v1.4.551
danielmiessler/Fabricv1.4.551Oct 23, 2026by github-actions[bot]
Upgrading?
Release notes summary
This release fixes caller context handling across all AI vendor plugins, ensuring cancellation and deadlines are honored consistently. It propagates caller contexts through streaming requests, model discovery, credential lookup, and Abacus model catalog requests. Regression tests were added to cover cancellation and deadline behavior.
Key Highlights
- Fixed caller context cancellation handling across all AI providers.
- Propagated caller contexts through streaming requests for every AI provider.
- Honored cancellation during model discovery and credential lookup.
- Passed caller contexts to Abacus model catalog requests.
- Added regression tests covering cancellation and deadline handling.
Full Release Notes
## Changes ### PR [#2308](https://github.com/danielmiessler/Fabric/pull/2308) by [ksylvan](https://github.com/ksylvan): fix: honor caller context in AI vendor plugins - Fixed caller context cancellation handling across all AI providers. - Propagated caller contexts through streaming requests for every AI provider. - Honored cancellation during model discovery and credential lookup. - Passed caller contexts to Abacus model catalog requests. - Added regression tests covering cancellation and deadline handling.
Related Repositories
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
The world’s fastest framework for building websites.
:cherry_blossom: A command-line fuzzy finder