Sourced from openai-agents's releases.

v0.2.5

What's Changed

• Fix tag errors in sessions document page by @​seratch in openai/openai-agents-python#1307
• Update all translated document pages by @​github-actions[bot] in openai/openai-agents-python#1308
• Add temporal demo to docs by @​rm-openai in openai/openai-agents-python#1310
• Fix #1238 by enhancing HandoffInputData and enable passing async functions by @​seratch in openai/openai-agents-python#1302
• Add support to realtime API for setting "speed" of the models responses by @​sect2k in openai/openai-agents-python#1309
• Update all translated document pages by @​github-actions[bot] in openai/openai-agents-python#1313
• Examples: use agent to interact with Remote PDF Documents by @​princeaden1 in openai/openai-agents-python#1319
• Enhance exception guide in docs by @​MuhammadHamidRaza in openai/openai-agents-python#1321
• Update all translated document pages by @​github-actions[bot] in openai/openai-agents-python#1322
• Realtime: make example customizable: by @​rm-openai in openai/openai-agents-python#1332
• Export MultiProvider in public API (Fix #1325) by @​kobol in openai/openai-agents-python#1326
• Add tracing guide for non-OpenAI LLMs in docs/tracing.md by @​UmmeHabiba1312 in openai/openai-agents-python#1329
• Update all translated document pages by @​github-actions[bot] in openai/openai-agents-python#1336
• docs: Clarify and enhance run_demo_loop utility documentation for beginners by @​UmmeHabiba1312 in openai/openai-agents-python#1330
• Fix set_api_key breaking cached property mechanism by @​DanielHashmi in openai/openai-agents-python#1339
• Update all translated document pages by @​github-actions[bot] in openai/openai-agents-python#1341
• Handle processor exceptions and fix tracing log formatting by @​mshsheikh in openai/openai-agents-python#1292
• Fix(mcp): Unreachable structured content branch in invoke_mcp_tool by @​Kunmeer-SyedMohamedHyder in openai/openai-agents-python#1250
• Feat: separate tool_call_item and tool_call_output_item in stream events by @​gdisk in openai/openai-agents-python#974
• Clarify shallow-copy behavior of tools and handoffs in Agent.clone() by @​abdul-kabir-jawed in openai/openai-agents-python#1296
• Fix #1277 missing StopAtTools and ToolsToFinalOutputFunction in agents module by @​seratch in openai/openai-agents-python#1278
• Fix #980 Chat Completions: fails with function name for tool_choice parameter w/ streaming enabled by @​seratch in openai/openai-agents-python#1206
• Fix type annotation and clarify tool behavior docs by @​mshsheikh in openai/openai-agents-python#1355
• Fix style and wording issues in handoffs.py by @​mshsheikh in openai/openai-agents-python#1356
• Fix docstring formatting and add safe check for empty message content by @​mshsheikh in openai/openai-agents-python#1360
• Add functionality to update agent during realtime session by @​marysha-openai in openai/openai-agents-python#1366
• feat(viz): draw MCP servers by @​aaron-ang in openai/openai-agents-python#1368
• Update all translated document pages by @​github-actions[bot] in openai/openai-agents-python#1369
• Realtime: fix interrupt logic by @​rm-openai in openai/openai-agents-python#1370
• Realtime: send session update before tool response by @​rm-openai in openai/openai-agents-python#1388
• v0.2.5 by @​rm-openai in openai/openai-agents-python#1398

New Contributors

• @​sect2k made their first contribution in openai/openai-agents-python#1309
• @​princeaden1 made their first contribution in openai/openai-agents-python#1319
• @​UmmeHabiba1312 made their first contribution in openai/openai-agents-python#1329
• @​Kunmeer-SyedMohamedHyder made their first contribution in openai/openai-agents-python#1250
• @​gdisk made their first contribution in openai/openai-agents-python#974
• @​abdul-kabir-jawed made their first contribution in openai/openai-agents-python#1296
• @​marysha-openai made their first contribution in openai/openai-agents-python#1366
• @​aaron-ang made their first contribution in openai/openai-agents-python#1368

Full Changelog: https://github.com/openai/openai-agents-python/compare/v0.2.4...v0.2.5

v0.2.4

What's Changed

• Add automation script to generate mkdocstrings files by @​seratch in openai/openai-agents-python#1048
• Set up codex for issues and PRs by @​rm-openai in openai/openai-agents-python#1214

... (truncated)

Sourced from openai-agents's changelog.

Release process/changelog

The project follows a slightly modified version of semantic versioning using the form 0.Y.Z. The leading 0 indicates the SDK is still evolving rapidly. Increment the components as follows:

Minor (Y) versions

We will increase minor versions Y for breaking changes to any public interfaces that are not marked as beta. For example, going from 0.0.x to 0.1.x might include breaking changes.

If you don't want breaking changes, we recommend pinning to 0.0.x versions in your project.

Patch (Z) versions

We will increment Z for non-breaking changes:

• Bug fixes
• New features
• Changes to private interfaces
• Updates to beta features

Breaking change changelog

• 5539afc v0.2.5 (#1398)
• 27de49a Realtime: send session update before tool response (#1388)
• bc71e8b Realtime: fix interrupt logic (#1370)
• 88b8199 Update all translated document pages (#1369)
• 54e4087 feat(viz): draw MCP servers (#1368)
• 237d672 Add functionality to update agent during realtime session (#1366)
• 907533a Fix docstring formatting and add safe check for empty message content (#1360)
• e197187 Fix style and wording issues in handoffs.py (#1356)
• 5c73311 Fix type annotation and clarify tool behavior docs (#1355)
• 818344c Fix #980 Chat Completions: fails with function name for tool_choice parameter...
• Additional commits viewable in compare view

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)