fix: keep OpenAI reasoning responses stateful

[KyleAMathews]

Executive Summary

Built-in OpenAI/OpenAI Codex reasoning model payloads now force store: true so OpenAI Responses continuations can replay reasoning/tool-call state reliably. This prevents follow-up agent steps from failing with missing rs_* reasoning item errors.

Root Cause

OpenAI Responses reasoning/tool-call continuations can include prior rs_* reasoning items in subsequent requests. The upstream Responses payload defaults to store: false, which means OpenAI does not persist those items server-side. When a later request references one of those non-persisted item ids, OpenAI can return:

Item with id ... not found

Approach

When applying built-in provider payload defaults for OpenAI reasoning models, keep the existing reasoning-effort normalization and also force the Responses payload to be stateful:

return {
  ...body,
  store: true,
  reasoning: {
    ...existingReasoning,
    effort,
  },
}

The test coverage verifies that:

• OpenAI reasoning payloads get store: true.
• An incoming store: false is intentionally overridden.
• Non-OpenAI providers, such as DeepSeek, do not receive this payload override.

Key Invariants

• Only built-in OpenAI/OpenAI Codex reasoning model payload defaults should force store: true.
• Existing payload fields should be preserved unless intentionally overridden.
• Existing reasoning effort normalization should continue to apply.

Non-goals

• This does not change non-OpenAI provider behavior.
• This does not implement a stateless/ZDR-compatible encrypted reasoning replay path.
• This does not patch @mariozechner/pi-ai; it applies the built-in agent payload default at our integration layer.

Trade-offs

The alternative is to keep store: false and preserve/replay full reasoning.encrypted_content for stateless operation. That is more complex and unnecessary for the built-in agent default path. Using store: true matches OpenAI's stateful Responses flow and directly fixes the observed continuation failure.

Verification

GITHUB_BASE_REF=main node scripts/check-changeset.mjs
pnpm --filter @electric-ax/agents exec vitest run test/model-catalog.test.ts
pnpm --filter @electric-ax/agents typecheck

Also attempted the prep command's suggested Vitest thread flag:

pnpm --filter @electric-ax/agents exec vitest run test/model-catalog.test.ts --pool-options.threads.maxThreads=2

That failed because this Vitest version rejects the flag as an unknown option (--poolOptions). The same targeted test passes without that unsupported flag.

Files Changed

• .changeset/openai-reasoning-store-true.md — patch changeset for @electric-ax/agents.
• packages/agents/src/model-catalog.ts — forces store: true for built-in OpenAI reasoning payload defaults.
• packages/agents/test/model-catalog.test.ts — updates expectations and adds regression coverage for OpenAI-only store: true behavior.

[github-actions]

Electric Agents Desktop Builds

Build artifacts for commit b0bf1af.

Platform	Status	Artifact
macOS Apple Silicon	Passed	DMG
macOS Intel	Passed	DMG
Windows x64	Passed	Installer
Linux x64	Passed	AppImage / deb

Workflow run

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 70.13%. Comparing base (671a38f) to head (b0bf1af).
✅ All tests successful. No failed tests found.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #4557      +/-   ##
==========================================
- Coverage   74.35%   70.13%   -4.22%     
==========================================
  Files          52       79      +27     
  Lines        6897     9427    +2530     
  Branches     2190     2958     +768     
==========================================
+ Hits         5128     6612    +1484     
- Misses       1753     2798    +1045     
- Partials       16       17       +1     

Flag	Coverage Δ
packages/agents	70.53% <ø> (?)
packages/agents-server	74.10% <ø> (-0.25%)	⬇️
packages/electric-ax	46.42% <ø> (?)
typescript	70.13% <ø> (-4.22%)	⬇️
unit-tests	70.13% <ø> (-4.22%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.