Skip to content

v6.12

Choose a tag to compare

View all tags
@ekassos ekassos released this 28 Oct 02:44
· 775 commits to main since this release
817-srv389-web241
c33ff82
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Release Notes

This update provides important bug fixes and improvements.

Groups

Updates & Improvements

  • Next-Gen Assistants can now be copied to new Groups.

Resolved Issues

  • Fixed: A Group Clone request may fail because of lazy loading code changes introduced.

Internal

Updates & Improvements

  • Adds the following configuration option to the Sentry backend integration:
    • max_request_body_size = "always": This parameter controls whether integrations should capture HTTP request bodies. always: The SDK will always capture the request body as long as Sentry can make sense of it.

Logging In & Navigation

Updates & Improvements

  • External Login information is removed from the main User object and only loaded when a user access their Profile page under a new /me/external-logins endpoint.
  • In an effort to speed up loading times, all lazy loading of relationship objects in models.py has been removed in favor of explicit loading when needed.

Prompts

Resolved Issues

  • Fixed: Prompt Randomization fails for Next-Gen Assistants.

Threads

New Features

  • Adds new admin-only endpoint /class/{class_id}/thread/{thread_id}/details that returns:
    • The Thread object with a large number of relationships loaded
    • A conversation_items array that displays messages, tool calls, and reasoning steps in ascending output_index order.

Updates & Improvements

  • The ChatInput message box remains in focus after the assistant response generation is completed.
  • Removed debugging statements including "Received chunks…" from code.
  • New error management code will surface more errors, especially those encountered before the thread is created.

Vector Stores

Resolved Issues

  • Fixed: Creating a Vector Store when sending a message may fail because of lazy loading code changes introduced.

Deployment Information

Schema Upgrade Migration Script Permissions Update Task Definition Update Configuration Update
No No No No No

Deployment Details

  • N/A

Related PRs

  • fix(next-gen)/ Randomization prompts may fail by @ekassos in #1053
  • feat/ Remove all lazy loading by @ekassos in #1050
  • fix/ Cannot update assistant with CI files by @ekassos in #1054
  • feat/ Allow copying next-gen assistants by @ekassos in #1055
  • feat/ Retain focus on ChatInput message box after message is complete by @ekassos in #1056
  • feat/ Add new get_thread_details endpoint by @ekassos in #1057
  • internal/ Add max_request_body_size parameter to Sentry init by @ekassos in #1058

Full Changelog: 810-srv383-web239...817-srv389-web241

Contributors

ekassos
Assets 2
Loading