Drop the b9828 source pin and take llama.cpp from a refreshed
nixpkgs-unstable (0.4.0), which supports the Laguna and Gemma 4
architectures. Run llama-server in router mode with a preset file:
abliterated Qwen3.6-35B-A3B and Gemma 4 26B-A4B for benchmarking,
Poolside Laguna S 2.1 as the primary coding agent, and Ornith kept for
comparison. At most two models stay resident; idle models unload after
six hours. Add llama-models and llama-unload helper commands.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Pin herdr v0.9.0 from the upstream flake (nixpkgs-unstable only has
0.7.1) and install it on straylight to host coding-agent terminals.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Add gen-update-targets.sh to parse flake.nix and generate grouped
update targets (update-kyle, update-mc). Makefile now has install
(copy) and link (symlink) targets for rebuild-nixos. Also fix mc
flake input URLs to use /mc/ org path.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Install mciasctl, mciasgrpcctl, mcrctl, and mcproxyctl via new
configs/mcpkg.nix module. Adds flake inputs for mcias, mcr, and
mc-proxy from git.wntrmute.dev.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
kyleandClaude Fable 5.1
Kyle IsomandClaude Opus 4.8