596](https://github.com/getsentry/sentry-python/pull/5596)
+
+#### Other
+
+- (crons) Add owner field to MonitorConfig by @julwhitney13 in [#5610](https://github.com/getsentry/sentry-python/pull/5610)
+- (otlp) Add collector_url option to OTLPIntegration by @sl0thentr0py in [#5603](https://github.com/getsentry/sentry-python/pull/5603)
+
+### Bug Fixes 🐛
+
+- (ai) Truncate list-based message content in AI monitoring by @ericapisani in [#5631](https://github.com/getsentry/sentry-python/pull/5631)
+- (anthropic) Close span on `GeneratorExit` by @alexander-alderman-webb in [#5643](https://github.com/getsentry/sentry-python/pull/5643)
+- (celery) Propagate user-set headers by @sentrivana in [#5581](https://github.com/getsentry/sentry-python/pull/5581)
+- (langchain) Wrap finish_reason in array for gen_ai span attribute by @ericapisani in [#5666](https://github.com/getsentry/sentry-python/pull/5666)
+- (logging) Fix deadlock in log batcher by @sentrivana in [#5684](https://github.com/getsentry/sentry-python/pull/5684)
+- (profiler) Prevent buffer race condition during rapid start/stop cycles by @ericapisani in [#5622](https://github.com/getsentry/sentry-python/pull/5622)
+- (utils) Avoid double serialization of strings in safe_serialize by @ericapisani in [#5587](https://github.com/getsentry/sentry-python/pull/5587)
+- Enable unused import ruff check and fix unused imports by @sentrivana in [#5652](https://github.com/getsentry/sentry-python/pull/5652)
+
+### Documentation 📚
+
+- (openai-agents) Remove inapplicable comment by @alexander-alderman-webb in [#5495](https://github.com/getsentry/sentry-python/pull/5495)
+- Add AGENTS.md by @sentrivana in [#5579](https://github.com/getsentry/sentry-python/pull/5579)
+- Add `set_attribute` example to changelog by @sentrivana in [#5578](https://github.com/getsentry/sentry-python/pull/5578)
+
+### Internal Changes 🔧
+
+#### Anthropic
+
+- Check system and response ID attributes on spans created by `stream()` by @alexander-alderman-webb in [#5665](https://github.com/getsentry/sentry-python/pull/5665)
+- Skip accumulation logic for unexpected types in streamed response by @alexander-alderman-webb in [#5564](https://github.com/getsentry/sentry-python/pull/5564)
+- Factor out streamed result handling by @alexander-alderman-webb in [#5563](https://github.com/getsentry/sentry-python/pull/5563)
+- Stream valid JSON by @alexander-alderman-webb in [#5641](https://github.com/getsentry/sentry-python/pull/5641)
+- Stop mocking response iterator by @alexander-alderman-webb in [#5573](https://github.com/getsentry/sentry-python/pull/5573)
+
+#### Openai Agents
+
+- Do not fail on new tool fields by @alexander-alderman-webb in [#5625](https://github.com/getsentry/sentry-python/pull/5625)
+- Stop expecting a specific function name by @alexander-alderman-webb in [#5623](https://github.com/getsentry/sentry-python/pull/5623)
+- Set streaming header when library uses `with_streaming_response()` by @alexander-alderman-webb in [#5583](https://github.com/getsentry/sentry-python/pull/5583)
+- Replace mocks with `httpx` for streamed responses by @alexander-alderman-webb in [#5580](https://github.com/getsentry/sentry-python/pull/5580)
+- Replace mocks with `httpx` in non-MCP tool tests by @alexander-alderman-webb in [#5602](https://github.com/getsentry/sentry-python/pull/5602)
+- Replace mocks with `httpx` in MCP tool tests by @alexander-alderman-webb in [#5605](https://github.com/getsentry/sentry-python/pull/5605)
+- Replace mocks with `httpx` in handoff tests by @alexander-alderman-webb in [#5604](https://github.com/getsentry/sentry-python/pull/5604)
+- Replace mocks with `httpx` in API error test by @alexander-alderman-webb in [#5601](https://github.com/getsentry/sentry-python/pull/5601)
+- Replace mocks with `httpx` in non-error single-response tests by @alexander-alderman-webb in [#5600](https://github.com/getsentry/sentry-python/pull/5600)
+- Remove test for unreachable state by @alexander-alderman-webb in [#5584](https://github.com/getsentry/sentry-python/pull/5584)
+- Expect `namespace` tool field for new `openai` versions by @alexander-alderman-webb in [#5599](https://github.com/getsentry/sentry-python/pull/5599)
+
+#### Other
+
+- (graphene) Simplify span creation by @sentrivana in [#5648](https://github.com/getsentry/sentry-python/pull/5648)
+- (httpx) Resolve type checking failures by @alexander-alderman-webb in [#5626](https://github.com/getsentry/sentry-python/pull/5626)
+- (pyramid) Support alpha suffixes in version parsing by @alexander-alderman-webb in [#5618](https://github.com/getsentry/sentry-python/pull/5618)
+- (rust) Don't implement separate scope management by @sentrivana in [#5639](https://github.com/getsentry/sentry-python/pull/5639)
+- (strawberry) Simplify span creation by @sentrivana in [#5647](https://github.com/getsentry/sentry-python/pull/5647)
+- 🤖 Update test matrix with new releases (03/16) by @github-actions in [#5671](https://github.com/getsentry/sentry-python/pull/5671)
+- Remove custom warden action by @sentrivana in [#5653](https://github.com/getsentry/sentry-python/pull/5653)
+- Add `httpx` to linting requirements by @alexander-alderman-webb in [#5644](https://github.com/getsentry/sentry-python/pull/5644)
+- Remove CodeQL action by @sentrivana in [#5616](https://github.com/getsentry/sentry-python/pull/5616)
+- Normalize dots in package names in `populate_tox.py` by @alexander-alderman-webb in [#5574](https://github.com/getsentry/sentry-python/pull/5574)
+- Do not run actions on `potel-base` by @sentrivana in [#5614](https://github.com/getsentry/sentry-python/pull/5614)
+
 ## 2.54.0
 
 ### New Features ✨

docs/conf.py

@@ -31,7 +31,7 @@
 copyright = "2019-{}, Sentry Team and Contributors".format(datetime.now().year)
 author = "Sentry Team and Contributors"
 
-release = "2.54.0"
+release = "2.55.0"
 version = ".".join(release.split(".")[:2])  # The short X.Y version.
 
 

requirements-testing.txt

@@ -4,6 +4,7 @@ tomli;python_version<"3.11"  # Only needed for pytest on Python < 3.11
 pytest-cov
 pytest-forked
 pytest-localserver
+pytest-timeout
 pytest-watch
 jsonschema
 executing

sentry_sdk/_batcher.py

@@ -31,6 +31,7 @@ def __init__(
         self._record_lost_func = record_lost_func
         self._running = True
         self._lock = threading.Lock()
+        self._active: "threading.local" = threading.local()
 
         self._flush_event: "threading.Event" = threading.Event()
 
@@ -70,23 +71,40 @@ def _ensure_thread(self) -> bool:
         return True
 
     def _flush_loop(self) -> None:
+        # Mark the flush-loop thread as active for its entire lifetime so
+        # that any re-entrant add() triggered by GC warnings during wait(),
+        # flush(), or Event operations is silently dropped instead of
+        # deadlocking on internal locks.
+        self._active.flag = True
         while self._running:
             self._flush_event.wait(self.FLUSH_WAIT_TIME + random.random())
             self._flush_event.clear()
             self._flush()
 
     def add(self, item: "T") -> None:
-        if not self._ensure_thread() or self._flusher is None:
+        # Bail out if the current thread is already executing batcher code.
+        # This prevents deadlocks when code running inside the batcher (e.g.
+        # _add_to_envelope during flush, or _flush_event.wait/set) triggers
+        # a GC-emitted warning that routes back through the logging
+        # integration into add().
+        if getattr(self._active, "flag", False):
             return None
 
-        with self._lock:
-            if len(self._buffer) >= self.MAX_BEFORE_DROP:
-                self._record_lost(item)
+        self._active.flag = True
+        try:
+            if not self._ensure_thread() or self._flusher is None:
                 return None
 
-            self._buffer.append(item)
-            if len(self._buffer) >= self.MAX_BEFORE_FLUSH:
-                self._flush_event.set()
+            with self._lock:
+                if len(self._buffer) >= self.MAX_BEFORE_DROP:
+                    self._record_lost(item)
+                    return None
+
+                self._buffer.append(item)
+                if len(self._buffer) >= self.MAX_BEFORE_FLUSH:
+                    self._flush_event.set()
+        finally:
+            self._active.flag = False
 
     def kill(self) -> None:
         if self._flusher is None:
@@ -97,7 +115,12 @@ def kill(self) -> None:
         self._flusher = None
 
     def flush(self) -> None:
-        self._flush()
+        was_active = getattr(self._active, "flag", False)
+        self._active.flag = True
+        try:
+            self._flush()
+        finally:
+            self._active.flag = was_active
 
     def _add_to_envelope(self, envelope: "Envelope") -> None:
         envelope.add_item(

sentry_sdk/_span_batcher.py

@@ -43,36 +43,50 @@ def __init__(
         self._record_lost_func = record_lost_func
         self._running = True
         self._lock = threading.Lock()
+        self._active: "threading.local" = threading.local()
 
         self._flush_event: "threading.Event" = threading.Event()
 
         self._flusher: "Optional[threading.Thread]" = None
         self._flusher_pid: "Optional[int]" = None
 
     def add(self, span: "StreamedSpan") -> None:
-        if not self._ensure_thread() or self._flusher is None:
+        # Bail out if the current thread is already executing batcher code.
+        # This prevents deadlocks when code running inside the batcher (e.g.
+        # _add_to_envelope during flush, or _flush_event.wait/set) triggers
+        # a GC-emitted warning that routes back through the logging
+        # integration into add().
+        if getattr(self._active, "flag", False):
             return None
 
-        with self._lock:
-            size = len(self._span_buffer[span.trace_id])
-            if size >= self.MAX_BEFORE_DROP:
-                self._record_lost_func(
-                    reason="queue_overflow",
-                    data_category="span",
-                    quantity=1,
-                )
-                return None
-
-            self._span_buffer[span.trace_id].append(span)
-            self._running_size[span.trace_id] += self._estimate_size(span)
+        self._active.flag = True
 
-            if size + 1 >= self.MAX_BEFORE_FLUSH:
-                self._flush_event.set()
-                return
+        try:
+            if not self._ensure_thread() or self._flusher is None:
+                return None
 
-            if self._running_size[span.trace_id] >= self.MAX_BYTES_BEFORE_FLUSH:
-                self._flush_event.set()
-                return
+            with self._lock:
+                size = len(self._span_buffer[span.trace_id])
+                if size >= self.MAX_BEFORE_DROP:
+                    self._record_lost_func(
+                        reason="queue_overflow",
+                        data_category="span",
+                        quantity=1,
+                    )
+                    return None
+
+                self._span_buffer[span.trace_id].append(span)
+                self._running_size[span.trace_id] += self._estimate_size(span)
+
+                if size + 1 >= self.MAX_BEFORE_FLUSH:
+                    self._flush_event.set()
+                    return
+
+                if self._running_size[span.trace_id] >= self.MAX_BYTES_BEFORE_FLUSH:
+                    self._flush_event.set()
+                    return
+        finally:
+            self._active.flag = False
 
     @staticmethod
     def _estimate_size(item: "StreamedSpan") -> int:

sentry_sdk/consts.py

@@ -1491,4 +1491,4 @@ def _get_default_options() -> "dict[str, Any]":
 del _get_default_options
 
 
-VERSION = "2.54.0"
+VERSION = "2.55.0"

sentry_sdk/integrations/anthropic.py

@@ -120,16 +120,7 @@ def setup_once() -> None:
         AsyncStream.close = _wrap_async_close(AsyncStream.close)
 
         """
-        client.messages.stream() can return an instance of the MessageStream class, which implements the iterator protocol.
-        Analogously, the function can return an AsyncMessageStream, which implements the asynchronous iterator protocol.
-        The private _iterator variable and the close() method are patched. During iteration over the _iterator generator,
-        information from intercepted events is accumulated and used to populate output attributes on the AI Client Span.
-
-        The span can be finished in two places:
-        - When the user exits the context manager or directly calls close(), the patched close() finishes the span.
-        - When iteration ends, the finally block in the _iterator wrapper finishes the span.
-
-        Both paths may run. For example, the context manager exit can follow iterator exhaustion.
+        client.messages.stream() patches are analogous to the patches for client.messages.create(stream=True) described above.
         """
         Messages.stream = _wrap_message_stream(Messages.stream)
         MessageStreamManager.__enter__ = _wrap_message_stream_manager_enter(
@@ -453,7 +444,7 @@ def _wrap_synchronous_message_iterator(
 ) -> "Iterator[Union[RawMessageStreamEvent, MessageStreamEvent]]":
     """
     Sets information received while iterating the response stream on the AI Client Span.
-    Responsible for closing the AI Client Span, unless the span has already been closed in the close() patch.
+    Responsible for closing the AI Client Span unless the span has already been closed in the close() patch.
     """
     try:
         for event in iterator:
@@ -493,12 +484,12 @@ def _wrap_synchronous_message_iterator(
 
 
 async def _wrap_asynchronous_message_iterator(
-    stream: "Union[Stream, MessageStream]",
+    stream: "Union[AsyncStream, AsyncMessageStream]",
     iterator: "AsyncIterator[Union[RawMessageStreamEvent, MessageStreamEvent]]",
 ) -> "AsyncIterator[Union[RawMessageStreamEvent, MessageStreamEvent]]":
     """
     Sets information received while iterating the response stream on the AI Client Span.
-    Responsible for closing the AI Client Span, unless the span has already been closed in the close() patch.
+    Responsible for closing the AI Client Span unless the span has already been closed in the close() patch.
     """
     try:
         async for event in iterator:
@@ -789,7 +780,7 @@ def _wrap_close(
     f: "Callable[..., None]",
 ) -> "Callable[..., None]":
     """
-    Closes the AI Client Span, unless the finally block in `_wrap_synchronous_message_iterator()` runs first.
+    Closes the AI Client Span unless the finally block in `_wrap_synchronous_message_iterator()` runs first.
     """
 
     def close(self: "Union[Stream, MessageStream]") -> None:
@@ -810,7 +801,6 @@ def close(self: "Union[Stream, MessageStream]") -> None:
             response_id=self._response_id,
             finish_reason=self._finish_reason,
         )
-
         self._span.__exit__(None, None, None)
         del self._span
 
@@ -861,7 +851,7 @@ def _wrap_async_close(
     f: "Callable[..., Awaitable[None]]",
 ) -> "Callable[..., Awaitable[None]]":
     """
-    Closes the AI Client Span, unless the finally block in `_wrap_asynchronous_message_iterator()` runs first.
+    Closes the AI Client Span unless the finally block in `_wrap_asynchronous_message_iterator()` runs first.
     """
 
     async def close(self: "AsyncStream") -> None:

setup.py

@@ -21,7 +21,7 @@ def get_file_text(file_name):
 
 setup(
     name="sentry-sdk",
-    version="2.54.0",
+    version="2.55.0",
     author="Sentry Team and Contributors",
     author_email="hello@sentry.io",
     url="https://github.com/getsentry/sentry-python",

tests/test_logs.py

@@ -783,3 +783,39 @@ def before_send_log(log, _):
     )
 
     get_client().flush()
+
+
+@minimum_python_37
+@pytest.mark.timeout(5)
+def test_reentrant_add_does_not_deadlock(sentry_init, capture_envelopes):
+    """Adding to the batcher from within a flush must not deadlock.
+
+    This covers the scenario where GC emits a ResourceWarning during
+    _add_to_envelope (or _flush_event.wait/set), and the warning is
+    routed through the logging integration back into batcher.add().
+    See https://github.com/getsentry/sentry-python/issues/5681
+    """
+    sentry_init(enable_logs=True)
+    capture_envelopes()
+
+    client = sentry_sdk.get_client()
+    batcher = client.log_batcher
+
+    reentrant_add_called = False
+    original_add_to_envelope = batcher._add_to_envelope
+
+    def add_to_envelope_with_reentrant_add(envelope):
+        nonlocal reentrant_add_called
+        # Simulate a GC warning routing back into add() during flush
+        batcher.add({"fake": "log"})
+        reentrant_add_called = True
+        original_add_to_envelope(envelope)
+
+    batcher._add_to_envelope = add_to_envelope_with_reentrant_add
+
+    sentry_sdk.logger.warning("test log")
+    client.flush()
+
+    assert reentrant_add_called
+    # If the re-entrancy guard didn't work, this test would hang and it'd
+    # eventually be timed out by pytest-timeout