terra: finish removing Hermes Agent (module import + secrets)
Follow-up to e5ba1bf — that commit only staged the deleted module file.
Drops the flake module import, opencode_go_api_key/telegram_bot_token
secrets, and the stale hermes-agent.nix cross-reference in ollama's
context_length comment.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
@@ -18,7 +18,6 @@ in
|
||||
../../services/desktop/desktop-hyprland.nix
|
||||
../../services/desktop/desktop-apps.nix
|
||||
../../services/desktop/librechat.nix
|
||||
../../services/desktop/hermes-agent.nix
|
||||
];
|
||||
|
||||
networking.hostName = "terra";
|
||||
@@ -98,10 +97,9 @@ in
|
||||
loadModels = [ "gemma4:12b" "qwen3.6:35b-a3b" ];
|
||||
# Ollama truncates context far below the model's real window unless
|
||||
# told otherwise (the OpenAI-compat /v1 route it's reached through has
|
||||
# no way to set this per-request — see services/desktop/hermes-agent.nix,
|
||||
# which points at this server and mirrors the same number in
|
||||
# model.context_length). 131072 chosen as the practical ceiling after
|
||||
# load-testing with real prompts, not just idle `ollama ps` checks:
|
||||
# no way to set this per-request). 131072 chosen as the practical
|
||||
# ceiling after load-testing with real prompts, not just idle
|
||||
# `ollama ps` checks:
|
||||
# 32768 (31.6k-token prompt) and 65536 (40.8k-token prompt) both stayed
|
||||
# 100% GPU with VRAM barely moving (~10.1G / ~10.67G of 16G) — KV cache
|
||||
# cost barely grows with context, likely sliding-window/local attention
|
||||
|
||||
Reference in New Issue
Block a user