build(deps): bump openai-agents from 0.20.0 to 0.21.1 in /openai-agents-sdk

[dependabot]

Bumps openai-agents from 0.20.0 to 0.21.1.

Release notes

Sourced from openai-agents's releases.

v0.21.1

What's Changed

• feat(core): add model call timeouts by @​seratch in openai/openai-agents-python#4428
• feat(sandbox): add run-scoped sandbox working directories by @​seratch in openai/openai-agents-python#4427
• feat(sandbox): allow Docker sandboxes to disable networking by @​koadegno in openai/openai-agents-python#4452
• feat(sandbox): add Modal sandbox resource options by @​Filimoa in openai/openai-agents-python#4455
• fix(core): honor exact call approval decisions by @​seratch in openai/openai-agents-python#4447
• fix(core): count Responses requests without usage by @​seratch in openai/openai-agents-python#4453
• fix(core): close all MultiProvider children after failures by @​fszcd in openai/openai-agents-python#4438
• fix(core): reject partially matched stacked anchors by @​Coiggahou2002 in openai/openai-agents-python#4431
• fix(chat-completions): Chat Completions reasoning replay by @​seratch in openai/openai-agents-python#4432
• fix(realtime): truncate audio at zero elapsed time by @​Chirag6722 in openai/openai-agents-python#4457
• fix(realtime): end iteration after clean server close by @​seratch in openai/openai-agents-python#4461
• fix(sessions): prevent advanced SQLite structure table conflicts by @​seratch in openai/openai-agents-python#4454
• fix(sessions): include compaction usage in run totals by @​seratch in openai/openai-agents-python#4446
• fix(sandbox): validate view_image raster content by @​seratch in openai/openai-agents-python#4462
• fix(sandbox): keep model paths POSIX-normalized by @​sylvesterkaczmarek in openai/openai-agents-python#4416
• fix(sandbox): normalize apply_patch paths as POSIX by @​sylvesterkaczmarek in openai/openai-agents-python#4437

Documentation & Other Changes

• docs: updates for v0.21.0 release by @​seratch in openai/openai-agents-python#4381
• docs: list Tuning Engines tracing integration by @​cerebrixos in openai/openai-agents-python#4440
• fix: update cffi lock for Python 3.14 by @​seratch in openai/openai-agents-python#4448
• release: 0.21.1 by @​seratch in openai/openai-agents-python#4467

New Contributors

• @​Coiggahou2002 made their first contribution in openai/openai-agents-python#4431
• @​fszcd made their first contribution in openai/openai-agents-python#4438
• @​cerebrixos made their first contribution in openai/openai-agents-python#4440
• @​Filimoa made their first contribution in openai/openai-agents-python#4455
• @​koadegno made their first contribution in openai/openai-agents-python#4452
• @​Chirag6722 made their first contribution in openai/openai-agents-python#4457

Full Changelog: openai/openai-agents-python@v0.21.0...v0.21.1

v0.21.0

Key Changes

This minor release does not introduce a known breaking SDK behavior change. The minor version bump is for the new provider-neutral testing APIs and the OpenAI Python v3 compatibility update.

Highlights:

• Added agents.testing, agents.realtime.testing, and agents.voice.testing utilities for deterministic Agent, Sandbox, Realtime, and Voice workflow tests without provider requests.
• Updated OpenAI provider compatibility to openai>=3.0.0,<4, including HTTPX2-aware request, response, transport, and exception handling.
• Hardened RunState interruption snapshots, recursive agent-tool approvals, max-turn finalization, streaming cleanup, and sensitive-error redaction.
• Improved MCP lifecycle snapshot isolation and added configurable retry backoff ceilings.
• Added Sandbox Runloop existing-secret support and tightened view-image path grants.
• Added stricter Voice validation for invalid channels, frame rates, incomplete multichannel frames, and non-finite audio rates.

... (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

0.22.0

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.

0.21.0

Version 0.21.0 requires openai v3 and moves the Agents SDK's OpenAI HTTP integrations to HTTPX2. Applications that use the default OpenAI client do not need to change their client setup, but applications that customize the OpenAI HTTP layer may need to migrate transport-facing code.

Highlights:

• The required OpenAI dependency is now openai>=3.0.0,<4. A clean core installation uses HTTPX2 and no longer installs legacy httpx as a direct dependency.
• The default OpenAI provider, Voice provider, Responses WebSocket support, tracing exporter, and provider retry normalization now use HTTPX2. Their existing Agents SDK public configuration and runtime behavior remain unchanged.
• Applications that pass http_client= to AsyncOpenAI should migrate custom clients, transports, authentication, event hooks, mock transports, timeout values, URLs, requests, responses, and transport exception handling from httpx to httpx2. Prefer the OpenAI Python SDK's DefaultAsyncHttpx2Client when the application needs the OpenAI client's defaults plus custom HTTP options. See Custom HTTP clients with openai v3.
• The Agents SDK does not convert arbitrary legacy HTTPX objects to HTTPX2. The OpenAI Python SDK's temporary legacy-client compatibility path requires an explicit httpx installation and should be treated as a migration bridge.
• Local MCP HTTP customization continues to follow the installed MCP package: MCP Python SDK v1 supplies and uses legacy httpx, while MCP Python SDK v2 uses httpx2. Ordinary MCP connections do not need application changes. See MCP Python SDK v1 and v2.
• Public provider-neutral testing utilities now cover Agent model, Sandbox session, Realtime session, and Voice pipeline workflows without provider or process dependencies. See Testing for recipes and guidance on when to keep the real provider adapter or integration boundary.

Commits

• b01ea1d release: 0.21.1 (#4467)
• 2632043 fix(realtime): end iteration after clean server close (#4461)
• 4cb461a fix(sandbox): validate view_image raster content (#4462)
• fdcec69 fix: forward Docker network mode in security test
• e5f75fd fix(realtime): truncate audio at zero elapsed time (#4457)
• 2f1c83d feat(sandbox): allow Docker sandboxes to disable networking (#4452)
• 3a888de feat(extensions): add Modal sandbox resource options (#4455)
• b4faf70 feat(core): add model call timeouts (#4428)
• 2588d15 fix: prevent advanced SQLite structure table conflicts (#4454)
• 94da8ed fix(core): count Responses requests without usage (#4453)
• Additional commits viewable in compare view