ddtrace 2.10.0rc3

on Python PyPI

New Features

• Anthropic: Adds support for tracing message calls using tools.
• LLM Observability: Adds support for tracing Anthropic messages using tool calls.
• azure: Removes the restrictions on the tracer to only run the mini-agent on the consumption plan. The mini-agent now runs regardless of the hosting plan

Bug Fixes

• Code Security: add the boto package to the IAST patching denylist.
• celery: changes error.message span tag to no longer include the traceback that is already included in the error.stack span tag.
• CI Visibility: fixes source file information that would be incorrect in certain decorated / wrapped scenarios and forces paths to be relative to the repository root, if present.
• LLM Observability: This resolves a typing hint error in the ddtrace.llmobs.utils.Documents helper class constructor where type hints did not accept input dictionaries with integer or float values.
• LLM Observability: This fix resolves an issue where the OpenAI, Anthropic, and AWS Bedrock integrations were always setting temperature and max_tokens parameters to LLM invocations. The OpenAI integration in particular was setting the wrong temperature default values. These parameters are now only set if provided in the request.
• redis: This fix resolves an issue in the redis exception handling where an UnboundLocalError was raised instead of the expected BaseException.
• ASM: This fix resolves an issue where the requests integration would not propagate when apm is opted out (i.e. in ASM Standalone).
• profiling: Fixes an issue where task information coming from echion was encoded improperly, which could segfault the application.
• tracing: fixes a potential crash where using partial flushes and tracer.configure() could result in an IndexError
• flask: Fix scenarios when using flask-like frameworks would cause a crash because of patching issues on startup.
• wsgi: Ensures the status of wsgi Spans are not set to error when a StopIteration exception is raised marked the span as an error. With this change, StopIteration exceptions in this context will be ignored.
• langchain: tag non-dict inputs to LCEL chains appropriately. Non-dict inputs are stringified, and dict inputs are tagged by key-value pairs.

Other Changes

• LLM Observability: the SDK allowed users to submit an unsupported numerical evaluation metric type. All evaluation metric types submitted with numerical type will now be automatically converted to a score type. As an alternative to using the numerical type, use `score instead.