chore(deps): bump openai-agents from 0.21.0 to 0.22.0 in /openai-agents-sdk

[dependabot]

Bumps openai-agents from 0.21.0 to 0.22.0.

Release notes

Sourced from openai-agents's releases.

v0.22.0

Key Changes

Version 0.22.0 is a minor release because it adds substantial runtime hardening and tightens an existing provider configuration contract. Applications that combine an explicit openai_client with organization or project must move those values to the AsyncOpenAI client.

Highlights:

• Redacts terminal function-tool output rejected by agent output guardrails from replayable and persisted SDK state.
• Raises ModelBehaviorError for non-streaming Responses with terminal status failed or incomplete.
• Rejects conflicting provider options when OpenAIProvider receives an explicit client.
• Isolates usage accounting between independent RunState checkpoints while preserving nested-agent aggregation.
• Expands agents registered through handoff(agent) in generated graphs.
• Clarifies the existing shallow-copy behavior of Agent.clone() and RealtimeAgent.clone().

What's Changed

• fix(core): redact blocked tool outputs from replay state by @​seratch in openai/openai-agents-python#4507
• fix(core): reject ignored explicit-client options for OpenAIProvider by @​sylvesterkaczmarek in openai/openai-agents-python#4497
• fix(core): preserve Griffe logger inheritance by @​sylvesterkaczmarek in openai/openai-agents-python#4494
• fix(core): reject terminal failed/incomplete responses in non-streaming get_response by @​weike-zhang in https://github.* * fix(core): isolate usage between RunState checkpoints by @​chiruu12 in openai/openai-agents-python#4479 fix(sandbox): require apply_patch update hunks by @​li2631026381-alt in openai/openai-agents-python#4470
• fix(sandbox): enforce Windows mypy compatibility by @​seratch in openai/openai-agents-python#4499
• fix(tracing): respect model-data logging redaction for record_model_error_on_span by @​sylvesterkaczmarek in openai/openai-agents-python#4496
• fix(tracing): clean up processors after tracing is disabled by @​sylvesterkaczmarek in openai/openai-agents-python#4502
• fix(visualization): expand handoff() targets in agent graphs by @​hsusul in openai/openai-agents-python#4517

Documentation & Other Changes

• docs: document v0.21.1 runtime behavior by @​seratch in openai/openai-agents-python#4460
• docs: correct Agent.clone list attribute semantics by @​thegoodengineer in openai/openai-agents-python#4474
• docs: add testing resources to llms indexes by @​teachershuang in openai/openai-agents-python#4509
• ci: align Python version coverage by @​seratch in openai/openai-agents-python#4475
• test: use sys.executable instead of tee for the stdio placeholder command by @​ErenAta16 in openai/openai-agents-python#4478
• fix: keep Codex verification for development sandboxed by @​seratch in openai/openai-agents-python#4508 com/fix(models): reject terminal failed/incomplete responses in non-streaming get_response openai/openai-agents-python#4516
• release: 0.22.0 by @​seratch in openai/openai-agents-python#4523

New Contributors

• @​li2631026381-alt made their first contribution in openai/openai-agents-python#4470
• @​thegoodengineer made their first contribution in openai/openai-agents-python#4474
• @​teachershuang made their first contribution in openai/openai-agents-python#4509
• @​weike-zhang made their first contribution in openai/openai-agents-python#4516
• @​chiruu12 made their first contribution in openai/openai-agents-python#4479

Full Changelog: openai/openai-agents-python@v0.21.1...v0.22.0

v0.21.1

What's Changed

... (truncated)

Changelog

Sourced from openai-agents's changelog.

0.22.0

Version 0.22.0 tightens failure handling and data isolation for several existing APIs. Applications that construct OpenAIProvider with an explicit client and also pass organization or project to the provider must remove those duplicate arguments.

Highlights:

• When an agent-level output guardrail blocks final output produced directly by a terminal function tool, the SDK retains a replay-valid call/output pair only when validated fields permit safe reconstruction. The original function_call_output payload is replaced with the fixed text "Output withheld by an output guardrail." in session history, RunState, and streamed result state, and payload-bearing current-response guardrail metadata is cleared or replaced. If the current response contains reasoning or another unsupported shape, the SDK discards the complete current-response suffix instead. Earlier accepted turns and guardrail results remain available. See Output guardrails.
• Non-streaming OpenAI Responses calls now raise ModelBehaviorError when the returned response has terminal status failed or incomplete, matching the existing streamed terminal-event handling. This applies to OpenAIResponsesModel and the Responses path in AnyLLMModel. See Exceptions.
• [OpenAIProvider][agents.models.openai_provider.OpenAIProvider] now also raises UserError when openai_client is combined with organization or project. The existing conflicts with api_key, base_url, and websocket_base_url are unchanged. Configure these values on the explicit AsyncOpenAI client instead. See API keys and clients.
• Each RunResult.to_state() checkpoint now owns an independent usage snapshot. A resumed result starts with the checkpoint totals and adds its own model calls without mutating the source result or sibling checkpoints. Nested Agent.as_tool() resumes continue to aggregate post-resume usage into the active outer run. See Usage in RunState checkpoints.
• Agent visualization now recursively expands the tools, MCP servers, and downstream handoffs of a target registered with handoff(agent), matching direct Agent entries in an agent's handoffs list. See Generating a graph.
• The Agent.clone() and RealtimeAgent.clone() API guidance now states their existing shallow-copy behavior precisely: list attributes that are not overridden remain the same list objects. Pass a new list when the clone must own the container independently. See Cloning/copying agents.

Commits

• 4df9ecf release: 0.22.0 (#4523)
• fb8fa1b fix(core): isolate usage between RunState checkpoints (#4479)
• 9432f7e fix(visualization): expand handoff() targets in agent graphs (#4517)
• 0486792 fix(core/extensions): reject terminal failed/incomplete responses in non-stre...
• 36dbc36 docs: add testing resources to llms indexes (#4509)
• ed644fc fix(core): redact blocked tool outputs from replay state (#4507)
• 2c55603 test: make stream event ordering deterministic
• 21a1f9b fix: avoid Windows integration bootstrap crashes
• 32e4526 ci: change windows ci configuration for stability
• ebb746d fix: keep Codex verification for development sandboxed (#4508)
• Additional commits viewable in compare view