chore(deps): bump openai-agents from 0.22.0 to 0.22.2 in /openai-agents-sdk

[dependabot]

Bumps openai-agents from 0.22.0 to 0.22.2.

Release notes

Sourced from openai-agents's releases.

v0.22.2

What's Changed

• feat: support current image generation tool options by @​seratch in openai/openai-agents-python#4932
• fix(sandbox): prevent UnixLocal file API symlink races by @​seratch in openai/openai-agents-python#4931
• fix(sessions): reset compaction response chain after pop by @​rksharma-owg in openai/openai-agents-python#4934

Documentation & Other Changes

• docs: document v0.22.1 behavior updates by @​seratch in openai/openai-agents-python#4577
• release: 0.22.2 by @​seratch in openai/openai-agents-python#4935

Full Changelog: openai/openai-agents-python@v0.22.1...v0.22.2

v0.22.1

What's Changed

• feat(core): support image results in web search tools by @​seratch in openai/openai-agents-python#4898
• feat(core): customize output guardrail blocked messages by @​seratch in openai/openai-agents-python#4594
• feat(mcp): add server-wide guardrails to MCP tools by @​seratch in openai/openai-agents-python#4632
• feat(sandbox): add configurable Unix-local environment isolation by @​seratch in openai/openai-agents-python#4640
• feat(sandbox): allow labels on Docker sandbox containers by @​seanxuu in openai/openai-agents-python#4564
• feat(voice): expose streamed transcription options by @​seratch in openai/openai-agents-python#4645
• fix(core): detach aggregated request usage entries by @​green3sf in openai/openai-agents-python#4519
• fix(core): fail closed on empty tool arguments by @​hsusul in openai/openai-agents-python#4545
• fix(core): strip created_by when replaying RunItems as input by @​hsusul in openai/openai-agents-python#4568
• fix(core): strict_schema error message, REPL whitespace input, debug docstrings by @​simpleqt in openai/openai-agents-python#4600
• fix(core): max_turns no longer clobbers a tripped input guardrail exception in streaming by @​shoemoney in openai/openai-agents-python#4606
• fix(core): preserve serialized approval resume ownership by @​seratch in openai/openai-agents-python#4613
• fix(core): read tool args without Pydantic property shadowing by @​hsusul in openai/openai-agents-python#4627
• fix(core): accept JSON Schema type arrays of object for tool outputs by @​hsusul in openai/openai-agents-python#4647
• fix(core): honor End of File hunks when the file ends in a newline by @​lllakshit in openai/openai-agents-python#4661
• fix(core): preserve tuple annotations for variadic tool arguments by @​Excelius-Wang in openai/openai-agents-python#4655
• fix(core): fix streamed response span losing response/input when consumer stops at completed event by @​XuQuanxin04 in openai/openai-agents-python#4692
• fix(core): apply **kwargs value annotation to each keyword value by @​abhay-codes07 in openai/openai-agents-python#4714
• fix(core): reject **kwargs keys that collide with named tool parameters by @​rajarshidattapy in openai/openai-agents-python#4674
• fix(core): reject fixed-length tuple annotations for variadic tool arguments by @​subhashpolisetti in openai/openai-agents-python#4735
• fix(core): preserve Field constraints on variadic tool parameters by @​rioyu123 in openai/openai-agents-python#4739
• fix(core): close model providers created by Runner by @​Excelius-Wang in openai/openai-agents-python#4785
• fix(core/voice): honor OpenAI provider options over default clients by @​green3sf in openai/openai-agents-python#4530
• fix(chat-completions): merge a streamed turn's message into its pending tool-call message by @​mmjerge in openai/openai-agents-python#4728
• fix(chat-completions): raise ModelBehaviorError on truncated empty completions by @​weike-zhang in openai/openai-agents-python#4513
• fix(chat-completions) reject unpaired function outputs in Chat Completions by @​apcha-oai in openai/openai-agents-python#4699
• fix(extensions): skip AdvancedSQLiteSession usage store when the branch has no turn by @​rioyu123 in openai/openai-agents-python#4822
• fix(extensions): nest extra_body on the any-llm chat path by @​hsusul in openai/openai-agents-python#4544
• fix(mcp): deep-copy cached tools before returning them by @​hsusul in openai/openai-agents-python#4525
• fix(mcp): clear active MCP servers after cleanup by @​sylvesterkaczmarek in openai/openai-agents-python#4586
• fix(mcp): deduplicate managed servers by @​hsusul in openai/openai-agents-python#4591
• fix(realtime): advance crossed guardrail thresholds by @​hsusul in openai/openai-agents-python#4590
• fix(realtime): preserve item status on retrieved conversation items by @​shoutoutuoadi325 in openai/openai-agents-python#4598

... (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

Commits

• 83c737f release: 0.22.2 (#4935)
• 25af629 fix(sessions): reset compaction response chain after pop (#4934)
• e3a03ed fix(sandbox): prevent UnixLocal file API symlink races (#4931)
• 2b5057f feat: support current image generation tool options (#4932)
• 544b8b0 docs: update translated pages
• f355af6 docs: document v0.22.1 behavior updates (#4577)
• f0b884a release: 0.22.1 (#4576)
• ee37563 fix: simplify verification and stabilize sandbox tests (#4916)
• 8bed141 fix(sessions): preserve Session transformations during generation tracking (#...
• dc80569 fix(sandbox): preserve workdir for shell command lists (#4915)
• Additional commits viewable in compare view