openai-agents-js releases

What's Changed

• fix: make tracing shutdown best-effort on process exit by @seratch in https://github.com/openai/openai-agents-js/pull/1306

Documentation & Other Changes

• docs: update MCP examples by @seratch in https://github.com/openai/openai-agents-js/pull/1305
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1307

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.11.2...v0.11.3

What's Changed

• fix: add configurable sandbox archive extraction limits by @seratch in https://github.com/openai/openai-agents-js/pull/1299
• fix: include structured sandbox provider error details by @seratch in https://github.com/openai/openai-agents-js/pull/1301
• fix: include Cloudflare sandbox exec and cleanup error details by @seratch in https://github.com/openai/openai-agents-js/pull/1300
• fix: preserve GitRepo root subpath aliases by @seratch in https://github.com/openai/openai-agents-js/pull/1294
• fix: validate sandbox GitRepo subpaths by @seratch in https://github.com/openai/openai-agents-js/pull/1290
• fix: guard no-op tracing span IDs by @seratch in https://github.com/openai/openai-agents-js/pull/1292
• fix: add strict feature validation for chat completions by @seratch in https://github.com/openai/openai-agents-js/pull/1279
• fix: keep trace batch processing alive after exporter errors by @seratch in https://github.com/openai/openai-agents-js/pull/1291
• fix: drop reasoning items orphaned by dropped tool calls by @seratch in https://github.com/openai/openai-agents-js/pull/1280
• fix: preserve latest response id on resume by @seratch in https://github.com/openai/openai-agents-js/pull/1281
• fix: allow callback-only handoff hooks by @seratch in https://github.com/openai/openai-agents-js/pull/1283
• fix: exclude computer instances from provider detection by @seratch in https://github.com/openai/openai-agents-js/pull/1284
• fix: preserve output audio content from output item events (realtime) by @seratch in https://github.com/openai/openai-agents-js/pull/1287
• fix: treat null audio channels as unset (realtime) by @seratch in https://github.com/openai/openai-agents-js/pull/1289
• fix: align Chat Completions strict validation by @seratch in https://github.com/openai/openai-agents-js/pull/1303
• fix avoid duplicating reasoning across parallel tool calls in ai-sdk by @seratch in https://github.com/openai/openai-agents-js/pull/1285

Documentation & Other Changes

• docs: skip corrupt Prisma session records by @seratch in https://github.com/openai/openai-agents-js/pull/1288
• docs: skip corrupt FileSession items during pop by @seratch in https://github.com/openai/openai-agents-js/pull/1298
• docs: fix md formatting for Python version note by @YazdanRa in https://github.com/openai/openai-agents-js/pull/1297
• docs: refine examples auto-run defaults by @seratch in https://github.com/openai/openai-agents-js/pull/1302
• test: isolate and speed up slow sandbox tests by @seratch in https://github.com/openai/openai-agents-js/pull/1304
• test: keep output guardrail tripwires behind sibling completion by @seratch in https://github.com/openai/openai-agents-js/pull/1286
• chore: stabilize examples auto-run for local MCP and sandbox runs by @seratch in https://github.com/openai/openai-agents-js/pull/1295
• chore: upgrade pnpm toolchain to 11.0.9 by @seratch in https://github.com/openai/openai-agents-js/pull/1293
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1282

New Contributors

• @YazdanRa made their first contribution in https://github.com/openai/openai-agents-js/pull/1297

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.11.1...v0.11.2

What's Changed

• fix(sandbox): align Blaxel parity behavior by @mstolarzblaxelai in https://github.com/openai/openai-agents-js/pull/1276
• fix: preserve sandbox env resolvers across manifest merges by @mstolarzblaxelai in https://github.com/openai/openai-agents-js/pull/1275

Documentation & Other Changes

• docs: updates for v0.11.0 by @seratch in https://github.com/openai/openai-agents-js/pull/1271
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1274
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1277

New Contributors

• @mstolarzblaxelai made their first contribution in https://github.com/openai/openai-agents-js/pull/1275

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.11.0...v0.11.1

Key Changes

RealtimeAgent's default is now gpt-realtime-2

Since this version, the default model for RealtimeAgents is gpt-realtime-2: https://developers.openai.com/api/docs/models/gpt-realtime-2

Sandbox local source materialization change

In this version, sandbox local source materialization keeps LocalFile.src and LocalDir.src within the materialization baseDir unless the source path is covered by Manifest.extraPathGrants. The baseDir is the SDK process current working directory when the manifest is applied; relative local sources are resolved from that directory, while absolute local sources must already be inside it or under an explicit grant. This closes a local artifact boundary issue, but it can affect applications that intentionally copy trusted host files or directories from outside that base directory into a sandbox workspace.

import { Manifest, localDir, skills } from '@openai/agents/sandbox';
import { localDirLazySkillSource } from '@openai/agents/sandbox/local';
import { dirname, join } from 'node:path';
import { fileURLToPath } from 'node:url';

// Outside the base dir
const sharedSkillsDir = '/opt/company/agent-skills';

// Under the base dir
const appRoot = dirname(fileURLToPath(import.meta.url));
const repoDir = join(appRoot, 'repo');

const manifest = new Manifest({
  // Having extraPathGrants for the path outside the baseDir is now required
  extraPathGrants: [
    {
      path: sharedSkillsDir,
      readOnly: true,
      description: 'Shared skill bundle.',
    },
  ],
  entries: {
    // This one doesn't need extraPathGrants
    repo: localDir({ src: repoDir }),
  },
});

const skillCapability = skills({
  lazyFrom: localDirLazySkillSource({
    src: sharedSkillsDir,
  }),
});

What's Changed

• feat: default realtime sessions to gpt-realtime-2 by @seratch in https://github.com/openai/openai-agents-js/pull/1270
• fix: constrain local sandbox artifact sources to source base directory by @seratch in https://github.com/openai/openai-agents-js/pull/1267

Documentation & Other Changes

• chore(deps): bump hono from 4.12.14 to 4.12.16 in the npm_and_yarn group across 1 directory by @dependabot[bot] in https://github.com/openai/openai-agents-js/pull/1269
• docs: make computer-use examples use headless click demo by @seratch in https://github.com/openai/openai-agents-js/pull/1273
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1272

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.10.1...v0.11.0

What's Changed

• fix: restore session history when responses compaction replacement fails by @seratch in https://github.com/openai/openai-agents-js/pull/1265
• fix: validate hosted MCP approval policies by @seratch in https://github.com/openai/openai-agents-js/pull/1268

Documentation & Other Changes

• docs: update for #1248 by @seratch in https://github.com/openai/openai-agents-js/pull/1249
• docs: updates for #1250 by @seratch in https://github.com/openai/openai-agents-js/pull/1251
• docs: updates for #1255 by @seratch in https://github.com/openai/openai-agents-js/pull/1256
• docs: document function tool execution concurrency by @seratch in https://github.com/openai/openai-agents-js/pull/1259
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1260
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1266

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.10.0...v0.10.1

Key Changes

Default model change

In this version, the SDK default model is now gpt-5.4-mini instead of gpt-4.1. This could affect agents and runs that do not explicitly set a model. Because the new default is a GPT-5 model, implicit default model settings now include GPT-5 defaults such as reasoning.effort="none" and verbosity="low".

The new default model should work better for most use cases (see the report at https://github.com/openai/openai-agents-js/pull/1248), but if you need to keep the previous default model behavior for some reasons, set a model explicitly on the agent or run config or set the OPENAI_DEFAULT_MODEL environment variable.

maxTurns configuration

This version adds a new option maxTurns=null to disable the Agents SDK run turn limit while preserving the existing default of DEFAULT_MAX_TURNS (10) when maxTurns is omitted.

Tool execution concurrency

This version adds a new SDK-side runtime configuration for local function tool execution concurrency: toolExecution.maxFunctionToolConcurrency on RunConfig, preserves default behavior when unset. The change keeps provider-side ModelSettings.parallelToolCalls separate from SDK-side local execution scheduling.

Server-prefixed MCP tool naming

This version adds a new option MCPConfigin Agent to align with the Python SDK. When Its includeServerInToolNames is set to true, the SDK includes the MCP server name in the tool name to prevent tool name conflicts with other MCP servers.

What's Changed

• feat: switch the default model to a newer mini model (affecting only when a model is unset) by @seratch in https://github.com/openai/openai-agents-js/pull/1248
• feat: allow maxTurns null to disable turn limits by @seratch in https://github.com/openai/openai-agents-js/pull/1247
• feat: accept manifest init shorthands in sandbox configuration by @seratch in https://github.com/openai/openai-agents-js/pull/1250
• feat: add function tool concurrency config by @seratch in https://github.com/openai/openai-agents-js/pull/1254
• feat: align local MCP config with the Python SDK by @seratch in https://github.com/openai/openai-agents-js/pull/1255
• fix: reject external symlink targets during Cloudflare workspace hydrate by @seratch in https://github.com/openai/openai-agents-js/pull/1258

Documentation & Other Changes

• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1253
• chore: upgrade pnpm to 10.33.4 by @seratch in https://github.com/openai/openai-agents-js/pull/1257
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1252

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.9.1...v0.10.0

What's Changed

• fix: preserve duplicate-name agent identity in RunState serialization by @seratch in https://github.com/openai/openai-agents-js/pull/1243
• fix: #1190 reconcile streamed function calls when server-managed runs abort by @seratch in https://github.com/openai/openai-agents-js/pull/1241
• fix: avoid replaying assistant conversation item IDs by @seratch in https://github.com/openai/openai-agents-js/pull/1235

Documentation & Other Changes

• docs: add sandbox agents guides by @seratch in https://github.com/openai/openai-agents-js/pull/1200
• docs: update docs for #1216 by @seratch in https://github.com/openai/openai-agents-js/pull/1217
• docs: updates for #1233 by @seratch in https://github.com/openai/openai-agents-js/pull/1234
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1236
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1237
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1238
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1242
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1245
• chore: upgrade GitHub Actions workflow pins by @seratch in https://github.com/openai/openai-agents-js/pull/1239
• chore: upgrade dev & docs dependencies by @seratch in https://github.com/openai/openai-agents-js/pull/1246
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1240

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.9.0...v0.9.1

What's Changed

Sandbox Agents

This release adds Sandbox Agents, a beta SDK surface for running agents with persistent workspaces and sandbox-backed capabilities in JavaScript.

Sandbox agents build on the existing Agent, Runner, and run flow, while adding workspace manifests, sandbox sessions, capabilities, snapshots, memory, and resume support. They let agents inspect files, run commands, edit repositories, apply patches, generate artifacts, and continue work across runs.

Refer to the Sandbox Agents guide and examples/sandbox/ for more details.

Key additions include:

• SandboxAgent, exported from @openai/agents/sandbox, with sandbox defaults such as defaultManifest, baseInstructions, capabilities, and runAs.
• Manifest, a workspace contract for synthetic files and directories, local files and directories, Git repositories, environment, users, groups, permissions, and mounts.
• SandboxRunConfig, which wires sandbox clients, live sessions, serialized session resume, manifest overrides, snapshots, and materialization limits into each run.
• Built-in capabilities for filesystem access, shell access, patching and editing, image inspection, lazy skills, memory, and compaction.
• Sandbox-aware RunState serialization for resuming runner-managed sandbox sessions.

Sandbox Clients and Hosted Providers

Sandbox agents support local, containerized, and hosted execution backends:

• UnixLocalSandboxClient for local development.
• DockerSandboxClient for container isolation and image parity.
• Hosted sandbox clients for Blaxel, Cloudflare, Daytona, E2B, Modal, Runloop, and Vercel through @openai/agents-extensions/sandbox/* subpath exports.

Provider-specific examples are available under examples/sandbox/extensions/.

Workspaces, Snapshots, Resume, and Memory

This release adds a workspace model for sandbox sessions, including synthetic files and directories, local files and directories, Git repositories, local bind mounts, Docker volume strategies, and typed remote mounts where supported by the selected backend.

It also adds local and remote snapshot store interfaces for carrying workspace contents across runs, plus runner-managed resume through serialized sandbox session state.

Sandbox memory lets future sandbox-agent runs learn from prior runs by storing extracted lessons in the workspace, injecting concise summaries into later runs, and supporting progressive disclosure through deeper rollout summaries. Memory supports read-only and generate-enabled modes, live updates, automatic generation when sessions are flushed, multi-turn grouping, separate memory layouts, and pluggable MemoryStore implementations.

Examples

A new examples/sandbox/ suite demonstrates:

• Basic SandboxAgent execution with a manifest.
• Unix-local and Docker sandbox runners.
• Interactive Unix-local PTY usage.
• Sandbox handoffs and sandbox agents as tools.
• Host-defined tools combined with sandbox agents.
• Filesystem, shell, image, patch, compaction, lazy skill, and memory capabilities.
• Snapshot-based resume and multi-agent or multi-turn memory.
• Hosted provider runners for Blaxel, Cloudflare, Daytona, E2B, Modal, Runloop, and Vercel.

Runtime, Tracing, and Model Plumbing

The release includes the runtime plumbing needed for sandbox agents to work naturally inside the JavaScript SDK:

• Runner-managed sandbox preparation, capability binding, lifecycle handling, cleanup, and resume.
• Per-agent sandbox session tracking for handoffs and agents-as-tools flows.
• Public sandbox agent identity preservation across model filters and runtime hooks.
• Sandbox operation spans for session startup, command execution, filesystem work, snapshots, memory, and provider operations.
• runAs support for compatible shell and filesystem operations.
• Remote sandbox concurrency limits for manifest and local directory materialization.

What's Changed

• feat: add sandbox agents (#1199) by @seratch in https://github.com/openai/openai-agents-js/pull/1210
  • fix: keep public sandbox agent identity in filters by @seratch in https://github.com/openai/openai-agents-js/pull/1226
  • fix: support remote sandbox concurrency limits by @seratch in https://github.com/openai/openai-agents-js/pull/1225
  • fix: reject symlink ancestors in remote local sources by @seratch in https://github.com/openai/openai-agents-js/pull/1223
  • fix: support sandbox filesystem runAs across providers by @seratch in https://github.com/openai/openai-agents-js/pull/1224
  • fix: align sandbox mounts with Python and protect rclone credentials by @seratch in https://github.com/openai/openai-agents-js/pull/1228
  • fix: narrow sandbox public entrypoint by @seratch in https://github.com/openai/openai-agents-js/pull/1230
• feat: expose Responses WebSocket keepalive options by @seratch in https://github.com/openai/openai-agents-js/pull/1219
• feat: add context management model settings by @seratch in https://github.com/openai/openai-agents-js/pull/1233
• feat: add tool item convenience accessors by @seratch in https://github.com/openai/openai-agents-js/pull/1195
• fix: #1212 add code interpreter output include option by @seratch in https://github.com/openai/openai-agents-js/pull/1213
• fix: surface model refusals during run resolution by @seratch in https://github.com/openai/openai-agents-js/pull/1216

Documentation & Other Changes

• docs: use locked MCP filesystem server in examples by @mcgrew-oai in https://github.com/openai/openai-agents-js/pull/1193
• docs: update readme for npm packages by @seratch in https://github.com/openai/openai-agents-js/pull/1227
• ci: improve the automation to set milestone for a PR by @seratch in https://github.com/openai/openai-agents-js/pull/1214
• test: add optional sandbox storage mount integrations by @seratch in https://github.com/openai/openai-agents-js/pull/1229
• chore: upgrade pnpm to 10.33.2 by @seratch in https://github.com/openai/openai-agents-js/pull/1211
• chore: upgrade pnpm to 10.33.3 by @seratch in https://github.com/openai/openai-agents-js/pull/1231
• chore: bump the npm_and_yarn group across 1 directory with 4 updates by @dependabot[bot] in https://github.com/openai/openai-agents-js/pull/1194
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1196

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.8.5...v0.9.0

What's Changed

• feat: #1186 expose createAiSdkUiMessageStream by @mavrickdeveloper in https://github.com/openai/openai-agents-js/pull/1187

Documentation & Other Changes

• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1189
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1188

New Contributors

• @mavrickdeveloper made their first contribution in https://github.com/openai/openai-agents-js/pull/1187

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.8.4...v0.8.5

What's Changed

• fix: #1176 normalize compacted Responses user messages before storing them by @seratch in https://github.com/openai/openai-agents-js/pull/1181
• fix(agents-core): deduplicate trace provider shutdown cleanup by @seratch in https://github.com/openai/openai-agents-js/pull/1182
• fix(agents-realtime): fail fast on unsupported SIP VAD fields by @wsk-builds in https://github.com/openai/openai-agents-js/pull/1170
• fix(agents-extensions): #1163 preserve nested audio config by @wsk-builds in https://github.com/openai/openai-agents-js/pull/1171
• fix(agents-core): restore discriminated union tool schemas by @wsk-builds in https://github.com/openai/openai-agents-js/pull/1172

Documentation & Other Changes

• docs: update external link for Respan by @Nightingalelyy in https://github.com/openai/openai-agents-js/pull/1155
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1156
• docs: fix tools example commands by @wsk-builds in https://github.com/openai/openai-agents-js/pull/1158
• docs(agents-extensions): sync AI SDK docs and examples by @wsk-builds in https://github.com/openai/openai-agents-js/pull/1160
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1161
• docs(nextjs): fix README source path by @wsk-builds in https://github.com/openai/openai-agents-js/pull/1165
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1174
• test(agents-extensions): add AI SDK UI boundary coverage by @wsk-builds in https://github.com/openai/openai-agents-js/pull/1162
• test: stabilize leak detection harness by @wsk-builds in https://github.com/openai/openai-agents-js/pull/1169
• test: preserve tracing in real-model integration fixtures by @seratch in https://github.com/openai/openai-agents-js/pull/1183
• chore: harden pnpm configuration across CI and docs by @mcgrew-oai in https://github.com/openai/openai-agents-js/pull/1159
• fix(husky): disable trufflehog auto-update in pre-commit by @wsk-builds in https://github.com/openai/openai-agents-js/pull/1166
• chore(deps): bump the npm_and_yarn group across 4 directories with 1 update by @dependabot[bot] in https://github.com/openai/openai-agents-js/pull/1157
• chore(deps): bump the npm_and_yarn group across 1 directory with 3 updates by @dependabot[bot] in https://github.com/openai/openai-agents-js/pull/1153
• chore(deps): bump hono from 4.12.8 to 4.12.12 in the npm_and_yarn group across 1 directory by @dependabot[bot] in https://github.com/openai/openai-agents-js/pull/1154
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1168

New Contributors

• @Nightingalelyy made their first contribution in https://github.com/openai/openai-agents-js/pull/1155
• @mcgrew-oai made their first contribution in https://github.com/openai/openai-agents-js/pull/1159
• @wsk-builds made their first contribution in https://github.com/openai/openai-agents-js/pull/1158

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.8.3...v0.8.4

What's Changed

• fix: #1148 reject duplicate agent names in RunState serialization by @seratch in https://github.com/openai/openai-agents-js/pull/1149

Documentation & Other Changes

• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1151
• chore(deps): bump the github-actions group with 4 updates by @dependabot[bot] in https://github.com/openai/openai-agents-js/pull/1146
• chore(deps): bump defu from 6.1.4 to 6.1.6 in the npm_and_yarn group across 0 directory by @dependabot[bot] in https://github.com/openai/openai-agents-js/pull/1152
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1150

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.8.2...v0.8.3

What's Changed

• feat: #279 add OpenAI raw model stream event narrowing helpers by @seratch in https://github.com/openai/openai-agents-js/pull/1091

Documentation & Other Changes

• docs: add retry settings by @seratch in https://github.com/openai/openai-agents-js/pull/1087
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1088
• fix(docs): scope the Zod v3 alias for Astro 6 by @seratch in https://github.com/openai/openai-agents-js/pull/1094
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1093

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.7.0...v0.7.1

What's Changed

• feat: add custom rejection messages for approvals by @seratch in https://github.com/openai/openai-agents-js/pull/1058

Documents & Other Changes

• docs: updates for #1036 by @seratch in https://github.com/openai/openai-agents-js/pull/1037
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1042
• docs: updates for #1040 by @seratch in https://github.com/openai/openai-agents-js/pull/1041
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1043
• docs: improve TypeScript docs entry points and guide navigation by @seratch in https://github.com/openai/openai-agents-js/pull/1044
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1045
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1046
• chore: upgrade pnpm to 10.30.3 and clarify SHA pinning by @seratch in https://github.com/openai/openai-agents-js/pull/1047
• docs: clarify dynamic prompts and runtime doc caveats by @seratch in https://github.com/openai/openai-agents-js/pull/1048
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1049
• docs: align agent and voice agent guides with current SDK behavior by @seratch in https://github.com/openai/openai-agents-js/pull/1050
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1051
• chore: upgrade dev & docs dependencies by @seratch in https://github.com/openai/openai-agents-js/pull/1052
• docs: clarify run context, handoffs, and human-in-the-loop guides by @seratch in https://github.com/openai/openai-agents-js/pull/1053
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1054
• chore(deps): bump hono from 4.12.2 to 4.12.4 in the npm_and_yarn group across 1 directory by @dependabot[bot] in https://github.com/openai/openai-agents-js/pull/1055
• chore: add implementation strategy guidance for compatibility decisions by @seratch in https://github.com/openai/openai-agents-js/pull/1056
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/1059

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.5.3...v0.5.4

What's Changed

• feat(core,realtime): add function tool timeouts by @seratch in https://github.com/openai/openai-agents-js/pull/965

Documents & Other Changes

• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/967

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.4.9...v0.4.10

What's Changed

• feat(extensions): add codex run-context thread reuse and same-thread workflow by @seratch in https://github.com/openai/openai-agents-js/pull/940
• chore(deps): bump @modelcontextprotocol/sdk from 1.25.2 to 1.26.0 in the npm_and_yarn group across 1 directory by @dependabot[bot] in https://github.com/openai/openai-agents-js/pull/939

Documents & Other Changes

• chore: upgrade dev deps by @seratch in https://github.com/openai/openai-agents-js/pull/936
• chore(skills): migrate repository skill paths to .agents/skills by @seratch in https://github.com/openai/openai-agents-js/pull/935
• docs(guides): add missing option coverage across runner, mcp, sessions, and extensions by @seratch in https://github.com/openai/openai-agents-js/pull/937
• docs: update translated document pages by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/938
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/941

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.4.5...v0.4.6

What's Changed

• feat: #921 add structured input builders for agent tools by @seratch in https://github.com/openai/openai-agents-js/pull/924
• feat: add MCP server errorFunction support by @seratch in https://github.com/openai/openai-agents-js/pull/926
• feat: add MCP tool meta resolver support by @seratch in https://github.com/openai/openai-agents-js/pull/919
• feat: #663 add computer tool approvals and run context arg by @seratch in https://github.com/openai/openai-agents-js/pull/920
• feat: #763 add onSafetyCheck hook for computer safety checks by @seratch in https://github.com/openai/openai-agents-js/pull/925
• feat(core,realtime): add configurable approval-rejection tool error messages by @seratch in https://github.com/openai/openai-agents-js/pull/932
• fix: #932 consider traceIncludeSensitiveData option by @seratch in https://github.com/openai/openai-agents-js/pull/933
• fix: populate streamed chat completion choices in generation traces by @seratch in https://github.com/openai/openai-agents-js/pull/934
• fix: preserve zod descriptions in json schema output by @seratch in https://github.com/openai/openai-agents-js/pull/923

Documents & Other Changes

• chore(deps): bump the github-actions group with 2 updates by @dependabot[bot] in https://github.com/openai/openai-agents-js/pull/928
• chore(deps): bump fastify from 5.3.3 to 5.7.3 in the npm_and_yarn group across 1 directory by @dependabot[bot] in https://github.com/openai/openai-agents-js/pull/931
• chore(deps): bump the npm_and_yarn group across 4 directories with 1 update by @dependabot[bot] in https://github.com/openai/openai-agents-js/pull/918
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/922

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.4.4...v0.4.5

What's Changed

• docs: document updates for #687 runInParallel option for input guardrails by @seratch in https://github.com/openai/openai-agents-js/pull/688
• fix: #699 Forward fetch parameter to SSEClientTransport in MCPServerSSE by @aasullivan in https://github.com/openai/openai-agents-js/pull/700
• feat: Add ToolOptions to agents-core package export by @ianyimi in https://github.com/openai/openai-agents-js/pull/704
• fix: strip leading {} from streaming tool call arguments (Bedrock) by @anton-tw in https://github.com/openai/openai-agents-js/pull/712
• fix: #708 data: string in an input_image message item does not work with some providers by @seratch in https://github.com/openai/openai-agents-js/pull/717
• fix: preserve Gemini thought_signature in multi-turn tool calls by @shibu-web in https://github.com/openai/openai-agents-js/pull/718
• feat: #713 Access tool call items in an output guardrail by @seratch in https://github.com/openai/openai-agents-js/pull/716
• feat: #695 Customizable MCP list tool caching by @seratch in https://github.com/openai/openai-agents-js/pull/715
• Upgrade pnpm to 10.24.0 by @seratch in https://github.com/openai/openai-agents-js/pull/720
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/714

New Contributors

• @aasullivan made their first contribution in https://github.com/openai/openai-agents-js/pull/700
• @ianyimi made their first contribution in https://github.com/openai/openai-agents-js/pull/704
• @anton-tw made their first contribution in https://github.com/openai/openai-agents-js/pull/712
• @shibu-web made their first contribution in https://github.com/openai/openai-agents-js/pull/718

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.3.3...v0.3.4

What's Changed

• feat: Add prompt_cache_retention option to ModelSettings by @seratch in https://github.com/openai/openai-agents-js/pull/668
• fix: #638 add unit tests demonstrating how to get usage in streaming mode by @seratch in https://github.com/openai/openai-agents-js/pull/673
• fix: #316 developer-friendly message for output type errors by @seratch in https://github.com/openai/openai-agents-js/pull/672
• fix: #675 top-level voice param in realtime session config does not work by @seratch in https://github.com/openai/openai-agents-js/pull/677
• fix: #683 Failing to run MCP servers when deserializing run state data by @seratch in https://github.com/openai/openai-agents-js/pull/685
• fix: #523 transcript removal issue when being interrupted by @seratch in https://github.com/openai/openai-agents-js/pull/674
• feat: #678 Add a list of per-request usage data to Usage by @seratch in https://github.com/openai/openai-agents-js/pull/686
• feat: #679 Add runInParallel option to input guardrail initialization by @seratch in https://github.com/openai/openai-agents-js/pull/687
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/671

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.3.2...v0.3.3

What's Changed

• feat: Add reasoning.effort: none parameter for gpt-5.1 by @seratch in https://github.com/openai/openai-agents-js/pull/657
• fix: Omit tools parameter when prompt ID is set but tools in the agent is absent by @seratch in https://github.com/openai/openai-agents-js/pull/658
• fix: #638 Add usage data from stream on response (Chat Completions) by @rclayton-godaddy in https://github.com/openai/openai-agents-js/pull/652
• chore: update versions by @github-actions[bot] in https://github.com/openai/openai-agents-js/pull/661

New Contributors

• @rclayton-godaddy made their first contribution in https://github.com/openai/openai-agents-js/pull/652

Full Changelog: https://github.com/openai/openai-agents-js/compare/v0.3.1...v0.3.2