v1.9.7

Kedreamix/Linly-Talkerv1.9.7May 5, 2026by nicko-ai

AI Summary

Patch release focusing on hardening stateless OpenAI Responses reasoning replay, particularly when browser-auth runs with store=false.

Key Highlights

  • Fixed stateless reasoning replay when store=false
  • Requested `encrypted_content` for store=false replay paths
  • Sanitized legacy unencrypted reasoning spans before replay
  • Preserved per-run ModelSettings boundaries

New Features

  • Stateless reasoning replay fixes
  • Reasoning span sanitization
  • ModelSettings boundary preservation
  • Encrypted content request support

Full Release Notes

Patch release for Agent Swarm TUI / browser-auth history replay.

## Changes
- Fix stateless OpenAI Responses reasoning replay when browser-auth runs with store=false.
- Request reasoning.encrypted_content for store=false replay paths.
- Sanitize legacy unencrypted reasoning spans before replay.
- Preserve per-run ModelSettings boundaries and avoid leaking resolved agent settings into reusable RunConfig objects.
- Add focused coverage plus a live OpenAI stateless reasoning replay proof.

## What's Changed
* fix: harden stateless Responses reasoning replay by @nicko-ai in https://github.com/VRSEN/agency-swarm/pull/641

**Full Changelog**: https://github.com/VRSEN/agency-swarm/compare/v1.9.6...v1.9.7