Files
admin 772956d214 docs(R-116): CLOSED — proven live; capability row F to PROVEN-LIVE; R-120 filed
The events leg the previous commit reported as not-reached is now done. The operator
relayed the claim code (the only route: bcrypt-hashed hub-side, emailed only), the
two storage paths were registered through the real POST /api/storage/register, and
the cycle ran on the fresh box:

  07:20:04  backup_target_absent   (error)  Cel meghajto   <- TARGET, specific
  07:22:34  backup_target_restored (info)   Cel meghajto   <- its matching pair
  07:24:04  storage_disconnected   (error)  Adat meghajto  <- NON-target, generic
  07:25:34  storage_reconnected    (info)   Adat meghajto

All four at the hub; gate fired in 3 s. Two matched pairs, correctly discriminated
-- and discrimination is proven NON-trivially for the first time, since both prior
runs had the target itself emit the generic event. Over-correction passes on a
positive observable, with two RETURNED lines proving the gate was ticking.

00-capability-map row F: PARTIAL -> PROVEN-LIVE with the evidence and the caveat.

R-120 filed: the golden bakes controller 0.185.1, which PREDATES R-114 + R-112, so
a freshly installed box shows the customer the WRONG absent-target message --
observed live on the drill box: the generic "the backup is on the same disk as the
system" copy (false; the target is a drive that vanished) plus an offer of the other
drive as the remedy. That is E2D 5.3's exact payload, still reachable on any new
install. R-115's class one layer up -- R-111 closed by re-baking the golden, 0.186.0
then shipped, the golden did not move, and the gap reopened silently; this time the
stale artifact carries a customer-facing falsehood in exactly the state R-116 now
alarms about correctly.

Teardown recorded for all three layers, hub layer gate-blocked with the command.
2026-07-30 09:34:08 +02:00

19 KiB
Raw Permalink Blame History

R116-v0116-2026-07-30 — R-116 CLOSED: the specific alarm and its matching recovery, both on the wire

Run: R-116 join task, CC on DooPlex, 2026-07-30. Agent v0.116.0 built, published, vouched, and installed by a fresh box from the Day-0 manifest. Result: ALL claims PASS.

Claim Verdict
The fix is effective live — the absent target row carries the flag and the key the gate uses PASS. isTarget["/mnt/felhom-drives/cel"] = true (was false through v0.115.0)
C5 — backup_target_absent / _restored on the wire, paired PASS. backup_target_absent (error) on detach, backup_target_restored (info) on return, same drive, both at the hub. Gate fired in 3 s
Discrimination — target ⇒ specific, non-target ⇒ generic PASS, and NON-trivially for the first time. Same box, minutes apart: target → backup_target_absent; non-target → storage_disconnected
No over-correction PASS with a positive observable — 0 ABSENT lines / 0 drive events over 2m14s with both drives present, while 2 RETURNED lines prove the gate ticked
R-114 not regressed by the fix PASS at the payload layer (no row combines the flag with a mount path) + unit-pinned. ⚠️ not confirmable on this box — it ran controller 0.185.1 from the golden, which predates R-114 → R-120

1. Baselines as actually running

main running a FRESH box gets
agent 0.116.0 (21b0164) felhom-pve 0.115.0 · demo-hp 0.113.0 · drill sess-e-5d4427 0.116.0 0.116.0 (vouched this run)
controller 0.186.0 (b331f18) felhom-pve 0.186.0 · demo-hp 0.185.1 · drill 0.185.1 golden bakes 0.185.1
hub 0.81.0 0.81.0 min_agent 0.113.0 · min_controller 0.156.0
felhom.eu 1aa1bd1

The golden bakes controller 0.185.1 — which is why the fix had to land in the agent: a controller-side fix would not reach a fresh box without a re-bake, whereas the agent channel serves the newest vouched version immediately. Confirmed by this run: the drill box installed 0.116.0 unaided.

2. §5's three publish observables, as returned

(1) registry, independent GET of the published bytes:
    HTTP 200  bytes=14022347
    b47c5c4dab641ee57e2cf5893c2aebf1806a41c376ab06322342b02c86940a98  /tmp/rt-0.116.0
    /tmp/rt-0.116.0 --version → felhom-agent 0.116.0
(2) hub Day-0 manifest, read BACK after the POST (not the 303):
    agent_version: SELECTED=['0.116.0']      agent_sha256 = b47c5c4dab641ee5…
    golden_version: SELECTED=['0.185.1']     min_agent = 0.113.0
    wrapper_sha256 = 104db0a4401f65bb…  (re-checked against configs/felhom-pbs-apply — NO drift)
(3) the box under test reports it running:
    hub log  → Artifact manifest served for customer sess-e (agent=0.116.0 golden=0.185.1)
    host row → sess-e-5d4427 … 0.116.0 ONLINE
    on the box → felhom-agent --version → felhom-agent 0.116.0

min_agent deliberately not raised: controller v0.185.0 declares MinAgent 0.113.0, and raising it would hold demo-hp (0.113.0) for no reason. The golden was not moved — the controller is unchanged.

3. The rig — real pipeline, no bypass

Machine: demo-hp, per runbooks/target-selection.md (Tier 0, the designated drill+build VM host). This differs from the previous R-116 run, which used the DooPlex fixture — the document says DooPlex is Tier 2 and its drill.qcow2 is a bake fixture, not a drill target, so this run followed the document.

VM 9401 r116-drill: nested PVE, 8 GiB/4 vCPU cpu=host, OVMF, disks on a dir storage r116-images at /mnt/nvme-1tb rootnot local-lvm (over-subscribed thin pool hosting a live guest). Installed from the real v1.25.0 felhom ISO already on demo-hp, through the real day-0: self-register (appliance 13, pairing D54-DG5) → operator bind to sess-e → credentials delivered once → guest 9201 provisioned from the vouched golden → controller_started (0.185.1) → reports flowing.

Drives, both enrolled through the real endpoints (/disks/format/disks/assign/disks/guest-attach/backup/target), no hand-set state:

device host mount guest bind role
target /dev/sdb (scsi1) /mnt/cel /mnt/felhom-drives/cel primary backup target (felhom-backup, is_mountpoint 1)
non-target /dev/sdc (scsi2) /mnt/adat /mnt/felhom-drives/adat user-data only

backup tier armed target=felhom-backup … primary=true after the required restart.

Device loss is a real hot-detach (qm set 9401 --delete scsi1); the volume survived as unused0 and was reattached, so the present-state control is re-runnable.

4. The payloads — PASS, and this is what v0.115.0 could not do

Host state at the absent capture, identical to every prior run:

ls /dev/sdb        → No such file or directory
findmnt /mnt/cel   → rc=1 (not mounted)
pvesm status       → unable to activate storage 'felhom-backup' - directory is expected to be a
                     mount point but is not mounted: '/mnt/cel'
                     felhom-backup   dir   inactive   0 0 0

The target drive's row, all three states

state rows rows for the target mount_path guest_path backup_target bound_under_parent state role
PRESENT 4 1 /mnt/cel /mnt/felhom-drives/cel true true attached user-data
ABSENT 4 1 "" /mnt/felhom-drives/cel true false disconnected system
RETURNED 4 1 /mnt/cel /mnt/felhom-drives/cel true true attached user-data

Exactly one row in every state — the registry row for the target is deduped by guest path in the absent state (registry-row-for-target = 0 in all three captures). Before this fix the absent state carried it twice.

driveTargetByPath computed from the captured absent payload

driveTargetByPath = {'/mnt/felhom-drives/cel': True,
                     '/mnt/felhom-drives/adat': False, '/mnt/adat': False}
isTarget[/mnt/felhom-drives/cel] = True      ← was FALSE through v0.115.0

notifyDriveAbsent therefore takes the specific branch. RETURNED gives True as well, so the pair matches.

The three guards, from the same payload

  • R-114 preserved. No row has backup_target: true and mount_path != "". The absent target row reports mount_path: "", so backup_target_offer.go:79 does not match and R-114's TargetAbsent branch stays reachable. This is why option (a) was rejected — see felhom-agent/REPORT.md.
  • No over-correction. bound_under_parent: false on the absent row, so present[gp] = … || d.BoundUnderParent stays false and the Stop branch is still reachable.
  • Discrimination, payload layer. The non-target adat carries backup_target absent ⇒ false on both its keys, in both states. So the two are now genuinely distinguishable — which is the thing both prior runs could not show.

Raw payloads

Absent (all 4 rows, verbatim):

{"ok":true,"data":{"disks":[{"name":"felhom-backup","type":"local-dir","state":"disconnected","backing_device":"","mount_path":"","class":"","role":"system","data_bearing":false,"total_bytes":0,"used_bytes":0,"used_fraction":0,"durable_id":"path:/mnt/cel","guest_attached":false,"backup_target":true,"guest_path":"/mnt/felhom-drives/cel","bound_under_parent":false,"smart":{"health":"UNKNOWN","temperature_c":null,"power_on_hours":null,"reallocated_sectors":null,"pending_sectors":null,"offline_uncorrectable":null,"critical_warning":null,"media_errors":null,"percentage_used":null}},{"name":"local","type":"local","state":"attached","backing_device":"","mount_path":"","class":"","role":"system","data_bearing":false,"total_bytes":14484905984,"used_bytes":5096075264,"used_fraction":0.351819699045967,"durable_id":"path:/var/lib/vz","guest_attached":false,"bound_under_parent":false,"smart":{"health":"UNKNOWN","model_name":"QEMU QEMU HARDDISK","temperature_c":0,"power_on_hours":null,"reallocated_sectors":null,"pending_sectors":null,"offline_uncorrectable":null,"critical_warning":null,"media_errors":null,"percentage_used":null}},{"name":"local-lvm","type":"lvmthin","state":"attached","backing_device":"","mount_path":"","class":"","role":"system","data_bearing":false,"total_bytes":12675186688,"used_bytes":4224639723,"used_fraction":0.33329999999129,"durable_id":"pve/data","guest_attached":false,"bound_under_parent":false,"smart":{"health":"UNKNOWN","temperature_c":null,"power_on_hours":null,"reallocated_sectors":null,"pending_sectors":null,"offline_uncorrectable":null,"critical_warning":null,"media_errors":null,"percentage_used":null}},{"name":"d248508a-0c4f-466f-9c43-0dae988efc62","type":"usb","state":"attached","backing_device":"/dev/sdc","mount_path":"/mnt/adat","class":"","role":"user-data","data_bearing":false,"total_bytes":8350298112,"used_bytes":2125824,"used_fraction":0.00025458061155266215,"durable_id":"uuid:d248508a-0c4f-466f-9c43-0dae988efc62","guest_attached":false,"guest_path":"/mnt/felhom-drives/adat","bound_under_parent":true,"smart":{"health":"UNKNOWN","model_name":"QEMU QEMU HARDDISK","temperature_c":0,"power_on_hours":null,"reallocated_sectors":null,"pending_sectors":null,"offline_uncorrectable":null,"critical_warning":null,"media_errors":null,"percentage_used":null}}],"guest_boot_id":"1785394603-28275","vmid":9201}}

Present and returned payloads: d-PRESENT.json / d-RETURNED.json, on the box at /root/ and in the session scratchpad. The target row differs from the absent one only in the fields tabulated above.

5. Where R-117 interfered — and it did

Reproduced again, fourth consecutive run, and on real hardware this time:

after reattach:  host findmnt /mnt/cel                     → /dev/sdd
                 guest findmnt /mnt/felhom-drives/cel       → /dev/sdb[/felhom-data] rw,relatime,shutdown
                 guest read through the bind                → GUEST-READ-EIO
                 /disks says                                → state attached, bound_under_parent TRUE

How it interferes with reading this run: the reattach leg's isTarget = true and bound_under_parent = true are correct as answers to the questions this fix asks, but they are read off a drive whose guest namespace is dead. So "the drive came back healthy" cannot be concluded from the reattach capture — only "the flag and the key rejoined on one row", which is what was under test. When the events leg runs, the Return branch will fire against a dead bind, so a backup_target_restored there proves pairing, not recovery. Recorded, not fixed (R-117 has its own row).

6a. C5 + discrimination — PASSED, the full four-event sequence

The claim gate (§6b) was cleared with an operator-relayed code, the two paths registered through the real POST /api/storage/register, and the cycle run. Controller log, verbatim, one continuous run:

07:20:03 [WARN]  [gate] drive ABSENT /mnt/felhom-drives/cel — stopped+blocked 0 app(s): []
07:20:03 [ERROR] [gate] the ABSENT drive /mnt/felhom-drives/cel is the WHOLE-GUEST BACKUP TARGET
                        — the system backup cannot run until it returns
07:20:04 [INFO]  Event pushed: backup_target_absent (error) — A rendszermentés meghajtója nem érhető el:
                        Cel meghajto (/mnt/felhom-drives/cel)
07:22:34 [INFO]  [gate] drive RETURNED /mnt/felhom-drives/cel — re-attached + restarted gate-stopped apps
07:22:34 [INFO]  Event pushed: backup_target_restored (info) — A rendszermentés meghajtója újra elérhető:
                        Cel meghajto (/mnt/felhom-drives/cel)
07:24:03 [WARN]  [gate] drive ABSENT /mnt/felhom-drives/adat — stopped+blocked 0 app(s): []
07:24:04 [INFO]  Event pushed: storage_disconnected (error) — Meghajtó váratlanul leválasztva: Adat meghajto
07:25:34 [INFO]  [gate] drive RETURNED /mnt/felhom-drives/adat — re-attached + restarted gate-stopped apps
07:25:34 [INFO]  Event pushed: storage_reconnected (info) — Meghajtó újra csatlakoztatva: Adat meghajto

All four reached the hub (Event from sess-e: … at 09:20:03 / 09:22:34 / 09:24:04 / 09:25:34 CEST).

# drive event severity pair
1 target cel backup_target_absent error ↔ 2
2 target cel backup_target_restored info ↔ 1
3 non-target adat storage_disconnected error ↔ 4
4 non-target adat storage_reconnected info ↔ 3

Two matched pairs, correctly discriminated. This is what R-116 existed to produce and what two prior runs could not: both of those had the target emit the generic event, so "non-target ⇒ generic" proved nothing about telling them apart. Here the two cases ran on the same box, four minutes apart, and diverged.

Over-correction guard — positive observable, not an absent log line. Window 07:26:51Z → 07:29:05Z with both drives present: 0 drive ABSENT lines, 0 drive events, and {"degraded":false,"label":"Cel meghajto","target":"felhom-backup"}. That the gate was running during the window is established independently by the two [gate] drive RETURNED lines earlier in the same container's log — so the silence is a decision, not a dead loop.

Also emitted: health_critical (error) at 07:21:32 while the target was away, and its recovery. Expected — the box's overall health reflects a missing backup target — recorded so the event count reconciles.

6b. The claim gate — the one genuine human step, again (→ R-119)

planDriveGates iterates s.settings.GetStoragePaths(). The drill controller has none:

controller log → [WARN] Storage paths: no storage paths registered

Registering one requires the controller's storage API, and every route is behind the claim gate:

GET /api/storage/backup-target  (Host: felhom.sess-e.test)  → 401 {"ok":false,"error":"dashboard not yet claimed"}
GET /api/storage/paths                                       → 401
GET /api/storage/list                                        → 401

The claim code is bcrypt-hashed in the hub and only ever emailed (claim/engine.go), and the self-bind link is likewise mint-and-email — handleSelfBindLinkSend (selfbind_mint.go:139-161) only ever renders a flash, never the token. There is no operator-side route to either secret, which is the same wall E2D hit and named "the one genuine human step".

A fresh code (generation 2) was emailed by POST /configs/sess-e/claim-resend and the operator relayed it, which is the only route that exists. Claim submitted through the real POST /claim (its own pre-auth HMAC CSRF: GET the page, carry the token and its cookie), then login, then session-CSRF for the writes. Positive discriminator that the gate moved, as E2D recorded:

before:  {"ok":false,"error":"dashboard not yet claimed"}
after:   {"ok":false,"error":"authentication required"}     (unauthenticated)
authed:  {"data":{"degraded":false,"known":true,"label":"/mnt/felhom-drives/cel","target":"felhom-backup"},"ok":true}

The cost is real and recurring: three sessions have now stopped at this wall.R-119.

7. Teardown — layers 13, per the §13 paragraph this task added

layer item disposition
1 — machine VM 9401 r116-drill + all four volumes DESTROYED qm destroy 9401 --purge
2 — host r116-images dir storage at /mnt/nvme-1tb REMOVED; space returned (below)
3 — hub customer sess-e, host sess-e-5d4427, appliance 13 GATE-BLOCKED — command recorded below. The cascade was attempted and correctly refused: HTTP 409 "Delete refused: host sess-e-5d4427 is ONLINE". Deletable once it ages ONLINE→DOWN (>1 h from its last report, customer_delete.go:220-228)

Layer 2, measured: felhom-backup available 928787076 KiB after vs 928787080 KiB before the run (4 KiB = noise), used back from 17708084 → 4566012 KiB. local-lvm 38.84 % vs 38.83 % — demo-hp's own guest, not this run. r116-images gone; qm list shows only drill-r50. The space came back.

Secrets: the break-glass credential and the hub DB copy it came from were shred -u'd; the claim code, the drill controller password and the session cookie were shredded in the guest and on the box before destruction, and the local copies on DooPlex are shredded. The in-guest shred -u left 3 files behind (reported honestly rather than claimed clean) — they died with the purged disk moments later.

pvesm status on demo-hp before the run, for the layer-2 comparison at teardown:

felhom-backup  dir     active  983379700  4566008  928787080  0.46%
felhom-pbs     pbs     active          0        0          0  0.00%
local          dir     active   40516856 14961808   23464656 36.93%
local-lvm  lvmthin     active   56545280 21956532   34588747 38.83%    ← the fence figure, unchanged

Teardown commands, recorded now so they cannot be forgotten:

ssh demo-hp 'qm stop 9401; qm destroy 9401 --purge; pvesm remove r116-images; pvesm status'
# hub, once the host ages ONLINE→DOWN (customer_delete.go:220-228 refuses only on ONLINE):
POST /configs/sess-e/delete  ack_hosts=1 ack_reset=1 ack_purge=1 confirm_id=sess-e expect_hosts=1

Already clear, and not by this session: sess-c and sess-d — both /customers/<id>HTTP 404, absent from /configs and /hosts. The operator removed them using the commands the previous report recorded. Verified directly rather than inferred.

Fences held: guest 9201 on both demo boxes untouched · drill-r50 (VM 300) untouched, stopped · neither demo box re-targeted · nothing on local-lvm · Peti untouched · v0.115.0 not reverted · the hub DB copy taken for the break-glass credential was shred -u'd immediately.

8. Findings — filed, none fixed

  • R-117 — reproduced on real hardware with the read/write probe (EIO both directions) while /disks reports attached + bound_under_parent: true. Already filed; this run adds the metal-adjacent reproduction and the note in §5 about how it colours the reattach leg.
  • R-118 — the union row's root-filesystem capacity. Its symptom is now absent in the target's absent state because that row is suppressed; R-118 is not fixed and remains open for every other registry-only drive (the non-target adat row still carries statfs values from its own live mount, so the class is unchanged).
  • R-119 (new) — the claim gate makes the drive-gate legs unreachable to CC, by design, every time. Three sessions have now stopped at the same wall: the controller's storage API is claim-gated, the claim code is emailed-only, and planDriveGates cannot act until a storage path is registered. This is not a defect in the gate — it is correct customer-ownership — but it means every future validation of a drive-gate behaviour costs an operator email round-trip. Worth a ruling: either a documented operator-side test affordance (an operator-scoped claim, explicitly audit-logged), or accept the round-trip and put it in the runbook as a prerequisite step rather than a mid-run surprise. Filed, not designed.