Small OpenCode plugin that helped me with broken tool calls from a local Qwen mo

<!-- SC_OFF --><div class="md"><p>Hi,</p> <p>I taught Computer Science for 30 years in a French School of Electrical Engineering, Computer Science Department.</p> <p>I recently

<!-- SC_OFF --><div class="md"><p>Built a free alternative to Claude Code ($20-$200/mo) that uses NVIDIA's open models through the same CLI framework (FREE!).</p> <p><strong>How

<!-- SC_OFF --><div class="md"><p>Been using ClaudeCode CLI with Opus 4.6 and many MCP's and honestly its addicting. </p> <p>Just tell it what to build and it does everything —

<!-- SC_OFF --><div class="md"><p>Unfortunately OpenCode didn't have a stock way to add a model from a vLLM server until today, so made a small script for a one-line refresh of

<!-- SC_OFF --><div class="md"><p>In LM Studio the new Qwen 3.5 models (4b 9b 27b 122b) when analyzing large (more than 50k tokens) texts start to output gibberish. It is not a

<!-- SC_OFF --><div class="md"><p>Beginner here, now I have a good GPU and ollama using docker. Pulled the Gemma4 weights and was able to add it to cursor using ngrok. </p>

<!-- SC_OFF --><div class="md"><p>I am trying out some tools that are from the openwebui community that I have directed towards my LM Studio server instance. It seems really hit

<!-- SC_OFF --><div class="md"><p>Been heads down building graphify since April 5th. The idea: instead of stuffing your entire codebase into context every session, build a