Version 2.36.5 of n8n, released on August 21, 2026, is a focused patch that addresses a single but important issue in the core platform. The AI Assistant’s model verification step previously had a cap on the number of tokens it could process. This patch increases that cap, making the verification more flexible for different model […]
n8n 2.36.5 Fixes AI Assistant Model Verification Token Limit Read More »
The langchain-fireworks integration has been updated to version 1.6.0, bringing new capabilities and important fixes for self-hosted LangChain deployments. The headline feature is the addition of document reranking, which allows users to improve retrieval quality by reordering documents based on relevance before passing them to the model. On the core side, standard model exception types
LangChain Fireworks 1.6.0 Adds Document Reranking and Tool Call Fixes Read More »
n8n has shipped version 2.36.3, a patch release that brings several under-the-hood fixes to improve stability and efficiency for self-hosted deployments. The update mainly targets core internals and the workflow editor. On the core side, the release prevents task runners from being restarted when they are simply slow, avoiding unnecessary disruptions in long-running workflows. It
n8n 2.36.3 Patch Release Fixes Task Runner and Editor Issues Read More »
What’s New in This Update The langchain-openai package has been bumped from version 1.5.2 to 1.6.0, with a focus on making errors easier to understand and manage. The core library now includes standard exception types for model-related failures, so self-hosted users can catch and respond to errors more consistently across different providers. Additionally, the OpenAI
LangChain-OpenAI 1.6.0 Released with Clearer Error Handling Read More »
Traefik has rolled out a new release focused on stability and clarity, with a series of bug fixes across its core proxy features, Kubernetes integrations, and documentation. Core Proxy and TLS Fixes Several issues in the proxy engine were addressed. The FastProxy module now rejects out-of-range status codes returned by backends, preventing unexpected behavior. HTTP/3
Traefik Delivers Stability and Clarity in Latest Release Read More »
Multiple security vulnerabilities have been found in Oracle products, with the most critical ones potentially allowing arbitrary code execution. If an attacker successfully exploits these severe flaws, they could gain the same privileges as the currently logged-in user. Depending on that user’s level of access, the attacker could then install software, view, modify or delete
Critical Security Vulnerabilities Identified in Oracle Products Read More »
After years of technical research and foundational work, the Fedora Badges application service has been rebuilt from the ground up, and it is heading to production. Whether you have been collecting badges for years or you are brand new to the Fedora Project community, here is what is waiting for you there. Completely modernized user
Fedora Badges Gets a Complete Overhaul: Modern UI, Rarity Tiers, and More Read More »
n8n 2.36.2 Release Notes n8n has just rolled out version 2.36.2 on August 19, 2026, a maintenance release that addresses a handful of issues affecting self-hosted users. The update focuses on improving API discovery, resolving credential handling in workflows, and fixing a minor UI glitch in the agent preview. On the API side, the /discover
n8n 2.36.2 Brings Targeted Bug Fixes Read More »
Version 1.5.2 of the langchain-openai package has been released, following a 1.5.2a1 pre-release, with a set of targeted improvements aimed at developers running OpenAI models through LangChain, especially in self-hosted or gateway-mediated environments. One of the key fixes in this release addresses how reasoning item boundaries are handled. Previously, when working with OpenAI responses that
Version 5.15.1 of the Transformers library is now available as a patch release, addressing several bugs that affected self-hosted deployments. The most notable fixes target DFlash and MTP candidate generators, where token placement on the correct device was corrected when using device_map=”auto”, and the logit distributions for candidate generators that rely on sampling have been
Transformers v5.15.1 Patch Release Resolves DFlash and MTP Generator Issues Read More »
