--ds4-prefill dense made requires_monolithic_model() true, and a monolithic
load asks ggml for the entire 187 GiB expert set as one device-0 buffer:
"allocating 191932.25 MiB on device 0: cudaMalloc failed: out of memory",
followed by "monolithic HIP load required for dense prefill". Approximate
prefill (dense, sparse) is expressible only where the experts are resident
(in-process owners). exact feeds the prompt token by token, which is the
path the hybrid tier streams experts for. Chunk follows DS41.md's
cold-expert recipe (1024).
The llama.cpp hunk (ggml_cuda_node_launches_nothing) was needed on main's
tree; the branch restructured that file and compiles clean, so only the
apt-list and cmake-3.31 hunks remain. Regenerated from the host clone.
The deepseek41 architecture exists only on Luce-Org/lucebox's
feat/ds41-engine branch; main rejects the checkpoint with
"unsupported model architecture 'deepseek41'". Re-aim the image build at
that branch and fix the launch shape, which had been copied from the V4
DS4.md recipe:
- drop --ds4-fused-decode and --ds4-fused-verify-f16-kv, and use
--ds4-prefill dense: V4.1's validate_model_features refuses the V4-only
prefill/fused paths (layer split and --mmproj too).
- --chunk 4096 (the V4.1 dense-prefill measurement point), --max-ctx
131072 (the V4.1 default window), --prefix/--prefill-cache-slots 0 as
the DS41.md bring-up recipe.
- drop --cache-type-k/v: the DeepSeek4 backend ignores them; the MLA
compressed caches are F16 by design.
- expose BOTH R9700s and set LUCE_EXPERT_STREAM_DEVICE=1, so hip:0 owns
the dense weights plus the hot expert stack while hip:1 holds the
streamed-expert slot cache instead of competing with it.
- quadlet: 384 routed experts per layer, Engram tables, 40 layers.
Replaces frank-medium (vllm-radiance TP=2) on :7770. The 377.2 GiB
43-layer MoE (256 routed experts, top-6) is mmapped: dense work and the
MLA KV cache on the R9700, routed experts computed on CPU from the
page cache (246 GiB RAM). The unit bypasses the image entrypoint
(Qwen/DFlash-only flag set) and execs luce_server with the DS4 launch
shape; --ds4-fused-decode's monolithic-load fallback IS the serving
mode here. deploy_llm_primary gates on image + model byte count,
stops/masks the radiance unit, waits for :7770, installs and starts.
Runbook: frank-primary-lucebox-ds4.md.
0.99 failed the vLLM startup memory check before weight load: the R9700
reports 31.86 GiB total but only 31.23 GiB free at device-init (the ROCm/HIP
context + NCCL + radiance custom all-reduce consume the 0.63 GiB gap), so
0.99 (31.54 GiB) exceeded free and the container crash-looped. 0.98 (31.22
GiB) is the ceiling and the prior production value.
Also fixed the runbook KV math that had shipped with the 0.99 change: the
~730k pool estimate was impossible (MXFP6's 25.16 GiB weights > MXFP4's
19.37 GiB, so the pool is smaller, not larger than MXFP4's 486k) and the
34.2 GiB/card figure was not the R9700 total. Recomputed ~420k tokens at 0.98
fill.
Knowledge-base follow-up to a45f396. The runbook, both index one-liners, and
the AGENTS.md topology row all still declared FP8 active; flipped to
just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq with unquantized bf16 KV (pool
486,464 tokens, full 262,144 window), and recorded the causal nuance: fp8 KV
was on both arms, so the FP8-vs-MXFP4 gap was weight precision, not KV - clean
KV is a quality hypothesis for W4A8, not a throughput one. No verdict yet.
The quadlet's "TEXT ONLY ... 400 here" comment was wrong: vision works on the
MXFP4 checkpoint (Qwen3_5ForConditionalGeneration carries the vision tower
through the Gemma4 merge path, unquantized) - verified by naming a solid red
48x48 PNG "Red". Comment corrected; harness models.yml input stays [text,image].
Docs-only; no re-deploy (the endpoint already serves vision).
Swap the serving checkpoint back to
just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq (quark/W4A8) and serve it with
KV_DTYPE=auto (unquantized bf16 KV) instead of the hardcoded fp8. fp8 KV
stacked on MXFP4's already-quantized W4A8 weights compounds attention-path
precision loss; clean KV tests whether that was hurting output quality. The
freed MXFP4 weights (19.37 vs 30.9 GB) buy the KV pool back, so the full
262,144 native window fits unquantized - MAXLEN returns to 262144.
The entrypoint gains a KV_DTYPE tunable (default fp8, the historical behavior),
shared across both quantization paths; the quadlet sets auto. Rollback: SNAP
back to the FP8 checkpoint with KV_DTYPE=fp8 and MAXLEN=192000.
Only the 8084 forward is exposed; the desktop GUI runs inside the
container netns and is internal-only. Drop the now-unneeded
CUSTOM_HTTPS_PORT (no host-port conflict exists inside the netns).
lscr.io/linuxserver/calibre:9.15.0 (desktop build) running calibre-server
as the s6 main service on internal 8090 -> host 8084, auth-gated with a
plaintext userdb (mode 600) bootstrapped once by the deploy handler.
The desktop GUI is kept on 8080/8182, basic-authed with the same
credential pair via the machine-local env file.
The template was staged in the working tree (then stashed by a peer for the
prometheus deploy) but never committed, so the live container kept serving
/patches/qwen-fixed-v22.3.jinja. Commit the repo-tracked template and flip
the quadlet: CHAT_TEMPLATE now points at it, mounted read-only at
/templates/qwen-sharp-v22.4.0.jinja. The entrypoint already passes
--chat-template on the shared exec path, so this applies to the FP8 shape.
Rollback: one env flip back to /patches/qwen-fixed-v22.3.jinja.
DFlash2 (100.0 t/s decode, 287.1 t/s burst-4) beats MTP self-speculation
(85.9 t/s, 179.7 t/s) despite a lower accept length (4.24 vs 5.66): the
small separate drafter steps faster than the target's own MTP layer applied
autoregressively. DFlash2 is the deployed shape; both swap-script paths now
default to dflash/7. Docs updated.
The entrypoint now reads the model's weight quantization from config.json
and serves the plain FP8 path (no MXFP4 patches, --quantization=fp8, MTP
self-speculation, ROCM_AITER unified attention with the R4D all-reduce)
or the MXFP4 patch-and-serve path. A model swap is now: change SNAP
(+ SPEC_METHOD/SPEC), restart.
- radiance-entrypoint.sh: quantization detection, gated MXFP4 env vars
and patch block, --quantization fp8 flag
- quadlet: SNAP -> Qwen3.8-27B-Uncensored-FP8, SPEC_METHOD=mtp, SPEC=8,
KV_MEM=0 (profile the shape, the documented plain-FP8 default)
- deploy-remote.sh: model-aware gates (read SNAP/SPEC_METHOD from the
quadlet; drafter gate only for dflash, r4d.so gate only for mxfp4)
- tests: quantization-aware drafter/spec and KV-pool tests
- hf-fetch.sh: generic, resumable, verified, idempotent HF fetch tool
- frank-medium-fp8.manifest: 17 files (10 config + 7 shards) with sizes
and LFS sha256
The conversation battery (scripts/bench-conversation.py, salted, same 10
prompts, 2026-09-20) measured three arms on the two R9700s:
arm I llama.cpp layer split 32:33 + DFlash2, Q8_0 geo decode 45.7 t/s, TTFT 0.72 s, burst-4 71.7 t/s
arm L llama.cpp tensor split 1:1 (RCCL), no drafter geo decode 30.5 t/s, TTFT 0.71 s, burst-4 54.3 t/s
arm R radiance vLLM TP=2 + DFlash2-FP8, MXFP4 geo decode 95.8 t/s, TTFT 0.21 s, burst-4 259.4 t/s
Radiance wins every axis, so it takes the alias. The board swap is what made
arm R possible: TP=2 was archived on 2026-09-16 because the second card sat
behind B650 chipset bridges with AtomicOpsCap: Routing-, and the ProArt
B850-Creator put both cards on CPU GPP root ports (Gen5 x8, Routing+, ReqEn+).
The R4D one-shot all-reduce needs no RCCL collective anyway.
- un-retire dankserver/frank-medium/: the TP=2 quadlet (banner rewritten —
it is the deployed shape now), radiance-entrypoint.sh, the healthcheck.
The replica pair and its affinity proxy stay archived; one process owns
both cards now.
- retire scripts/frank-medium.{service,env} + serve-frank-medium.sh and
bench-spec-ab.py to scripts/.AGENTTRASH/20260920-llama-layersplit/ as the
rollback path. build-llama-rdna4.sh and download-frank-medium-gguf.sh
stay: they are the tooling that rollback needs.
- deploy-remote.sh: deploy_llm_medium now gates on the image (pull once,
re-tag to the localhost name the quadlet resolves), the MXFP4 checkpoint,
the drafter, the pinned patch clone and the patched libr4d; retires the
llama root unit into the home trash instead of relinking it; then
install_quadlet + wait_container_healthy 1800s (first start compiles).
retire_vllm_medium_quadlets becomes retire_vllm_replica_quadlets — the
a/b/proxy trio only, since frank-medium is installed again.
- planner + test-changed map dankserver/frank-medium/** to frank-medium
and its seam; the scripts-trio mapping is gone with the files.
- tests/frank_medium_unit.bats rewritten for the container contract: boot
persistence of a GENERATED unit (no enable on this host's v1 generator),
TP=2 with the atomics-era NCCL workarounds kept out, the DFlash2 depth vs
the MXFP4 decode-kernel row band, the KV pin's coupling to the shape it
was calibrated at plus pool/VRAM arithmetic, the endpoint/tool/reasoning
contract, and the archive invariants.
- homepage card + docs updated, and they were stale twice over: they still
described the ajgazin Swift 35:30 / 393k payload, not the deployed shape.
Known regression, documented in the unit: vision. The MXFP4 checkpoint is
language_model_only and the launcher loads no projector, so images are a 400
here; the harness's vision role already routes to frank-small.
The vllm-radiance replica pair could not use both cards for one model: TP=2
needs a cross-card collective and the second R9700 cannot dispatch one. The
same wall blocks vLLM's pipeline parallelism, whose stage handoff is an RCCL
send/recv of the hidden state (distributed/parallel_state.py) -- a fact worth
writing down, because the obvious reading of the ask ('use PP to dodge the
atomics problem') is exactly backwards.
llama.cpp's layer split needs no collective at all: layers are distributed and
the boundary activation is a per-backend copy, once per forward pass. One
process, both cards, one model. The runtime is mainline llama.cpp at fb27a525
(the ref is pinned by DFlash2 AND qwen35 MTP; the ROCmFPX fork this host had
before has neither), built for gfx1201 against the private ROCm 7.14 toolchain
the earlier build already used, and bundled next to the binary.
Server: ajgazin Swift-Qwen3.8-27B-Uncensored UD-Q8_K_XL with the model's MTP
head in the file, plus the z-lab DFlash2 Q8_0 block-diffusion drafter at depth
7 (its block is 8, so 7 is the ceiling llama.cpp allows). Text only: vision
stays on frank-small.
Retired into the trash rather than deleted: the three vLLM quadlets, the
radiance entrypoint/healthcheck, the routing proxy and its tests, and the two
bench scripts that drove 'vllm bench serve' inside the retired image. The
deploy handler now stops them, waits for 7770 to be released, installs the
ROOT unit and refuses to start anything when the runtime or payload is
missing. The planner maps the scripts/ trio to frank-medium only, and the
scoping seam asserts the retired service dir is gone rather than merely
unmapped.
Dankserver's node-exporter has been dead since a reboot: `podman ps -a` showed
it `Exited (143)` and Prometheus' `node-dankserver` job has been scraping
nothing. It ran only from `dankserver/compose.yaml`, which is the failure mode
this repository's boot-persistence rule exists for (rootless Podman does not
restart bare containers after the stop that shutdown performs), and the compose
form bound the wildcard address — the unauthenticated-metrics-API-on-every-
interface posture already removed on Dankclaw.
- dankserver/observability/quadlet/node-exporter.container — mirrors the
Dankclaw unit, listening on exactly 127.0.0.1:9100 (host-local probes) and
192.168.0.235:9100 (Prometheus on Dankclaw), with Restart=always and
WantedBy=default.target.
- the compose service is deleted: one owner per container name.
- deploy_observability now installs from "$TARGET/observability/quadlet"; it
hardcoded the Dankclaw path, so a Dankserver unit could not be installed by
the shared dispatcher at all.
- planner: "node-exporter" joins the Dankserver service set, with a path rule
for dankserver/observability/**; the dispatcher's allowlist gains
dankserver:node-exporter.
Seams cover the silent halves: both listen addresses present and the wildcard
absent, the compose service gone, the allowlist entry present, and the planner
mapping the path to the service.
The proxy trusted its health table, which the watcher refreshes every 10 s. A
replica that restarts — and a deploy restarts both — therefore produced a
window in which requests routed to the dead card got a 502 back, even though
the other card was serving the whole time.
A failed connection now demotes that replica immediately and retries the
request on another live one, before anything is written to the client.
vLLM's OpenAI endpoints are stateless, so re-sending a request that never
reached an engine is safe; a failure after streaming has begun is still not
retried. The failover is logged, because a silent one hides a card that is
down.
Measured with card 1 stopped mid-flight: six requests, six 200s, one failover
line in the log, no client-visible error. Before this commit that burst
returned 502s.
The two replicas behind :7770 were on plain round-robin, which throws away
prefix-cache hits: an agent loop re-sends its system prompt and file context
every turn, and alternating replicas means every other turn pays a cold
prefill. Measured with 90k-token contexts, warm-turn TTFT was 2676 ms.
Pinning everything to one replica is not the answer either — a cold batch
(the shape a benchmark or a burst of parallel subagents produces) then loses a
card's worth of prefill: 16 requests took 30.1 s pinned against 18.6 s spread.
So the policy routes by request shape. A continuation (more than one message —
the agent-loop signature) is pinned to the replica that served its prefix;
anything else spreads across the cards by counter. Measured: 19.97 s for the
burst and 1095 ms warm-turn TTFT — the best of both, without a regression on
either workload.
The policy lives in proxy/routing.py, separate from the HTTP plumbing in
proxy/affinity-proxy.py, so it can be tested without aiohttp, a network or a
GPU. tests/frank_medium_proxy.bats covers it, and it earned its keep: the
first version hashed fresh prefixes to pick a card, which sends every member of
a same-prefix burst to one card (29.8 s, measured), and a stale index in the
pin path returned 500 on every continuation. Both are now assertions.
ROUTING=roundrobin and ROUTING=affinity stay available to re-measure the
choice on this host; the default is adaptive.
The single-GPU replicas died with torch.OutOfMemoryError during KV
allocation (2.16 GiB requested, 116 MiB free, 29.34 GiB already held by
PyTorch) because the entrypoint blanked KV_MEM=0 into an omitted flag. The
image's patched KV sizing reads an explicit 0 as 'profile this shape'; with
the flag absent vLLM sizes the cache from --gpu-memory-utilization alone and
overshoots. Passing 0 literally is the shape the bench numbers were measured
on, and MAXSEQS gets its default back under set -u.
The radiance MXFP4 stack cannot run TP=2 on this host. RCCL's collective
kernels carry a hidden hostcall-buffer parameter, and ROCr refuses to
dispatch them on a device without PCIe atomics: the AQL dispatch fails with
hipErrorIllegalState ("the operation cannot be performed in the present
state"), which is what every two-rank collective hit. The second R9700 sits
behind the chipset bridges 05:00.0/06:09.0, which advertise
`AtomicOpsCap: Routing-` — a read-only capability, so no software can enable
atomic routing on that path and the driver's
pci_enable_atomic_ops_to_root() fails for that card. The first card, on CPU
root port 00:01.1, has atomics enabled.
Ruled out: kernel version (7.0.0-28/-30/-31 identical, after a full upgrade),
iommu=pt, P2P hardware (45.3 GB/s between the cards), the shipped librccl (a
from-source rebuild reproduces the failure at the same call path), vLLM and
pynccl (a bare two-rank torch.distributed allreduce fails the same way), all
NCCL transport knobs, and single-rank tests (NCCL short-circuits at
world_size=1, so one-card success proves nothing).
Deployment: three rootless Quadlets — frank-medium-a (:7771, card 1),
frank-medium-b (:7772, card 2), both TP=1 at 114688 context (262144 and
131072 do not fit one card's KV) with vLLM-profiled KV — and
frank-medium-proxy (:7770), a round-robin that preserves the fleet contract
of one endpoint and one served model name. frank-medium.container stays as
the TP=2 target for a host whose second card is atomic-capable; the deploy
handler does not install it and trashes any stale copy.
Measured through the proxy (vllm bench serve, random dataset, --ignore-eos):
conc 1 42.8 tok/s, conc 4 147.6 tok/s, conc 8 230.8 tok/s, 32k prefill at
~2.8k tok/s per card, TPOT p50 23.6-28.8 ms.
Also: healthcheck reads PORT so one probe serves all three units, the hermes
example and the harness models.yml drop to the real 114688 context, and the
runbook records the full evidence chain.
Rootless Quadlet on dankserver serving
just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq (the radiance stack's
designated alternate target; ships its fp8 MTP head, no rewrite step) with
the DFlash2-FP8 drafter at SPEC=7 on the 2x R9700s (TP=2, host network,
:7770, alias frank-medium unchanged).
- dankserver/frank-medium/: quadlet unit, container entrypoint (fork of
serve-mxfp4.sh's patch block at pinned clone commit 97353293), healthcheck
- dispatcher retires the root llama.cpp unit, re-tags the registry image to
the localhost alias, installs the quadlet, waits on /health
- planner maps dankserver/frank-medium/* to frank-medium; scripts-era
mappings removed
- ROCmFPX-era env/serve/unit/download scripts staged in scripts/.AGENTTRASH
with .rocmfpx suffix; seams updated (frank_medium_quadlet.bats new)
FrankBook-Pro becomes the only *arr/qBittorrent deployment. Every fleet
container (qB + five arrs) now shares gluetun's netns, so all egress —
torrent, indexer APIs, metadata lookups — exits the WireGuard tunnel by
construction (AllowedIPs=0.0.0.0/0); the arrs' own ports publish on the
gluetun unit, none on the arr units themselves.
- dankserver/compose.yaml: remove the six arr services (the Aug 20 compose
copy — never healthy, superseded; config dirs trashed on the host)
- dankclaw/Caddyfile + shared/homepage/services.json: arr vhosts and
probes repoint 192.168.0.235 -> 192.168.0.112 (FrankBook-Pro)
- frankbook-pro units: five arrs join gluetun netns (Wants/After/Network);
gluetun publishes 9696/8989/7878/8686/8787 alongside 8080/6881
- tests/frankbook_quadlet.bats: new VPN egress seam — every arr+qB unit
must share gluetun's netns and publish no port; gluetun must publish the
whole fleet's ports
- deploy-plan.py: gluetun changes carry the whole netns family (a gluetun
recreation kills all six joiners); dankserver compose set loses the arrs
- AGENTS.md: deployment is complete only when unit tests AND the Playwright
E2E suite both pass
Rootless podman on dankserver already maps container root (PUID=0) to
the dank user (uid 1000) by default — /proc/<pid>/uid_map reads
0->1000, 1..->100000+. Verified across plex, tautulli, jellyfin,
calibre-web, copyparty, romm. userns_mode: host is unnecessary, and
podman-compose 1.5.0 cannot apply it anyway (compose services run in
pods; --userns and --pod cannot be set together). The real fix for the
never-booted arr stack was chowning the root-owned /opt/<svc>/config
dirs to 1000:1000.
The arr services were committed (b9de886) with PUID=0 but no userns_mode.
Under rootless podman's default subuid mapping, container-root cannot write
host-root-owned bind mounts, so every app died in logger init
(UnauthorizedAccessException on /config/Sentry) before binding its port —
the stack 502'd since it was first brought up (2026-09-04 00:33).
Per the fleet convention (AGENTS.md, plex/tautulli migration): PUID=0 +
UserNS=host maps container-root to dank (1000), which owns /opt data roots
and /mnt/entropy. Config dirs chowned 1000:1000 at bring-up.
Also drops a duplicate 'networks: [appnet]' key on prowlarr.
The C5 probe failed for the wrong reason: plex.container lost its Network=
key in the same edit churn that ate tautulli's ContainerName. Plex ran on
the default podman network — published 32400 still worked (clients fine)
but tautulli could not resolve the plex alias, breaking the seeded
PMS_Web_Host=plex. Restore appnet membership; structure now parallel to
tautulli.container. Lesson recorded: after multi-hunk line edits on these
unit files, diff the whole file — key-order churn has eaten three keys
already.
Without ContainerName= the v1 generator names the container
systemd-tautulli; the fleet references containers by their plain names
(podman inspect/exec, deployer health checks). Container was healthy but
renamed — caught by post-cutover verification, not by the seam; the seam
only asserts file keys, so pin the name here and keep plex/tautulli
structures parallel.
- tautulli.container: HealthCmd switches to the repo's proven curl pattern
(jellyfin unit) — quadlet's systemd-style value parsing mangles embedded
double quotes; PublishPort=8181:8181 restored (a mis-aimed line edit
replaced it; the PublishPort seam test caught the regression)
- deploy_plex readiness gate: 36x5s -> 120x5s; the 2026-09 cutover showed
the first container boot of a years-old library runs ~10 min while PMS
pre-binds 32400 and empty-replies; 180s failed the gate twice with a
healthy, still-booting service
Evidence from the failed first cutover: podman top shows container root
maps to dank (1000) under UserNS=host rootless (subuid range 100000:65536
cannot express 997), so PUID=997 fell back to root and PMS crash-looped on
write access to its 997:984-owned data root. Fleet model instead: PUID=0/
PGID=0 (container root = dank, same as jellyfin/copyparty data roots) and
deploy_plex chowns /var/lib/plexmediaserver to 1000:1000 inside the
first-cutover block. Zero bytes moved; rollback regains one chown -R
997:984 step, documented in Plex.md. Seam test pins PUID=0/PGID=0 and the
absence of any userns key.
podman 5.7 podman-user-generator on dankserver hard-fails the whole unit on
the unknown key ('unsupported key UsernsMode in group Container'), so the
first cutover attempt masked the native unit and then found no plex.service
at all. Swap both units to UserNS=host (same --userns=host flag), update the
ownership-contract seam test to pin the exact key, and correct both docs.
Pin the seam: the v1 generator rejects unknown Container keys silently at
deploy distance — the test now pins UserNS=, not the misspelled alias.
- plex: lscr.io/linuxserver/plex:1.43.3.10896-cb3ebc72d-ls322 (verified ==
ghcr latest digest; plan's ls9 pin superseded by the re-verify clause),
/var/lib/plexmediaserver bind-mounted in place as /config, /mnt/entropy
mounted ro at the same path, PUID=997/PGID=984 + UsernsMode=host so the
container's file identity is byte-compatible with the native unit
- tautulli: lscr.io/linuxserver/tautulli:v2.18.1-ls242 (verified == ghcr
latest digest), fresh /home/dank/Containers/tautulli config root,
PUID=1000/PGID=1000, python3 /home healthcheck
- both on dankserver_appnet with aliases; 32400/8181 published as before
The cutover unit joined dankserver_appnet but dropped the compose-era
0.0.0.0:3923 mapping (live inspect: bridge, 3923 published), so
copyparty listened inside the netns while the host refused. New seam
asserts every host-facing port matches the pre-cutover PortBindings:
romm 8085->8080, jellyfin 8096, calibre-web 8083, copyparty 3923.
The podman 5.x v1 quadlet generator rejected the whole jellyfin unit on
the unsupported Device= key (generator log: unsupported key 'Device' in
group 'Container'), so no jellyfin.service was generated and the cutover
restart failed with 'Unit not found' after the data root had already
migrated cleanly. gluetun proves AddDevice= is the house key. New seam
test denies Device= across all six dankserver units and pins the
AddDevice=/dev/dri replacement.
Cutover of the six surviving dankserver services from compose-era bare
containers to boot-persistent Quadlet units (WantedBy=default.target; podman
5.x v1 generator honors it at user-manager start).
Units are faithful to live inspect ground truth (image pins = running tags,
not compose inventory):
- romm trio shares one data root: /home/dank/Containers/romm mounted whole at
/romm; mariadb datadir and redis data dir live inside it. Aliases mariadb/
redis preserved on dankserver_appnet via Network=...:alias=. Secrets stay in
the host-local env file (EnvironmentFile + ${VAR} expansion in the generated
ExecStart, gitea precedent). copyparty passes its admin account via
Exec=-a ${COPAY_ACCOUNT}:${COPAY_PASSWORD} (Exec= not Command=: the v1
generator hard-fails on Command=); entropy stays rw only there.
- jellyfin keeps every creation-time env as Environment= lines (zero drift);
Device=/dev/dri + GroupAdd=keep-groups preserve hardware transcoding.
- calibre-web pins the exact running image tag (id 986277563e76 =
0.6.27-ls397), pasta network preserved.
Deployer: first-cutover handlers retire the old container, rescue unshadowed
anonymous-volume content (podman volume export + tar --skip-old-files), mv
data roots on the same fs, then start units in dependency order with health
gates. Re-deploys restart only the selected unit. deploy-plan.py maps compose
keys mariadb/redis to the new unit names; allowlists updated. New seam test
tests/dankserver_quadlet.bats pins boot-persistence + v1-generator contract;
test-changed.sh maps the new dirs to it. Full suite green (209 tests).
-v /w::A granted anonymous full rwmda on the LAN (verified: anon PUT -> 201,
PROPFIND -> 207). New perms ::r:ra,dank: browse/download for anonymous
(required by the guarded files.franksdank.cloud chain), admin for dank,
no w/m/d for anyone. Runbook corrected with the --help-accounts semantics.
Under rootless podman, LSIO's PUID=1000 maps to host uid 101000 — a phantom
user owning nothing: Sonarr's own validator rejected /tv because the process
could not write it. Container-root under a single-user userns maps to the host
user (dank), which owns every /mnt/entropy media dir and /opt config dir.
Identity is now mapping-independent instead of depending on subuid offsets.
calibre-web untouched (working; churn avoided).
Ground truth from the image itself: python3 -m copyparty --help-accounts shows
-a takes USER:PASS and -v takes SRC:DST:PERMS:FLAGS — the COPAY_PASS/COPAY_MODE
envs this compose carried are not consumed by this image at all (zero COPAY_
references in the package). With no accounts and no volumes configured, the ac
edition serves its cwd read/write for everyone: the stack was running an
unauthenticated world-writable share of the 91T array. Now: admin account dank
with the A flag on volume /w; anonymous gets nothing.
The ac edition's entrypoint (cpp.sh -> python3 -m copyparty) consumes config
via /z/initcfg, not argv; -v is the volume flag and ate the next arg,
crash-looping argparse. The image mounts everything under /cfg/copyparty as
volumes by marker-file convention — plant the marker on the host instead.
The image entrypoint is /bin/ash /z/cpp.sh -c /z/initcfg: copyparty flags are
passed through command, and the ac edition mounts volumes with -m, not via a
COPAY_VOL env. Without any volume mounted every request resolved zero volumes
and the app answered HTTP 500 with its own error page. Verbose flag included
for the bring-up; drop it once stable.
The ac edition maps volumes from COPAY_* envs; without a volume root every
request resolves zero volumes and the app answers HTTP 500 with its own error
page. Point it at /w where the LUKS array is mounted.
ghcr.io/9001/copyparty:latest does not exist — ghcr answers 403 on the token
request for nonexistent repos, which is why the bring-up failed at pull. The
upstream publishes ghcr.io/9001/copyparty-ac (ac = full edition) and serves
whatever is mounted at /w, so the compose mounts the LUKS array there; config
persists in /opt/copyparty/cfg per upstream layout.
Jellyfin ran as user 1000:1000 inside a rootless user namespace, where host
uid 1000 maps to container uid 0 — the pinned uid is unmapped, so /config/log
creation EACCES'd and the service SIGSEGV'd on boot. Container root (= host
dank) is correct under rootless podman; group_add 992 (render) still maps via
the userns group map, so GPU access is preserved.
Readarr: lscr.io/linuxserver/readarr:latest does not exist — LSIO ships only
arch-prefixed nightly/version tags for readarr (verified against the ghcr tag
API). Pin amd64-1.0.980, the newest stable tag.
The compose stack mounted /mnt/media/{movies,shows,tv,music,books,downloads}
— a prefix that has never existed on this host. The 91T LUKS array mounts at
/mnt/entropy and its libraries are case-exact (Movies, TVShows, Music,
eBooks). Also restores prowlarr's config mount (eaten by an off-by-one in the
prior edit) and fixes TZ New_York->Los_Angeles on the arr stack.
Per user direction, Caddy runs only on dankclaw. It fronts every
service on both hosts: local services by container name, quadlet
services by published LAN port, dankserver services by published LAN
port (192.168.0.235:PORT).
- dankclaw/Caddyfile: merged vhost list (was: two Caddyfiles, one per
host). gitea's single vhost moves in from the retired gitea-caddy
quadlet (option B). Upstreams fixed to live reality: gitea :3000,
search :8081 (gluetun), chat :3005 (open-webui quadlet), media
services via 192.168.0.235. Retired: llms (open-webui on dankserver
is removed; chat is its successor), the dankserver homepage (302 to
the shared one).
- dankserver/Caddyfile, dankclaw/gitea/Caddyfile: deleted (git rm).
- dnsmasq addn-hosts: every name -> 192.168.0.143 (the one Caddy
host); no .235 records, no llms.
- compose.yaml: removed the openwebui/postgres/gitea services (they
are quadlets now); caddy service mounts the rendered Caddyfile from
/home/dank/Containers/caddy, healthcheck probes the bare-IP
catch-all (302).
- deploy.sh: per-target logic (dankserver = pull-only, health via the
shared Caddy at 192.168.0.143); renders CADDY_BASICAUTH_HASH from
the host .env into the mounted Caddyfile.
- .env.example: CADDY_BASICAUTH_HASH on dankclaw; Porkbun block
dropped from dankserver (its Caddy is gone); SEARXNG_BASE_URL to
the flat name; stale OPENAI_* block dropped (quadlet is
self-contained).
- tests: caddyfile.bats now asserts the single-Caddyfile invariant;
dnsmasq.bats cross-checks vhosts -> .143 and the retired names.
/opt is root-owned; the established data-location pattern (see
docs/Architecture/Storage Policy.md, open-webui quadlet) is
/home/dank/Containers/<service>.
Frank