The vault was 155 pages / 31,210 lines, most of it measurement ledgers for
payloads that no longer run. A throughput figure for a runtime nobody operates is
not a record: AI moves faster than the vault, so the number is wrong before
anyone reads it, and a wrong number in a runbook gets believed. Per the new
purpose test in `AGENTS.md` → *Documentation Policy*, it is destroyed.
Gone (`.AGENTTRASH/20261019-destruction/`, KILL-LIST.txt is the manifest):
- the `frank-medium` endpoint and its five era pages, `frank-npu`, FastFlowLM,
the ikllama/kingjones/dealign/frank-redo eras, the ling/swift15/freetoken/ubatch
campaign pages, qwen3.8 spec-matrix and strix-optimizations, the two
"Running Qwen3.6 …" pages;
- the whole `Pipeline Parallelism/` folder (no live script passes a pipeline flag)
and the multi-device/x4-pair/hybrid/offload experiment pages;
- every vLLM page — no vLLM endpoint exists on this fleet;
- `LLM/deployment.md` (`Architecture/Deployment Flow.md` is the test-referenced
owner) and the external surveys (SGLang, Lemonade, llama.cpp forks/diff,
self-hosted app census, the TTS survey) that were obsolete by construction;
- `log.md`, 2,380 lines. Git holds the chronology; a causal law belongs to the
page that owns the thing it governs, never to a diary.
Survivors: 101 pages, 17,542 lines, 0 OKF violations, 0 unresolved links. Eras
tables keep the window, payload, runtime, reason and rollback pointer; the rate
columns are blanked. The live shapes stay verbatim — those numbers are what the
deployer and `models.yml` consume.
Structural repair:
- 13 pages were the same document twice (each exactly 2x its HEAD size),
a second frontmatter block whose closing fence had been glued onto a body
line by a frontmatter rewrite that re-read its own output. Un-doubled by
cutting at the second frontmatter and keeping the copy whose body is a
superset; the orphan census reports 0 lost tokens against HEAD.
- log.md: one entry per date, bare `## YYYY-MM-DD` headings, newest first —
66 dated headings merged into 34, titles demoted to bold leads, every
content line verified present. The file had been descending at the head
and ascending at the tail.
Ownership moves:
- New `LLM/frank-medium.md` is the locator for the retired Dankserver
endpoint: era windows quoted from each era page's own banner, no numbers
restated, and the two unresolved date conflicts recorded instead of
silently resolved. `frank-archon.md` links to it instead of restating the
pre-rename window.
- The four Pipeline-Parallelism stubs (frontmatter only, no body) are gone;
`Multi-Node Runtimes.md` owns runtime construction, launch, mixed-vendor
verdicts and cross-split spec decode, and the four links that pointed at
the stubs were repointed at it or at the drafter page.
- Authentik's three stub pages fold into `Authentik.md`, with the process
detail and the outpost reference split out so the parent stays under the
length hint.
Verified corrections (host census + live probe, 2026-10-19):
- The MXFP4 checkpoint two pages called the "on-disk rollback" is gone:
/home/dank/models/ holds StillDeadcode, rad and tpl.jinja. Stated once, on
the era page that owns that payload; the swap page now links to it.
- frank-medium-radiance-mxfp4: the 4.24/7 accept rate belongs to the DFlash2
arm measured on the FP8 target, not to the MXFP4 era; the 3-family soak run
census is kept once (155 requests) instead of twice (~120 and 155).
- Fleet shapes re-confirmed against the live endpoints before touching any
page: 3x200000 fp8 KV, 2x200704, 2x262144.
Index rows are regenerated, not hand-carved. Net -1,849 vault lines.
The docs-fact census wave re-read the live hosts and re-keyed every page
it could: runtime/payload identities, ports, sizes, ledger figures, unit
state, and the retirement banners that drifted as the fleet moved. The
wave was interrupted mid-run, so this commit carries only what passed the
integrity gates: every touched page parses (front matter or H1+status
convention intact, balanced fences, no truncated tables, trailing
newline), the docs_completeness and link-integrity seams are green, and
bats is 384/384.
Numbers that this session proved on live hosts are keyed to the measured
value, not the page's earlier claim.
OpenWebUI model picker narrowed to exactly frank-secondary (connections
frank-large/frank-primary disabled in openai.api_configs, model table rebuilt,
stale frank-small model_id retargeted to the served alias). Documented the
auth-gated API surface (anonymous probes all 401; keys per account).
Authentik roster gains artem (pk 16) in the human-user template.
kassie (pk 14) and alex (pk 15, deleted pk 7 then recreated) now share the
ridley shape: <user>@franksdank.cloud + Non-Admin Users + jellyfin_users +
openwebui_users. Audit before destroy: the old alex row carried no MFA
device, token, entitlement, or proxy session - checked across the MFA
device tables, authentik_core_token, and providers_proxy_proxysession
(the fleet's column names differ from the ORM names: events.user is
denormalized JSON, certificatekeypair has no user_id). Events survive the
delete, so the audit trail keeps its shape.
Co-Authored-By: omp <omp@franksdank.cloud>
The UserWriteStage writes prompt_data['password'] via user.set_password().
A PasswordStage only authenticates the current password. Document the
correct mechanism (password field on the default-user-settings prompt +
empty-password guard policy) and the throwaway-user verification.
The default-user-settings-flow was missing a PasswordStage, so users could
edit name/email/locale but not their password. Added a PasswordStage
(InbuiltBackend) bound at order 101. Documented the flow's stage table and
the two ORM gotchas (MTI through model, required backends array).
Retiring dankclaw/compose.yaml and adding alert rules invalidated claims across
the repo, including in the rule file agents read first. Clean cutover includes
the prose.
**Tests that had gone hollow.** Four assertions grepped dankclaw/compose.yaml
for a service name. With the file gone they passed by *absence* — a gate that
can no longer fail. Each now asserts the real invariant ("no dankclaw compose
file competes with the quadlet units") and keeps a live check for a re-added
entry, so it still fails when one appears: verified by recreating a compose file
with a comfyui service and watching three tests go red, then removing it.
**AGENTS.md, which was wrong about ComfyUI.** It said ComfyUI runs CPU-only
("no ROCm wheels for gfx1151, CUDA images wrong"). That was true in the
compose era and is false now: the restored unit runs with /dev/kfd + /dev/dri and
must NOT pass --cpu. An agent trusting the rule file would have re-broken it.
Also corrected: the observability paragraph ("RUNNING BUT UNCONFIGURED, no
datasource, no rules" — all three have been configured since 2026-09-16), the
Active runbook row that still named halogen for frank-large, halogen's absence
from the Retired table, the benchmark policy naming halogen's harness, and the
seam list.
**Unit and page claims.** prometheus.container said "no alerting rules anywhere
in this stack"; node-exporter.container said Dankserver runs from its compose
stack; Prometheus.md documented three jobs as working (they scrape HTML: they
can never report up) and said no dashboard existed; index.md and the three
authentik service pages pointed at the retired file; Authentik.md's upgrade
instruction told you to bump an image tag in it.
One bad edit of my own on the way (a stale line number clobbered a See Also
entry in Prometheus.md) — caught by reading back, fixed, and the vault link
checker now proves the cross-references hold.
The loki/grafana/seerr proxy providers were script-provisioned with no
flows and no Application: null flows made the embedded outpost's Rust
deserializer reject the whole config (all guarded vhosts down after any
outpost reload), and the missing apps bounced post-login to authentik's
user UI instead of the app. Backfilled both live; documented the two
provisioning rules and updated the provider inventory. SSO e2e now
asserts the app landing (pathname leaves /if/, no IdP markers in body)
instead of only the hostname.
Token exchange chain verified end-to-end in-process on the live provider
(pk 9): authorize -> ORM-minted code -> form-encoded token exchange with
Basic client auth -> userinfo. Key findings documented:
- Application row + grant_types must exist before authorize can complete
- token endpoint consumes form-encoded bodies only (JSON body => no
grant_type parsed -> unsupported_grant_type); client auth is Basic-only
- PropertyMappingEvaluator.evaluate(*args,**kwargs) forwards kwargs to
BaseEvaluator.evaluate(expression_source), so context kwargs become the
expression source and every evaluation raises a swallowed exception;
userinfo therefore answers sub-only claims for every provider in this
fork. Scope granting filter (provider= M2M descriptor) is always empty.
- Grafana identity = sub hash until the evaluator bug is fixed upstream.
Meta-header routing and forward_auth removed from the described design — both
disproved live. Documents: Host-based provider routing with per-guarded-host
proxy providers (lockstep rule), the null-flows wedge that starves the
embedded outpost config fetch, the Anubis /outpost.goauthentik.io/* transport
exemption, the single-file bind-mount stale-policy inode gotcha, Invalid next
URL as a dead design, and the public-DNS record requirement per guarded host.
The forward_auth target /outpost.goauthentik.io/auth/caddy does not exist
in authentik 2026.8 (verified live: 404 for every header combination; the
URL tree has no outpost auth prefix at all — the outpost worker dials back
to core over ws/outpost/<uuid>/ instead). Unauthenticated subrequests got
404, Caddy treated >=400 as 'not authenticated' and redirected browsers to
the dead path — users saw authentik's own Not-Found page.
Fix: guarded vhosts now proxy the whole request through authentik-server:9000
with X-authentik-meta-outpost/-provider/-app headers (the exact header set
this build's Traefik controller emits, adapted for Caddy). Unauthenticated
clients get the login flow served in place; once a session exists,
authentik proxies on to the provider's internal_host — now
http://caddy:8017, a new post-auth internal listener that routes straight to
the app. The chain terminates; nothing dials back into authentik.
Live DB changes applied alongside (postgres is the source of truth):
provider pk=1 authentication_flow=default-authentication-flow (was NULL —
the actual cause of the 404s) and internal_host=http://caddy:8017 (was
self-referential http://authentik-server:9000).
All in-repo path references (AGENTS.md, README, old scripts, report artifacts,
test code paths) rewritten in the same commit; focused-test map extended for
.gitignore, old/scripts/*, dankclaw/comfyui/*, and report/* per this repo's
own convention ('add one before committing'). Obsidian wikilinks are
title-based and unaffected.
Frank
