Changelog

Features

• (devserver) Support remote dataset version and environment selection (#622)

Bug Fixes

• (adk) Avoid logging stream cleanup as errors (#626)
• (langchain) Prevent async runs from inheriting ended spans (#624)
• Eval parameters omit null description (#613)
• (pydantic_ai) Allowlist kwargs pass-through, drop eager message reshape (#610)
• (strands) Allowlist metrics, add span_origin, fix agent metadata reads (#612)
• (temporal) Pass Exception directly to span.log(error=...) (#611)

Package: https://pypi.org/project/braintrust/0.31.0/

Full Changelog: py-sdk-v0.30.1...py-sdk-v0.31.0

Changelog

Bug Fixes

• (openai) Allowlist metadata pass-through, drop eager response serialization (#606)
• (openai) Preserve async parsing for streaming responses (#607)
• (openrouter) Allowlist metadata pass-through, drop eager serialization (#608)

Package: https://pypi.org/project/braintrust/0.30.1/

Full Changelog: py-sdk-v0.30.0...py-sdk-v0.30.1

Changelog

Features

• (perf/huggingface_hub) Optimize how dict attributes are set (#591)

Bug Fixes

• Normalize list score dicts in remote evals (#595)
• (mistral) Drop eager response serialization, use allowlist metadata pass-through (#604)
• (llamaindex) Stop emitting llm spans over delegated provider calls, add provider metadata (#602)
• (livekit_agents) Allowlist metadata fields, drop eager serialization (#603)
• (litellm) Use underlying provider for metadata, drop eager serialization (#594)
• (langchain) Add provider metadata, route tools to metadata, allowlist span fields (#593)
• (instructor) Add model/provider metadata, drop __future__ import (#592)
• (google_genai) Add provider metadata, route tools to metadata, drop eager serialization (#590)

Package: https://pypi.org/project/braintrust/0.30.0/

Full Changelog: py-sdk-v0.29.0...py-sdk-v0.30.0

Changelog

Features

• Per-integration instrumentation.name on span origin (#576)

Bug Fixes

• (crewai) Add provider metadata, route tools to metadata, drop eager serialization (#587)
• (dspy) Align span shape with spec, drop over-serialization, avoid nested llm spans (#588)
• (cohere) Drop redundant _try_to_dict pass in tool-call iteration (#586)
• (claude_agent_sdk) Add provider metadata, drop deep-copy serialization, allowlist hook fields (#585)
• (bedrock_runtime) Improve metrics, tools, and attachments on spans (#584)
• (anthropic) Drop redundant bt_safe_deep_copy passes in tracing (#583)
• (agno) Route tools to metadata, materialize media attachments, propagate exception objects (#582)
• (agentscope) Improve data attached to spans (#581)
• (adk) Fix llm span metadata (provider, tools, errors) (#580)

Package: https://pypi.org/project/braintrust/0.29.0/

Full Changelog: py-sdk-v0.28.0...py-sdk-v0.29.0

Changelog

Features

• Add span origin provenance (#570)

Bug Fixes

• (litellm) Use allowlist for span metadata (#578)
• Preserve custom PYTHON_ENV span origin (#577)

Package: https://pypi.org/project/braintrust/0.28.0/

Full Changelog: py-sdk-v0.27.0...py-sdk-v0.28.0

Changelog

Features

• (anthropic) Trace messages.parse outputs (#562)

Bug Fixes

• Function invocation 405s on EU/self-hosted (strip /v1/proxy from proxy_conn) (#541)
• Avoid duplicate spans when a full fetch follows a typed fetch (#546)
• Fix Temporal replay span parent propagation (#560)

Other Changes

• Expose realtime flag for span fetcher (#542)

Package: https://pypi.org/project/braintrust/0.27.0/

Full Changelog: py-sdk-v0.26.0...py-sdk-v0.27.0

Changelog

Features

• (prompts) Add async prompt loading (#537)
• (evals) Forward/pick up bt eval <...> --sample N flag (#532)
• Otel compatible distributed tracing (#496)
• (pydantic_ai) Support pydantic-ai 2.0 (#538)

Package: https://pypi.org/project/braintrust/0.26.0/

Full Changelog: py-sdk-v0.25.0...py-sdk-v0.26.0

Changelog

Features

• (bedrock) Trace bedrock runtime calls (#519)
• (openai) Trace inline moderation metadata (#507)
• (agentscope) Support 2.x integration APIs (#501)
• Add classifier function push builder (#497)

Bug Fixes

• (experiments) Pass base_experiment_id to summarize (#512)
• (langchain) Stop double-counting anthropic cache tokens in prompt totals (#510)
• Strip nulls from remote eval prompt parameter defaults (#508)

Package: https://pypi.org/project/braintrust/0.25.0/

Full Changelog: py-sdk-v0.24.0...py-sdk-v0.25.0

Changelog

Features

• (invoke) Expose overrides field on invoke() (#489)
• Upwards-recursively read .env.braintrust containing BRAINTRUST_API_KEY (#466)

Bug Fixes

• Honor org git metadata settings for experiments (#486)
• (livekit_agents) Skip empty LiveKit function tool spans (#476)
• (google_genai) Make sure streaming spans attach to correct parent (#484)

Other Changes

• Centralize env parsing (#472)

Package: https://pypi.org/project/braintrust/0.24.0/

Full Changelog: py-sdk-v0.23.0...py-sdk-v0.24.0

Changelog

Features

• Add Instructor integration (#465)
• Add HuggingFace Hub integration (#452)

Bug Fixes

• (logger) Defensively collect no git metadata when org returns nothing (#453)

Other Changes

• Dataset pipeline follow ups (#470)
• Dataset pipelines (#384)

Package: https://pypi.org/project/braintrust/0.23.0/

Full Changelog: py-sdk-v0.22.1...py-sdk-v0.23.0