v1.4.524
danielmiessler/Fabricv1.4.524Oct 16, 2026by github-actions[bot]
Upgrading?
AI Summary
This release fixes a core bug where the selected vendor model spelling was not being preserved correctly. The update ensures that explicit vendor and vendor/model-prefix requests maintain the correct canonical spelling. Additionally, regression tests were added to handle case-insensitive IDs and varying catalog orders.
Key Highlights
- Fixed core module to preserve the selected vendor's canonical model spelling.
- Ensures correct spelling for explicit vendor and vendor/model-prefix requests.
- Added regression tests for case-insensitive IDs with different vendor spellings.
- Validates behavior across different catalog orders.
New Features
- Preserve vendor model spelling for explicit requests
- Add regression tests for case-insensitive ID handling
Full Release Notes
## Changes ### PR [#2244](https://github.com/danielmiessler/Fabric/pull/2244) by [taljeon](https://github.com/taljeon): fix(core): preserve the selected vendor model spelling - Preserve the selected vendor's canonical model spelling for explicit vendor and vendor/model-prefix requests. - Add regression tests for case-insensitively equal IDs with different vendor spellings and catalog order.
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