Starstruk Logo MarkStarstruk

v4.8.0

NirDiamant/GenAI_Agentsv4.8.0Sep 23, 2026by github-actions[bot]

Upgrading?

What changed from v4.7.0 → v4.8.0?What's new in v4.9.0 after v4.8.0?

AI Summary

A comprehensive maintenance release that addresses audit logging, Multi-Factor Authentication (MFA) handling, and localization issues.

Key Highlights

  • Added audit logging for unauthenticated requests and Machine-to-Machine (M2M) operations
  • Improved MFA setup wizard defaults and verification code throttling logic
  • Fixed Ukrainian (uk) i18n translations
  • Enhanced security by removing user passwords from JWT claims copy

Full Release Notes

## Changelog
### Bug fixes
* eff25f63b7e6231b0d57d43330a5e8a5582e4266 fix: allow an org-scoped subject to update its own organization
* af0b022c2cd954197f5872bb0a1c41a597803dc2 fix: attribute audit records of unauthenticated requests to an organization
* 92c2db60a4a2249c91171b5f1adc141b97e4ff9f fix: correct Ukrainian (uk) i18n translations (#5869)
* 3cd925ab44d40a0373d21a582ceac3a37df49b64 fix: default the MFA setup wizard to the organization's required factor
* 2db20ea4ddaeb7bf1b0e609f044be6f8ffacfd5d fix: don't prefill a random invalid phone number for new users
* 5370339c113a10008c18b5e658946bceb8bac0fc fix: hide tag-restricted applications from the /apps page
* df8d1b4238e770bb93f7bdbef3560951ac6603dd fix: honor the requested audience in RFC 8693 token exchange
* cd5571de25a069fdad405899a2c6ca18a593d5c1 fix: keep the user's password out of the JWT claims copy
* 5565c822e762e2aa3acf29844e8d357eef38e59a fix: record the audit logs of M2M operations
* f7b2c8237e5ecbd1d2d3bb45c8aaf97460e6235e fix: scope the verification code resend throttle to the requesting user
* 7cb1462fb3aa5a0698efc18c7754ac9d85aa89ea fix: store the backend MFA type in the organization's MFA items

Related Repositories

rasbt/LLMs-from-scratch★ 107,042

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

lyogavin/airllm★ 40,155

AirLLM 2.8T LLM inference with single 4GB GPU

NirDiamant/RAG_Techniques★ 29,958

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

microsoft/OmniParser★ 25,539

A simple screen parsing tool towards pure vision based GUI agent

karpathy/nn-zero-to-hero★ 24,906

Neural Networks: Zero to Hero