Python SDK v0.26.0

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

Python SDK v0.25.0

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

Python SDK v0.24.0

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

Python SDK v0.23.0

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

Python SDK v0.22.1

Changelog

Bug Fixes

• (langchain) Preserve anthropic cache metrics (#455)
• (claude-agent-sdk) Improve error logging (#450)

Other Changes

• (logger) Accept serializable objects as metadata (#437)

Package: https://pypi.org/project/braintrust/0.22.1/

Full Changelog: py-sdk-v0.22.0...py-sdk-v0.22.1

Python SDK v0.22.0

Changelog

Features

• Trace litellm async moderation (#448)

Bug Fixes

• (livekit) Measure eou detection delay (#446)
• (langchain) Avoid double-counting cached input tokens (#445)
• Update type hint for OneOrMoreScores (#444)

Package: https://pypi.org/project/braintrust/0.22.0/

Full Changelog: py-sdk-v0.21.0...py-sdk-v0.22.0

Python SDK v0.21.0

Changelog

Features

• (livekit) Add agents integration (#407)

Package: https://pypi.org/project/braintrust/0.21.0/

Full Changelog: py-sdk-v0.20.0...py-sdk-v0.21.0

Python SDK v0.20.0

Changelog

Features

• (autogen) Trace agents inside teams (#419)
• More explicit default git settings (#408)
• (litellm) Trace text completion calls (#406)

Bug Fixes

• (strands) Close spans with no-op OTEL provider (#420)
• (cohere) Support chat stream context managers (#418)
• (openai) Filter omit sentinel from metadata (#426)
• (logger) Do not retry on 413s (#427)
• Update GitPython constraint for security fix (#423)
• Support autoevals inline score typing (#403)
• (cohere) Preserve v2 stream citations (#391)
• (mistral) Add conversation tool spans (#392)
• (langchain) Normalize anthropic cache token metrics (#411)
• (parameters) Improve dict types (#399)

Package: https://pypi.org/project/braintrust/0.20.0/

Full Changelog: py-sdk-v0.19.0...py-sdk-v0.20.0

Python SDK v0.19.0

Changelog

Features

• (openai) Trace streaming audio transcriptions (#375)
• (anthropic) Add prompt cache ttl metrics (#344)
• (temporal) Add temporal integrations auto instrumentation (#367)

Bug Fixes

• (mistral) Add tool spans for completions (#381)
• (cohere) Add tool spans for chat tool calls (#380)
• (devserver) Honor evaluator.project_id when request omits it (#372)

Package: https://pypi.org/project/braintrust/0.19.0/

Full Changelog: py-sdk-v0.18.0...py-sdk-v0.19.0

Python SDK v0.18.0

Changelog

Features

• (openai_agents) Pull cached tokens through into metrics (#364)
• (perf/pydantic_ai) Simplify trace shaping (#357)
• (perf/adk) Reduce tracing serialization overhead (#358)
• (llamaindex) Add native LlamaIndex SDK integration (#355)

Bug Fixes

• Make OpenAI wrapping compatible with ddtrace (#370)
• Handle PEP 649 NameError in inspect.signature on Python 3.14 (#361)
• Use Mapping instead of dict for EvalResult.scores (#360)

Maintenance

• Modernize typing for Python 3.10+ minimum (#356)

Package: https://pypi.org/project/braintrust/0.18.0/

Full Changelog: py-sdk-v0.17.0...py-sdk-v0.18.0