docs(frank-zealot): carry the 19:44 production boot into the runbook

Left uncommitted by the deploy session: the production decode rate (75.8 t/s,
within 1% of the trial arm), the shipped boot ledger, the live probe census,
and the picker-row law (OpenWebUI meta.description is live DB state a swap
must follow into the database, written without restarting open-webui).
This commit is contained in:
Frank
2026-10-17 21:02:16 -07:00
parent 2def6282b5
commit 4607604ef7
@@ -103,6 +103,10 @@ DSpark drafter boot in the llama.cpp eras. Any resize must re-read the settled
|Two concurrent streams, 256 tok each|**54.7 + 54.7 = 109.4 t/s aggregate** — `--parallel 2` really batches|
|Long-context retrieval (25,960-token prompt, needle at position 180 of 300 passages)|exact: *"Frank keeps the fleet in git, only through it."*|
Production boot (the 19:44 cutover deploy, same binary/flags/file): **75.8 t/s**
single-stream decode at a short prompt — within 1 % of the trial arm, so the
ladder above carries to the shipped shape.
## Behavior contract (probes, not assumptions)
- **Reasoning** lands in `reasoning_content` (`--reasoning-format deepseek`) ✓.
@@ -165,6 +169,18 @@ DSpark drafter boot in the llama.cpp eras. Any resize must re-read the settled
(`/home/dank/models/Qwen35-9B-HauhauCS-Q6K/`,
`~/GitPackages/llama-master/build-cuda/`), and the retired era keeps its own
page: [[frank-zealot-llama-qwen35-9b-q6k-2x200704]].
- **Deployed 2026-10-17 19:44** (`deploy.sh dankclaw --service frank-zealot
--service homepage`): boot ledger 22,664 used / 1,461 free, engine fit
projected 21,439 and left 2,119 ≥ 1,872 MiB, KV 13,328.00 MiB at
`n_ctx_seq = 200,704`, `n_slots = 2`, projector loaded; live probes green
(`/v1/models` serves `frank-zealot`, exact `pong` + `reasoning_content`,
`tool_calls` `{"city":"Seattle"}`, 512 px PNG → **Red**). e2e gate 33/33.
- **Picker row is live state:** the OpenWebUI `model` row's
`meta.description` named the 9B, so it was re-keyed in the database too
(backup `webui.db.bak-20261017a`). The row was written WITHOUT restarting
`open-webui` — the cached list refreshes on its next restart, and forcing one
would have logged every family session out for a cosmetic string. See
[[OpenWebUI]] for the picker trio.
## Related