OpenToolslogo
ToolsExpertsNewsletter
AdvertiseLearn AI
  1. Home
  2. /
  3. News
  4. /
  5. OpenAI Agents SDK preview separates local profiles from portable checkpoints
Updated 7 minutes ago

Share this article

PostShare

In This Article

  • Two persistence paths in a separate SDK preview
  • Choose the conversation artifact before planning recovery
  • A portable checkpoint still needs a compatible application
  • An unknown tool outcome can prevent local reopening
  • A recovery handoff record to prepare before interruption

Most Popular

1AI SDK 6.0.324 preserves tool disabling when SDK tools are absent2Workflow adds atomic starts3MCP Inspector’s pattern checks diverge

Topics

AI agentsOpenAIDeveloper tools

AI news in your inbox

Weekly updates on tools, models, and the companies building them.

Subscribe

Related News

AI SDK 6.0.324 preserves tool disabling when SDK tools are absent

Nov 7, 2026

AI SDK 6.0.324 preserves tool disabling when SDK tools are absent

The v6 patch keeps an explicit toolChoice: none when SDK tools are omitted or empty. Perplexity users also need the compatible provider guard; package versions and the serialized request answer different upgrade questions.

Developer tools
Workflow adds atomic starts

Nov 6, 2026

Workflow adds atomic starts

Run admission and tool retries protect different identities.

AI agentsDeveloper tools
MCP Inspector’s pattern checks diverge

Nov 6, 2026

MCP Inspector’s pattern checks diverge

v1.0.4 skips patterns; v2.14.0 limits evaluation.

MCPDeveloper tools

Footer

Company name

The right AI tool is out there. We'll help you find it.

LinkedInX

Knowledge Hub

  • News
  • Resources
  • Newsletter
  • Blog
  • AI Tool Reviews
  • YouTube Summary
  • YouTube Transcript Generator

Industry Hub

  • AI Companies
  • AI Tools
  • AI Models
  • MCP Servers
  • Muse Connectors
  • AI Tool Categories
  • Top AI Use Cases

For Builders

  • Submit a Tool
  • Submit a MCP
  • Experts & Agencies
  • Advertise
  • Compare Tools
  • Favourites

Legal

  • Privacy Policy
  • Terms of Service

© 2026 OpenTools - All rights reserved.

Archive photograph of OpenAI cofounder Sam Altman speaking at TechCrunch Disrupt San Francisco in October 2019.
Source: Photo: Steve Jennings/Getty Images for TechCrunch, “TechCrunch Disrupt San Francisco 2019 - Day 2,” © 2019 Getty Images, via Wikimedia Commons and TechCrunch Flickr. CC BY 2.0. Cropped and resized. · Source image

OpenAI Agents SDK preview separates local profiles from portable checkpoints

By OpenTools Team · November 7, 2026

Alpha.6 adds LocalStorage and expands SessionState recovery. Its pinned guide keeps runtime compatibility, current tool authority and unknown external effects as separate checks.

Two persistence paths in a separate SDK preview

OpenAI’s Agents SDK preview adds LocalStorage for reopening a conversation from a local profile and expands portable SessionState recovery, according to its tracked alpha.6 changelog. Those are different recovery choices: keeping a profile directory available and moving a serialized checkpoint require different artifacts and application setup.

The alpha.6 prerelease was published November 3; its tracked changelog still labels that version “Unreleased.” (Release record)

This guide concerns the preview API at v0.24.0-alpha.6. The pinned repository README directs users to GitHub release wheels and says the openai-agents package on PyPI is the previous SDK, without the API shown here. The analysis below combines the pinned documentation’s storage and recovery contracts; we have not installed the preview or tested recovery. Its practical question is which conversation artifact an application can retain, and what must be supplied again before work continues.

Choose the conversation artifact before planning recovery

The sessions guide describes three choices:

  • A live Session: retain the open Session when the conversation only needs to continue within the current application process.
  • A local profile: retain the profile directory and session.id. Reopen using the same directory and resume=saved_id, with current application configuration.
  • A portable snapshot: obtain SessionState from await session.save_state(), keep it in trusted storage, and serialize with state.to_json() when needed. The guide loads that value with SessionState.from_json().

A local profile permits one native writer at a time. It cannot export portable state through save_state(), suspend() or fork(), and the guide says not to combine local storage or resume with portable state. Choosing a profile therefore does not leave a documented portable-export route available later.

For a handoff to another process or host, list the retained conversation artifact separately from the resources the application must reconstruct. The guide explicitly says portable checkpoints do not copy workspace files or live processes; both restoration methods need current tools, context and provider configuration. A saved conversation is only one part of that handoff.

A portable checkpoint still needs a compatible application

Portable restore requires the same pinned Codex revision as the SDK that saved the checkpoint, according to the restore guide. Recognizing the JSON format is insufficient. Keep the matching SDK wheel available; changing the checkpoint’s codex_revision field does not migrate its contents.

The application must also open each restore with a fresh Agent and isolated storage, match saved Python and manual tool definitions, accepted instructions and any applicable output type, and supply current callbacks, credentials and context. Current MCP declarations can narrow an old selection. Saved text does not choose credentials or grant permissions.

Instruction recovery needs its own policy decision. The guide’s state.instructions accessor uses trusted checkpoint storage as the instruction source. If the application instead requires independently configured current instructions, restore requires an exact match and rejects a mismatch. Editing saved native history to insert new instructions or credentials is not the documented solution.

Saved model settings are another compatibility check: portable restore retains them. The guide rejects non-None opening model or model_settings overrides, including an empty settings object. Its permitted idle-update path comes after restoration; Sessions opened with NativeAgents cannot change the model or model settings. A recovery record should identify the configuration that will actually resume.

An unknown tool outcome can prevent local reopening

The local recovery section says reopening fails with RuntimeError when saved history includes a function call whose outcome is unknown, or an active child runtime that cannot be restored. No new model request starts in either case. One example in the guide is a crash after an external effect occurred but before its result was recorded.

The prescribed first step is to preserve the profile and inspect the application’s records of external effects before starting another conversation. Repeating resume does not resolve the unknown outcome. The guide provides no public operation to repair that history, and checking external records does not itself repair it.

That boundary changes the next operator’s decision. Conversation recovery and effect verification need separate entries: one records whether the SDK can reopen the conversation; the other records what the application can establish about work already performed. The checkpoint warning likewise says a checkpoint does not coordinate concurrent processes or guarantee durable execution. If an effect occurred but its result was never accepted, retrying may repeat it.

A recovery handoff record to prepare before interruption

A useful handoff can combine those documented limits into five entries. This is an unexecuted planning record, not a recovery test or a guarantee:

  1. Persistence choice and artifact: identify an open Session, a retained local directory plus conversation ID, or a trusted portable checkpoint. Record where it is kept and which application owns it.
  2. Compatible runtime: for a portable checkpoint, retain the matching SDK wheel and pinned Codex revision. Record the saved model/settings that restoration will keep.
  3. Current application bindings: identify the tool definitions, callbacks, credentials, context and instruction policy required by the intended restore. Keep secrets in the application’s normal credential store.
  4. Capture state: distinguish an idle save_state() from a supported settled manual suspend(). Check the applicable capability and checkpoint readiness; the guide says readiness reserves nothing and saving checks again.
  5. External-effect evidence: identify the application records an operator can inspect after interruption. Record unknown outcomes as unknown, and retain the original conversation artifact rather than assuming a retry repaired it.

The same guide says restoring idle child histories does not automatically resume interrupted child work, and retained planning data does not start work or grant tools. That makes a successful restore an input to the application’s next decision about work, with the documented compatibility and effect checks still relevant.

Reporting is based on the pinned documentation, © 2025 OpenAI, MIT license. The guide’s separate NetworkPolicy/offline-executor subsection is marked unreleased and is outside the behavior described here.

Archival photograph: OpenAI cofounder Sam Altman at TechCrunch Disrupt San Francisco on October 3, 2019. Photo source; CC BY 2.0. Cropped and resized; the photograph supplies company context.

Sources

  1. 1.tracked alpha.6 changelog (github.com)
  2. 2.Release record (github.com)
  3. 3.restore guide (github.com)
  4. 4.© 2025 OpenAI, MIT license (github.com)
  5. 5.Photo source (commons.wikimedia.org)
  6. 6.CC BY 2.0 (creativecommons.org)
  7. 7.github.com (github.com)
  8. 8.flickr.com (flickr.com)
  9. 9.github.com (github.com)
  10. 10.creativecommons.org (creativecommons.org)

Tags

AI agentsOpenAIDeveloper tools