Search is the one capability that fits the profile holding none: every other capability either
reads this installation or changes it, and chat's whole contract is that it can do neither. The
assistant deliberately does not get it — its contract is that answers come from this install's
own documents, and a web result there is an answer that looks sourced and is not. A chat question
about this machine hands off to the assistant before the search would run, so it never reaches
the internet even with the box ticked.
Off by default, and not because it is dangerous: searching sends the operator's question outside
the house, which is theirs to decide. Asked for per turn as well as enabled in conf.
Provider-agnostic, as asked — searxng, brave, tavily. Only whichever is configured here can be
verified; all three read every field by name, so a shape that changes underneath yields no
results rather than wrong ones.
The explain fixtures asserted chat holds no capabilities at all, which is exactly the guarantee
worth keeping. caps=only: now states the set rather than its emptiness, so the check still fails
the day something else is granted there.
Several scripts delete inside a conf path — the orphan cleaner runs rm -rf under a download dir
and rsync runs --delete against a destination — so /mnt/user/Movies becoming /mnt/user is the
edit that turns a cleanup into a sweep. Depth cannot be the test, because /tv and /movies are
real container-internal values here; direction can. Clearing a path, making it relative and
'..' segments go with it, and autofix additionally requires a proposed path to exist, since
every probe it has is a network probe and proves nothing about a directory. Refusals now reach
the caller: a save whose only change was refused answered ok with no explanation.
Seven findings had been sitting in needs_operator with no way to reach the operator: the only
way to read one was the sweep tool over SSH. The card states the gate as well as the list,
because an empty list means nothing found when repair is on and nothing is looking when it is
off. Buttons come from the actions the endpoint returned for that row, so a tab left open
overnight cannot offer a choice the store has moved past.
A stored transcript is replayed into a later prompt when reopened, so a key typed while
changing a setting would be handed back to the model on every subsequent turn.
Eleven call sites wrote master.conf with tmp+rename and nothing else — no backup, no
parse check, no audit — including the two toggles the UI uses most and the raw editor
that installs a whole hand-edited file.
A job killed hard never corrects its own record, so 'running' outlives the
process and the pid can since belong to something else; array-start jobs get
setsid too, so Stop can reach past their direct children.
UI-launched jobs inherited php-fpm's process group, so stopping one that was
actually running group-killed the WebGUI; setsid makes the job its own group
leader and stop.php now refuses to signal any group it does not lead.
vv_cache_clear() went in without it, so every start and stop fatalled on the line after the
docker command had already run — the action succeeded and the page was told it failed.
Every poll after the first asked for ?live=1, so the page paid a full collection — partner SSH
timeouts included — every two seconds while the tmpfs cache it was built around went unused.
Polls are now guarded against overlap and stop while the tab is hidden, repeated failures say so
instead of leaving the last good reading on screen, and two functions nothing called are gone.
The response was discarded, so a refused stop looked like a completed one, and the payload the
card redraws from is cached for 300s with no invalidation — the container carried on showing as
running until the once-a-minute writer caught up. Stop now confirms; start still does not.
The Tools card adopted the AI scripts on the host check alone, and api/ai.php only
tested AI_ENABLED in front of ask, so a disabled subsystem still had rows to run and
an endpoint that answered.
Explicit buttons rather than an automatic router. Misclassifying a Varaverk
question as chat produces a confident invention about the user's system, which
is exactly what retrieval exists to prevent — with buttons there is no hidden
heuristic to be wrong and the strict profile is the default you land on.
Only Varaverk Assistant retrieves; the other two would be carrying passages
that cannot help write a folder-copy script. Memory goes to all three, since
that is what lets chat know the setup without claiming authority over it.
History depth is per profile and set server-side: retrieval costs ~2500 of
16384, so the profiles that skip it can hold a real conversation. Code
Sketcher is told to flag flags it is unsure of, after it invented
rsync --no-overwrite.
A small operator-written file handed to the model at the start of every
conversation — who you are, how this install is set up, what has already been
decided. Injected ahead of the retrieved passages and marked operator-authored
so it outranks anything they contradict, and never cited as a source.
Deliberately not indexed and deliberately under DATA_DIR: it changes
constantly, vector similarity is the wrong way to retrieve things you were
told to remember, and gitignoring it keeps personal notes out of a pushed
repository. The character cap is a context budget — this text costs its share
of 16k on every single turn.
The pattern required a tier prefix, so the master gate the rsync page renders
alongside the tier toggles was rejected as an invalid flag name and sprang
back to off. There was no way to enable syncing from the UI. Masked until now
because every POST to this endpoint was being swallowed as multipart.
A POST the browser demonstrably sent — correct token, correct body — left no
trace: no CSRF termination, no fatal, and no action log. Rejected-before-PHP
and died-inside-the-include are indistinguishable from outside, so the first
statement now records that execution arrived.
There is no nginx access log on this host and the CSRF prepend exits with an
empty body, so a request that never arrived and one that arrived and failed
were indistinguishable — the page just sat at "starting…". The job-file write
was also suppressed with @, which would produce exactly that hang: a token
returned for a job that can never report.
Token and poll rather than SSE, so the api layer keeps one response
convention and reuses the pattern manual_sync already proved. History is
capped at three turns because the model is only fully offloaded at 16384
context and unbounded history would cross that silently. The tab exists
only while AI_ENABLED is true, rejected server-side and not merely hidden.
Unraid already enforces CSRF on every POST via auto_prepend, but its
injector is jQuery-only — the plugin's native fetch() calls carried no
token and were being terminated before the endpoint ran, silently,
because csrf_terminate exits with an empty body that r.json() swallows.
Writing down what each endpoint actually guarantees made the places it
didn't obvious — shell arguments reaching a crontab or a bash -c
unescaped, master.conf written without tmp+rename, and conf edits that
could be saved without ever being parsed.
- WEBGUI_PHP_WAIT was referenced by webgui_watchdog.sh but never defined
in master.conf, always silently falling back to a hardcoded default
- arrs.php/confform.php still pointed at Media/ for arr cleanup/discovery
scripts moved to Arrs_Stack/ in b4bc926 — broke the Arrs page's stats
and the per-script settings editor for those scripts
- docker_folders.php read directly from the optional folder.view3 plugin's
file instead of Varaverk's own docker_folders.json (the primary store
since the Docker tab got its own config) — left the Monitor page's
Docker Folders widget empty on any host without folder.view3 installed
- vv_wd_remote_data() read remote watchdog state files from hardcoded
/tmp or /boot/config paths instead of the remote's actual STATE_DIR
(which resolves dynamically and can differ under flash mode) — remote
node's Watchdog panel was always empty; same wrong path also used for
two local reads (system_watchdog_oom.db, watchdog_appdata_growth.db)
- rsync.php referenced a {HOST}_MONTHLY_SYNC_SHARES conf var that never
existed (monthly_maintenance.sh has no rsync section) — nulled out to
match the existing pattern used for the fallback window
- vv_arr_node_names() did a pointless identity array_map
- vv_dk_webui() had its own duplicate local-IP resolution instead of
using vv_local_ip(), despite config.php's comment claiming that exact
duplication was already consolidated
Custom Scripts (the Scheduler page's inline editor) used to save into the
git-tracked Custom/ folder, so anything saved there would end up on GitHub.
They now live in /boot/config/plugins/user.scripts/Varaverk/Scripts, same
folder family as Unraid's own User Scripts plugin. Import Script lets you
browse the whole server and move an existing script in instead of only
creating new ones inline — always a move, never a copy, so no stray
duplicate is left where it came from.
findmnt returns 'flash/boot' for a ZFS dataset, not a /dev/* path.
lsblk -no pkname then fails, leaving transport as 'unknown'. Resolve
ZFS pools to a backing device via zpool before checking transport.
All state/data file paths in scripts and PHP now resolve via STATE_DIR / DATA_DIR /
PERSISTENT_CONF_CACHE instead of hardcoded /boot/config/ or /tmp/ paths, so the
ecosystem works in both internal and appdata storage modes.
PHP layer (watchdog.php, partnership.php, fallback.php, monitor.php, snapshot.php,
config.php): all state reads switched to STATE_DIR constant; remote state reads use
the new vv_remote_state_cmd() helper which resolves the remote's SCRIPTS_DIR via
their varaverk.cfg before building the path.
conf_sync.sh: fixed SCRIPTS_ROOT → SCRIPTS_DIR bug on MY_CONF path; added
_remote_scripts_dir() to resolve partner's SCRIPTS_DIR before SCP pull.
fallback.php page: added controls card (PARTNERSHIP_ENABLED, FALLBACK_ENABLED,
FALLBACK_RSYNC_ENABLED toggles), status grid, and settings card.
README and Manual updated for System_Essentials, Watchdogs, Fallback, Rsync,
Media, Monitors, Orchestrators, Partnership: added new scripts (conf_sync,
conf_cache_save/restore, conf_cache_watchdog, play_state_sync, start_webhook_listener,
upgrade_webhook_handler), corrected all stale /boot/config/ state file paths to
$STATE_DIR/$DATA_DIR, noted webgui/php_fpm/mover/user_scripts scripts moved to
Plugin/unraid/System_Essentials, fixed start_webhook_listener.sh header (Node.js,
not PHP -S).
Web files now served via symlink to the git repo so git pull changes survive
reboots without rebuilding the txz. Also includes: docker pull/rebuild/restart
with live log streaming, arr_profile_enforcer for Sonarr/Radarr quality
profiles, monitor page cache fix (background writer now in cron), and
ARR_KIDS/SONARR/RADARR profile name vars in master.conf.
host.conf.template: add AUTH STACK section (NPM/lldap/Authelia) so
conf_upgrade.sh stops stripping those keys from host*.conf at 1am.
setup wizard: storage mode selector auto-detects USB vs NVMe at first
run; user can override; triggers storage_migrate.sh when mode differs
from current SCRIPTS_DIR location.
claude_startup.sh: reads HOST*_STORAGE_MODE_INTERNAL to pick internal
or appdata path rather than always requiring array to be mounted.
- Replace python3/PyYAML Authelia ACL parser with pure PHP (no deps available on Unraid)
- Cert tab now pulls live from NPM API instead of cert_monitor.sh — auto-discovers all managed certs sorted by urgency
- Watchdog page: add missing GB constant and _fmtBytes/_relTime functions that were causing silent render failure
- Rsync settings card: pin to far-right 3 columns (grid-column:6/-1), toggle grid narrowed to 2 columns
- Add CLAUDE.md project context file on /boot for session persistence across reboots
- claude_startup.sh: symlink CLAUDE.md into /root on array start
- Auth stack: fold cert monitor into Auth Stack page as fourth tab (Certs);
remove standalone cert page and top-level tab
- cert_monitor.sh: write JSON status cache to State_Files/cert_status.json
after each run; expose per-domain days/expiry via _CERT_DAYS/_CERT_EXPIRY globals
- api/cert.php: new — serves cached cert status; falls back to configured
domains as UNKN when no cache exists; POST action=run triggers live check
- arrs db fallbacks: vv_arr_cleanup_stats/discovery_stats/recovery_stats now
read from data/*.db files when log JSON files don't yet exist
- config.php vv_conf_vars(): unescape bash \$ → $ so passwords with dollar
signs read correctly from conf files
- host1.conf: fill in HOST1_NPM_USER/PASS and HOST1_LLDAP_USER/PASS
- Partnership adapter pattern: Unraid-specific container logic extracted to
Plugin/unraid/Partnership/; platform-agnostic structure stays in Partnership/
- First-run wizard: uniform multi-step flow for all hosts; HOST2 pull moved
to checklist; auto SSH keygen and API key creation on save
- api/checklist.php: live setup checklist with pull_master action
- Fullscreen toggle: hide Unraid header/menu; state persists via localStorage
Gmer4Lfe