// AI Platform Drift
OpenAI Agents JS SDK v0.22.0-alpha.2 requires coordinated five-package upgrade, removes SDKRunner
OpenAI Agents JavaScript SDK releases · published 2026-11-13 06:46 UTC
WHAT CHANGEDOpenAI Agents JavaScript SDK v0.22.0-alpha.2 removes the experimental SDKRunner bridge and @openai/agents/migration imports. All five bundled packages (@openai/agents, @openai/agents-codex, @openai/agents-core, @openai/agents-openai, @openai/agents-realtime) must upgrade together. New environments default to writePolicy: 'strict', which permits only workspace writes and explicitly granted writableRoots; older checkpoints without an executor-policy digest require explicit writePolicy: 'legacy' to restore with an executor. Portable checkpoints require the exact native Codex revision that saved them.
WHY IT MATTERSApplications using SDKRunner or migration imports will break. Upgrading only some of the five packages will cause version conflicts. Existing checkpoints cannot restore in strict-write environments without explicit legacy policy configuration, forcing either policy changes or new conversations. Portable checkpoints become unrestorable if the exact Codex revision is unavailable.
WHAT TO DOBefore upgrading, identify all uses of SDKRunner and @openai/agents/migration. Upgrade all five packages together in a single operation. For applications with saved checkpoints, either configure writePolicy: 'legacy' on restore environments or plan to start new conversations under strict execution. Review the migration guide at the release URL for native Agent, Session, and Turn API replacements.
Model-reported confidence 95% (not measured accuracy)
Primary source ↗
written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
+## v0.22.0-alpha.2 +https://github.com/openai/openai-agents-js/releases/tag/v0.22.0-alpha.2 +2026-11-08T08:27:27Z + +v0.22.0-alpha.2 +Highlights + +Add native fileSearch(), codeInterpreter(), and imageGeneration() tools, with retained provider results and streamed progress. codeInterpreter() also accepts allowedCallers. webSearch() adds filters, location, tool choice, and citation details. +Control active work with exact-step steering, typed supervisory outcomes, and maxModelSteps. Optional RunBudget limits gate later work based on root requests, observed tokens, and estimated cost. +Recover native conversations through application-owned SessionStore storage, with durable tool-call records and explicit reconciliation of uncertain results. fileSessionStore() provides a local file adapter. This preview supports root conversations with application-managed function tools; it does not support MCP, manual tools, environments, native children, goals, or portable checkpoints. +Connect native agents over A2A 1.0 through @openai/agents/a2a. Call remote agents, serve a native Agent, or integrate deferred remote work. The adapter uses JSON-RPC polling; your application owns authorization, durable storage, execution, and reconciliation of uncertain mutations. +Build speech workflows with VoicePipeline, OpenAISpeechProvider, and NativeSessionVoiceWorkflow from @openai/agents/voice. The native workflow speaks validated final string output after the turn settles. A Realtime example delegates substantive work to a native Session. + +Upgrade actions + +Keep all five bundled SDK packages together when upgrading: @openai/agents, @openai/agents-codex, @openai/agents-core, @openai/agents-openai, and @openai/agents-realtime. The new @openai/agents-codex package owns the native runtime; application imports remain at @openai/agents and its supported subpaths. +Replace the removed experimental SDKRunner bridge and @openai/agents/migration imports. Use native Agent, Session, and Turn APIs directly, or retain classic workflows at @openai/agents/classic. Native and classic agents and state remain separate. Follow the migration guide. +Review executor write grants. New environments default to writePolicy: 'strict', which permits workspace writes and explicitly granted writableRoots. Local environments support strict writes only. Older checkpoints without an executor-policy digest require an explicit remote writePolicy: 'legacy' environment to restore with an executor. Start a new conversation to use strict execution. Portable checkpoints require the exact native Codex revision that saved them. + +Added + +Control captured turns with turn.steerExact() and acceptance receipts, turn.waitForAttention(), and typed interruption outcomes. Exact steering rejects a stale native step with StaleTurnError. +Limit root work with maxModelSteps, including the remaining limit after manual suspension. Optional RunBudget limits cover root request admissions, observed tokens, and estimated cost. Budgets gate subsequent work; they do not guarantee a spending cap or cover independent child requests. +Edit sampling-only input, instructions, and tool presentations with prepareRequest. Original history, validators, handlers, and permissions retain authority. This opt-in profile requires explicit HTTP, standard Responses models, and eligible root function or MCP tools; it excludes environments, hosted tools, children, compaction, and active portable checkpoints. +List and read MCP resources and templates with listMcpResources(), listMcpResourceTemplates(), and readMcpResource(). Discover and retrieve prompts with listMcpPrompts() and getMcpPrompt(). These operations require an idle Session and return application-owned data without adding it to model context. MCP declarations can select no tools for resource-only use. +Opt into workspace search through project_glob and project_grep. Use sandboxEnvironment() to connect native execution to existing sandbox storage, or read-only, same-path local directory mounts on Linux. Provider-backed storage requires an application-supplied authenticated executor connection. +Add explicit TraceContext propagation, tool callback trace context, sampled turn receipts, passive request metadata, and retained response observations with provider-reported status and usage. +Inspect selected native errors through the read-only responseIntegrityReason field. It is null when the original owned cause is unavailable. +Retain selected original model context alongside a supplied compaction summary. Idle local Sessions with NativeGoals can also set or update a paused goal. +Return a failed tool result after a callback timeout with timeoutBehavior: 'error_as_result' and optional timeoutErrorFunction. The default still fails the turn. Timeout handling joins entered callback cleanup and cannot undo completed effects. + +Fixed + +Recover MCP connections without replaying calls whose outcomes are unknown. Stop sampling after final HTTP 401 or 403 responses and bound credential recovery across transport fallback. +Preserve synchronous function results, cache-write token counts, and tracing and privacy settings across queued submissions and later child turns. Report unknown model context windows as null. +Preserve cleanup ownership after failed one-shot runs and reconciliation. Cancellation and Session close prevent new automatic compaction requests. +Reduce native binary size and memory use, reuse compatible HTTP clients and bundled model catalogs across Sessions, and avoid loading the classic agent runtime through native sandbox helpers.
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
| triage verdict | MATERIAL at 0.92, needed 0.5 |
|---|---|
| triage reasoning | Alpha release with multiple breaking changes, removed APIs, new mandatory patterns, and migration requirements. |
| signals | new alpha release with breaking changes · removed experimental SDKRunner bridge and migration imports · new default executor write policy: 'strict' (breaking change) · new required package coordination: five bundled SDK packages must upgrade together · new RunBudget limits feature affecting cost and token tracking · new SessionStore storage API for conversation recovery · new A2A 1.0 agent-to-agent integration · new VoicePipeline and speech workflow support · new MCP resource/prompt discovery APIs · migration guide required for SDKRunner removal |
| suppression | — |
| triage model | anthropic/claude-haiku-4.5 ($0.00000) |
| writer model | anthropic/claude-sonnet-4.5 ($0.00000) |