Python SDK v0.15.0

Changelog

Features

• Add per-input trial_count support to Eval() (#274)
• (mistral) Trace audio api calls (#275)
• (anthropic) Trace beta managed agents apis (#270)
• (mistral) Trace OCR API calls (#268)
• (openai|litellm) Attach speech outputs (#267)
• (litellm) Trace transcription calls (#264)
• (litellm) Trace image generation calls (#261)
• (openai) Trace responses api tool spans (#253)
• (anthropic) Trace server tool content blocks as tool spans (#255)
• (openai) Preserve streaming refusal output (#258)

Bug Fixes

• CachedSpanFetcher no longer caches empty results permanently (#79)
• (openai) Trace chat streaming audio attachments (#271)
• (openai) Log audio file attachments (#265)
• (adk) Avoid duplicate sync runner invocation spans (#252)
• (integrations) Unify multimodal attachment materialization (#247)

Package: https://pypi.org/project/braintrust/0.15.0/

Full Changelog: py-sdk-v0.14.0...py-sdk-v0.15.0

Python SDK v0.14.0

Changelog

Features

• (openai) Trace images api calls (#245)
• (openai) Instrument Audio API (speech, transcriptions, translations) (#232)

Bug Fixes

• (framework) Split Output TypeVar into Output and Expected (#243)
• (framework) Preserve defaults for unmatched callback params (#241)
• (cli) Reject whitespace in python bundle filenames (#237)
• Resolve reportUnknownMemberType under pyright strict mode (#242)
• (anthropic) Capture structured output metadata (#238)
• (claude_agent_sdk) Log ResultMessage metrices (#225)
• (anthropic) Capture time_to_first_token when using .text_stream (#234)

Maintenance

• Generated SDK types (#248)
• Generated SDK types (#246)

Other Changes

• Include sandbox runtime in list request (#227)

Package: https://pypi.org/project/braintrust/0.14.0/

Full Changelog: py-sdk-v0.13.0...py-sdk-v0.14.0

Python SDK v0.13.0

Changelog

Features

• (google_genai) Trace interactions api methods (#210)
• (openai) Migrate openai wrapper and add claude agent sdk integration (#206)
• (integrations) Add mistral sdk integration (#199)

Bug Fixes

• (openai) Preserve logprobs for streaming chat spans (#215)
• (pydantic_ai) Support moved tool manager module (#224)
• (claude_agent_sdk) Use result message output (#218)
• (anthropic) Convert multimodal base64 inputs to attachments (#212)
• Allow eval filtering with EvalCase objects (#211)
• (claude_agent_sdk) Trace top-level query calls (#216)
• (claude_agent_sdk) Serialize thinking blocks with type (#213)
• (devserver) Tighten cors origin validation (#203)
• (dspy) Add adapter callback tracing (#190)
• (anthropic) Move ephemeral cache creation fields to metadata (#205)
• (anthropic) Capture server-side tool usage metrics (#192)

Maintenance

• Add minimum supported versions for genai and dspy (#220)
• Generated SDK types (#221)

Package: https://pypi.org/project/braintrust/0.13.0/

Full Changelog: py-sdk-v0.12.1...py-sdk-v0.13.0

Python SDK v0.12.1

Changelog

Bug Fixes

• (anthropic) Capture nested usage metrics and metadata (#189)
• Encode request body as UTF-8 bytes to prevent Latin-1 corruption (#194)
• Fix python sandbox parameters (#191)

Package: https://pypi.org/project/braintrust/0.12.1/

Full Changelog: py-sdk-v0.12.0...py-sdk-v0.12.1

Python SDK v0.12.0

Changelog

Features

• (langchain) Add automatic instrumentation (#183)
• Add openrouter integration (#158)
• Add agentscope integration for tracing (#147)
• (google_genai) Add generate_images tracing support (#161)

Bug Fixes

• (litellm) Patch async embeddings for auto instrumentation (#186)
• (anthropic) Log stop reason in span output (#185)
• (google_genai) Attach grounding_metadata to streaming responses (#155)
• (temporal) Forward kwargs to maximize temporal version compat (#179)

Other Changes

• Rehydrate remote prompt parameters (#166)

Package: https://pypi.org/project/braintrust/0.12.0/

Full Changelog: py-sdk-v0.11.0...py-sdk-v0.12.0

Python SDK v0.11.0

Changelog

Features

• Instrument claude agent sdk hooks (#141)
• (perf) Optimize _to_bt_safe and bt_safe_deep_copy hot paths (#139)
• Add support for nested subagents tool calls in ADK integration (#131)
• Instrument Anthropic Messages Batch API (#127)
• Add patch command to HTTPConnection
• Introduce new integrations API and convert anthropic (#118)
• Instrument google genai embed_content methods (#111)

Bug Fixes

• Add context manager support to traced stream wrappers in openai integration (#120)
• Add x-bt-use-gateway to CORS allowed headers (#119)
• Warn when Eval() receives an empty dataset (#109)
• Capture thinking config in span metadata for anthropic integration (#110)

Package: https://pypi.org/project/braintrust/0.11.0/

Full Changelog: py-sdk-v0.10.0...py-sdk-v0.11.0

Python SDK v0.10.0

Changelog

Features

• Port load_parameters to the Python SDK (#90)
• Make atexit flush registration optional (#81)
• Tracing for raw_response in wrap_openai (#80)

Bug Fixes

• Prevent serialization from emitting pydantic serializer warnings (#95)
• Make sure request error gets logged in same line as message (#96)
• Make agno rely on provider attribute (#92)

Other Changes

• Align span metadata type (#89)
• Add sandbox registration to python sdk (#26)

Package: https://pypi.org/project/braintrust/0.10.0/

Full Changelog: py-sdk-v0.9.0...py-sdk-v0.10.0

Python SDK v0.9.0

Changelog

Features

• Improve claude agent sdk spans (#66)
• Wrap Agent.to_cli_sync (#57)
• Add tags support to SDK builder classes (#33)

Bug Fixes

• Make sure parallel agent calls get correct child spans in claude agent sdk (#73)
• Multi turn evaluation causes JSON serialization error (#62)
• Make sure cross context cleanup doesn't raise an error (#58)

Maintenance

• Run python publishing via gha trigger (#72)
• Allow for nox commands to be passed down (#56)

Other Changes

• Improve claude agent sdk tests (#65)
• Enable claude agent sdk tests in CI (#68)

Package: https://pypi.org/project/braintrust/0.9.0/

Full Changelog: py-sdk-v0.8.0...py-sdk-v0.9.0

Python SDK v0.8.0

Changelog

Features

• Add pytest integration (#25)
• Add Agno Workflow tracing support (#46)
• Improve compatibility with agno 2.5.0 (#41)
• Capture ExceptionGroup sub-exceptions in traceback (#20)

Bug Fixes

• Add performance extra to braintrust package (#50)
• Make ADK and pydantic integration wrappers thread safe (#23)

Maintenance

• Bump SDK version to 0.8.0 (#49)
• Clean up Python SDK READMEs (#51)
• Remove API key usage in CI (#39)
• Exclude test packages from setuptools (#40)

Other Changes

• Use mise everywhere and clean up contributing docs (#52)
• Remove redundant imports inside the methods (#34)

Package: https://pypi.org/project/braintrust/0.8.0/

Full Changelog: py-sdk-v0.7.0...py-sdk-v0.8.0

py-sdk-v0.7.0

What's Changed

• fix: Declare merged_git_metadata_settings before usage (#10)
• feat: Auto-enable Google ADK integration in braintrust package (#13)
• feat: Allow passing tags for evals and experiments (#16)

Full Changelog: py-sdk-v0.6.0...py-sdk-v0.7.0