Fan out subagents to compare mainline llama.cpp, charlie12345/ROCmFPX,
and ik_llama.cpp, then add their findings to the project knowledge base:
- docs/Research/Llama Cpp Runtimes.md (positioning + quantization + server fit)
- docs/Research/Llama Cpp Code Diff.md (code-level quant diff, table, recommendations)
- docs/Research/SGLang.md (what SGLang is, comparison, our-boxes fit)
- docs/Research/index.md (Research progressive-disclosure index)
Cross-linked from docs/index.md (root) and docs/LLM/index.md.
AGENTS.md:
- Add Documentation Authoring section: docs/ is an OKF bundle; point doc authors
at the canonical spec in the system-config knowledge base
(~/.pi/agent/docs/references/okf-spec.md), not the orphaned
docs/references/okf-spec.md; consolidate read-index/one-concept-per-file/
progressive-disclosure/citation rules.
- Map AGENTS.md to docs_completeness.bats in the focused pre-commit hook (it was
last committed before the hook existed and had no mapping).
frank-default-large now serves the kingjones Qwen3.8-27B-ROCmFPX-Q8_0-AGENT
model with a standalone MTP draft head (Q4_0), f16 K + TurboQuant V KV cache,
and the Sharp chat template. Context is maxed to 262144 (one slot); reasoning
is on with preserve_thinking + preserve_reasoning in the chat kwargs.
- frank-default-large.env: Q8_0 AGENT model paths, CTX_SIZE=262144, REASONING=on,
REASONING_FORMAT=none, CHAT_TEMPLATE_KWARGS {enable_thinking, preserve_thinking,
preserve_reasoning}
- serve-frank-large.sh: standalone draft-mtp profile (already switched off the
Kairic/PromptForge path)
- download-q8agent.sh: reproducible HF fetch of the three payload files
- docs/LLM/kingjones-q8agent-rocmfpx.md: Q8_0 AGENT runbook
- AGENTS.md: topology + ACTIVE runtime section + TTM/GTT load note
- qwen3.8-strix-optimizations, Dankclaw Improvements: TTM pages_limit now 114 GiB
(applied 2026-08-25), full 262k KV + Q8 payload fit in one slot
- frank_large_config.bats: assert 262144 context, reasoning + preserve_* enabled
The TTM/GTT was raised to 114 GiB (29,883,536 pages) to hold the full 262k KV.
SearXNG queries all ~50 upstream engines from one Gluetun VPN exit IP, so
rate-sensitive engines (Google, DuckDuckGo) answer with reCAPTCHA/429 and
SearXNG suspends the offending engine for hours-to-days, showing up as
"unavailable". Add docs/Dankclaw/SearXNG Providers.md covering: the
suspension model, the two failure modes (CAPTCHA vs selector drift), engine
config (settings.yml engines: list — duplicate google, timeout,
retry_on_http_error, JSON feed), request tuning (outgoing block, UA rotation,
suspended_times — correcting the old rate_limit/useragents blog myths),
routing/proxies (per-engine proxies, dedicated 2nd Gluetun, dedicated IP), and
verification (/json, /config, check.searx.space). Crosslink into SearXNG.md
and index.md.
Replace the retired kingjones ROCmFP4 STRIX MTP payload on Dankclaw with
cafonz/Qwen3.8-27B-ROCmI4-MTP-GGUF (eemin namespace, public), served by the
charlie12345/ROCmFPX llama.cpp build (ROCmI4 W4A4, c49ebdbd) on the Strix Halo
iGPU. Q4_0_ROCMI4 with an embedded NextN/MTP head (no separate draft file);
strict-Qwen MTP n16/p0.60/backend sampling on ROCm0. Binary
/home/dank/rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server; model dir
/home/dank/models/eemin-Qwen3.8-27B-ROCMI4-MTP. Updated serve script + env,
ubatch bench, large-config bats test, docs, AGENTS.md.
3 slots x 229376 (262144 - 32768) = 688128 total context. Updates the
.env, models.json (contextWindow/maxTokens 229376 per slot), and the
index/deployment/ornith runbook references.
- frank-default-small (Dankserver): Ornith-1.5-35B-A3B-CRACK Q8_0, bundled
native draft-mtp (n_max 4), MoE expert FFN tensors pinned to CPU via an
explicit --override-tensor \.ffn_(up|down|gate|gate_up)_(ch|)exps=CPU
(replaces --n-cpu-moe), Qwen-Sharp chat template.
- frank-default-large (Dankclaw): kingjones Qwen3.8-27B-Uncensored-Q6_0
ROCmFP4 AGENT dense GGUF, standalone mtp-Qwen3.8-27B-Q4_0 draft head
(--model-draft, draft-mtp n_max 4), Qwen-Sharp chat template. Drop the
retired PromptForge .pfs sidecar lanes.
- Track scripts/chat-template.jinja (v22.4.0 Sharp) and apply via
--chat-template-file on both services.
- Docs: new kingjones-strix-mtp and dealign-ornith-crack runbook pages;
update index, deployment, and both system specs; models.json names.
Smoke-tested both models on the real hardware on scratch ports before
commit: model loads, MTP draft attaches, Sharp template applies, chat
completion returns.
FTL's generated dnsmasq.conf has no conf-dir: /etc/dnsmasq.d/ is never
read (the 2026-08-24 scratch-name test proved the file was inert; names
only resolved from the query cache). The only file-based local-record
mechanism is hostsdir=/etc/pihole/hosts. Mount the record file there.
Doc: record the pitfall in Pi-hole.md.
Fanned out 5 read-only doc-auditor subagents (one per service group) that
fact-checked the knowledge base against the live system + repo config,
researched official setup docs online, and verified progress. Applied:
- All 34 broken links fixed (real pages / external URLs / correct relative
paths); 0 broken links remain. No .AGENTTRASH links (the 4 mentions are
accurate descriptive text, not links).
- Fact-check fixes: Readarr retired (May 2026), Radarr v4->v6, Calibre
9.2.1 live, Calibre-Web 0.6.25 live, Copyparty v1.20.21, LLM index
ncmoe 38 + 786432 ctx, frank-default-small active (not frank-pp-worker),
Hermes/SearXNG/Grafana hostnames, Loki/Alloy local images, Observability
diagram (Promtail->Alloy), VLLM retired note, DFlash status, benchmark
live-drift notes, Homepage test count 116.
The other vhosts (gitea, grafana, search, ...) now use username 'dankuser'
with CADDY_BASICAUTH_HASH, which is set to the same hash as the homepage
(dankpassword.123). So the whole protected surface logs in as
dankuser / dankpassword.123; the operator /admin/ page still uses frank.
Updated the two tests that asserted the old 'dank' username.
The homepage user page + shared data now use a dedicated CADDY_HOMEPAGE_HASH
(username dankuser), separate from the shared family password (CADDY_BASICAUTH_HASH,
username dank, still used by the other vhosts) and the operator password
(CADDY_ADMIN_HASH, username frank, the /admin/ page). This lets the homepage be
re-logged independently without touching the other sites. deploy.sh renders the
new placeholder; the .env.example documents all three hashes.
The homepage is live on Dankclaw. Update the Status (deployed) and the Auth
section (the handle-block design, the Caddyfile directive-sorting pitfall, the
host /srv/homepage mount, and the container-recreate note). Cross-reference the
agent KB Caddyfile syntax page.
The caddy container mounted the repo's shared/homepage (the static source) to
/srv/homepage. But the deploy writes the generated files (status.json from the
status checker, deployed.js from the deploy) to the host's /srv/homepage. So
the container served the static files (200) but 404'd the generated ones.
Mount the host's /srv/homepage instead, which holds both the static files (the
deploy copies them) and the generated ones.
Caddy SORTS top-level directives, so a 'rewrite' runs before 'basicauth'.
The rewrite changed /admin/ to /admin.html, and the path-based auth matchers
then saw /admin.html (which matched the family 'not path /admin/*' block, not
the operator '/admin/*' block) — so the operator password was checked against
the family hash and 401'd.
Serve each page from its own 'handle' block (which preserves order, so the
auth is checked on the original path before any file rewrite):
- handle /admin* : operator (frank) only, try_files /admin.html
- handle @data : shared data + assets, family (dank) OR operator (frank), so
the admin page's fetches of services.json/status.json reuse the operator
credential
- handle : everything else (the user page), family (dank)
'@admin rewrite ...' is parsed as a one-liner matcher DEFINITION, so it
re-defined @admin and Caddy rejected the config ('matcher is defined more
than once'), crash-looping the container. Per the Caddyfile matcher docs the
matcher token is the first ARGUMENT after the directive: 'rewrite @admin
/admin.html'. The '*' disambiguator is only needed pre-2.8.0. Validated the
rendered config against the porkbun image: 'Valid configuration'.
Two real bugs found on the first production deploy:
- /admin/ 404'd: file_server looked for /srv/homepage/admin/ (a dir), but the
page is admin.html. Add '@admin rewrite * /admin.html' so the /admin/ path
serves admin.html.
- The pages used relative refs (style.css, app.js, services.json, status.json),
which from /admin/ resolved to /admin/... (404). Add <base href="/"> so all
refs resolve to the site root on both pages.
- status.json was written 0600 (root); the checker now chmods it 0644 so Caddy
can serve it regardless of its user.
The homepage deploy's mkdir/cp/write of /srv/homepage ran as the deploy user
and hit 'Permission denied' (/srv is root-owned). Prefix them with the sudo
wrapper, write deployed.js via a temp file + sudo cp, and chmod the tree
a+rX so Caddy can serve it. Run the one-off checker as root too (it writes
status.json into /srv/homepage).
A missing CADDY_*_HASH in the .env made the 'grep | tail | cut' pipeline
return non-zero, which aborted the deploy under 'set -e' before it could warn
and keep the placeholder. Add '|| true' so an absent hash warns instead of
aborting. (The homepage deploy aborted here because CADDY_ADMIN_HASH was not
in the repo-root .env the deploy reads.)
- Homepage.md: status is now 'built, pending deploy' (all assets + checker +
deploy are in the repo, 112 tests green). To go live: add CADDY_ADMIN_HASH
to the target .env, then deploy.sh.
- Homepage Design Grilling.md: the build is complete (all 6 slices, full TDD);
the only remaining step is the operator adding the admin hash + deploying.
- pi log.md: build-complete entry.
Red tests first.
- tests/homepage_deploy.bats: the deploy ships the homepage (assets to
/srv/homepage, the checker timer, both Caddy hashes, deployed.js) and is
git-driven (pulls main); the checker runs as a systemd timer.
- scripts/homepage-status.service / .timer: the checker as a oneshot service
+ a 3-minute timer (Q2/Q35).
- scripts/deploy.sh: the Caddyfile render now substitutes BOTH hashes
(REPLACE_WITH_HASH <- CADDY_BASICAUTH_HASH, REPLACE_WITH_ADMIN_HASH <-
CADDY_ADMIN_HASH). A new homepage step copies the assets to /srv/homepage,
generates deployed.js from the deployed commit's datetime (Q43), installs
the checker timer, and runs the checker once so status.json exists at once.
- tests/llm_units.bats: scoped the three LLM-unit tests to
frank-default-*.service (the homepage unit is a different pattern: it
installs to /usr/local/bin and runs from /srv at deploy time).
Red tests first.
- tests/homepage_caddy.bats: the homepage site block carries a root hash and
a distinct /admin/-scoped admin hash (Q18/Q38), and serves /srv/homepage.
- dankclaw/Caddyfile: the homepage block now uses named matchers -
@user (not /admin/*) with the shared hash, @admin (/admin/*) with the
operator-only hash (REPLACE_WITH_ADMIN_HASH, rendered from CADDY_ADMIN_HASH
at deploy). Both placeholders are distinct.
Red tests first, then the pages.
- tests/homepage_pages.bats: the pages reference the data + theme; no
auto-refresh (Q41); no cursor alteration (Q28); the styling toggle strips
to bare HTML (Q27); the footer shows the last master deployment datetime
(Q43).
- index.html / admin.html: the user and admin pages. A grid of TUI panels,
a summary line, the bare toggle, the deployed-at footer.
- app.js: reads status.json + services.json once (no auto-refresh), renders
one panel per service for the page's category, the toggle, the footer.
- style.css: the terminal TUI theme (green-on-black, phosphor palette,
scanlines) + a ?bare=1 mode that strips to unstyled HTML. No custom cursor.
Functionally verified with a Node DOM shim: 9 user panels, correct summary,
correct footer datetime.
Red tests first (the old services.json was an object, not the new list schema).
- tests/homepage_config.bats: the config is a JSON list; every entry has
name/category/probe; category is user|admin; method is tcp|http; a
showLink entry has a url and a status-only entry does not.
- shared/homepage/services.json: the real fleet. User: SearXNG, ComfyUI,
OpenWebUI, Gitea, Calibre-Web, RomM, Copyparty, Plex, Jellyfin. Admin:
Hermes, Grafana, Prometheus, Loki, node-exporter, alloy, Caddy, dnsmasq,
Gluetun (wip - a tunnel has no simple local port), the two LLMs, mariadb,
valkey, Postgres. Ports confirmed from the repo config (compose/quadlet).
docs fields are empty for now (the /docs/ workstream fills them as each
service goes active).
Red test first: a raw TCP listener that never speaks HTTP must read down
under an http probe (up under tcp), while a real HTTP server reads up. This
test caught a real hang — the backgrounded listener inherited the test
runner's stdout pipe and held it open; fixed by redirecting its output and
killing both listeners in teardown.
scripts/homepage-status.py: probe() now dispatches on method. http does an
urlopen (any HTTP status = up; no connection = down); tcp connects.
The checker is now complete: tcp + http + wip + atomic write + generated_at.
Remaining slices: services.json schema, the pages + theme + toggle, the
Caddyfile (validate + two hashes), the git-driven deploy.
Full TDD (Q36): red test first, then the minimal implementation.
- tests/homepage_checker.bats: seam = homepage-status.py <services.json>
<out.json>. Asserts an open port is up, a closed port is down, a wip
service is wip (not probed), and the output carries generated_at.
- scripts/homepage-status.py: reads the config, probes each backend (tcp,
5 s timeout), skips wip, writes status.json atomically (temp + rename).
Remaining slices: http probe method, services.json schema, the pages +
theme + toggle, the Caddyfile (validate + two hashes), the git-driven deploy.
- Homepage Design Grilling.md: final decision table (Q1-Q43) + the deltas where
the operator changed the recommendation (per-service probe method, 5s timeout,
TUI panels, toggleable styling, no cursor alteration, no auto-refresh, /docs/
path, user-facing docs, git-driven deploy, full TDD, last-deploy footer).
- Homepage.md: updated to the settled design (per-service probe, 5s, TUI panels,
styling toggle, no auto-refresh, /docs/ workstream, git-driven deploy, TDD).
- pi log.md: 2026-08-23 entry recording the settled design and build order.
Build order is unblocked. No homepage code built yet.
- Homepage.md: rewritten to the settled design (single site, user + /admin/
pages, server-side status.json via a 3-min systemd-timer checker, terminal
TUI theme). Added mermaid diagrams: site structure, status states, checker
flow. Recorded the classification (user vs admin; *arr excluded; LLM admin;
backends status-only) and the documented future shift to client-side probing.
- Homepage Design Grilling.md (new): the decision log — settled Q1-Q5 plus 38
open questions (Q6-Q43) across 10 categories, each with a recommendation.
- docs/index.md: link the grilling page (satisfies the index-links-every-page test).
- report/homepage-grilling-2026-08-22.html: self-contained terminal-TUI progress
report (settled decisions, verified stack baseline, overnight processing, work
threads, the open questions, and how to continue).
Baseline recorded: Dankclaw fully up (10/10); the Dankserver media stack is down
(only Calibre-Web + the LLM are up; no .env on the target) — a separate thread.
No homepage code built yet; the design is pending the operator's answers to Q6-Q43.
The explanatory comment contained an unescaped loop-variable token, which
the local shell (set -u) tried to expand while building the double-quoted
remote script ('unit: unbound variable'). Reword the comment.
The relink loop wrapped the source path in single quotes, which shipped a
literal ${unit} to the remote and created a dangling symlink
(/etc/systemd/system/frank-default-large.service -> .../${unit}.service),
so 'systemctl enable' failed with 'unit does not exist'. The path has no
spaces; unquoting lets ${unit} expand on the remote for both source and
destination.
Operator request (2026-08-22): the primary inference server
(frank-default-large, the 27B CIRU model on Dankclaw) moves to the
standard llama.cpp port 7770. Both LLM services now listen on :7770,
distinguished by host (dankserver vs dankclaw).
Functional changes:
- scripts/frank-default-large.env: LISTEN_PORT 52625 -> 7770
- scripts/serve-frank-large.sh: default LISTEN_PORT 52625 -> 7770
- scripts/deploy.sh: LLM_HEALTH[dankclaw] -> :7770
- open-webui quadlet: OPENAI_API_BASE_URL -> 192.168.0.143:7770
(re-pointed so chat keeps working; data dir preserved)
- scripts/bench-fast-greedy.sh: PORT 52625 -> 7770
Tests updated to the new topology (both LLM endpoints on :7770 by host;
open-webui -> :7770). Docs + pi KB updated; dated historical runbooks
keep their point-in-time ports. models.json (pi client) re-pointed to
:7770 separately, effective on the next client restart.
- docs/index.md: LLM Fleet section (all 34 pages linked), merge note,
See Also now internal
- docs/LLM/index.md: retitled, dangling [[Dankserver]]/[[Dankclaw]]
links fixed, sibling section replaced with internal links
- docs/LLM/deployment.md: rewritten for the unified deploy flow,
manual-update paths point at the merged checkout, incident history
kept intact
- Deployment Flow / Dankclaw Stack / Gitea: stale vllmScripts
references and retired-topology notes updated to the 2026-08-22
state
- Historical docs (frank-redo, PP deployment, FastFlowLM) keep their
dated runbook paths as-is (records of retired topologies)
deploy.sh now deploys both workloads per target in one run:
push -> pull on /home/dank/serverAppConfigs -> podman stack steps
(dankclaw) -> LLM unit relink + daemon-reload + service restart ->
homepage health + LLM health (up to 20 min model-load wait).
Sudo: plain sudo on the fleet hosts (passwordless verified
2026-08-22); FRANK_SUDO_PW covers headless runs elsewhere. The
vllmScripts deploy.sh is superseded.
Units: frank-default-{small,large,npu}.service now reference
/home/dank/serverAppConfigs/scripts/... (the merged checkout).
bench-spec-stack.sh: env file path updated to the merged checkout.
README: merged service table (stack + LLM), structure incl. old/ and
docs/LLM/, unified deploy note, merge note.
.gitignore: merged both files; !scripts/*.env exception for the LLM
tunables (paths and numbers, never credentials); .obsidian/,
__pycache__/, .venv/ from the vllmScripts side.
One repo, one git protocol, one deploy script. Merged from the two
former AGENTS.md files:
- Overview: both workloads, both hosts, the 2026-08-22 merge note,
current LLM fleet topology (frank-default-small :7770 Dankserver,
frank-default-large :52625 Dankclaw)
- Git workflow + testing (serverAppConfigs protocol, test step kept)
- Deployment: the unified deploy.sh (stack + LLM per target)
- Secret rules: no passwords in the repo; FRANK_SUDO_PW covers
headless sudo (the live sudo password is NOT carried forward)
- Deletion & Trash Policy (from the vllmScripts 2026-08-22 commit)
- Benchmarking policy (stop the service before any bench)
- Pi model config, runtime & troubleshooting (v3 CIRU active,
Kairic/DFlash2/FastMTP retired), HIP env naming rule, crash-loop
procedure, operational quirks (passwordless sudo verified
2026-08-22), Dankclaw memory model
New seams (written first, red against the pre-merge tree):
- llm_units.bats: every scripts/*.service unit points at files that
exist in this repo (the merged checkout path), env files included
- llm_secrets.bats: the live sudo password is never tracked (the
vllmScripts AGENTS.md once documented it)
- deployment_flow.bats: deploy.sh must restart the LLM services on
both targets and health-check both endpoints (7770, 52625)
- helpers.bash: has_no_leaked_sudo_pw (two-part assembly, same
pattern as the gitea check)
The LLM fleet serve scripts, systemd units, env tunables, and bench
harnesses join the deploy scripts. The vllmScripts deploy.sh is
removed here; its functionality is folded into the unified
scripts/deploy.sh in a follow-up commit.
bench-spec-stack.sh gains the executable bit (required by the
scripts_syntax test seam).
The LLM fleet documentation (deployment runbook, model runbooks,
benchmarks, research archive, retired-topology history) joins the
project knowledge base as docs/LLM/. Wikilinks resolve by filename,
so no link updates are needed for the move.
The vllmScripts repository (LLM inference fleet: serve scripts, systemd
units, env tunables, deployment runbook, research docs) is merged into
this repository. Its full history is grafted under llm/ with a
two-parent merge commit so no commit is lost.
A follow-up commit reorganizes llm/ into the repo layout:
llm/docs -> docs/LLM, llm/scripts -> scripts, llm/old -> old.
Explicit rule: stage deletions in a dated ~/.AGENTTRASH/YYYYMMDD-topic
directory, list sizes, and wait for user approval before purging. rm,
rm -rf, and git clean -f forbidden without explicit permission. Applies
to every host.
LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0 unconditionally. FASTGREEDY=1 now
means: reasoning off, deterministic sampler defaults, compatible with
all non-greedy requests (temp != 0, penalties, reasoning budget). This
is the card's 'compatible mode' profile.
The bridge gateway (10.89.3.1) lives in the rootless netns; llama-server
runs in the host netns, so the gateway refuses. 192.168.0.143:52625
reaches it through the rootless NAT (verified from the container).
Same LAN-IP pattern the doc already prescribes for the Dankserver
backend.
A 'caddy reload' delivered over the admin API cannot apply a config
that disables the admin API -- the fix cannot ride the API it is meant
to enable (2026-08-22: admin off sat in the running config across
deploys). Track the reload result; on failure, restart the container
so it reads the rendered file on start.
Reasoning off, argmax fastpath on, deterministic sampler. The fast
greedy path rejects non-greedy requests with 400; chat clients must
send temperature 0.
The Caddyfile had 'admin off', which disables Caddy's config file
watcher. Rendered Caddyfile changes never loaded until the container
was recreated, so the double-hash basicauth fix sat on disk unapplied
across deploys (2026-08-22). Admin binds to 127.0.0.1:2019 inside the
container and the port is unpublished, so nothing outside reaches it.
deploy.sh now issues an explicit 'caddy reload' (retry loop) after
'up -d', with the file watcher as backstop.
basicauth (2026-08-22 incident):
- the Caddyfile template carried its own $2a$14$ prefix and deploy.sh
substituted the full hash (prefix included), rendering an invalid
double-prefixed hash. Every basicauth vhost rejected every password
with 401 and Caddy logged nothing.
- template is now a bare REPLACE_WITH_HASH token; tests pin the render
contract (no prefix in template; rendered line is exactly 'dank <hash>').
open-webui (2026-08-22 incident):
- its slirp4netns helper process died, leaving the container running
with only 'lo' in its netns: port 3005 accepted TCP and reset every
request, so chat served empty responses for ~2 days, unlogged.
- move to a pinned bridge network (systemd-open-webui, 10.89.3.0/24,
gw 10.89.3.1) — no per-container helper to die.
- LLM endpoint reached via the gateway (host.containers.internal is
slirp-only): OPENAI_API_BASE_URL=http://10.89.3.1:52625.
- add a quadlet healthcheck: /health (app) + non-loopback interface
(network liveness; the dead-tap state leaves only 'lo').
- deploy script now copies the .network file too.
- docs updated (OpenWebUI History section, Caddy basic-auth contract).
buildah can serve a stale COPY --from layer (cache keyed on stage
name), so a Containerfile edit silently produced an unchanged image.
The image now carries a cfhash label; a mismatch forces a --no-cache
rebuild.
- alpine's /bin/busybox is musl-dynamic and cannot execute in the
distroless loki image (missing loader); busybox-static links in
- alloy 1.x refuses to configure the ui service from a config block;
the default UI already listens on 127.0.0.1:12345 where the
healthcheck probes
- alloy 1.x renamed the server component to ui; the old block failed the
initial load and the container crash-looped
- grafana/loki is distroless and grafana/alloy lacks wget, so their
healthchecks could never run; local images add a static busybox from
alpine for that one command
- deploy.sh builds all three local images if missing
- tests: 3 new seams
Measured the rootless mapping: container root IS the invoking user
(dank, owner of the /opt data dirs); the images' default users (loki
10001, prometheus nobody, grafana 472) map to subuids that own nothing.
1000:1000 was the wrong direction.
Frank