Files
felhom-controller/controller/internal/web/recovery_handlers.go
T
admin 636c51e542 R-193: the recovery screen — unlocking, and only unlocking (v0.200.0)
A customer whose machine was rebuilt had everything needed to get their data
back and no way to find out: the only route was a command line. This is the
screen that closes that.

IT UNLOCKS, AND ONLY UNLOCKS (operator ruling). It explains, takes the recovery
code, opens the repository and shows what is in there — apps, dates, sizes. It
restores nothing: restore is already per-app and lives in the backups area, and
a screen that unlocks and then offers to overwrite is two decisions wearing one
button.

ONE CORE, TWO CALLERS. RecoverInstallCore is split out of RecoverAndInstall; the
CLI wrapper keeps its exit codes and printed lines byte-identical, and the
handler drives the same function. Two implementations of the one operation that
can permanently lose a customer's data would drift, and only one would be
tested. Asserted from source on both sides by AST.

THREE WAYS OUT, none a dismiss button: recover; 'most nem' (the full page stops
interrupting, the backups-area entry point stays PERMANENTLY, bound to the offer
and never to the postpone flag); and 'I do not want the old data' — confirmed
TWICE and reaching the SHIPPED move-aside, which sets aside and never deletes.

THE CODE IS HANDLED NO MORE LOOSELY THAN ON THE COMMAND LINE: POST body only,
never logged, never persisted, never echoed, cleared on every path, no-store,
autocomplete off. No lockout — the code is a ten-word phrase, and locking a
customer out of their own data for a typo is worse than anything it prevents.

TWO DEFECTS THE TESTS CAUGHT, both fixed: an UNCLAIMED (legacy-open) box would
have been shown the page, because RequireAuth passes such a box through; and the
inventory nil-dereferenced when no off-site target was configured, which is
exactly the pristine rebuilt shape.
2026-08-05 12:45:48 +02:00

209 lines
11 KiB
Go

package web
import (
"context"
"net/http"
"time"
"gitea.dooplex.hu/admin/felhom-controller/internal/backup"
)
// R-193 — THE RECOVERY SCREEN. A customer whose machine was rebuilt has everything they need to get
// their data back and, until this page, no way to find out: the only route was a command line.
//
// IT UNLOCKS, AND ONLY UNLOCKS (operator ruling, 2026-08-05). It explains the situation, takes the
// recovery code, opens the repository, and shows what is in there. It does NOT restore anything.
// Restoring is already per-app and already lives in the backups area; putting files back is a
// separate item. A screen that unlocks and then offers to overwrite is two decisions wearing one
// button.
//
// THREE WAYS OUT, and none of them is a dismiss button:
// - RECOVER — the main path (/recovery/unlock).
// - MOST NEM — the full page stops interrupting; the backups-area entry point stays PERMANENTLY,
// because the data is still there whether or not anyone clicked (/recovery/postpone).
// - I DO NOT WANT THE OLD DATA — deliberate, explained, confirmed TWICE, and it reaches the
// SHIPPED move-aside (`/backup/offbox/reset`), which sets the store aside and never deletes.
//
// THE RECOVERY CODE IS HANDLED NO MORE LOOSELY THAN ON THE COMMAND LINE (§8.3): POST body only, never
// a query string, never logged at any level, never persisted, never echoed back, cleared on every
// path, and the page is served no-store with autocomplete off.
// recoveryOffer reports whether this box is in the situation the screen exists for. The predicate and
// its two shapes live in backup.OffsiteRecoveryOffer — read its header before changing anything here.
func (s *Server) recoveryOffer() bool {
// CLAIMED AND BEHIND THE PASSWORD (§8.1). Before claiming there is no customer, and this page
// states metadata about the household's own backups — accepted as metadata rather than content
// (operator ruling 2026-08-05), which is only true while it sits behind the household password.
// A legacy-open box (no password anywhere) reaches ServeHTTP through RequireAuth's pass-through,
// so WITHOUT this line the interception would fire on an unauthenticated visitor. Caught by
// TestRecovery_B_DoesNotAppearForAnyoneElse/not_claimed, which failed before it was added.
if !s.authEnabled() {
return false
}
return s.backupMgr != nil && s.backupMgr.OffsiteRecoveryOffer()
}
// recoveryInterrupts reports whether the FULL PAGE should take over the landing pages. "Most nem"
// suppresses this and nothing else — recoveryOffer stays true, so the backups-area entry point
// survives. That asymmetry is the whole of Scenario E.
func (s *Server) recoveryInterrupts() bool {
if !s.recoveryOffer() {
return false
}
return s.settings == nil || !s.settings.GetRecoveryNoticePostponed()
}
// recoveryNoStore stamps the page uncacheable. The rendered page carries no secret, but it does carry
// the form the code is typed into, and a cached copy of a recovery form is a form served from disk.
func recoveryNoStore(w http.ResponseWriter) {
w.Header().Set("Cache-Control", "no-store, no-cache, must-revalidate, private")
w.Header().Set("Pragma", "no-cache")
}
// recoveryPageHandler renders the screen (GET /recovery). Reachable whenever the situation holds —
// including after "most nem", which is how the backups-area entry point can point at it forever.
func (s *Server) recoveryPageHandler(w http.ResponseWriter, r *http.Request) {
s.renderRecovery(w, r, "", "", nil)
}
// renderRecovery is the one render path: pre-unlock (explanation + code form), or post-unlock (the
// read-only listing). errorMsg/flash are already-customer-facing Hungarian; NEITHER EVER CONTAINS THE
// CODE — see unlockHandler.
func (s *Server) renderRecovery(w http.ResponseWriter, r *http.Request, errorMsg, flash string, inv *backup.OffsiteInventory) {
recoveryNoStore(w)
data := s.baseData("recovery", "Adatok visszaszerzése")
data["CSRFField"] = s.csrfField(r)
data["Offer"] = s.recoveryOffer()
data["Postponed"] = s.settings != nil && s.settings.GetRecoveryNoticePostponed()
data["Error"] = errorMsg
data["Flash"] = flash
data["SealedAt"] = s.recoverySealedAt()
// The set-aside choice is offered ONLY when the shipped move-aside can actually run — it refuses
// unless the tier is orphaned. Showing a button that is guaranteed to refuse would be worse than
// not showing it, and rewriting the move-aside is explicitly out of scope.
data["CanSetAside"] = s.backupMgr != nil && s.backupMgr.OffboxOrphaned()
data["ConfirmSetAside"] = r.URL.Query().Get("setaside") == "1"
if inv != nil {
data["Unlocked"] = true
data["InvApps"] = inv.Apps
data["InvEmpty"] = inv.Empty
data["InvUntagged"] = !inv.Empty && len(inv.Apps) == 0
}
w.Header().Set("Content-Type", "text/html; charset=utf-8")
if err := s.tmpl.ExecuteTemplate(w, "recovery", data); err != nil {
s.logger.Printf("[ERROR] [web] Template error (recovery): %v", err)
http.Error(w, "Internal error", http.StatusInternalServerError)
}
}
// recoverySealedAt returns the human date the hub says the sealed package was created (""
// when unknown). Non-secret: a timestamp, and the page must not pretend to know more than that
// before a code is entered.
func (s *Server) recoverySealedAt() string {
if s.escrowSealedAtFn == nil {
return ""
}
return s.escrowSealedAtFn()
}
// SetEscrowSealedAt wires the ACK's escrow created_at (report.EscrowAutoConfirmer). INIT-ONLY.
func (s *Server) SetEscrowSealedAt(fn func() string) { s.escrowSealedAtFn = fn }
// recoveryRecoverer returns the agent seam that unseals the package. nil → the shared agentClient(),
// the same channel the CLI uses; tests inject. The seam exists so the HANDLER can be driven in a test
// — a helper-level test would not observe a mutation that lives in the handler (§10).
func (s *Server) recoveryRecoverer() (backup.OffsiteKeyRecoverer, error) {
if s.recoveryRecovererFn != nil {
return s.recoveryRecovererFn()
}
return s.agentClient()
}
// SetRecoveryRecoverer overrides the agent seam (tests).
func (s *Server) SetRecoveryRecoverer(fn func() (backup.OffsiteKeyRecoverer, error)) {
s.recoveryRecovererFn = fn
}
// recoveryUnlockHandler takes the recovery code and drives the SHARED core (POST /recovery/unlock).
//
// R HANDLING, and it must not drift from the CLI's:
// - POST body only. A GET with a query string would put R in the access log, the browser history
// and any Referer header the page later emits.
// - never logged. Not at any level, not truncated, not hashed-and-logged.
// - never persisted — not in the session, not in a cookie, not in a file.
// - cleared on every path below, success and failure alike.
// - never echoed. No message built here contains it; the agent's errors name the step, not the code.
//
// NO LOCKOUT (§8.4). The code is a 10-word EFF phrase — guessing is not the risk — and locking a
// customer out of their own data because they mistyped is a worse failure than anything it prevents.
// Failures ARE logged locally (without the code) so a box being probed is visible in the debug ring.
func (s *Server) recoveryUnlockHandler(w http.ResponseWriter, r *http.Request) {
if !s.recoveryOffer() {
http.Redirect(w, r, "/backups/remote", http.StatusFound)
return
}
_ = r.ParseForm()
code := r.PostFormValue("recovery_code") // PostFormValue: body only, never the query string
if code == "" {
s.renderRecovery(w, r, "Add meg a helyreállítási kódot.", "", nil)
return
}
rec, err := s.recoveryRecoverer()
if err != nil {
code = ""
s.logger.Printf("[ERROR] [web] recovery: agent channel unavailable: %v", err)
s.renderRecovery(w, r, "A gép házon belüli kapcsolata most nem elérhető — próbáld újra néhány perc múlva.", "", nil)
return
}
ctx, cancel := context.WithTimeout(context.Background(), 90*time.Second)
defer cancel()
// THE SHARED CORE — the same function the command line drives. There is no second recovery
// implementation in this codebase (R-193 §8.5).
res, rerr := backup.RecoverInstallCore(ctx, s.backupMgr, rec, code, true)
code = "" // cleared here, before any branch below, on success and failure alike
if rerr != nil {
// The agent's error names the STEP (fetch / unseal / place) and carries no secret. It is not
// shown raw: a customer needs to know what to check, not what age's KDF returned.
s.logger.Printf("[WARN] [web] recovery: unlock failed: %v", rerr)
s.renderRecovery(w, r, "A megadott helyreállítási kódot nem fogadtuk el. Ellenőrizd, hogy mind a tíz szót pontosan, szóközökkel elválasztva írtad be — a kis- és nagybetűk nem számítanak. Semmi nem változott, nyugodtan próbáld újra.", "", nil)
return
}
switch res.Outcome {
case backup.RecoverRefused:
s.logger.Printf("[WARN] [web] recovery: refused — a different repository password is already present")
s.renderRecovery(w, r, "Ezen a gépen már van egy másik mentési kulcs. A régi előzmény visszanyitása felülírná azt, ezért nem hajtottuk végre. Vedd fel a kapcsolatot a Felhom ügyfélszolgálatával.", "", nil)
return
}
s.logger.Printf("[INFO] [web] recovery: the offsite repository key was recovered and placed (outcome=%s)", res.Outcome)
// Unlocked. Now show what is in there — read-only.
ictx, icancel := context.WithTimeout(context.Background(), 2*time.Minute)
defer icancel()
inv, ierr := s.backupMgr.OffsiteInventoryList(ictx)
if ierr != nil {
s.logger.Printf("[WARN] [web] recovery: unlocked but the inventory could not be read: %v", ierr)
empty := backup.OffsiteInventory{}
msg := "A kulcs visszakerült, de a mentések listáját most nem sikerült beolvasni. Nézd meg a Biztonsági mentés oldalt néhány perc múlva."
if backup.ErrNoOffsiteTarget(ierr) {
// The pristine rebuilt shape: the key is in place but the box has no off-site coordinates
// yet. It resolves by itself once the tier is re-applied, so say that rather than showing a
// failure the customer cannot act on.
msg = "A kulcs visszakerült. A gép még most kapcsolódik újra a házon kívüli tárhelyhez — a mentéseid listája néhány perc múlva jelenik meg a Biztonsági mentés oldalon."
}
s.renderRecovery(w, r, msg, "", &empty)
return
}
s.renderRecovery(w, r, "", "A mentéseid zárolása feloldva. Az alábbiakat találtuk a tárolóban — semmit nem állítottunk vissza.", &inv)
}
// recoveryPostponeHandler records "most nem" (POST /recovery/postpone). It suppresses the FULL-PAGE
// interruption ONLY: recoveryOffer stays true, so the backups-area entry point survives permanently.
func (s *Server) recoveryPostponeHandler(w http.ResponseWriter, r *http.Request) {
if s.settings != nil {
if err := s.settings.SetRecoveryNoticePostponed(true); err != nil {
s.logger.Printf("[WARN] [web] recovery: recording the postpone failed: %v", err)
}
}
s.logger.Printf("[INFO] [web] recovery: the customer chose to postpone; the backups-area entry point stays")
http.Redirect(w, r, "/launcher", http.StatusFound)
}