felhom.eu/hub/internal/offsite/offsite.go

// Package offsite orchestrates per-customer offsite-tier provisioning against the Hetzner storage-box API
// (SLICE 1): idempotent create of a shared sub-account or a dedicated box, generation of the transient
// one-time password, and the NON-SECRET target descriptor that rides ConfigJSON to the controller. The
// controller-side apply-bridge (SLICE 2) and escrow auto-confirm (SLICE 3) are out of scope here.
//
// Fail-closed: any API/action error returns without a provisioned resource being recorded — the caller
// must NOT mark offsite enabled/served on error. Idempotent: every create is guarded by a label lookup
// first (box/sub-account names are not unique — SPIKE §2).
package offsite

import (
	"context"
	"crypto/rand"
	"encoding/json"
	"fmt"
	"log"
	"math/big"
	"strings"
	"time"

	"gitea.dooplex.hu/admin/felhom-hub/internal/hetznerapi"
	"gitea.dooplex.hu/admin/felhom-hub/internal/store"
)

// sftpPort is the storage-box SSH/SFTP port (SPIKE: 23).
const sftpPort = 23

// Descriptor is the NON-SECRET offsite target that rides ConfigJSON to the controller. It NEVER carries
// the password or the SSH key.
type Descriptor struct {
	Enabled  bool   `json:"enabled"`
	Type     string `json:"type,omitempty"`      // "shared" | "dedicated"
	Host     string `json:"host,omitempty"`      // <user>.your-storagebox.de (dedicated) / <user>-subN… (shared)
	User     string `json:"user,omitempty"`
	Port     int    `json:"port,omitempty"`      // 23
	RepoPath string `json:"repo_path,omitempty"` // /home/<repo>
	QuotaGB  int    `json:"quota_gb,omitempty"`  // shared soft-quota (Felhom-enforced; no native lever)
	BoxType  string `json:"box_type,omitempty"`  // dedicated (Hetzner-hard quota via the type)
	// HostFingerprint is the box's SSH host-key fingerprint (SHA256:…), captured at provision so the
	// controller VERIFIES the box identity instead of blind-TOFU (SLICE 2). Non-secret.
	HostFingerprint string `json:"host_fingerprint,omitempty"`
}

// HostKeyScanner returns a box's SSH host-key fingerprint (SHA256:…). Seam'd so tests inject a fake.
type HostKeyScanner interface {
	Fingerprint(ctx context.Context, host string, port int) (string, error)
}

// Input is the operator's offsite choice.
type Input struct {
	Enabled bool
	Type    string // "shared" | "dedicated"
	QuotaGB int    // shared
	BoxType string // dedicated, e.g. "bx11"
}

// Provisioner provisions offsite resources. It depends on the CloudAPI interface (tests inject a fake).
type Provisioner struct {
	API       hetznerapi.CloudAPI
	Store     *store.Store
	Scanner   HostKeyScanner // captures the box host-key fingerprint (fail-closed if nil/scan-fails)
	PoolBoxID int64          // the shared-pool storage-box id (e.g. 611421)
	Location  string         // dedicated-box location, e.g. "fsn1"
	Logger    *log.Logger
	// ScanBackoff is the retry schedule for the host-key scan (F2: a fresh sub-account's DNS name lags
	// creation by seconds-to-a-minute, so the first scan typically fails with "no such host"). nil → the
	// default ~60s ladder. Tests inject zeros. The total must fit inside applyOffsite's 3-min detached ctx.
	ScanBackoff []time.Duration
}

// defaultScanBackoff: 5 retries, ~60s total — sized to the observed DNS propagation lag.
var defaultScanBackoff = []time.Duration{2 * time.Second, 4 * time.Second, 8 * time.Second, 16 * time.Second, 30 * time.Second}

func (p *Provisioner) logf(f string, a ...any) {
	if p.Logger != nil {
		p.Logger.Printf(f, a...)
	}
}

// customerLabel is the idempotency/teardown key.
func customerLabel(customerID string) map[string]string { return map[string]string{"felhom-customer": customerID} }
func customerSelector(customerID string) string         { return "felhom-customer=" + customerID }

// repoPath is the controller-facing RepoPath — each account is chrooted, /home is writable (SPIKE).
const repoPath = "/home/felhom-repo"

// ProvisionOffsite ensures the customer's offsite resource exists and returns the non-secret descriptor.
// On a fresh create it generates + stores the one-time password (Store.SaveOneTimeSecret). On an existing
// resource (found by label) it is a no-op create → returns the descriptor without a new password. The
// caller merges the descriptor into ConfigJSON and saves. Disable → returns {Enabled:false} (NO deprovision).
func (p *Provisioner) ProvisionOffsite(ctx context.Context, customerID string, in Input) (*Descriptor, error) {
	if !in.Enabled {
		return &Descriptor{Enabled: false}, nil
	}
	var d *Descriptor
	var err error
	switch in.Type {
	case "shared":
		d, err = p.provisionShared(ctx, customerID, in)
	case "dedicated":
		d, err = p.provisionDedicated(ctx, customerID, in)
	default:
		return nil, fmt.Errorf("offsite: unknown type %q (want shared|dedicated)", in.Type)
	}
	if err != nil {
		return nil, err
	}
	// Capture the box host-key fingerprint so the controller verifies (no blind TOFU). Fail-closed: don't
	// serve a descriptor the controller can't verify. Applies to both fresh and idempotent paths.
	if p.Scanner == nil {
		return nil, fmt.Errorf("offsite: no host-key scanner configured (cannot capture the pin)")
	}
	port := d.Port
	if port == 0 {
		port = sftpPort
	}
	fp, err := p.scanWithRetry(ctx, d.Host, port)
	if err != nil {
		return nil, fmt.Errorf("offsite: host-key scan %s: %w", d.Host, err)
	}
	d.HostFingerprint = fp
	return d, nil
}

// scanWithRetry retries the host-key scan on failure (F2: fresh-resource DNS lag). Fail-closed past the
// budget; ctx cancellation aborts between attempts.
func (p *Provisioner) scanWithRetry(ctx context.Context, host string, port int) (string, error) {
	backoff := p.ScanBackoff
	if backoff == nil {
		backoff = defaultScanBackoff
	}
	fp, err := p.Scanner.Fingerprint(ctx, host, port)
	for i := 0; err != nil && i < len(backoff); i++ {
		p.logf("[offsite] host-key scan %s failed (attempt %d/%d, retrying in %s): %v", host, i+1, len(backoff)+1, backoff[i], err)
		select {
		case <-ctx.Done():
			return "", ctx.Err()
		case <-time.After(backoff[i]):
		}
		fp, err = p.Scanner.Fingerprint(ctx, host, port)
	}
	return fp, err
}

// ReissueCredentials resets the customer's offsite credential and stores a FRESH one-time password — the
// EXPLICIT operator recovery for a consumed-password dead-end (a fresh guest at DR, or a
// consumed-but-failed install). It is NOT implicit rotation: ProvisionOffsite never calls this. Scoped
// hard: the reset targets ONLY the resource labelled `felhom-customer=<id>`, and refuses unless the label
// lookup finds exactly one. The password value is never logged (the action is).
func (p *Provisioner) ReissueCredentials(ctx context.Context, customerID, typ string) error {
	pw, err := genPassword()
	if err != nil {
		return err
	}
	switch typ {
	case "shared":
		if p.PoolBoxID == 0 {
			return fmt.Errorf("offsite: no shared pool box configured")
		}
		subs, err := p.API.ListSubaccounts(ctx, p.PoolBoxID, customerSelector(customerID))
		if err != nil {
			return fmt.Errorf("offsite: reissue lookup: %w", err)
		}
		if len(subs) != 1 {
			return fmt.Errorf("offsite: reissue needs exactly 1 sub-account labelled for %s, found %d — refusing", customerID, len(subs))
		}
		act, err := p.API.ResetSubaccountPassword(ctx, p.PoolBoxID, subs[0].ID, pw)
		if err != nil {
			return fmt.Errorf("offsite: reset sub-account password: %w", err)
		}
		if err := p.API.WaitAction(ctx, act); err != nil {
			return fmt.Errorf("offsite: reset action: %w", err)
		}
		p.logf("[offsite] re-issued shared credentials for %s (subaccount %d)", customerID, subs[0].ID)
	case "dedicated":
		boxes, err := p.API.ListStorageBoxes(ctx, customerSelector(customerID))
		if err != nil {
			return fmt.Errorf("offsite: reissue lookup: %w", err)
		}
		if len(boxes) != 1 {
			return fmt.Errorf("offsite: reissue needs exactly 1 box labelled for %s, found %d — refusing", customerID, len(boxes))
		}
		act, err := p.API.ResetBoxPassword(ctx, boxes[0].ID, pw)
		if err != nil {
			return fmt.Errorf("offsite: reset box password: %w", err)
		}
		if err := p.API.WaitAction(ctx, act); err != nil {
			return fmt.Errorf("offsite: reset action: %w", err)
		}
		p.logf("[offsite] re-issued dedicated credentials for %s (box %d)", customerID, boxes[0].ID)
	default:
		return fmt.Errorf("offsite: reissue: unknown type %q (want shared|dedicated)", typ)
	}
	if err := p.Store.SaveOneTimeSecret(customerID, pw); err != nil {
		return fmt.Errorf("offsite: store re-issued one-time password: %w", err)
	}

	// v0.57.0 (2.3, the escrow-honesty fix). ⚠ ITS STATED REASON WAS FALSE AND IS CORRECTED HERE
	// (R-196, 2026-08-04). The comment used to read "the restic repo password just changed" — this
	// function does NOT change it and CANNOT: the repository password is generated on the box
	// (controller `WriteOffboxSecrets`) and never leaves it except sealed inside the R-wrapped escrow.
	// What this function changes is the PROVIDER account password (①), which is a different secret at
	// a different layer. The false premise survived because the EFFECT (a stale escrow) is real, so
	// nobody checked the CAUSE — and it sent two separate investigations the wrong way in one day
	// (audits/SPIKE-offsite-credential-recovery-2026-08-04.md Q4).
	//
	// WHY THE MARK IS STILL MADE, on honest grounds: a re-issue is the operator's response to a
	// broken delivery, and the box's re-apply may mint a fresh repository password (it does exactly
	// that whenever `<DataDir>/offbox/repo_password` is absent — the guest-rebuild shape). The mark is
	// therefore PRECAUTIONARY, not evidential. The evidential signal is R-197's
	// `offsite_repo_key_changed`, which fires on a measured hash difference at the next ceremony.
	// KNOWN CONSEQUENCE, left in place deliberately: on the ordinary re-issue shape — a box that still
	// holds its repo_password file — the password does NOT change, so this marks a healthy escrow
	// stale and asks the customer for an unnecessary ceremony. R-196 stays OPEN for that; it is a
	// behaviour change, not a comment fix, and it must not ride a comment-correction commit.
	//
	// Mark the escrow stale so the hub stops advertising "ceremony done" and the customer's escrow
	// wizard is offered again; a fresh ceremony seals the current password and clears the flag. Every
	// credential change also emits a visible customer event (offsite_reissued always; escrow_stale
	// only when a blob was invalidated). Best-effort: the password reset already succeeded — a
	// bookkeeping failure here must not fail it.
	escrowStaled := false
	if host, herr := p.Store.GetHostByCustomer(customerID); herr == nil && host != nil {
		if esc, eerr := p.Store.GetHostEscrow(host.HostID); eerr == nil && esc != nil {
			if serr := p.Store.MarkEscrowStale(host.HostID); serr != nil {
				p.logf("[offsite] WARN mark-escrow-stale for %s: %v", customerID, serr)
			} else {
				escrowStaled = true
			}
		}
	}
	if _, serr := p.Store.SaveEvent(customerID, "offsite_reissued", "info",
		"Az offsite (házon kívüli) mentési hozzáférést újra kiadtuk — az új egyszeri jelszót a vezérlő a következő frissítéskor átveszi.",
		"", "hub"); serr != nil {
		p.logf("[offsite] WARN save offsite_reissued event for %s: %v", customerID, serr)
	}
	if escrowStaled {
		if _, serr := p.Store.SaveEvent(customerID, "escrow_stale", "warning",
			"A helyreállítási kulcs-letét elavult az offsite jelszó cseréje miatt — futtasd le újra a helyreállítási szertartást (Biztonsági mentés → Helyreállítás).",
			"", "hub"); serr != nil {
			p.logf("[offsite] WARN save escrow_stale event for %s: %v", customerID, serr)
		}
	}
	return nil
}

// OffsiteIdentifier returns the customer's provisioned offsite name (sub-account username / box name)
// for the RESET preview inventory, "" if none is provisioned. Read-only.
func (p *Provisioner) OffsiteIdentifier(ctx context.Context, customerID, typ string) (string, error) {
	switch typ {
	case "dedicated":
		boxes, err := p.API.ListStorageBoxes(ctx, customerSelector(customerID))
		if err != nil || len(boxes) == 0 {
			return "", err
		}
		return boxes[0].Name, nil
	default: // shared / ""
		if p.PoolBoxID == 0 {
			return "", nil
		}
		subs, err := p.API.ListSubaccounts(ctx, p.PoolBoxID, customerSelector(customerID))
		if err != nil || len(subs) == 0 {
			return "", err
		}
		return subs[0].Username, nil
	}
}

// Deprovision DELETES the customer's offsite storage — the RESET teardown (v0.61.0). The offsite repo
// DATA dies with the sub-account/box; irreversible, gated by the operator RESET confirm. IDEMPOTENT:
// zero labelled sub-accounts/boxes = already gone = success (a re-run after a partial reset does not
// error). The id is re-derived by the customer label each time — nothing stored to go stale.
func (p *Provisioner) Deprovision(ctx context.Context, customerID, typ string) error {
	switch typ {
	case "dedicated":
		boxes, err := p.API.ListStorageBoxes(ctx, customerSelector(customerID))
		if err != nil {
			return fmt.Errorf("offsite: deprovision lookup: %w", err)
		}
		if len(boxes) == 0 {
			p.logf("[offsite] deprovision: no box labelled for %s — already gone", customerID)
			return nil
		}
		for _, b := range boxes {
			act, err := p.API.DeleteStorageBox(ctx, b.ID)
			if err != nil {
				return fmt.Errorf("offsite: delete box %d: %w", b.ID, err)
			}
			if err := p.API.WaitAction(ctx, act); err != nil {
				return fmt.Errorf("offsite: delete box action: %w", err)
			}
			p.logf("[offsite] deprovisioned dedicated box %d for %s (repo data destroyed)", b.ID, customerID)
		}
		return nil
	default: // shared / ""
		if p.PoolBoxID == 0 {
			return fmt.Errorf("offsite: no shared pool box configured")
		}
		subs, err := p.API.ListSubaccounts(ctx, p.PoolBoxID, customerSelector(customerID))
		if err != nil {
			return fmt.Errorf("offsite: deprovision lookup: %w", err)
		}
		if len(subs) == 0 {
			p.logf("[offsite] deprovision: no sub-account labelled for %s — already gone", customerID)
			return nil
		}
		for _, sub := range subs {
			act, err := p.API.DeleteSubaccount(ctx, p.PoolBoxID, sub.ID)
			if err != nil {
				return fmt.Errorf("offsite: delete sub-account %d: %w", sub.ID, err)
			}
			if err := p.API.WaitAction(ctx, act); err != nil {
				return fmt.Errorf("offsite: delete sub-account action: %w", err)
			}
			p.logf("[offsite] deprovisioned shared sub-account %d for %s (repo data destroyed)", sub.ID, customerID)
		}
		return nil
	}
}

func (p *Provisioner) provisionShared(ctx context.Context, customerID string, in Input) (*Descriptor, error) {
	if p.PoolBoxID == 0 {
		return nil, fmt.Errorf("offsite: no shared pool box configured")
	}
	// Idempotency: an existing labelled sub-account is reused (no second create).
	existing, err := p.API.ListSubaccounts(ctx, p.PoolBoxID, customerSelector(customerID))
	if err != nil {
		return nil, fmt.Errorf("offsite: list subaccounts: %w", err)
	}
	if len(existing) > 0 {
		s := existing[0]
		p.logf("[offsite] shared already provisioned for %s (subaccount %d)", customerID, s.ID)
		return &Descriptor{Enabled: true, Type: "shared", Host: s.Server, User: s.Username, Port: sftpPort, RepoPath: repoPath, QuotaGB: in.QuotaGB}, nil
	}
	// Fresh create: generate the transient password, create, wait, fetch the full object.
	pw, err := genPassword()
	if err != nil {
		return nil, err
	}
	id, action, err := p.API.CreateSubaccount(ctx, p.PoolBoxID, hetznerapi.CreateSubaccountRequest{
		HomeDirectory:  "felhom-" + customerID,
		Password:       pw,
		AccessSettings: hetznerapi.AccessSettings{SSHEnabled: true, ReachableExternally: true},
		Labels:         customerLabel(customerID),
		Description:    "felhom offsite " + customerID,
	})
	if err != nil {
		return nil, fmt.Errorf("offsite: create subaccount: %w", err)
	}
	if err := p.API.WaitAction(ctx, action); err != nil {
		return nil, fmt.Errorf("offsite: subaccount create action: %w", err)
	}
	sub, err := p.API.GetSubaccount(ctx, p.PoolBoxID, id)
	if err != nil {
		return nil, fmt.Errorf("offsite: fetch subaccount: %w", err)
	}
	if err := p.Store.SaveOneTimeSecret(customerID, pw); err != nil {
		return nil, fmt.Errorf("offsite: store one-time password: %w", err)
	}
	p.logf("[offsite] shared provisioned for %s (subaccount %d, user %s)", customerID, sub.ID, sub.Username)
	return &Descriptor{Enabled: true, Type: "shared", Host: sub.Server, User: sub.Username, Port: sftpPort, RepoPath: repoPath, QuotaGB: in.QuotaGB}, nil
}

func (p *Provisioner) provisionDedicated(ctx context.Context, customerID string, in Input) (*Descriptor, error) {
	boxType := in.BoxType
	if boxType == "" {
		boxType = "bx11"
	}
	existing, err := p.API.ListStorageBoxes(ctx, customerSelector(customerID))
	if err != nil {
		return nil, fmt.Errorf("offsite: list boxes: %w", err)
	}
	if len(existing) > 0 {
		b := existing[0]
		p.logf("[offsite] dedicated already provisioned for %s (box %d)", customerID, b.ID)
		return &Descriptor{Enabled: true, Type: "dedicated", Host: b.Server, User: b.Username, Port: sftpPort, RepoPath: repoPath, BoxType: boxType}, nil
	}
	pw, err := genPassword()
	if err != nil {
		return nil, err
	}
	id, action, err := p.API.CreateStorageBox(ctx, hetznerapi.CreateBoxRequest{
		Name:           "felhom-" + customerID,
		StorageBoxType: boxType,
		Location:       p.Location,
		Password:       pw,
		AccessSettings: hetznerapi.AccessSettings{SSHEnabled: true, ReachableExternally: true},
		Labels:         customerLabel(customerID),
	})
	if err != nil {
		return nil, fmt.Errorf("offsite: create box: %w", err)
	}
	if err := p.API.WaitAction(ctx, action); err != nil {
		return nil, fmt.Errorf("offsite: box create action: %w", err)
	}
	box, err := p.API.GetStorageBox(ctx, id)
	if err != nil {
		return nil, fmt.Errorf("offsite: fetch box: %w", err)
	}
	if err := p.Store.SaveOneTimeSecret(customerID, pw); err != nil {
		return nil, fmt.Errorf("offsite: store one-time password: %w", err)
	}
	p.logf("[offsite] dedicated provisioned for %s (box %d, user %s)", customerID, box.ID, box.Username)
	return &Descriptor{Enabled: true, Type: "dedicated", Host: box.Server, User: box.Username, Port: sftpPort, RepoPath: repoPath, BoxType: boxType}, nil
}

// SetOffsiteFrozen freezes/unfreezes the customer's SHARED sub-account (SLICE 4: readonly access) — an
// OPERATOR lever, NEVER automatic: freezing also blocks prune/forget, which is the customer's only way
// DOWN from over-quota, so only a human weighs that trade-off. Same exactly-1 label guard as the
// re-issue. Preserves the sub-account's other access settings (SSH must stay on — only readonly flips).
// Dedicated boxes have no freeze path (Hetzner enforces their size physically; the UI hides the button).
func (p *Provisioner) SetOffsiteFrozen(ctx context.Context, customerID string, frozen bool) error {
	if p.PoolBoxID == 0 {
		return fmt.Errorf("offsite: no shared pool box configured")
	}
	subs, err := p.API.ListSubaccounts(ctx, p.PoolBoxID, customerSelector(customerID))
	if err != nil {
		return fmt.Errorf("offsite: freeze lookup: %w", err)
	}
	if len(subs) != 1 {
		return fmt.Errorf("offsite: freeze needs exactly 1 sub-account labelled for %s, found %d — refusing", customerID, len(subs))
	}
	as := subs[0].AccessSettings
	as.Readonly = frozen
	act, err := p.API.UpdateSubaccountAccess(ctx, p.PoolBoxID, subs[0].ID, as)
	if err != nil {
		return fmt.Errorf("offsite: update access: %w", err)
	}
	if err := p.API.WaitAction(ctx, act); err != nil {
		return fmt.Errorf("offsite: freeze action: %w", err)
	}
	p.logf("[offsite] set frozen=%v (readonly) for %s (subaccount %d)", frozen, customerID, subs[0].ID)
	return nil
}

// MergeDescriptor merges the offsite descriptor under the "offsite" key of a ConfigJSON object, preserving
// all other keys. Returns the new ConfigJSON string. NEVER carries a secret (Descriptor is non-secret).
// ClearProvisionedDescriptor returns config_json with the offsite descriptor reset to its
// pre-first-install shape — the customer-RESET clear (v0.61.0). The TIER CHOICE
// (enabled/type/quota_gb/box_type — customer config, SURVIVES a RESET) is kept; every PROVISIONED
// field (host/user/port/repo_path/host_fingerprint — operational state, DIES with the Hetzner
// resource) is cleared, so re-onboarding re-provisions fresh against the retained choice. No-op-safe:
// an absent/empty offsite block returns the input unchanged.
func ClearProvisionedDescriptor(configJSON string) (string, error) {
	cur, err := ReadDescriptor(configJSON)
	if err != nil {
		return "", err
	}
	if cur == nil {
		return configJSON, nil // no offsite block — nothing to clear
	}
	cleared := &Descriptor{Enabled: cur.Enabled, Type: cur.Type, QuotaGB: cur.QuotaGB, BoxType: cur.BoxType}
	return MergeDescriptor(configJSON, cleared)
}

// ReadDescriptor extracts the non-secret offsite Descriptor from a customer's ConfigJSON, or (nil, nil)
// when there is no offsite block (never provisioned). This is the AUTHORITATIVE tier/quota source — the
// pool-box Σ(quota) aggregate (v0.64.0, R-5) and the RESET clear both read through it, NEVER the report
// echo (a stale/absent report would undercount the sold promises; ConfigJSON is the operator's intent).
func ReadDescriptor(configJSON string) (*Descriptor, error) {
	obj := map[string]json.RawMessage{}
	if strings.TrimSpace(configJSON) != "" && configJSON != "{}" {
		if err := json.Unmarshal([]byte(configJSON), &obj); err != nil {
			return nil, fmt.Errorf("offsite: parse config_json: %w", err)
		}
	}
	raw, ok := obj["offsite"]
	if !ok {
		return nil, nil
	}
	var d Descriptor
	if err := json.Unmarshal(raw, &d); err != nil {
		return nil, fmt.Errorf("offsite: parse offsite descriptor: %w", err)
	}
	return &d, nil
}

func MergeDescriptor(configJSON string, d *Descriptor) (string, error) {
	obj := map[string]json.RawMessage{}
	if strings.TrimSpace(configJSON) != "" && configJSON != "{}" {
		if err := json.Unmarshal([]byte(configJSON), &obj); err != nil {
			return "", fmt.Errorf("offsite: parse config_json: %w", err)
		}
	}
	db, err := json.Marshal(d)
	if err != nil {
		return "", err
	}
	obj["offsite"] = db
	out, err := json.Marshal(obj)
	if err != nil {
		return "", err
	}
	return string(out), nil
}

// genPassword returns a transient password satisfying the Hetzner 4-class policy (upper+lower+digit+special).
func genPassword() (string, error) {
	const alnum = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"
	b := make([]byte, 24)
	for i := range b {
		n, err := rand.Int(rand.Reader, big.NewInt(int64(len(alnum))))
		if err != nil {
			return "", err
		}
		b[i] = alnum[n.Int64()]
	}
	// Guarantee all four classes (transient + single-use + reset after install).
	return string(b) + "Aa9%", nil
}