Bump openai-agents from 0.0.7 to 0.15.1 in /openai-agents

[dependabot]

Bumps openai-agents from 0.0.7 to 0.15.1.

Release notes

Sourced from openai-agents's releases.

v0.15.1

What's Changed

• feat: expose Responses WebSocket keepalive options by @​seratch in openai/openai-agents-python#3080
• fix: restore UnixLocal PTY terminal signal defaults by @​seratch in openai/openai-agents-python#3082
• fix: #3074 restore SIGINT defaults for UnixLocal PTY children by @​Aphroq in openai/openai-agents-python#3075

Documentation & Other Changes

• docs: add 0.15 changelog by @​seratch in openai/openai-agents-python#3058
• docs: update translated document pages by @​github-actions[bot] in openai/openai-agents-python#3064
• docs: improve quickstart documentation for Windows OS users by @​seratch in openai/openai-agents-python#3071
• docs: update translated document pages by @​github-actions[bot] in openai/openai-agents-python#3072
• test: cover guardrail name fallback to function name by @​Quratulain-bilal in openai/openai-agents-python#3073
• chore: harden Dapr Redis integration fixture loading by @​Aphroq in openai/openai-agents-python#3078
• Release 0.15.1 by @​github-actions[bot] in openai/openai-agents-python#3083

New Contributors

• @​Aphroq made their first contribution in openai/openai-agents-python#3078

Full Changelog: openai/openai-agents-python@v0.15.0...v0.15.1

v0.15.0

Key Changes

Better model refusal handling

In this version, model refusals are now surfaced explicitly as ModelRefusalError instead of being treated as empty text output or, for structured outputs, causing the run loop to retry until MaxTurnsExceeded.

This affects code that previously expected a refusal-only model response to complete with final_output == "". To handle refusals without raising, provide a model_refusal run error handler:

result = Runner.run_sync(
    agent,
    input,
    error_handlers={"model_refusal": lambda data: data.error.refusal},
)

For structured-output agents, the handler can return a value matching the agent's output schema, and the SDK will validate it like other run error handler final outputs.

What's Changed

• fix: #3055 surface model refusals during run resolution by @​seratch in openai/openai-agents-python#3057

Documentation & Other Changes

• docs: add missing space after period in MCPServerStdio docstring by @​GopalGB in openai/openai-agents-python#3053
• chore(deps): bump actions/github-script from 8.0.0 to 9.0.0 by @​dependabot[bot] in openai/openai-agents-python#3059

... (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

0.15.0

In this version, model refusals are now surfaced explicitly as ModelRefusalError instead of being treated as empty text output or, for structured outputs, causing the run loop to retry until MaxTurnsExceeded.

This affects code that previously expected a refusal-only model response to complete with final_output == "". To handle refusals without raising, provide a model_refusal run error handler:

result = Runner.run_sync(
    agent,
    input,
    error_handlers={"model_refusal": lambda data: data.error.refusal},
)

For structured-output agents, the handler can return a value matching the agent's output schema, and the SDK will validate it like other run error handler final outputs.

0.14.0

This minor release does not introduce a breaking change, but it adds a major new beta feature area: Sandbox Agents, plus the runtime, backend, and documentation support needed to use them across local, containerized, and hosted environments.

Highlights:

• Added a new beta sandbox runtime surface centered on SandboxAgent, Manifest, and SandboxRunConfig, letting agents work inside persistent isolated workspaces with files, directories, Git repos, mounts, snapshots, and resume support.
• Added sandbox execution backends for local and containerized development via UnixLocalSandboxClient and DockerSandboxClient, plus hosted provider integrations for Blaxel, Cloudflare, Daytona, E2B, Modal, Runloop, and Vercel through optional extras.
• Added sandbox memory support so future runs can reuse lessons from prior runs, with progressive disclosure, multi-turn grouping, configurable isolation boundaries, and persisted-memory examples including S3-backed workflows.
• Added a broader workspace and resume model, including local and synthetic workspace entries, remote storage mounts for S3/R2/GCS/Azure Blob Storage/S3 Files, portable snapshots, and resume flows via RunState, SandboxSessionState, or saved snapshots.
• Added substantial sandbox examples and tutorials under examples/sandbox/, covering coding tasks with skills, handoffs, memory, provider-specific setups, and end-to-end workflows such as code review, dataroom QA, and website cloning.
• Extended the core runtime and tracing stack with sandbox-aware session preparation, capability binding, state serialization, unified tracing, prompt cache key defaults, and safer sensitive MCP output redaction.

... (truncated)

Commits

• ceb238f Release 0.15.1 (#3083)
• 41c646d fix: restore UnixLocal PTY terminal signal defaults (#3082)
• 4b2881c feat: expose Responses WebSocket keepalive options (#3080)
• a47b7ea fix: #3074 restore SIGINT defaults for UnixLocal PTY children (#3075)
• 42c3015 chore: harden Dapr Redis integration fixture loading (#3078)
• ae224b4 test: cover guardrail name fallback to function name (#3073)
• 756fa43 docs: update translated document pages (#3072)
• 841f72f docs: improve quickstart documentation for Windows OS users (#3071)
• 611d080 docs: update translated document pages (#3064)
• 48d7e9c docs: add 0.15 changelog (#3058)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

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 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)

[dependabot]

Superseded by #31.