Starstruk Logo MarkStarstruk

v1.4.526

danielmiessler/Fabricv1.4.526Oct 18, 2026by github-actions[bot]

Upgrading?

What changed from v1.4.525 → v1.4.526?What's new in v1.4.527 after v1.4.526?

AI Summary

This release addresses critical compatibility issues with Anthropic's Claude Haiku 5.5 and Mythos models by adjusting sampling parameters and adaptive thinking settings. It introduces support for new Claude models including Fable 5.1 and Sonnet 5.5, while upgrading various internal dependencies.

Key Highlights

  • Fixed Anthropic API errors for Haiku 5.5, Mythos, and Opus 4.7/4.8 by removing non-default sampling parameters
  • Extended adaptive thinking support to Opus 4.7, Opus 4.8, Haiku 5.5, and Mythos 5/5.1
  • Added new Claude models: Fable 5.1, Sonnet 5.5, Haiku 5.5, and Mythos 5 & 5.1
  • Enabled million-token context beta support for newly added models
  • Upgraded dependencies: mimetype, Ollama, and openai-go

New Features

  • Added support for new Claude models (Fable 5.1, Sonnet 5.5, Haiku 5.5, Mythos 5/5.1)
  • Enabled million-token context beta support for newly listed models
  • Upgraded Ollama dependency to v0.40.6
  • Upgraded openai-go dependency to v3.81.0
  • Upgraded mimetype dependency to v1.4.16

Full Release Notes

## Changes

### PR [#2270](https://github.com/danielmiessler/Fabric/pull/2270) by [pcbeingused333](https://github.com/pcbeingused333) and [kaylvan](https://github.com/kaylvan): fix(anthropic): send adaptive thinking and no sampling params to Haiku 5.5, Mythos and Opus 4.7/4.8

- Fixed Anthropic requests by omitting sampling parameters (such as the default 0.7 temperature) for Claude Haiku 5.5 and Mythos models, which reject non-default values.
- Extended adaptive thinking support to Opus 4.7, Opus 4.8, Haiku 5.5, and Mythos 5/5.1, preventing 400 errors caused by sending `budget_tokens` with `thinking.type=enabled`; Opus 4.6 remains the newest model that accepts it.
- Added new Claude models, including Fable 5.1, Sonnet 5.5, Haiku 5.5, and Mythos 5 and 5.1.
- Enabled million-token context beta support for all newly listed models.
- Upgraded dependencies: mimetype to v1.4.16, Ollama to v0.40.6, and openai-go to v3.81.0.

Related Repositories

ollama/ollama★ 184,217

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

fatedier/frp★ 110,055

A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.

infiniflow/ragflow★ 92,617

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

gohugoio/hugo★ 90,198

The world’s fastest framework for building websites.

junegunn/fzf★ 83,715

:cherry_blossom: A command-line fuzzy finder