chore(deps): bump openai-agents from 0.18.3 to 0.19.1 in /openai-agents-sdk

[dependabot]

⚠️ Dependabot is rebasing this PR ⚠️

Rebasing might not happen immediately, so don't worry if this takes some time.

Note: if you make any changes to this PR yourself, they will take precedence over the rebase.

---

Bumps openai-agents from 0.18.3 to 0.19.1.

Release notes

Sourced from openai-agents's releases.

v0.19.1

What's Changed

• feat(sandbox): support native host paths in path grants by @​seratch in openai/openai-agents-python#4009
• fix: redact Realtime audio format diagnostics by @​seratch in openai/openai-agents-python#3992
• fix: redact Blaxel unmount paths in logging by @​seratch in openai/openai-agents-python#3993
• fix: retry pre-response WebSocket server errors by @​dk3yyyy in openai/openai-agents-python#3991
• fix(run): cancel the parallel input-guardrail task when the model turn fails by @​gunjanjaswal in openai/openai-agents-python#3982
• fix(run): allow empty streamed model input by @​hsusul in openai/openai-agents-python#3995
• fix(models): route falsey mapped providers by @​hsusul in openai/openai-agents-python#3996
• fix(memory): count valid SQLite session items for positive limits by @​hsusul in openai/openai-agents-python#4001
• fix(run): count streamed retries when terminal usage is missing by @​hsusul in openai/openai-agents-python#4002
• fix(run): cancel streamed models when input guardrails fail by @​hsusul in openai/openai-agents-python#4004
• fix: preserve zero Blobfuse attribute cache timeout by @​hsusul in openai/openai-agents-python#4006
• fix(tracing): enforce max_batch_size during force_flush and shutdown in BatchTraceProcessor by @​hsusul in openai/openai-agents-python#3985
• fix(agent-tools): honor falsey input builders by @​hsusul in openai/openai-agents-python#4007
• fix: cancel sibling enablement checks on failure by @​hsusul in openai/openai-agents-python#4005

Documentation & Other Changes

• docs: updates for 0.19.0 by @​seratch in openai/openai-agents-python#3872
• docs: fix a URL in sandbox example code by @​ShawnSiao in openai/openai-agents-python#3987
• docs: repair tracing integration links by @​ShawnSiao in openai/openai-agents-python#3986
• docs: use decorators module throughout examples by @​seratch in openai/openai-agents-python#3946
• Release 0.19.1 by @​github-actions[bot] in openai/openai-agents-python#4010

New Contributors

• @​dk3yyyy made their first contribution in openai/openai-agents-python#3991
• @​ShawnSiao made their first contribution in openai/openai-agents-python#3987

Full Changelog: openai/openai-agents-python@v0.19.0...v0.19.1

v0.19.0

Key Changes

This minor release does not introduce a breaking change. The minor version bump reflects a significant new OpenAI Responses feature area: Programmatic Tool Calling.

Highlights:

• Added agents.tool.ProgrammaticToolCallingTool, which lets supported OpenAI Responses models generate JavaScript to coordinate eligible tools. It supports per-tool allowed_callers, structured function-tool outputs, and integration with Runner streaming, guardrails, approvals, sessions, and RunState. See Programmatic Tool Calling for setup and constraints.
• Added the public agents.decorators module and the shorter @tool alias alongside the existing function and guardrail decorators. Function tools now also support async callable objects.
• SDK configuration now consistently accepts either typed settings objects or dictionaries across agents, runs, models, sessions, sandboxes, and voice pipelines, with validation for unknown settings.
• Hardened error and diagnostic logging across models, tools, MCP, Realtime, sessions, sandboxes, and tracing to avoid exposing raw sensitive payloads while preserving useful debugging context.
• Improved AnyLLM, LiteLLM, and Chat Completions compatibility, preserved session history across model retries, and added retries for WebSocket overloads that occur before a response starts.
• Added VercelCloudBucketMountStrategy. Mounted sessions exclude bucket contents from workspace persistence and intentionally do not support dynamic mount changes or session resume.

What's Changed

• feat: add Programmatic Tool Calling support by @​seratch in openai/openai-agents-python#3833
  • fix: remove programmatic transcripts from handoff tool filtering by @​seratch in openai/openai-agents-python#3879

... (truncated)

Changelog

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

0.19.0

This minor release does not introduce a breaking change. The minor version bump reflects a significant new OpenAI Responses feature area: Programmatic Tool Calling.

Highlights:

• Added [ProgrammaticToolCallingTool][agents.tool.ProgrammaticToolCallingTool], which lets supported OpenAI Responses models generate JavaScript to coordinate eligible tools. It supports per-tool allowed_callers, structured function-tool outputs, and integration with Runner streaming, guardrails, approvals, sessions, and RunState. See Programmatic Tool Calling for setup and constraints.
• Added the public agents.decorators module and the shorter @tool alias alongside the existing function and guardrail decorators. Function tools now also support async callable objects.
• SDK configuration now consistently accepts either typed settings objects or dictionaries across agents, runs, models, sessions, sandboxes, and voice pipelines, with validation for unknown settings.
• Hardened error and diagnostic logging across models, tools, MCP, Realtime, sessions, sandboxes, and tracing to avoid exposing raw sensitive payloads while preserving useful debugging context.
• Improved AnyLLM, LiteLLM, and Chat Completions compatibility, preserved session history across model retries, and added provider retry guidance for WebSocket overloads that occur before a response starts so opt-in Runner retry policies can act when replay is permitted.
• Added create-time-only S3 mounts for Vercel sandboxes through VercelCloudBucketMountStrategy. Mounted sessions exclude bucket contents from workspace persistence and intentionally do not support dynamic mount changes or session resume.

0.18.0

This minor release does not introduce a breaking change. The minor version bump is for the Realtime agents default model update only.

Highlights:

• Realtime agents now use gpt-realtime-2.1 as the default model, so new Realtime setups use the latest recommended model without extra configuration.

0.17.0

In this version, sandbox local source materialization keeps LocalFile.src and LocalDir.src within the materialization base_dir unless the source path is covered by Manifest.extra_path_grants. The base_dir is the SDK process current working directory when the manifest is applied; relative local sources are resolved from that directory, while absolute local sources must already be inside it or under an explicit grant. This closes a local artifact boundary issue, but it can affect applications that intentionally copy trusted host files or directories from outside that base directory into a sandbox workspace.

To migrate, grant trusted host roots at the manifest level with SandboxPathGrant, preferably as read-only when the sandbox only needs to read those files:

from pathlib import Path
</tr></table> 

... (truncated)

Commits

• ddc39d0 Release 0.19.1 (#4010)
• 1dddc0d feat(sandbox): support native host paths in path grants (#4009)
• e75cdd2 fix: cancel sibling enablement checks on failure (#4005)
• 3f45d9e fix: honor falsey input builders in agent-tools (#4007)
• 71aa44e Preserve zero Blobfuse attribute cache timeout (#4006)
• 3142f3a fix(run): cancel streamed models when input guardrails fail (#4004)
• e8311b4 fix(run): count streamed retries when terminal usage is missing (#4002)
• 35c8805 fix(memory): count valid SQLite session items for positive limits (#4001)
• bb3d64e docs: update translated pages
• f1becff docs: update missing info
• Additional commits viewable in compare view