Removed comments & mercury tailscale key

hosts/terra/configuration.nix

@@ -63,9 +63,6 @@ in
     libxrandr
     libxinerama
     libxcb
-
-    # CLion Nova's C++ backend is a .NET 10 app that needs ICU or reports
-    # "Couldn't find a valid ICU package installed on the system".
     icu
   ];
 
@@ -97,38 +94,6 @@ in
   # rootless podman GPU containers (Vulkan whisper.cpp/llama.cpp).
   users.users.darman.extraGroups = [ "render" "video" ];
 
-  # ---- ollama (local LLM server, ROCm on the 6800 XT) ----
-  # Navi 21 (gfx1030) is officially ROCm-supported, so no
-  # HSA_OVERRIDE_GFX_VERSION needed. Upstream module already runs under
-  # DynamicUser with render/kfd/drm access wired, unlike jellyfin's static user.
-  services.ollama = {
-    enable = true;
-    package = pkgs.ollama-rocm;
-    # keep default model in sync with services/desktop/librechat.nix's
-    # endpoints.custom default (its schema needs a non-empty value even
-    # though fetch=true overrides it).
-    # gemma4:12b: daily-driver chat/coding model, fits fully in 16G VRAM; also
-    # doubles as LibreChat's memory-extraction agent (librechat.nix) since a
-    # smaller model confused the user's stated facts with its own boilerplate.
-    # qwen3.6:35b-a3b: MoE (3B active/36B total, ~24GB Q4_K_M) — doesn't fit
-    # in VRAM alone, so ollama offloads inactive experts to CPU RAM; sparsity
-    # makes that less painful than for a dense model this size, but still slower.
-    # VladimirGav/qwen3.8-27B-14GB-IQ4: dense 27B at IQ4 (~14GB) — nominally
-    # fits the 16G card but leaves little headroom, so expect partial CPU
-    # offload as context grows.
-    loadModels = [
-      "gemma4:12b"
-      "qwen3.6:35b-a3b"
-      "VladimirGav/qwen3.8-27B-14GB-IQ4"
-    ];
-    # Ollama truncates context far below a model's real window unless told
-    # otherwise. 131072 is the practical ceiling from load-testing: VRAM stays
-    # 100% GPU with no CPU spillover up to here, but headroom and prefill
-    # throughput both degrade near the top — going higher risks CPU spillover
-    # under concurrent GPU load (compositor, jellyfin transcode) for little gain.
-    environmentVariables.OLLAMA_CONTEXT_LENGTH = "131072";
-  };
-
   # ---- Dev-data disks — NOT in disko, mounted read-write, never wiped ----
   fileSystems."/mnt/hdd_01" = {
     device = "/dev/disk/by-uuid/b8445126-ec6d-4f88-818a-d9e13031d9a4";