From 14b3b3c6b800ec4342c608467aedeb8eea179a44 Mon Sep 17 00:00:00 2001 From: "K. Isom" Date: Fri, 18 Sep 2026 00:00:27 -0700 Subject: [PATCH] straylight: run Laguna with two slots over a unified KV pool A second request (opencode background agent, pi alongside opencode) no longer queues behind the first. kv-unified keeps the full 131072-token context available to either slot instead of splitting it to 65536. Co-Authored-By: Claude Opus 5 (1M context) --- hw/straylight/default.nix | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/hw/straylight/default.nix b/hw/straylight/default.nix index 07c929f..9db292d 100644 --- a/hw/straylight/default.nix +++ b/hw/straylight/default.nix @@ -49,7 +49,11 @@ let spec-draft-n-max = 4 cache-type-k-draft = f16 cache-type-v-draft = f16 - parallel = 1 + ; Two slots sharing one unified 131072-token KV pool: a second request (subagent, + ; another client) runs alongside instead of queueing, and either one may still use + ; the full 131072 as long as their combined context fits. + parallel = 2 + kv-unified = true ctx-size = 131072 ; Previous default model (a Qwen 3.5 derivative), kept for comparison runs. It was