felhom-agent/internal/escrow/identity.go

package escrow

import (
	"context"
	"encoding/base64"
	"encoding/json"
	"fmt"
	"os"
	"path/filepath"
	"strings"
)

// Slice 10D.1 — IDENTITY escrow. The K-escrow (above) wraps the PBS *encryption key* via the
// PBS-native scrypt path. The identity bundle `{tunnel_token, pbs_token}` is arbitrary secret bytes
// (not a PBS key), so it is wrapped under the SAME recovery code `R` with **age** (`age -p`: scrypt
// + ChaCha20-Poly1305 — a vetted passphrase-AEAD, not hand-rolled). Same two-factor, zero-knowledge
// shape as the K-escrow: the blob is opaque without `R`; `R` is the only out-of-band secret. The
// K-escrow + the 10C `Consume` path are UNTOUCHED — this is purely additive. Proven by the slice-10D
// identity-restore spike (documentation/tests/slice10d-identity-restore-spike-findings.md).
//
// age is a runtime dependency for the identity path (analogous to proxmox-backup-client for K).
var ageBinary = "/usr/bin/age"

// IdentityBundle is the box's recoverable identity — the secrets a re-enrolling box needs to come
// back "as host X". Carried only inside the R-wrapped blob; never stored or logged in the clear.
type IdentityBundle struct {
	TunnelToken string `json:"tunnel_token"` // the Cloudflare tunnel connector token
	PBSToken    string `json:"pbs_token"`    // the PBS access token (steady-state; rotated on re-establish)
	// WGPrivateKey is the offsite WG tunnel private key (S3; base64, 32 bytes). OPTIONAL: escrow
	// blobs created before S3 lack it and CANNOT be retro-fitted (R is never retained) — S5 DR
	// falls back to fresh-key re-registration, which keeps the box's /32 (hub S2 re-key-in-place).
	WGPrivateKey string `json:"wg_private_key,omitempty"`
	// ResticRepoPassword is the offsite restic repo password (fork-4). OPTIONAL: escrow blobs created
	// before fork-4 lack it and CANNOT be retro-fitted (R is never retained). It is the DATA key for the
	// offsite tier — irreplaceable (unlike the SFTP access key, which is regenerable at DR). The
	// controller's atomicity gate ensures no offsite ciphertext exists until this is escrowed.
	ResticRepoPassword string `json:"restic_repo_password,omitempty"`
}

// StagedResticPasswordPath is the well-known 0600 file where the controller-pushed restic repo password
// is transiently staged (by the local API) for the escrow-create ceremony to pick up, then wiped. A fixed
// path so the local-API writer and the CLI ceremony reader agree without threading config through.
func StagedResticPasswordPath() string {
	return filepath.Join("/var/lib/felhom-agent", "escrow-stage", "restic_repo_password")
}

// WipeStagedResticPassword removes the staged restic password (called by the ceremony after a successful
// escrow-create — the secret now lives only inside the R-wrapped blob). A missing file is a clean no-op.
func WipeStagedResticPassword() error {
	if err := os.Remove(StagedResticPasswordPath()); err != nil && !os.IsNotExist(err) {
		return fmt.Errorf("escrow: wipe staged restic password: %w", err)
	}
	return nil
}

// AttachResticPassword injects the offsite restic repo password from the staged 0600 file into the bundle
// when it exists (fork-4 escrow-create auto-inject). Returns whether it attached. The VALUE is validated
// (non-empty) but NEVER logged by callers — log the field NAME only (mirrors AttachWGKey). A missing file
// is a clean no-attach (pre-fork-4 behavior, byte-compatible bundle).
func AttachResticPassword(b *IdentityBundle, stagePath string) (bool, error) {
	raw, err := os.ReadFile(stagePath)
	if err != nil {
		if os.IsNotExist(err) {
			return false, nil
		}
		return false, fmt.Errorf("escrow: reading staged restic password: %w", err)
	}
	pw := strings.TrimSpace(string(raw))
	if pw == "" {
		return false, fmt.Errorf("escrow: staged restic password file %s is empty", stagePath)
	}
	b.ResticRepoPassword = pw
	return true, nil
}

// AttachWGKey injects the offsite WG private key into the bundle when the key file exists (S3
// escrow-create auto-inject). Returns whether it attached. The VALUE is validated (base64, 32
// bytes) but never logged by callers — log the field NAME only. A missing key file is a clean
// no-attach (pre-S3 behavior, byte-compatible bundle); a corrupt one is an error (the operator
// should know their escrow would silently lack a live identity).
func AttachWGKey(b *IdentityBundle, keyPath string) (bool, error) {
	raw, err := os.ReadFile(keyPath)
	if err != nil {
		if os.IsNotExist(err) {
			return false, nil
		}
		return false, fmt.Errorf("escrow: reading wg key file: %w", err)
	}
	s := strings.TrimSpace(string(raw))
	dec, err := base64.StdEncoding.DecodeString(s)
	if err != nil || len(dec) != 32 {
		return false, fmt.Errorf("escrow: wg key file %s is corrupt (not 32-byte base64)", keyPath)
	}
	b.WGPrivateKey = s
	return true, nil
}

// WrapIdentity wraps arbitrary bundle bytes under `R` via `age -p` (scrypt + ChaCha20-Poly1305) and
// returns the opaque blob. `R` is fed via the pty (2 prompts: passphrase + confirm); the plaintext
// and ciphertext flow as files, so only `R` touches the tty (never logged).
func WrapIdentity(ctx context.Context, bundle []byte, recoveryCode string) ([]byte, error) {
	if len(bundle) == 0 {
		return nil, fmt.Errorf("escrow: WrapIdentity needs a non-empty bundle")
	}
	if recoveryCode == "" {
		return nil, fmt.Errorf("escrow: WrapIdentity needs the recovery code (R)")
	}
	work, err := os.MkdirTemp("", "felhom-idesc-")
	if err != nil {
		return nil, fmt.Errorf("escrow: tempdir: %w", err)
	}
	defer os.RemoveAll(work)
	in, out := filepath.Join(work, "bundle"), filepath.Join(work, "blob")
	if err := os.WriteFile(in, bundle, 0o600); err != nil {
		return nil, fmt.Errorf("escrow: stage bundle: %w", err)
	}
	// `age -p -o <out> <in>` prompts the passphrase + confirm (2) and writes the armored blob.
	if err := runWithPassphrase(ctx, recoveryCode, 2, ageBinary, "-p", "-a", "-o", out, in); err != nil {
		return nil, fmt.Errorf("escrow: identity wrap (age -p): %w", err)
	}
	return os.ReadFile(out)
}

// UnwrapIdentity recovers the bundle bytes from an age blob with `R`. A WRONG R fails CLOSED at the
// scrypt KDF (`age -d` nonzero exit, no plaintext emitted) — never a plausible-but-wrong bundle.
func UnwrapIdentity(ctx context.Context, blob []byte, recoveryCode string) ([]byte, error) {
	if len(blob) == 0 {
		return nil, fmt.Errorf("escrow: UnwrapIdentity needs a non-empty blob")
	}
	if recoveryCode == "" {
		return nil, fmt.Errorf("escrow: UnwrapIdentity needs the recovery code (R)")
	}
	work, err := os.MkdirTemp("", "felhom-idesc-")
	if err != nil {
		return nil, fmt.Errorf("escrow: tempdir: %w", err)
	}
	defer os.RemoveAll(work)
	in, out := filepath.Join(work, "blob"), filepath.Join(work, "bundle")
	if err := os.WriteFile(in, blob, 0o600); err != nil {
		return nil, fmt.Errorf("escrow: stage blob: %w", err)
	}
	// `age -d -o <out> <in>` prompts the passphrase (1).
	if err := runWithPassphrase(ctx, recoveryCode, 1, ageBinary, "-d", "-o", out, in); err != nil {
		return nil, fmt.Errorf("escrow: the recovery code did not unwrap the identity escrow (wrong recovery code, or a corrupt blob): %w", err)
	}
	return os.ReadFile(out)
}

// WrapIdentityBundle marshals + wraps an IdentityBundle under R.
func WrapIdentityBundle(ctx context.Context, b IdentityBundle, recoveryCode string) ([]byte, error) {
	raw, err := json.Marshal(b)
	if err != nil {
		return nil, fmt.Errorf("escrow: marshal identity bundle: %w", err)
	}
	return WrapIdentity(ctx, raw, recoveryCode)
}

// UnwrapIdentityBundle unwraps + parses an IdentityBundle (slice 10D.3 restore-mode consumption).
func UnwrapIdentityBundle(ctx context.Context, blob []byte, recoveryCode string) (IdentityBundle, error) {
	raw, err := UnwrapIdentity(ctx, blob, recoveryCode)
	if err != nil {
		return IdentityBundle{}, err
	}
	var b IdentityBundle
	if err := json.Unmarshal(raw, &b); err != nil {
		return IdentityBundle{}, fmt.Errorf("escrow: recovered identity bundle is malformed: %w", err)
	}
	return b, nil
}