Articles - Page 2

OpenCode + a Self-Hosted Qwen3.6 Server: Provider Setup and the Chat-Template Fix That Makes Tool Calling Reliable

01-Sept-2026

OpenCode + a Self-Hosted Qwen3.6 Server: Provider Setup and the Chat-Template Fix That Makes Tool Calling Reliable

How to connect OpenCode to a self-hosted Qwen3.6 server, and why a community chat-template fix is required before its tool calling can be trusted.

Running Qwen3.6-35B-A3B at 262K Context with FreeToken MoE Offload

29-Aug-2026

Running Qwen3.6-35B-A3B at 262K Context with FreeToken MoE Offload

Qwen3.6-35B-A3B-FP8 on RTX 4090 with FreeToken: near-262K context verification, 51/51 statistical rerun, a 50-task correctness eval (46/50) with explicit truncation detection, and a systemd autostart setup.

How to Use One Prompt to Build a Complete AI Context Architecture for Your Codebase

18-Jul-2026

How to Use One Prompt to Build a Complete AI Context Architecture for Your Codebase

A plain-language guide to a single reusable prompt that makes an AI coding agent design AGENTS.md files, a skills folder, and a memory bank for your project —

Spring AI Agentic Patterns: Agent Skills for Clinical Decision Support

14-Jun-2026

Spring AI Agentic Patterns: Agent Skills for Clinical Decision Support

How med-expert-match-ce uses 9 domain-specific Agent Skills from spring-ai-agent-utils to build a modular, LLM-agnostic specialist-matching system on Spring

Loading tags...