Jellyfin 12 ships TMDB, TVDB, StudioImages and MusicBrainz as core plugins:
no DLL, only a configuration file under the data root, so the keys have to
reach that XML from somewhere that is not git. They live in the fleet's
per-service env-file convention -- /home/dank/Containers/jellyfin/provider-keys
(TMDB_API_KEY=, TVDB_API_KEY=, optional TVDB_PIN=, mode 600) -- and
scripts/jellyfin-providers.sh plan|install|verify reads only that file, prints
no key byte, and refuses a keys file that is not mode 600 or that has no line
for the provider about to be written. install is idempotent: it never touches
a key the UI already saved, backs up every XML it edits into
~/.AGENTTRASH/<date>-jellyfin-providers/ first, and only installs the TVDB
plugin when the pinned official zip carries the plugin guid.
The deployer runs install BEFORE it restarts jellyfin, because the plugin and
its keys are read at start-up and a restart-first deploy boots the old state.
A missing keys file warns instead of failing: a host without the keys still
deploys, degraded rather than broken. No plugin configuration XML is tracked.
The container has had one owner since the Quadlet cutover
(dankserver/jellyfin/quadlet/jellyfin.container). The block was a second owner,
and wrong on every path: jellyfin/jellyfin:latest instead of the pinned ghcr
image, /opt/jellyfin/* data roots that no longer exist, and a read-only
/mnt/entropy:/data bind that the metadata view has since replaced.
The planner no longer counts jellyfin as a compose service, so editing the
inventory cannot restart a media server; tests/deployment_scoping.bats pins that
contract for both jellyfin and plex.
The merged door was /mnt/media, which read like a third volume and split the host
state across two trees. It is now /var/lib/media-meta/view, so the array layer,
the SSD upper layer, the kernel workdir, the reap trash and the merged tree are
one directory — and the mount table gains no new /mnt entry beside the array.
systemd names a mount unit after its ESCAPED path, so the repo copy keeps the
readable name media-meta-view.mount while `install` writes the host file as
var-lib-media\x2dmeta-view.mount; `plan` prints both and the page records them, so
nobody hunts for a unit that "does not exist". install also creates the mount
point itself, because systemd will not.
The seam now additionally pins that the unit's Where= is exactly the path both
containers bind — guard and bind cannot drift apart. The Quadlet Lifecycle
phantom-path example is corrected too: it named an invented /mnt/media/*, while
the real phantom is the legacy /opt/jellyfin/* that dankserver/compose.yaml still
carries for a service whose roots moved to /home/dank/Containers/jellyfin.
New owner page Dankserver/Media Metadata View.md: the shape, the two binds and
why Plex keeps the /mnt/entropy container path, the commands, the laws (SSD-only
upper layer, never mount over an unmounted array, never delete through the view
because a whiteout only hides the array's copy, reap after any relayout, inotify
does not cross the merge), the failure signatures, and the rollback.
Jellyfin.md: /data is the view, so Local metadata works; the
"Read-only file system : '/data/…/movie.nfo'" line that used to be expected noise
is now the signature of a missing view. Plex.md: same bind, one fact changed.
Media Relayout.md: two new laws for the metadata that does not follow a rename.
AGENTS.md: runbook-index row plus a summary row. Root index regenerated.
A relayout renames on the raw array; the sidecars the media servers wrote live in
the NVMe upper layer of the view and stay at the old coordinates, which is how a
ghost folder (artwork and an .nfo, no video) is born. apply and rollback now
print the follow-up — scripts/media-view.sh reap — at the moment the operator
needs it, and the existing apply seam asserts the hint is in the output.
Both media servers read a Kodi-format sidecar (movie.nfo / tvshow.nfo /
episode.nfo) only when it sits next to the media file, and the library lives on
the RAID6 array, deliberately mounted read-only for every container and slow to
seek for a thousand tiny XML reads. So neither server binds the array any more:
both bind /mnt/media, an OverlayFS merge of the array (lowerdir, never written)
with /var/lib/media-meta on the NVMe (upperdir, where every write lands).
Jellyfin binds the view rw at /data and is the fleet's only metadata writer;
Plex binds it ro at /mnt/entropy, the container path its own database already
recorded, so only the host side of that bind moved and its library paths keep
resolving.
scripts/media-view.sh plans, installs, verifies, reports and reaps the view. It
refuses to mount over an unmounted array, refuses an upper layer on rotational
storage, and refuses a non-root install. deploy-remote.sh raises the view before
it restarts either media server, both units carry
ConditionPathIsMountPoint=/mnt/media so a missing view skips the start instead of
letting a scan clear the library database, and the planner routes the installer
and dankserver/host/** to the jellyfin+plex pair.
tests/media_overlay.bats (11 seams) pins the resolved shape, both refusals, the
two binds and their guard, the deployer's ordering, the planner mapping, and the
reap behaviour against a fixture (ghosts listed, then moved to the SSD trash --
files that exist only above are sidecars, not ghosts, so only directories are
candidates).
Six single-episode files stayed in the movie library when the threshold refused
them; the hand path is the same executor on a hand-written plan and the same
journal. The trap recorded here is the series year -- never inherit it from the
title whose bonus folder an episode happens to be parked in.
The seam ran through `grep -c`, which returned success on a non-zero count and
let a red suite through: description over the 120-char cap, and a timestamp
that check-okf reads against the local date, so a UTC stamp a day ahead of
Seattle is 'in the future'. index.md regenerated for the new description.
docs_completeness 6/6, exit status checked this time.
X-Emby-Token is refused for every key on 12.4 -- which is why this page
carried the false claim that no credential on the box could trigger a scan and
that the two Seerr keys were dead. The documented snippet now authenticates
with Authorization: MediaBrowser Token=..., reads 204 from /Library/Refresh,
and points at ~/.config/secrets/jellyfin (mirrored as JELLYFIN_API_KEY in the
ignored dankserver/.env). Law: prove a 401 against the ApiKeys table before
blaming the key.
Trashing 31 GiB of duplicate Monk to ~/.AGENTTRASH would have been a
cross-device copy of the thing being deleted, into 187 GiB of free space, on a
volume at 100% -- and rename(2) refuses it regardless. The stage belongs beside
the item.
The destination-hold refusal's evidence, stated exactly: 124 episodes both
sides, same episode list, every byte count identical, 31.5 GiB each way,
head+tail blake2b identical on a 6-episode sample.
Plus the law this came out of: a path-substring filter for a series name also
returns other shows (monk matches Monkey Dust), and whichever file a walk
reaches first standing in for an episode turns two libraries into a fake
duplicate — the same sloppiness aimed the other way deletes a unique file.
ep_of on both sides, and a hash before anything is trashed.
Two fixes found by one live sweep, shipped together because the second is
what makes the first finishable.
1. scripts/media-tv.py — the other half of media-plan.py's refusal to file
TV. Groups episode-shaped files by the series name before the marker
(media-titles.ep_of, imported not restated), writes a plan in the
executor's own format: <library>/<Series> (<year>)/Season <NN>/<own
name>.<ext>. Refuses a group below --min, an episode naming no season,
and an episode the destination library already holds at the same byte
count — the movie share carries a second copy of all 124 Monk episodes
the TV library has had for years; a duplicate is Frank's call, never a
tool's copy. Applied by media-apply.py with its own journal and
--root /mnt/entropy.
2. scripts/media-apply.py — gone meant "rmdir intended", so a folder whose
rmdir failed was blacklisted forever and no later sweep could finish it
(live movie sweep: 4517 targeted, 146 permanently stranded). gone now
means "actually gone": a failed intent is retried by the next sweep.
tests: 9 new tests in media_relayout.bats, each red against the previous
revision — 8 TV + 1 sweep retry behind a chmod 500 parent. ./tests/run.sh
633 green. No live move run yet.
The live sweep removed 2271 husks and left 146 standing, every one a release
folder blocked by a junk subfolder (Screens/, Sample/, a BDMV leaf) that no
file ever moved out of. Eligibility was per-folder, so the blocker was never a
target and its parent could never be removed.
Proof now carries downward: inside a folder the journal shows emptied, every
empty directory qualifies. Nothing under such a folder can hold data, and every
removal is still journalled as rmdir and undone by rollback.
The new test is red against the previous revision, green now. The live sweep
touched no file: 8193 before, 8193 after.
Keyed on the whole episode title, every episode of a box set became a group of
one and never reached the five-episode size that calls something a series, so
the live run filed 124 Monk episodes as 124 movie folders, each named after its
own episode. ep_of now returns the series — the name before SxxEyy / 1x04 /
Part N — and the planner groups and names the quarantine pile by that series,
so one show is one pile: 'Monk - S05E03 - Mr. Monk and the Big Game' is series
monk. The threshold keeps its job: a lone film named Part 2 stays a film.
Re-planning the live census with this moves nothing differently except the 124
Monk files, which now join the TV pile: 168 episode files across 3 series.
An apply leaves every release folder it emptied standing where it was: the
live library run left 1675 husks at the root. sweep takes the same journal
and deletes only folders it can prove this run emptied - a journalled move
out of the folder or something under it, nothing but empty directories left,
no journalled destination beneath it, not a folder the run created. A folder
nobody moved cannot be selected at all, so a hand-made placeholder survives,
and a symlink anywhere inside disqualifies the subtree. Every rmdir is
journalled, so rollback recreates what a sweep removed.
A by-digest pull leaves the image carrying every digest it was pulled under, so
reading RepoDigests[0] reported a healthy pinned image as wrong and refused a
window that was ready to run. Membership, not position. Also records the measured
step optimum: 106 tok/s at an 8,192-token step against 76 at 16,384 on a 32,768
calibration window, so the wide step has a ceiling, not a plateau.
Each gate the window used was a proxy, and each lied at least once:
- /health answered 200 from the dying production process (window dead at second zero)
- podman inspect named a rig container that had bound nothing
- the space check asked a directory that merely looked related
- the identity check compared podman's CONTAINER-internal pids (1, 7) to an ss host pid
scripts/qwen38-preflight.sh now checks cwd, the digest a tag actually resolves to,
free space on the tap's own filesystem, stale grams, every /dev/kfd holder's host pid
(podman top <ctr> hpid) and the :7770 listener's host pid against the service's, the
corpus and the reference recording; it prints PASS/FAIL per fact and exits 2. The
window calls it before a card is touched, and its duplicated checks are gone.
The runner stops frank-archon first, and the dying production process keeps its
listener for a moment while the freshly created rig container is still loading.
'podman inspect says running' plus '/health answers' therefore BOTH hold for the
wrong process: measured 2026-10-30, the window logged 'health ok waited=0s',
the pusher refused on the container name, and a 12M window died at second zero.
The gate now asks the kernel who owns :7770 (ss -ltnp) and requires that pid to
be one of the rig container's processes (podman top). Two tests, written red
first against the old rig_up: a foreign listener must fail the window without a
push, and an in-container listener must proceed and bank.
Also renames the new test fixture to tap_window_fixture: it had shadowed the
existing window_fixture helper, which broke the window dry-run test when the
whole file ran.
The law today's authentik bump paid for: start on an active unit is a no-op, so
the new digest installs and the old container keeps serving behind three green
gates. Restart applies a pin.
The handler called `systemctl --user start` on all three units. Start is a
no-op for an already-active unit, so installing a new digest under an active
authentik left the old container serving: today's 2026.8.3 -> 2026.8.5 bump
moved only the OUTPOST (whose handler restarts) and left server + worker on
2026.8.3 while the deploy, the health gate and the e2e suite were all green.
The generator re-renders from the .container, so a restart is the step that
applies a pin.
Frank's rule: the served iq4r this arm competes with was calibrated on a
10M-token set, so the arm is calibrated at least as deeply. The floor was
lowered to 1.5M on the vendor's '10M beats 1M by under 1%' note; that
measures the vendor's own plate, not ours — the arm is judged against a
10M-calibrated reference, so cutting the calibration 6x to save wall clock
buys a worse position on the only comparison that matters.
One round of the re-chunked corpus is ~9.31M tokens, so a 12M floor seals
in round 1 plus part of round 2. A round that seals nothing is normal (the
floor is pooled) and round_verdict treats it as continue, never failure.
Also fixes tests/qwen38_campaign.bats' window dry run: its fixture lands on
/tmp (a 16 GiB tmpfs) where the 60 GiB seal preflight can never pass, so the
test now uses the documented Q38_CALIB_MIN_FREE_MIB override instead of
asserting environment luck.
frank-dragoon: engine 0.18.20 (image e35133b2…), the 18-model NPU catalog, the
re-cut qwen3-embedding-0.6b device programs, and the wire surface the new engine
actually answers (GET /tokenize is 405, /props is 200, /completion and /ping
stay 404). Eras gains the 2026-10-30 row.
frank-zealot: fork build 12118 (0.7.0-dev, 024474448) with the payload-load
evidence (202 pq2_0 tensors, 202 Hadamard-folded weights), plus the law a
rebuild pays for: cmake --install strips the rpath and installs bin/+lib/, so
the configure needs CMAKE_INSTALL_RPATH and LLAMA_BIN names …/bin/llama-server.
Rebuilt the fork from origin/prism at 024474448 with the same configure the
10777 cutover used (Release, GGML_CUDA=ON, sm_86, gcc-13 host compiler, Ninja),
installed to /home/dank/GitPackages/llama-prism-0244744. The payload gate holds:
libllama carries 42 prism.hadamard strings (b10777 had 29) and libggml-base
still registers PQ2_0, so type 142 and the hadamard metadata still load.
LLAMA_BIN inherits a bin/lib install layout now, so the install needs an RPATH
($ORIGIN;$ORIGIN/../lib) — cmake's install step strips the build rpath and the
binary otherwise dies on libllama-server-impl.so.
The unit test that pinned the 10777 path now asserts the invariant its own
comment described (LLAMA_BIN names a llama-prism-* build) instead of a
directory one rebuild happens to install; the suite runs on a box with no
/home/dank, so existence is not checkable there.
Rollback: repoint LLAMA_BIN at llama-prism-b10777/llama-server (still on disk).
A version bump re-cuts the device programs, so a staged file of a different
size is stale rather than partial. `curl -C -` against it appended the new
tail to the old bytes and produced the right BYTE COUNT with the wrong
content — the sha256 gate caught it (consts.hnpb, 2026-10-30), and the
failure reads as a corrupt program rather than a fetch fault. Resume only
when the staged file is smaller than the manifest expects.
The engine pin moves to the newest vendor release (0.18.20, image built
2026-10-30). The payload lock is the gate this deploy has to pass: the v2
.hgn loads only in the flash-server line, so /health plus the boot ledger
decide, and the rollback is the 0c61bf84 digest on the same env line.
0.18.20's NPU catalog is NOT the 0.16.2 one: it names 14 device programs
(u0..u13) and an 8,495,512 B consts.hnpb where 0.16.2 had 10 and 5,086,496 B,
and the entrypoint verifies size+sha256 for every staged file before it
starts. HALOGEN_NPU_MODELS names qwen3-embedding-0.6b, so the staging set is
re-pinned to revision 8fd44c9f with the new block — bumping the engine alone
would refuse the boot on the NPU lane.
The tap did not arm on the production pin: a 17-hour calib run on 1.8.1
wrote zero bytes while /health, /stats and the push all read healthy.
On :latest (v1.14.0, revision 4a61d7296bc5) the same boot prints
'recorded passes: off, the program accumulates calibration Grams
(gram_accum)' and a 9,129-token push sealed 24,768 gram files (42.9 GB)
in the fitting shape - 4 slots at a 2,048-token step, production's own.
The vendor's calibration shape (--max-num-batched-tokens 65536,
--max-num-seqs 64, ~930 tok/s) cannot boot two 32 GiB R9700s: the
activation arena alone is 12.83 GiB of the 27.95 GiB claimable, and
every variant stops in the VRAM resolver (short 3.19 GiB .. 86 MiB,
then a starved cache).
Floor moves 12M -> 1.5M tokens: the vendor's own measurement is 'a
pooled Gram from 10M tokens beat one from 1M by under 1%', and 1.5M is
hours at this rig's rate instead of the 29 h a 6M floor cost.
The converter moves to the same digest: rad-convert's gptq:calib=<dir>
input is version-stable, so a latest-written tap converts on latest.
Nine pages under LLM/ document the upstream radiance engine at 8da043c:
- engine shape, plugin model, RAD2 container, ABI and environment
- every serve flag grouped with defaults and the law behind each knob
- the HTTP surface, request fields and refusal classes
- rad-convert, the recipe language, quantisers, imports, reuse, rad-export, KL scoring
- the (arch id, quant) family table and the recipe of record per model
- kernel/quantiser plugin authoring, encodings, build and checks
- architecture plugin authoring: declare, step, probe, lane and media rules
- rad-info/radbench/radtune and the shell harnesses
- the container contract, host prerequisites, readiness and restart triage
Also completes the dangling Related line on the frank-archon endpoint page.
Container images re-resolved against their registries today; each pin is the
manifest-list digest the tag answers now, so no container is served from a
build that upstream has already replaced.
Version-tag moves: authentik 2026.8.3 -> 2026.8.5 (server/worker/outpost and
the ldap image, which now carries the tag instead of a bare digest so the pair
can never drift apart), seerr v3.4.1 -> v3.5.1, calibre 9.15.0 -> 9.17.0,
calibre-web 0.6.27-ls402 -> ls407, plex ls329 -> ls330, tautulli
v2.18.1-ls245 -> v2.18.2-ls250.
Digest-only moves inside the same stream: postgres 16-alpine, mariadb 11,
redis 7-alpine, valkey 9-alpine, grafana, alertmanager, gluetun, searxng,
open-webui, jellyfin, romm, chromedp/headless-shell, lightpanda/browser.
Rollback is the previous digest on the same Image= line.
A 17-hour calibration tap on 2026-10-29/30 wrote ZERO bytes: the runner booted
FRANK_ARCHON_IMAGE (1.8.1) for every mode, and RADIANCE_CALIB_DIR/TOKENS only
arms the expert tap on the 1.2.x line. 1.8.1 still carries the plugin strings and
the "calibration wrote layer Hessians" message, /health answered, /stats showed
1,700 documents and 118 tok/s, and nothing anywhere said the tap was dead.
Four gates, each with the measurement that motivated it:
- CALIB_IMAGE pins the 1.2.0 digest for calib mode (stilldeadcode/radiance
@sha256:665775ed…), overridable only by naming --image deliberately. Proven by
the engagement test: `calibration wrote layer Hessians after 10207 tokens`.
- The tap dir's filesystem must have >= 60 GiB free (Q38_CALIB_MIN_FREE_MIB).
One seal wrote 39.4 GiB in seconds; pointed at a 37 GiB root it filled the
filesystem to zero and every later write came back short.
- restore() kills orphaned `radiance` processes still holding /dev/kfd before it
starts the service. `podman rm -f` does not kill the engine: an orphan made
production's ar_oneshot_2rank_wht6 init fail `device error`, and the unit
restarted 100 times with /health never answering.
- FRANK_QWEN38_CALIB_DIR / Q38_WINDOW_TRASH_ROOT make the tap dir and the bank
target configurable, so the tap lives on /mnt/entropy instead of the root fs.
Measured from the engine's own counters on the 2026-10-29 drain: prefill 71 tok/s steady state, a
180 s window showing 7 prefill steps of the capped 2,048 tokens and 3 preemptions. One 7,168-token
document is therefore ~100 s, round 1 (2,367 docs, 10.03M tokens) ~39 h, and the 12M-position
floor ~47 h of drained production — not the ~18 h the brief assumed.
The tap is the only phase whose cost is read volume per document: at the inherited 2,048-token step
a document is four steps, and each step re-streams every layer's routed expert union from the
container (43.4 GiB a rank live on disk). One wide step reads each layer's union once.
The 'one step, one slot count' audit law binds kldref and score because their KL numbers are only
comparable at an identical shape. Calib produces layer Hessians and no number any report compares,
so Q38_CALIB_MNBT / Q38_CALIB_SEQS are its own, defaulting to the inherited value — nothing moves
unless a probe asks. The KL modes ignore both.
Tests: 589/0 — the knob reaches calib's argv, does not reach kldref's, and a non-numeric value is
refused by name.
RADIANCE_CALIB_TOKENS=12000000 is a pooled floor and calib-7168.jsonl carries 10.03M tokens, so
round 1 of a corpus push seals nothing by construction. The gate PR #84 added failed exactly
there, one round too early, while the drain was already running.
Now round_verdict() separates the cases: 'shrink' (the tap lost bytes) fails the run, 'flat' says
so and continues, 'grew' continues, 'done' stops. A run that never sees the engine's completion
line still exits non-zero on max rounds, and the rig marker remains the lock that stops a push
into anything that is not the rig.
Test: round_verdict's four verdicts, behaviorally.
Four gates, all bought with the 2026-10-29 incident: the rig's calibration boot died of an OOM,
the chain's health loop expired without failing, and the pusher fed four rounds of 10M tokens
(86 minutes of prefill) into RESTORED PRODUCTION, recording nothing.
- run-qwen38-bf16.sh: --ngram-placement becomes a knob whose calib default is `disk` (the 95.37
GiB table pin is what starved that boot: 230.22 GiB pinned of 246, 8.06 GiB available) while
kldref and score keep `ram`. calib writes .rig-boot into the tap dir and retires it on a
non-zero exit, so a dead boot cannot leave the tap looking rig-authorized.
- calib-push.py: refuses before the first prompt unless the marker exists, names this container,
and that container is running. With the driver's existing tap-progress gate, a push can no
longer spend hours feeding an endpoint that is not the rig.
- qwen38-calib-window.sh: the calibration window as a gated chain — stop on a failed phase
instead of falling through the health wait, bank the 336 GiB reference container into trash
only when both phases exit 0 and the tap holds grams, and print the whole plan on --dry-run.
- kld-gate-qwen38.sh: two-report mode (candidate vs the served payload) for the disk where the
172.8 GiB FP8 anchor cannot live, plus the laws the report always carried and the gate never
read: a p99.9 tail ceiling and every by_source slice passing mean, tail and top-1.
- frank-archon.md: the pipeline laws (marker, n-gram tier, three-metric acceptance) and a Files
section that names the live campaign instead of the retired swift15 era.
Tests: 587/0 — 13 new behavioral cases (dry-run argv, marker refusals, two-report gate math).
The three corpus tools now share scripts/qwen38_common.py: tokenizer load with the
venv guidance, one n_tokens (so a KLD count cannot drift from the corpus it scores),
JSONL read/write, an atomic writer, and refuse(). make-calib-corpus.py's 170-line
main() with three nested closures became classify / split_pools / fragment_text /
build_frags / pack_class / emit_calib / emit_kld / manifest; its magic numbers are
named constants. rechunk-kld-corpus.py's main became validate / cut / rechunk around
a Window record, so the round-trip proof sits in one function that can be tested
without a tokenizer. calib-push.py grew parse_args / load_prompts / push_round, and
a malformed corpus now refuses with a line number instead of raising KeyError.
Parity, measured on dankserver against the pre-refactor scripts at the same seed:
calib.jsonl and kld.jsonl carry identical records in identical order, the manifest
is identical, and the re-chunked corpus is byte-identical (md5 e824e67d...). The one
byte-level change is JSON escaping — write_jsonl emits literal UTF-8, which is what
the re-chunker already wrote; the parsed records do not move.
Adversarial review of the campaign pipeline. Correctness: rechunk-kld-corpus.py wrote
each window as text and asserted only lengths, so a KLD reference could score a
different token sequence than the corpus holds — every window is now re-encoded and
the tool refuses on mismatch; make-calib-corpus.py no longer crashes on a .json that
is not a content-keyed JSONL, and its KLD cursor advanced by 2 per fragment (half the
pool unused). Silent waste: calib-push.py now aborts when the tap sealed nothing or
no prompt was accepted, instead of re-pushing 10M tokens per round; div-by-zero gone,
served model id parameterised. Races: run-qwen38-bf16.sh restore() removes the rig
container before starting production (today's orphan held the GPUs while the service
reported active), the calib tap dir is proven writable, the score ro-guard resolves
paths; convert-qwen38-w5nl64.sh refuses a missing --arm value, an existing
qwen38-convert-<arm> container, and a zero-exit convert that wrote no artifact.
stack-qwen38-official-fp8.py: bare asserts in verify() (skipped under -O) and a
non-128-lane PLE HD that only warned are hard failures. Speed: fragment token counts
computed once, KLD scored positions accumulated instead of a second full re-encode.
Tests: 576 ok / 0 fail.
PR #81's pool half measured inert the day it deployed: the 66,560 boot printed the
same elastic 26.73 GiB / experts 20.72 / kv cache 5.64 / vram_weights 24.30 as the
49,152 boot and opened the pool with 0 B used, and the qwen38-w5nl64 rig moved
vram_kv 269.99 -> 271.25 MiB (window still 7,436 tokens: its 95.37 GiB n-gram table
claim decides, not the pool). The step half stays. Tests: 576 ok / 0 fail.
The container opened the raised pool with 0 B used and printed the same elastic 26.73 GiB / experts 20.72 GiB / kv cache 5.64 GiB / vram_weights 24.30 GiB as the 49,152 boot, so the era's superseded ledger line is destroyed and the evidence table gains the ceiling-case row beside the 45,568 one it already carried. Tests: ./tests/run.sh 576 ok / 0 fail.
frank-archon.env: HOST_POOL_MIB 49,152 -> 66,560 a rank (tp x 65 GiB against the
246 GiB the box has), and the TTM pair 162,000/204,800 -> 197,000/224,000 — the
floor the bats ledger formula computes at the new pool. The pool is the KV lever
under the budget resolver: every MiB pinned in host RAM lowers the expert floor on
the card one-for-one and the cache takes it.
scripts/run-qwen38-bf16.sh: the campaign's private FRANK_QWEN38_MNBT (1,024) is
gone — MNBT now comes from FRANK_ARCHON_MAX_BATCHED_TOKENS, production's 2,048 and
the widest step the quantised expert file tiers stream. That 1,024 was PR #80's
answer to a starved cache; the pool is the fix, a narrow step was the symptom's
disguise, and a per-mode literal measures a shape nothing serves.
tests: frank_archon_unit greps the new pool value; qwen38_reference's SHAPE fixture
carries it, and the two MNBT-override tests become the inheritance assertion (every
mode's argv quotes the value the env file owns) plus the calib assertions.
vault: the shape block moves to the new numbers and the Eras table gains the row for
the era this replaces. The 2026-10-20 boot-ledger line stays as the old era's record
until the new boot's ledger replaces it.
The calibration mode kept a private step (8 seats at MNBT 65,536) that it
called "free throughput". The step's activation arena is billed to the card,
so the wide step cost the container its own expert slab and KV: at 65,536
the arena is 10.65 GiB and the claim falls to 16.85 GiB (weights 14.24 GiB
in VRAM, 56.24 GiB stranded on disk, KV 271 MiB for 8 seats), and the boot
dies with "startup stopped: out of memory" (measured 2026-10-29, while the
kldref boot at MNBT 1,024 — arena 504 MiB, claimable 30.87 GiB — had just
recorded for 16 hours without fault).
Every mode now takes its seat count from FRANK_ARCHON_MAX_SEQS, the file that
owns it, exactly as PR #77 established for the card split, and its step from
FRANK_QWEN38_MNBT. The per-mode literals in kldref and score follow, so one
number defines the geometry for all three. The test that pinned the old
exemption is re-pinned to the invariant that replaced it.
tests/run.sh: 576/576 green.
Portable POSIX-sh purge of exactly the fleet's deletion-policy trash: a
root's own .AGENTTRASH is emptied in place (the convention survives),
deeper .AGENTTRASH trees are removed with their nested entries accounted
once, symlinked/foreign-owned candidates are refused, / is refused.
Dry-run by default; --execute performs the plan and appends one dated log
line; every printed line is fixed at plan time in the on-disk plan table,
so dry-run and execute output can never drift.
Documented in Operations/Payload and Disk Reclaim.md section 6 (one fact
one owner - no new vault page). Tests: 14 green, ./tests/run.sh 576 green.
The reference rig declared a 32,768-token window while the boot ledger hands it
7,436, so 197 of the 198 inherited documents were too long to score. The engine
warns about the real pool; the flag was the only cited source.
Add scripts/rechunk-kld-corpus.py, which moves document boundaries without
moving tokens: each record is re-cut into windows of at most --max-doc-tokens
(7,168 = 7x1024, the largest whole kilopage under 7,436), and each window gets
its own score_from = len - --score-tail. The reference scores the same token
series at more positions and at a shorter context; the calibration corpus is
untouched, so no quant moves. Writes go through a temp file and the token
counts must match before the output is published.
The rig header now says what the pool actually is, and scripts/test-changed.sh
routes the new script to its own seam instead of the generic syntax fallback.
The rerun after 96c5a06 refused every corpus document again ("document 196 is
8507 tokens and the KV pool holds 7436"), and the boot table shows why the
host-pool change could not have helped: vram_budget.cpp put the container in its
`no lender` branch — elastic 25.56 GiB, experts 25.29 GiB (their plan-fixed
share), kv cache 271.25 MiB — identical at 12,288 and at 49,152 MiB of host
pool. The only supplier left there is the activation arena, and the engine says
so at vram_budget.cpp:117: "lower --max-num-batched-tokens (the arena scales
with it)". The log prices both rungs directly (a 2,048-token step costs 1.08
GiB, a 1,024-token step 504.39 MiB), so the default moves to 1,024: the cache
grows to 866 MiB / 24,300 tokens and scores every one of the 197 documents
(longest 11,970). Calibration keeps its wide 65,536; it was never tied to MNBT.
This also retracts the mechanism 96c5a06 recorded in the header ("the pool buys
KV as well as residency"). Inheriting the env's 49,152 / 96 stays right as
single-source-of-truth, but on this payload the pool is not the cache's supplier.
run-qwen38-bf16.sh carried its own --host-pool-mib 12288 / --gpu-headroom-mib 768,
copied from the w4-era swift15 rig. The engine derives the whole per-card split from
those two numbers, and the KV cache's funding is `elastic - expert_floor` where the
expert floor is a function of the pinned host pool — so the pool buys cache as well
as residency. The first kldref boot got a 270 MiB / 7,436-position pool and the
recorder refused all 197 corpus documents ("document 0 is 10554 tokens and the KV
pool holds 7436"), exiting 1.
The rig now sources FRANK_ARCHON_HOST_POOL_MIB / FRANK_ARCHON_GPU_HEADROOM_MIB from
scripts/frank-archon.env, the file that owns them (49152 / 96), with `:?` guards, and
the header records the law instead of the claim that the pool never touches logits.
tests/qwen38_reference.bats pins the shape verbatim, so its SHAPE contract moves with
it; the suite is green (558 tests).
Two tools the KLD gate depends on.
build-qwen38-bf16-rad.sh converts the checkpoint to a BF16 .rad with NO recipe
line, so every tensor stays bf16 - the reference must not carry the quantization
it is there to measure. It gates before writing 335 GiB: the checkpoint present
and fully verified by the fetcher's own verifier, the peak-disk bill (350,000
MiB: the checkpoint's 343,323 plus margin, because the .rad is built beside it),
an existing output retired to ~/.AGENTTRASH by --force instead of deleted, and
--plan-only before the real convert. --max-ctx 32768 is a declare-time check, not
a weight change: dropped, the resolver is handed the checkpoint's 262,144 window,
which at fp8 cache is 258.8 GiB on a 192 GiB machine.
run-qwen38-bf16.sh serves that container in three modes - kldref (record the
reference logits), score (record an arm's logits against that reference), calib
(open the Gram tap for the imatrix). It drains frank-archon and restores it on
every exit path, and the two logits modes ride ONE step size
(FRANK_QWEN38_MNBT, default 2048) and ONE window (FRANK_QWEN38_MAX_MODEL_LEN,
default 32768) so a reference and an arm cannot be measured at different shapes:
that is the whole validity of the KL number. Four slots over 2,048 matches
frank-archon.env's operating point (MAX_SEQS=4, MAX_BATCHED_TOKENS=2048); the
smaller host pool (12,288 vs 49,152) buys residency, which moves speed, not
logits. calib keeps 65,536 - decode-bound serving, never the gate.
kldref refuses before the drain when the corpus's longest record cannot fit the
declared window (limit = window x 3 chars, the pessimistic tokenizer bound; the
measured corpus is 38,263 chars, 2.6x inside 32,768). It runs on --dry-run too,
so the check is visible before a 20-minute drain is spent. 12 seam tests, each
red-proofed by neutralising the gate it pins.
32 black-box tests over the four tools the campaign runs, driven through their
own argv with fixture corpora - no GPU, no container, no rad-convert. Each test
is an output an operator reads: the verifier's MISSING line and exit, the byte
bill the derivation lands, the refusal text, the plan and the convert the driver
prints per arm, the interval verdict the gate returns.
Includes the planner seam the swift15 campaign lacked: the campaign's paths plan
NO deployable service, so merging this toolchain can never drain frank-archon.
The driver fixture carries four grams so --min-grams has a thin-pool control,
and the arm-driver invocation passes env assignments positionally after the
driver's own flags, so the seam exercises the real call shape.
The swift15 gate compared an arm against the BF16 reference and passed on
KL <= 0.03. That bar is now the wrong instrument: the fleet already ships the
publisher's FP8-native iq4r-moe payload, so an arm that beats BF16 but loses to
what is running is a downgrade. The gate takes three recordings - fp8 anchor,
iq4r anchor, candidate - and requires the candidate's KL strictly inside the
interval the two anchors define, at every slice, plus top-1 agreement no worse
than the served payload.
The anchors must be ordered (fp8 better than iq4r) or the run stops: an
unordered pair means the instrument or the recording is wrong, not that the arm
lost, and one number out of the report is named rather than guessed at.
--recover prints the tightened numbers the same way it prints the failing ones,
so the operator sees the bar they would have had to clear.
One template (every routed expert at five bits, E4M3 scales in 64-groups, the
top level rotated through the 128-wide Hadamard chosen by GPTQ against CALIB)
plus a driver that generates the per-arm expert row, so the other 60 lines can
never drift between arms: control (cd=3), cd=6, and act_order=1 with NO cd= -
libquant refuses the pair (lq_registry.cpp:105), so the AoA arm is its own
sweep, not a fourth column.
The header carries the campaign's order (fetch -> build reference -> one drained
window for the calibration tap and the KLD reference -> trash the bf16 container
-> imatrix -> arms -> fetch the FP8 anchor last -> gate -> trio edit), because
that sequence is point-of-use for whoever runs it next, and the disk sequencing
is forced: 754 GiB free does not hold checkpoint + reference + three arms.
Gates that bite before 5h13m of convert time is spent: the BF16 reference still
occupying the volume, a recording too thin to be a calibration (converting
uncalibrated is silently worse and only whispers on stderr), an imatrix outside
the mounted campaign dir, an arm that already exists, a protected derivation
that cannot land its target, and a destination that cannot hold the output. Each
arm runs --plan-only first so the engine's own fit check bills at plan time; the
served container's argv shape is what the arms declare.
rad-convert's GPTQ path reads importance from an imatrix GGUF; the reference
container's --kld-record pass emits per-expert and per-hidden Grams as raw
recordings. This folds them into one v3 file: a single expert-major f32 entry
per MoE layer plus the hidden-width entries, every data offset a multiple of
general.alignment as the loader requires.
Refusals, each one a silent-worse outcome the swift15 campaign hit: an expert
with no gram of its own carries the layer's pooled diagonal and the count is
reported (a silent zero is a down-quantized expert nobody priced); expert grams
with no pooled gram, a gram short by one float (names the file), the same global
expert recorded twice with different numbers, an empty recording directory, and
an existing output. --min-rows sets the noise floor below which a recording is
dropped. rows is u64 so a corpus that outgrows u32 survives the header instead
of wrapping.
The swift15 rule (top 7% by imatrix energy, bar-only) left the plane size to the
distribution. The w5nl64 arm trades a *pinned host pool* against KL, so the
operator needs to say how many GiB of bf16 experts the pool can afford and have
the set land there: --target-count walks the ranked candidates until the byte
bill matches, keeps the bar-only pass for experts that are disproportionate for
their size, and reports the pool's ceiling instead of padding when the count
cannot be reached.
TP=2 cuts the expert plane into two 256-expert rank halves, and an odd count in
either half unbalances the placement, so the parity audit is a refusal (exit 2,
'PARITY LAW BROKEN'), not a silent fix-up: the driver stops rather than
converting a payload whose expert placement no one priced.
The w5nl64 campaign measures against the vendor checkpoint, not the Swift-1.5
finetune: the served payload (qwen3.8-next-flash-fp8-iq4r-moe) is quantized from
this base, so fidelity must be scored against the same reference. 335.3 GiB
across 10 shards.
Verifier gates on the index's own shard list, each shard's declared byte count,
and the Hub's declared total - a curl without -f writes the 401 body as the
'shard' and reports success. --fetch refuses when the destination cannot hold
the checkpoint, because a 335 GiB download that fills the disk mid-shard costs
the whole campaign window.
iptables -I prepends, so the install block's final -I of the blanket DROP
landed it at position 1, above all three ACCEPTs: every packet to
18093/tcp died there (live 2026-10-21: 159 packets on the DROP, 0 on each
ACCEPT). The host's own health probe timed out beside a LISTENing socket
and the whole dankclaw drain aborted at the alertmanager gate twice.
Install now rebuilds the tail: delete any blanket DROP wherever it sits,
keep the ACCEPTs at the head, append the DROP last - converges on hosts
poisoned by the old order. New bats case runs install_signal_relay for
real against an iptables sandbox seeded with the poisoned order (red on
the old code, green on this one).
Per Frank, frank-archon is public alongside dragoon/zealot: three-leg DB
trio (conn enable, model row ctx 200000, access_grant principal='*'),
verified as role=user. Token-mint traps recorded (cwd, PID-1 secret).
Closing the command-center security queue #70/#71/#72/#73/#74: rolling tags
let a rebuild move under a running service with nobody approving it, and
make a CVE audit ungradeable. 36 quadlet units across dankclaw, dankserver
and frankbook-pro now carry tag@sha256; localhost/* builds stay exempt
(their build is the pin). The pihole and copyparty pins pull the fixed
builds; valkey 9.1.2 (already running) and redis 7.4.11 are pinned in
place, vendor fixes TBD.
New gate tests/quadlet_image_pins.bats: no unpinned registry image, no
generator-rejected key anywhere. Three seams that pinned the old exact-tag
law (frankbook readarr, open_webui, seerr) now require tag AND digest -
strictly stronger. Quadlet Lifecycle docs: batch-abort law, entrypoint
flags-only law, pin law.
Three stacked lessons, each proved live 2026-10-21:
- the image's ENTRYPOINT is /bin/blackbox_exporter, so Exec= repeating the
binary made it a positional arg: 'unexpected /bin/blackbox_exporter'.
- the podman gateway 169.254.1.2 is NOT bindable from the host netns - it
exists only inside each rootless netns: 'bind: cannot assign requested
address'. The scrape path does not need it bound: a bridge container
dialing the gateway lands on the host LOOPBACK (proved 200 from the
prometheus container), so the exporter binds 127.0.0.1 + LAN.
- HealthCmd shell form ('/bin/sh -c "..."') is passed as one quoted token
and quadlet folds the following --health-interval/--health-retries (and
the image) into the command string; the plain exec form the sibling units
use is correct.
Prometheus.md bind law corrected (gateway is a forward-to-loopback, not a
bind address); deploy-remote gate stays loopback, which is now honest.
Third boot failure: the exporter exited 100 ms in with 'unknown long
flag --listen-address' (proved against the pinned image, plus --help).
The bind semantics were right; the flag name was invented. --web.listen-address
is repeatable - one per address - so the dual gateway+LAN bind stands.
Proven again pre-deploy with the real argv: the run starts and dies
only on the deliberate /dev/null placeholder config.
The deploy died at 'Unit blackbox-exporter.service not found': a
.container without Image= is not generated at all, and the header
argued for Network=host it never declared. Completes the unit (digest
pinned prom/blackbox-exporter, Network=host) and fixes the bind
topology the first cut got wrong:
- Prometheus is bridge-networked and the netavark hairpin gap bars it
from its own host's LAN IP, so a LAN-only prober bind is unscrapable
and a loopback-only bind was claimed to ride the gateway on faith.
The prober now binds 9115 on the podman gateway (scrape path) AND
the LAN (healthcheck/diagnostics); the listen_address line leaves
blackbox.yml so config and Exec cannot disagree.
- comfyui probe target http://comfyui:8188 -> http://127.0.0.1:8188:
bridge container names do not resolve in the host netns; the
published 0.0.0.0:8188 answers on loopback there.
- New seam: every observability unit must declare Image= (red on the
shipped file by name); copier test pinned module presence instead
of the removed listen line. Docs updated to the real topology.
PR #69 wired the copier, planner entry and health gate but missed the
three dispatch gates: the client valid_service, the remote
service_is_allowed, and deploy_service's case list. The client gate
rejected --service blackbox-exporter outright; even past it the
dispatcher's catch-all hard-fails on dankclaw (no compose since
2026-09-16). New seam pins the class: every dankclaw service the
remote gate allows must carry a deploy_service case - proven red by
planting a gated, undispatched name.
Measured 2026-10-21 with frank-dragoon live: MemAvailable 15.3 GiB,
iGPU busy 1.75 GiB. The Qwen-Image weight sets (13.3-14.2 GB) do not
fit that budget, and the page's 122 GB /system_stats figure is the
aperture, not headroom. Adds the fit table and the
stop-mask-render-verify procedure (the 3090 bench law, applied to the
APU); ComfyUI.md gotcha links it.
Prometheus/Observability/Provisioning pages: every job up after the
blackbox swap, the copier list learns copy_blackbox_config and the
alloy validate gate, the config table gains alloy + blackbox rows, and
the logs bullet states the stream-label law instead of the retired
'awaiting deploy' note.
- caddyfile seam learns the documented exception: URL-shaped targets
are legal only inside a prober job (state is per-job; the first cut
leaked it and passed a planted URL).
- observability seams: blackbox unit + planner entries, both copiers
executed for real in sandboxes, alloy engine-validation refusal
(image-gated), dashboard panel invariants.
- AGENTS.md: structural target downs retired.
copy_alloy_config now validates the rendered config with the very
alloy image that will run it, before installing: a misplaced attribute
crash-loops the unit behind a green deploy, and no textual seam can
see it. copy_blackbox_config ships the prober config; the planner maps
the new unit and shared/blackbox/** to the blackbox-exporter service,
ordered before prometheus.
Loki metrics queries group only by indexed stream labels, so the
journal-as-JSON stream made every per-container view structurally
empty (measured 6.5k lines/5min flowing while the board read zero).
A loki.process relabel stage now extracts CONTAINER_NAME into a
'container' label. alloy 1.21's json stage has no on_error attribute
(validated against the pinned image) — format_as_json guarantees the
line shape, so no error branch exists.
observability.json: stale 'structural downs' panel description fixed,
target census matches the post-blackbox job set. logs-overview.json:
panels grouped by the promoted container label instead of the absent
container_name, so the board stops reading empty beside live traffic.
Prometheus 3 refuses HTML scrape bodies, so the comfyui/services probe
jobs were structurally dead targets reading as outages. HTTP liveness
now rides a blackbox exporter (shared/blackbox/blackbox.yml, loopback
bind, http_2xx module); prometheus.yml probes SearXNG, OpenWebUI and
ComfyUI via __param_target relabeling. The unit is a boot-persistent,
self-healing root quadlet.
copy_grafana_provisioning named llm-fleet.json alone, so a new board in
shared/grafana/provisioning/dashboards/ silently never reached
/opt/grafana/provisioning. Measured 2026-10-21: the containers board was
merged, seam-tested, and documented as working since 2026-10-20, yet was
NEVER provisioned — its panel fixes were undeployable; the other four
boards existed on disk only because someone hand-copied them once (and
host-system.json there had gone stale against the repo). The copier now
globs the directory, and GRAFANA_PROV_ROOT lets the new bats case run
the copier for real into a sandbox (red against the old hand-listed
body, green against the glob). Vault: the copier law + the containers
incident on Observability Provisioning, the corrected dashboards claim
on Observability.
Note: a mktemp sandbox + trap RETURN races bats' trap machinery (the
dir vanishes mid-function); BATS_TEST_TMPDIR is the safe idiom.
Census: all 5 provisioned dashboards, 56 targets, every expression
re-evaluated against the live Prometheus/Loki with template vars expanded
(queries must run from the host: both APIs bind 127.0.0.1; from the dev box
that is connection-refused, which is NOT a dashboard defect).
- host-system 'Load 5m / core' was STRUCTURALLY EMPTY: bare '/' drops
non-matching pairs and the right side collapses to {job} while the left
carries {job,instance} -> 0 series forever. Fixed with / on(job); proven
live (2 series).
- containers 'Memory vs limit (%)' was STRUCTURALLY EMPTY: every
container_spec_memory_limit_bytes on this fleet is 0 (no cgroup limits),
so the '> 0' filter can never match. Rewritten to share-of-host-total via
label_replace join of the node exporter's MemTotal by host (the parens
form is a PromQL parse error: nothing may follow group_left); 62 series
live. Panel unit percentunit kept -> expression returns a fraction.
- llm-fleet 'Firing fleet alerts' is legitimately empty when healthy
(ALERTS carries only firing/pending series); description now says so,
per the Stale Signal rule that 0-series-on-ALERTS is not a defect.
logs-overview and observability: all targets already returning data.
Purpose-test pass over the audit findings (every verdict re-verified
against the file before touching it; three scout findings were hallucinated
— a nonexistent filename, my own changelog line, and sanctioned Eras rows):
- Observability Provisioning: destroyed the 63-line 'Current delivered
state' block — chain topology/relay/delivery restates [[Observability]]
and [[Alertmanager]] (those are the owners). Its three sole-custody laws
MOVED to Stale Signal Audit as 'Three rules that outlive the incident':
down-beside-healthy -> read lastError; Prometheus alert state in process
vs Alertmanager's --storage.path persistence; candidate-arm metrics are
never fleet state.
- RDNA4 MoE VRAM budget: kept the laws (registry over-prices the pool;
never reuse a B/token ratio across geometries; pin pool bytes
floor-sized), era-labelled the rates, destroyed the measured ladder
table for the superseded shape-G/bf16 rungs.
- Stale Signal Audit: new rules section + Provisioning Related link.
check-okf 109/0, vault links 0 unresolved, docs seams green.
The lane's child dlopens libxrt_core.so.2 from /opt/xilinx/lib/<multiarch>/
as well; our mounts filled only /opt/xilinx/xrt/lib and the install path.
Since the host's libxrt2 was reconfigured 2026-10-20 the child dies naming
the missing prefix ('No such library
/opt/xilinx/lib/x86_64-linux-gnu/libxrt_core.so.2') and the engine
supervisor takes the WHOLE container down on a dead lane — measured
2026-10-21: frank-dragoon boot-looped 88 times with chat dead while the
GPU lines looked healthy.
Each XRT library now mounts THREE times from the same real file (never a
symlink); the multiarch name derives from FRANK_DRAGOON_XRT_DIR's basename
so the bats fixture proves the derivation. Proven end-to-end before commit:
production-shaped scratch boot + the three extra mounts answers the full
boot ledger, npu_api buckets u0..u9, and /health ok at the 262144 ceiling.
A dead lane is not survivable on this engine — arm it only with all three
prefixes (page law updated).
Shape + harness contract on the endpoint page, AGENTS.md, and the OMP
Harness worked example recomputed to the live pair; the 400-zone law now
names the 85 %-comments vs 95 %-config disagreement as the recurring
cause and points at the seam that enforces the arithmetic.
The 200,704 ceiling squeezed the harness contextWindow down to 155,648
(the 400-zone fit law needs ~45k of gap under the ceiling), which is why
long dragoon sessions kept hitting the 400 zone: the harness clamps
max_tokens to window - est - 4096, its chars/4 est under-counts ~3 %,
and config.yml compacts at 95 % while the pair was designed for 85 %.
Ceiling -> checkpoint's native 262,144 (no RAM move: the KV pool stays
401,408 and is what the ledger bills; the band ctx <= pool <= slots*ctx
still holds). The harness window becomes 200,000 with a 62,144 gap.
The fit-law seam now reads the declared window from the vault page (the
one owner) and checks the arithmetic at the live 95 % trigger, so a
ceiling/window pair that drifts back together fails tests/run.sh
instead of a live session.
Two shipped-2026-10-20 bugs that left gpu-dankclaw, gpu-dankserver and
cadvisor-dankclaw DOWN beside a green deploy:
- gpu-exporter.py built one ThreadingHTTPServer per bind but ran
serve_forever() on servers[0] only: the LAN-class socket sat listen()ing
but never accept()ed, loopback deploy gate passed, every scrape that
reached the other bind timed out on the SYN backlog. Now one thread per
extra bind. Regression test spins --serve on two loopback binds and
requires BOTH to answer /metrics.
- cadvisor-dankclaw scraped its own host's LAN IP. Measured from inside the
Prometheus container: a bridge container cannot dial its own host's LAN
address at all (hairpin refuses published ports too); the podman gateway
answers. Target moved to host.containers.internal:8080; the seam that
pinned the LAN address (asserting the wrong doctrine) is re-pinned to the
gateway plus a negative pin against the own-host LAN dial. Observability
page records the measured reachability law replacing the inferred one.
deploy.sh's valid_service and deploy-remote.sh's service_is_allowed are
two gates for the same door, and they drifted: the remote gate gained
cadvisor (2026-10-20) and gpu-exporter (2026-10-21) while the client gate
never did, so `--service cadvisor|gpu-exporter` died with "is not deployed
on <target>" at the client — the first-ever deploy of a new service is
exactly the case that needs the client gate to know it. dankserver:prowlarr
(planner can emit it for dankserver) was remote-only too.
Adds the four missing pairs to the client gate and a deployment_flow
contract test that diffs the two extracted lists per target — the test the
cadvisor PR should have carried. searxng-network stays the one sanctioned
client-only exception (network unit, no remote handler), documented inline.
ls329 is the newest build on the linuxserver channel and Plex 1.43.5.11029
is their newest release; the live pin (ls325 / 1.43.4.10903) is two Plex
releases behind. Digest-verified at pin time: the tag's manifest digest
equals the registry's current 'latest' (sha256:8f655bad...e9e2334), the
same law the page records. Quadlet restart runs PMS's usual one-minor
schema migration on first boot; the deployer's /identity HTTPS gate
tolerates the first-boot migration up to 600 s.
Rollback: revert this commit (one line).
Add a host-process GPU exporter, scrape it on both servers, and graph it
on the host-system dashboard. The fleet has four GPUs across three vendors
of interest (2x R9700 on Dankserver, the 8060S iGPU + RTX 3090 on Dankclaw)
and nothing exposed them until now.
scripts/gpu-exporter.py reads each AMD card's amdgpu sysfs
(gpu_busy_percent / mem_info_vram_* / hwmon temp1_input / power1_average)
plus one nvidia-smi --query-gpu CSV, and emits unified gpu_* Prometheus
families (utilization_percent, memory_used/total_bytes, temperature_celsius,
power_watts) labelled gpu/vendor/model. Absent hardware yields ABSENT series,
never a fabricated 0: the R9700s expose no sysfs power, so they simply carry
no gpu_power_watts line. Both sources are injectable, so the seam runs on a
GPU-less dev box; live-verified on Dankserver's real sysfs.
It runs as a plain user unit (not a quadlet): it must read the host's own DRM
sysfs and shell to nvidia-smi, which a container cannot do without GPU
passthrough. Same posture as signal-relay. The base unit binds loopback; the
deploy drop-in appends the host LAN address, never a wildcard (matching
node-exporter/cadvisor). deploy_gpu_exporter installs/enables/health-gates it
on both hosts and is wired into the planner (both targets), the test-changed
router, and two Prometheus scrape jobs using the node/cadvisor reach rules
(gateway on Dankclaw, LAN on Dankserver).
The stored 3.28 chars/token (measured 2026-10-11) had drifted to 3.20 as the
repo's docs grew, so leg B sent ~201,900-token prompts and took a legitimate
400 from the engine's own window check — which reads as a capacity-contract
failure on a healthy endpoint. One ~4k-token request now prices the ratio, and
the leg sizes to 97 % of the deployed window.
The shape block and boot ledger now quote the live 1.8.1 boot: experts 20.72 GiB
(78 %) / kv cache 5.64 GiB (21 %) = 747,492 tokens, 3.7 full-length sessions,
`--checkpoint-slots 40`, `queue_cap 32`, sampler 12 rows, `experts-from-host`
8.99 GiB a rank.
The KV Capacity law is rewritten from the pinned source instead of inference:
`core/mem/vram_budget.cpp:146-156` funds the cache as `elastic - expert_floor`,
`core/mem/kv.cpp:266` sets its ceiling from `max_seqs x max_ctx` (demand, never
funding), and `core/place/planner.cpp:100-104` makes the expert floor fall
one-for-one with `--host-pool-mib` — which is why +4,224 MiB of pinned host pool
bought the pool and cost 3.01 GiB of residency a card. The old "funds ~90 %,
never 100 %" phrasing was inference; the byte-identical 45,568 row is the ceiling
case, not a mystery. Slot-cost law carries the four-slot price (state +
checkpoint store + rows, still under the 25-row exact-wire bound). The two-slot
era is one row in Eras with its rollback commit. Date stamps in the trio
comments corrected to 2026-10-20.
Frank's order: 4 slots, a 700k pool, round UP if the resolver cannot land it
exactly. The cache target is MAX_SEQS x MAX_MODEL_LEN, so the demand is
800,000 fp8 tokens; the resolver funds ~91-93 % of demand (three boots of
evidence on the endpoint page), which clears 700k, and the VRAM has to come
from the expert plane -- which has to go somewhere, so HOST_POOL_MIB moves with
it. expert_vram_floor (core/place/planner.cpp:100-104) is exactly
plane + 2 units - host_room, and the live boot ledger pins that plane at 67.60
GiB a rank (23.73 GiB floor at 44,928 of room), so 49,152 drops the floor to
19.61 GiB and leaves the cache ~6.9 GiB: enough for the whole target, with the
leftover returned to the experts.
Costs, both real: pinned host RAM 87.75 -> 96.0 GiB (the pool is pinned once per
rank) and ~3.2 GiB a card of expert residency, read over the x8 Gen5 link when
the router picks a host-resident expert. The boot ledger's vram_kv line is the
referee; if it comes back under 700,000 tokens HOST_POOL_MIB goes up 1024 and
this redeploys.
TTM_MIN_MIB 150,000 -> 162,000 for the new pin ledger (2 x pool + PLE 48,824 +
prefix 8,192 + MNBT 2,048 + the auto checkpoint store, now 40 slots of 112 MiB =
161,848 MiB), and the bats ledger guard now counts the checkpoint store because
it grows with the slot count. The two env-value assertions in that seam are
bumped with the values they guard.
A prefill chunk that shares a step with decoding sequences holds the device for
the chunk's whole time: measured on this shape, decode-only steps 15.5 ms
against chunk steps 166 ms, and 4.7 % of the steps carry 34 % of the engine's
step time. Harness-visible decode falls 166 -> 13 tok/s (per stream 6.7 = one
token per shared step) once concurrent prefill passes 5k tok/s, and TTFT p90 for
an arriving request goes 2.4 -> 18.0 s.
BUSY_PREFILL_CHUNK stays `auto`: it is a prefill-speed dial, and the source
refuses to halve the chunk for decode rows alone -- which is why
engine_steps_held_total read zero for the whole 34.7 h boot. PREFILL_INTERLEAVE
is the knob that acts on the measured mechanism: N decode-only steps follow any
chunk step taken beside decoders. N=1 is the conservative first arm -- a stream
takes its token from the chunk step and one from the held step (~2 tokens per
182 ms instead of one per 166 ms); the cost lands on the prefilling prompt's
TTFT and on requests still queued, not on anything decoding.
Rollback: PREFILL_INTERLEAVE=0. Verification: the flag must reach argv (the
serve script only passes it when > 0), engine_steps_held_total must leave zero,
then the §9 bucket pair must move before N rises.
Per-container CPU/memory was invisible for the quadlet app stack — Grafana could
only see the host (node_exporter) and the LLM engines. This adds a rootless
cadvisor quadlet on each host and a `containers` dashboard.
cadvisor works on this rootless-Podman / cgroup-v2 host on one condition:
--cgroupns=host. Podman starts every container in a private cgroup namespace, so
without it cadvisor sees only its own cgroup root and exports a single series
(measured 2026-10-20: 1 series off, 996 on). The libpod socket does not name the
rootless app containers (it resolved 2 of 34), so naming comes from elsewhere:
the quadlet unit name is carried in the cgroup path
(app.slice/<name>.service/libpod-payload-<hex>), and Prometheus relabels it into
a `container` label. No podman socket needed.
cadvisor cannot bind per-interface like node_exporter, so each unit is a bridge
container publishing exactly 127.0.0.1:8080 and the host LAN address — never a
wildcard. Prometheus (a bridge container) reaches a host-published port at the
LAN address, so cadvisor-dankclaw/dankserver scrape 192.168.0.143:8080 /
192.168.0.235:8080. Only the families cadvisor actually exports for these
containers are graphed — CPU usage, memory working-set/limit, OOM — not network
or filesystem, which are absent under the host-PID layout.
Wired through the deployer (allowlist, deploy_observability case + /healthz gate,
dispatcher), the planner (both targets), and observability_quadlet.bats.
The replay law named `--checkpoint-policy floor`; config.cpp admits exactly
geometric-backoff (default), tip-only, keep-all and refuses anything else at
boot, so the recorded arm could never be deployed. Replaced with the real
semantics, priced from core/mem/prefix.{h,cpp}: the default keeps a geometric
ladder (9 snapshots for a 200k session at interval 2048 -- exactly the live
ledger line -- so a turn diverging d behind the tip can resume at tip-3d:
diverge at 120k, replay 21.7k); retention is not the write path, so keep-all
buys a bounded replay for pinned host RAM alone (196 slots x 111.98 MiB = 21.4
GiB against the store's eighth-of-host budget of 31.5 GiB, hard bound = room);
and shortening --checkpoint-interval cannot fix the deep case -- the coarsest
ladder scale is interval x 2^k under the depth, so the deepest gap stays about
half the prompt at every interval. §9 keeps only the three-name locator.
frank-archon Laws: add the measured interference census (decode-only step
15.5 ms vs 166 ms chunk steps; 4.7% of steps hold 34% of step time; median
decode 166 -> 13 t/s above 5k prefill tok/s, per-stream 6.7 t/s = one token
per shared step; TTFT p90 2.4 -> 18.0 s for arriving requests), the lag test
that kills the residency theory, the busy_cap arithmetic, and the correction
that --prefill-interleave is the decoder dial and auto is not.
Facts that change how an operator reads this box: /diagnostics exists and
reports link-below-max at 100% busy; latency metrics live under vllm:, cadence
under radiance:; preemption is vllm:num_preemptions_total (264 this boot, all
bursts) while the radiance gauge is instant depth; both root ports are x8 Gen5
max by board (31.5 GB/s ceiling, not 64); DDR is back at 4800 MT/s while the
4600 corruption fix is recorded -- verify before blaming garbage tokens.
§9 (LLM Performance Diagnosis): method corrected to the phase-ratio counters,
dead 1.0.13 numbers destroyed, four PromQL traps added (metric prefix, 1 s EMA
gauges vs 15 s scrape, counter resets across builds, 2-minute mean diluting the
chunk), instruments that cannot be reached from Prometheus, and the knob list
priced from the pinned 1.8.1 source instead of the stale guide.
The env comment claimed BUSY_PREFILL_CHUNK=auto protects decode rows; the 1.8.1
source (core/sched/scheduler.cpp busy_cap) reserves 1+spec rows per decoding
sequence and 1/8 of the budget per waiting request, and refuses to shrink the
chunk for decoders alone -- auto is a prefill-speed dial. The interleave comment
carried a 512 that is not this build's auto value (0 until the held-step
counter asks; 64 in help mode). The serve header still described three decode
slots; MAX_SEQS has been 2 since the 2026-10-19 reslice. No behavior change.
Audit of all 12 e2e specs for the 'green-but-vacuous' class that broke
Grafana's SSO. The suite is otherwise sound (incident-driven, leakage-based);
two real coverage gaps surfaced:
- notebook.franksdank.cloud (open-notebook, deployed 2026-10-19) was a guarded
vhost in NEITHER the 13-/14- GUARDED lists NOR any dedicated spec. A broken
upstream would stay invisible - the exact 17-hermes class. Added to the 14-
guard audit (unauth -> authentik gate, 'Open Notebook' leak marker) plus a
new 21- that proves authenticated reachability to open-notebook's own login
through the guard chain, with a positive app marker.
- prometheus.franksdank.cloud was only ever asserted '<500 and not a login
wall' (13-/11-), which a 404 also passes. New 22- adds the app-is-really-
there proof 20- gives Grafana: SSO handoff + its own /api/v1/status/buildinfo
answers {status:success}.
Both specs wired into the standard project (playwright testMatch), which the
e2e_scaffold bats gate enforces. Verified live against the fleet; full bats
suite green.
llm-fleet.json already owns LLM capacity+spec-decode. These three cover the
domains that had NO dashboard:
- host-system: node_exporter CPU/Load/Mem/Disk/Net/Uptime/FS/FDs for both
Dankclaw and Dankserver (templated by job node-dankclaw|node-dankserver)
- logs-overview: Loki volume + per-container error rate + a sample log panel;
container is parsed from the JSON line at query time (journal streams have
no container_name stream label)
- observability: the stack's own health - Prometheus target up/down + scrape
interval drift + samples/s + TSDB, Loki ingest/discard, Grafana CPU/mem.
Panel queries verified live against Prometheus/Loki; provisioned dashboards
confirmed via /api/search. Alertmanager is running but NOT scraped by
Prometheus - noted in the dashboard, no empty panels built on it.
The login lands once authentik emits the email claim (the IdP fix); Grafana needs
no USE_ID_TOKEN toggle, and dropping it also avoids a *_TOKEN false-positive in
the literal-secret seam. Correct the two SSO notes accordingly.
The Authentik SSO button returned "Server Error" (500): the grafana provider had
a NULL authorization_flow and the authorize view crashed building a None flow
planner. After that, the login failed with "InternalError" — no email claim
reached Grafana, so it fell back to GET <api_url>/emails, which authentik 404s.
Unit env: request authentik real scopes (openid email profile, not the GitLab
user:email that crashes the authorize view); standard userinfo API_URL with no
?api=1 (Grafana v13 turns ?api=1 into a /emails 403); email/sub/preferred_username
attribute paths; ALLOW_SIGN_UP=true since the Anubis->Authentik guard fronts the
callback. scripts/authentik-grafana-sso-fix.sh idempotently re-applies the two
IdP-side causes (NULL authorization_flow; grafana-email-scope returning a bare
string instead of {"email":..}). Verified end to end: RP login lands on / and
/api/user answers 200 with the real email, user provisioned as Viewer.
The vault claimed the fork property-mapping evaluator was broken and userinfo
returned only sub, so email could never reach Grafana (outcome unverified). That
was a misdiagnosis: the real causes were the NULL authorization_flow (the
NoneType.slug crash) and the email scope mapping returning a bare string rather
than a dict. Record the four verified causes and fixes, point to the repair
script and the new landing spec, and drop the unverified caveat.
Frank