v4.13.0rc1

✨ New Features

• Trace and span IDs are now generated more safely in AWS Lambda MicroVM environments, reducing the risk of duplicate IDs.
• Adds OpenTelemetry thread-context publication on Linux, enabling compatible profiling tools to correlate samples with the active trace and span.
• Adds `DD_TRACE_OTEL_SEMANTICS_ENABLED` to opt in to OpenTelemetry trace semantics for spans created through OpenTelemetry APIs and for OpenTelemetry Protocol (OTLP) trace export.
• Introduces per-integration kill-switch environment variables for AI Guard: `DD_AI_GUARD_ANTHROPIC_ENABLED` and `DD_AI_GUARD_LANGCHAIN_ENABLED` (both `true` by default).
• Add support for the `DD_APPSEC_AGENTIC_ONBOARDING` environment variable for AAP.
• Added `DD_BOTOCORE_BEDROCK_RESOLVE_INFERENCE_PROFILE` (default `false`) to resolve underlying foundation models for Bedrock calls using an application-inference-profile ARN as `modelId`.
• Introduces capture of session metadata (session id, user id, and app name) from the Google ADK `Session` object on LLM Observability spans.
• Spans generated under an agent are now automatically attributed to their nearest agent ancestor.
• Added `agent_service` as a preferred alias for the `ml_app` argument across LLMObs SDK methods.
• Auto-instrumented LLM integrations now automatically link Datadog Managed Prompts retrieved with `LLMObs.get_prompt()` and rendered with `.format()` to the resulting LLM span.
• `LLMObs.get_prompt()` now resolves environment-scoped prompt versions and supports targeting for A/B testing. Set `DD_ENV` to select the version for that environment. The signature is now keyword-only after `prompt_id` and accepts `targeting_key` and `**attributes`.
• Adds a `version` argument to `LLMObs.get_prompt()` for retrieving an exact prompt version.
• Introduces support for attaching images to messages on LLM spans. Input and output messages annotated via `LLMObs.annotate` now accept an optional `image_parts` field.
• The OpenAI integration now automatically instruments the Realtime API (`client.realtime.connect(...)`, both sync and async).
• Adds prompt management methods to `LLMObs` for creating, updating, deleting, and listing prompts and prompt versions in the prompt registry.
• Adds the `env_ids` argument to prompt creation and version update methods, allowing prompt versions to be deployed to feature-flag environments.
• `session_id` now propagates to following spans in a trace.
• Adds support for submitting LLM Observability spans for synchronous and asynchronous streaming chat completion calls using the `mistralai` client.
• Adds `DD_CODE_COVERAGE_FLAGS` to group and filter uploaded code coverage reports for CI visibility.
• Unhandled Python exceptions are now reported through the crashtracker, providing crash reports with exception type, message, and Python stack trace.
• Enables obfuscation by default for stats computation.
• Exception profiling is now enabled by default when the profiler is active on Python 3.12+.
• Exception profiling now captures the full Python call stack at the point of the raise.
• Adds experimental APM span enrichment for the Feature Flagging and Experimentation (FFE) OpenFeature provider when `DD_EXPERIMENTAL_FLAGGING_PROVIDER_SPAN_ENRICHMENT_ENABLED=true`.
• The experimental OpenFeature provider now reports aggregated server-side flag evaluations to Datadog.