Adds muse-glimmer-30b and muse-glimmer-30b-low to the local and personal
profiles, and points the five named agents at the -low alias.
-low, not the bare alias, because that is the configuration llmbench
actually measured: 15/24 tests_pass on the real suite at reasoning_strength
low, the best any local model has scored there. The bare alias runs at
Glimmer's default, which is its HIGHEST reasoning setting and cannot be
turned off -- measured 906 completion tokens for a one-line riddle against
360 at low. Both are declared, so switching is a model change, not an edit.
Context is 131072, from llama-swap's own `-c`.
These agents already exist in work.json/work-strict.json on gpt-5.6-terra
and are untouched there; local and personal had no agent block at all, so
this is additive.
Every local model was declared at 32768 (16384 for the OMO local aliases)
regardless of what llama-swap is configured to serve. gpt-oss-20b runs with
`-c 65536`, so opencode was compacting at half the real window -- and
local/librarian and local/explore, which both route to gpt-oss-20b, at a
quarter of it.
Compaction is not free and it is not neutral. Measured on mainframe
2026-09-21, one agent session against a model told it had 32k when it had
131k: four cache-cold prefills, and 780 seconds spent after a working fix
re-reading the same forty lines, because each compaction discarded the memory
of having already verified it. Reasoning spend per step went from 2-5 tokens
to 1739. The model was not confused; it had been made to forget.
Values are llama-swap's own `-c`:
gpt-oss-20b 65536 (was 32768)
local/librarian 65536 (was 16384 / 32768)
local/explore 65536 (was 16384 / 32768)
qwen3-coder-30b 32768 unchanged, already correct
gemma3-12b 32768 unchanged, already correct
The hosted entries were already right and are untouched.
⚠ These are hand-maintained and llama-swap's config is the source of truth.
If a `-c` changes there, change it here. llmbench now derives the same
numbers by parsing that file, and raises rather than guessing when an alias
is unknown -- a wrong context limit produces plausible numbers instead of an
error, which is how this went unnoticed.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01E9UH1zGZZtA9yhohmQrcT6
Replaces the previous repo, which had split into two histories that never
met (mainframe on a dead GitLab remote, the laptops on Gitea) with 146
dirty files across three machines and the NAS never enrolled at all.
Branch-per-machine is gone. One main, with host differences expressed as
small files under hosts/<hostname>/ rather than as branches, so there is
nothing to merge. The reconciled zsh layer reduces 15-33 line forks to
1-7 effective lines per host; distro differences (oh-my-zsh prefix,
syntax-highlighting path, fd vs fdfind) are probed in common/ instead.
Fresh history: the old one carried six plaintext credentials, 45 MB of
mail caches, browser caches and vendored binaries. 5,096 tracked files
and 144 MB become 462 files and 2.6 MB. The .gitignore is now an
allowlist, which is what keeps that true.
Root cause of the rot: ~/.local/bin was a symlink to scripts/ with GOPATH
inside it, so every go install wrote into version control (2.2 GB on the
work laptop). PATH now points at the repo instead of the reverse.
Also: Hyprland replaces sway and is sourced in two halves so $browser is
defined before use; singleton automations carry ConditionHost= alongside
host-layer-only placement; ddns moves from cron to a guarded timer;
package manifests and pkg-snapshot/pkg-restore replace the X11-era
install_scripts/; networkmanager-dmenu added to system76 (the binding
always existed, the package never did).
connor
