From 42a9f214f5a5ad26b0391b0bc616e60eac3f2097 Mon Sep 17 00:00:00 2001 From: drjones Date: Tue, 25 Aug 2026 06:52:42 +0000 Subject: [PATCH] route local LLM to qwen3.8 on .128 (was gemma4:26b); think:false + num_ctx 8192 --- src/server/llmClient.ts | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/src/server/llmClient.ts b/src/server/llmClient.ts index d20ed69..d09cba9 100644 --- a/src/server/llmClient.ts +++ b/src/server/llmClient.ts @@ -1,7 +1,7 @@ // Shared local-LLM client — Ollama on shadow-death (.128). // Single source of truth for host/model across the whole app. export const OLLAMA_HOST = process.env.OLLAMA_HOST || 'http://10.30.20.128:11434'; -export const OLLAMA_MODEL = process.env.OLLAMA_MODEL || 'gemma4:26b'; +export const OLLAMA_MODEL = process.env.OLLAMA_MODEL || 'qwen3.8:latest'; export interface LocalModelOptions { formatJson?: boolean; @@ -18,6 +18,8 @@ export async function callLocalModel(prompt: string, opts: LocalModelOptions = { options: { num_predict: opts.numPredict ?? 4096, temperature: opts.temperature ?? 0.2, + think: false, + num_ctx: 8192, }, }; if (opts.formatJson) body.format = 'json';