docs(openwebui): re-key the model rows at swap time; default is frank-archon

The picker's decoration rows carried two payload-swap drifts: frank-dragoon
still named halogen 0.16.2 (live 0.18.20) and frank-zealot build 10777 /
3x262,144 / MTP off (live build 12118 / 3x200,704 / draft-mtp armed). Worse,
their params.context.length values had swapped, so OpenWebUI advertised more
window than the zealot slot grants and gave up 61k tokens on dragoon. Live
rows re-keyed through the admin API and ui.default_models set to
frank-archon; the swap procedure in AGENTS.md now names the re-key step.
This commit is contained in:
Frank committed 2026-11-04 13:06:54 -08:00
1 parent cae283047f
commit 1b5c11fb60
2 files changed
+52 -1

No files matched your search

+4 -1
View File
@@ -278,7 +278,10 @@ archive.
**Swap the model. Do not instrument it.** A payload change is: edit the trio
(env / serve script / unit) → `scripts/deploy.sh <host> --service <svc>` →
`/health` answers → one chat turn, one tool call, and one vision probe on an
endpoint that serves images. That is the entire procedure.
endpoint that serves images → re-key that endpoint's OpenWebUI `model` row
(`meta.description` + `params.context.length`, API door in [[OpenWebUI]]). That is
the entire procedure — no deployer step touches `webui.db`, and a stale
`context.length` makes OpenWebUI advertise a window the endpoint does not grant.
- **No benchmarking unless Frank orders it.** No pre-swap baseline battery,
no A/B arms, no decode/prefill ladders, no acceptance tables, no numbers