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.
Frankandomp