feat(t-paliad-151) RemotePaliadinService + main.go env-var routing

Phase B step 2: lands the Paliadin backend that talks to mRiver via ssh + paliadin-shim. Local backend untouched — selection happens in cmd/server/main.go based on PALIADIN_REMOTE_HOST. Files: - internal/services/paliadin_remote.go (new) — RemotePaliadinService + RemotePaliadinConfig, with five SSH knobs (Host/Port/User/KeyPath/ KnownHostsPath). RunTurn does insertTurnRow → healthGate → bootstrap → callShim run-turn → splitTrailer → completeTurn, mirroring the local path's audit-row contract. ResetSession sends shim 'reset'. callShim runs `ssh -F /dev/null -i <key> -p <port> -o … host -- verb args`; ControlMaster intentionally not enabled (design §6.8). - internal/services/paliadin_remote.go also adds DisabledPaliadinService (returns ErrPaliadinDisabled from RunTurn/ResetSession; DB methods inherited from paliadinDB still work) so cmd/server/main.go can wire a non-nil Paliadin even when neither local tmux nor remote SSH is available. - ErrMRiverUnreachable sentinel for the friendly error code. - classifySSHError translates ssh exit 124 / Permission denied / network errors into the audit-row error_code field. - Compile-time conformance: var _ Paliadin = (*Local|*Remote|*Disabled) PaliadinService(nil). cmd/server/main.go switch: PALIADIN_REMOTE_HOST set → NewRemotePaliadinService else: tmux on PATH → NewLocalPaliadinService else: NewDisabledPaliadinService buildPaliadinRemoteConfig materialises PALIADIN_SSH_PRIVATE_KEY + PALIADIN_KNOWN_HOSTS (multi-line Dokploy secrets) into chmod-600/644 tmpfiles at boot. Defaults: SSHUser=m, SSHPort=22022 (bypasses Tailscale SSH on :22, see design §4.5). Fails fast on a configured remote-host without the matching key/known_hosts secrets. Local-tmux mode now requires `tmux` actually be on PATH at boot (exec.LookPath gate); previously the constructor unconditionally returned a service whose RunTurn would fail at runtime with ErrTmuxUnavailable. The handler-level "friendly error" UX is unchanged: DisabledPaliadinService surfaces ErrPaliadinDisabled which the frontend renders the same way. Build green; existing paliadin_test.go still passes (it tests package-level helpers, untouched). Remote-specific tests land in B4. Refs m/paliad#12
2026-05-08 02:16:50 +02:00
parent 56a3dc961e
commit 0c8a2f1a95
2 changed files with 433 additions and 14 deletions
--- a/cmd/server/main.go
+++ b/cmd/server/main.go
@@ -2,10 +2,13 @@ package main

 import (
 	"context"
+	"fmt"
 	"log"
 	"net/http"
 	"os"
+	"os/exec"
 	"os/signal"
+	"strconv"
 	"syscall"

 	// Embed Go's IANA tz database into the binary so time.LoadLocation works
@@ -165,20 +168,34 @@ func main() {
 			CardLayout:     services.NewCardLayoutService(pool),
 		}

-		// t-paliad-146 — Paliadin PoC. Always wired when DATABASE_URL
-		// is set; the per-request handler gate (requirePaliadinOwner)
-		// restricts access to the single owner email
-		// (services.PaliadinOwnerEmail). All other authenticated users
-		// get a 404 — the route effectively does not exist for them.
-		// On hosts without tmux + the `claude` CLI (e.g. the Dokploy
-		// container), the owner gate still applies; if m ever hits the
-		// route from such a host, the service returns "tmux unavailable"
-		// without ever invoking shell-out.
-		tmuxSession := os.Getenv("PALIADIN_TMUX_SESSION")
-		responseDir := os.Getenv("PALIADIN_RESPONSE_DIR")
-		svcBundle.Paliadin = services.NewLocalPaliadinService(pool, users, tmuxSession, responseDir)
-		log.Printf("paliadin: wired (owner=%s; gate is per-request, not per-deploy)",
-			services.PaliadinOwnerEmail)
+		// Paliadin backend selection (t-paliad-146 + t-paliad-151):
+		//   PALIADIN_REMOTE_HOST set → RemotePaliadinService (ssh to mRiver)
+		//   else: local tmux available → LocalPaliadinService (PoC path)
+		//   else: DisabledPaliadinService (handlers still 404 for non-owners
+		//         via the gate; for m, RunTurn returns ErrPaliadinDisabled
+		//         which surfaces as a friendly error).
+		//
+		// All three implement services.Paliadin; the per-request handler
+		// gate (requirePaliadinOwner) is unchanged and applies to every
+		// backend.
+		if remoteHost := os.Getenv("PALIADIN_REMOTE_HOST"); remoteHost != "" {
+			cfg, err := buildPaliadinRemoteConfig(remoteHost)
+			if err != nil {
+				log.Fatalf("paliadin: remote config: %v", err)
+			}
+			svcBundle.Paliadin = services.NewRemotePaliadinService(pool, users, cfg)
+			log.Printf("paliadin: remote mode → ssh %s@%s:%d (owner=%s)",
+				cfg.SSHUser, cfg.SSHHost, cfg.SSHPort, services.PaliadinOwnerEmail)
+		} else if _, err := exec.LookPath("tmux"); err == nil {
+			tmuxSession := os.Getenv("PALIADIN_TMUX_SESSION")
+			responseDir := os.Getenv("PALIADIN_RESPONSE_DIR")
+			svcBundle.Paliadin = services.NewLocalPaliadinService(pool, users, tmuxSession, responseDir)
+			log.Printf("paliadin: local tmux mode (owner=%s)", services.PaliadinOwnerEmail)
+		} else {
+			svcBundle.Paliadin = services.NewDisabledPaliadinService(pool, users)
+			log.Printf("paliadin: disabled (no PALIADIN_REMOTE_HOST, no local tmux; owner=%s)",
+				services.PaliadinOwnerEmail)
+		}
 		// Wire ApprovalService into the entity services so Create / Update /
 		// Complete / Delete consult paliad.approval_policies (t-paliad-138).
 		// Without this wiring, the policies and request tables exist but no
@@ -217,3 +234,83 @@ func main() {
 		log.Fatal(err)
 	}
 }
+
+// buildPaliadinRemoteConfig assembles a RemotePaliadinConfig from
+// environment variables, materialising the SSH private key and
+// known_hosts blobs into chmod-600/644 tmpfiles for OpenSSH to read.
+//
+// The blobs travel as Dokploy secrets (multi-line env vars). We never
+// persist them to disk — tmpfiles live for the process lifetime in
+// /tmp and disappear on container restart. Re-creating them every boot
+// is fine; the keys themselves rotate independently via Dokploy
+// secret updates.
+//
+// Required: PALIADIN_REMOTE_HOST, PALIADIN_SSH_PRIVATE_KEY, PALIADIN_KNOWN_HOSTS.
+// Optional: PALIADIN_REMOTE_USER (default "m"), PALIADIN_REMOTE_PORT
+// (default 22022 — bypasses Tailscale SSH on :22, see design §4.5).
+func buildPaliadinRemoteConfig(host string) (services.RemotePaliadinConfig, error) {
+	cfg := services.RemotePaliadinConfig{
+		SSHHost: host,
+		SSHUser: cmpOr(os.Getenv("PALIADIN_REMOTE_USER"), "m"),
+		SSHPort: 22022,
+	}
+	if p := os.Getenv("PALIADIN_REMOTE_PORT"); p != "" {
+		n, err := strconv.Atoi(p)
+		if err != nil || n <= 0 || n > 65535 {
+			return cfg, fmt.Errorf("PALIADIN_REMOTE_PORT %q: not a valid port", p)
+		}
+		cfg.SSHPort = n
+	}
+
+	keyPath, err := writeSecretFile("paliadin-id_ed25519-", os.Getenv("PALIADIN_SSH_PRIVATE_KEY"), 0o600)
+	if err != nil {
+		return cfg, fmt.Errorf("PALIADIN_SSH_PRIVATE_KEY: %w", err)
+	}
+	if keyPath == "" {
+		return cfg, fmt.Errorf("PALIADIN_REMOTE_HOST set but PALIADIN_SSH_PRIVATE_KEY empty")
+	}
+	cfg.SSHKeyPath = keyPath
+
+	knownHostsPath, err := writeSecretFile("paliadin-known_hosts-", os.Getenv("PALIADIN_KNOWN_HOSTS"), 0o644)
+	if err != nil {
+		return cfg, fmt.Errorf("PALIADIN_KNOWN_HOSTS: %w", err)
+	}
+	if knownHostsPath == "" {
+		return cfg, fmt.Errorf("PALIADIN_REMOTE_HOST set but PALIADIN_KNOWN_HOSTS empty")
+	}
+	cfg.KnownHostsPath = knownHostsPath
+
+	return cfg, nil
+}
+
+// writeSecretFile writes blob to a tmpfile with the given mode and
+// returns its path. Returns ("", nil) when blob is empty so callers
+// can distinguish "not set" from real I/O errors.
+func writeSecretFile(prefix, blob string, mode os.FileMode) (string, error) {
+	if blob == "" {
+		return "", nil
+	}
+	f, err := os.CreateTemp("", prefix+"*")
+	if err != nil {
+		return "", err
+	}
+	if _, err := f.WriteString(blob); err != nil {
+		_ = f.Close()
+		_ = os.Remove(f.Name())
+		return "", err
+	}
+	if err := f.Close(); err != nil {
+		return "", err
+	}
+	if err := os.Chmod(f.Name(), mode); err != nil {
+		return "", err
+	}
+	return f.Name(), nil
+}
+
+func cmpOr(s, fallback string) string {
+	if s != "" {
+		return s
+	}
+	return fallback
+}
--- a/internal/services/paliadin_remote.go
+++ b/internal/services/paliadin_remote.go
@@ -0,0 +1,322 @@
+package services
+
+// RemotePaliadinService — the prod path of the Paliadin backend.
+//
+// Design: docs/design-paliadin-tailscale-ssh-2026-05-07.md.
+//
+// Where the local backend (LocalPaliadinService) drives a tmux+claude
+// pane in-process, the remote backend shells out to ssh m@mriver
+// paliadin-shim — the script at scripts/paliadin-shim, installed at
+// /home/m/.local/bin/paliadin-shim on m's laptop. The shim owns the
+// tmux+claude pane on mRiver; this Go side just wraps each turn in one
+// SSH call.
+//
+// The path was chosen so paliad.de (deployed in a Dokploy container on
+// mLake, no `claude` CLI of its own) can keep using m's Claude Code
+// subscription instead of paying API tokens. Tailscale provides the
+// transport — mLake's tailscale0 interface is shared into the container
+// via network_mode: host (compose layer; not this file's concern).
+//
+// Wiring is gated on PALIADIN_REMOTE_HOST in cmd/server/main.go. When
+// that env var is unset, the binary falls back to LocalPaliadinService
+// (or DisabledPaliadinService if neither tmux nor remote is available).
+
+import (
+	"bytes"
+	"context"
+	"encoding/base64"
+	"errors"
+	"fmt"
+	"log"
+	"os/exec"
+	"strconv"
+	"strings"
+	"sync"
+	"time"
+
+	"github.com/google/uuid"
+	"github.com/jmoiron/sqlx"
+)
+
+// ErrMRiverUnreachable signals that the remote paliadin-shim could not
+// be contacted within the health-check window. The handler maps this to
+// the friendly mriver_unreachable error code (see frontend
+// friendlyErrorMessage).
+var ErrMRiverUnreachable = errors.New("paliadin: mriver unreachable")
+
+// RemotePaliadinConfig is the bag of knobs cmd/server/main.go passes
+// when constructing a RemotePaliadinService.
+type RemotePaliadinConfig struct {
+	SSHHost        string // 100.99.98.203 — mRiver's tailnet IP
+	SSHPort        int    // 22022 — bypasses Tailscale SSH on :22 (design §4.5)
+	SSHUser        string // m
+	SSHKeyPath     string // /tmp/paliadin-id_ed25519-<rand> (chmod 600)
+	KnownHostsPath string // /tmp/paliadin-known_hosts
+}
+
+// RemotePaliadinService implements Paliadin against a remote
+// paliadin-shim over SSH.
+type RemotePaliadinService struct {
+	paliadinDB
+	cfg RemotePaliadinConfig
+
+	// Single in-flight turn. mRiver's claude pane is single-user; we
+	// serialise turns the same way LocalPaliadinService does.
+	turnMu sync.Mutex
+
+	// Health-check cache. Avoids probing mRiver on every turn — once
+	// the cache is warm, RunTurn skips the probe for 10 seconds.
+	healthMu        sync.Mutex
+	healthOK        bool
+	healthCheckedAt time.Time
+
+	// Lazy bootstrap state. The system prompt only needs to be sent
+	// once per claude pane; on first RunTurn after a paliad restart we
+	// inject it, and remember we did so we don't re-send.
+	bootstrapMu sync.Mutex
+	bootstrapped bool
+
+	// Hook for tests — when non-nil, callShim delegates here instead
+	// of exec'ing ssh. Production code never sets this.
+	callShimHook func(ctx context.Context, args ...string) ([]byte, error)
+}
+
+// NewRemotePaliadinService wires the remote backend. Call only when
+// PALIADIN_REMOTE_HOST is set in the environment; the constructor does
+// not probe mRiver — first probe happens on the first RunTurn call via
+// healthGate.
+func NewRemotePaliadinService(db *sqlx.DB, users *UserService, cfg RemotePaliadinConfig) *RemotePaliadinService {
+	if cfg.SSHPort == 0 {
+		cfg.SSHPort = 22022
+	}
+	if cfg.SSHUser == "" {
+		cfg.SSHUser = "m"
+	}
+	return &RemotePaliadinService{
+		paliadinDB: paliadinDB{db: db, users: users},
+		cfg:        cfg,
+	}
+}
+
+// RunTurn drives one Q&A round against the remote claude pane. Same
+// audit-row contract as LocalPaliadinService: write the row first, run
+// the turn, complete the row on success, mark error on failure.
+func (s *RemotePaliadinService) RunTurn(ctx context.Context, req TurnRequest) (*TurnResult, error) {
+	s.turnMu.Lock()
+	defer s.turnMu.Unlock()
+
+	turnID := uuid.New()
+	startedAt := time.Now().UTC()
+
+	// Audit row first — leave traces even if we crash mid-turn.
+	if err := s.insertTurnRow(ctx, &PaliadinTurn{
+		TurnID:      turnID,
+		UserID:      req.UserID,
+		SessionID:   req.SessionID,
+		StartedAt:   startedAt,
+		UserMessage: req.UserMessage,
+		PageOrigin:  optionalString(req.PageOrigin),
+	}); err != nil {
+		return nil, fmt.Errorf("paliadin: insert turn row: %w", err)
+	}
+
+	// Health-gate before paying the cost of a real turn. Caches OK for
+	// 10 s so a fast back-to-back chat doesn't probe every time.
+	if err := s.healthGate(ctx); err != nil {
+		_ = s.markTurnError(ctx, turnID, "mriver_unreachable")
+		return nil, err
+	}
+
+	// Lazy bootstrap — first turn after a paliad restart sends the
+	// system prompt; subsequent turns skip.
+	if err := s.ensureBootstrapped(ctx); err != nil {
+		_ = s.markTurnError(ctx, turnID, "bootstrap_failed")
+		return nil, err
+	}
+
+	msg := sanitiseForTmux(req.UserMessage)
+	msgB64 := base64.StdEncoding.EncodeToString([]byte(msg))
+
+	body, err := s.callShim(ctx, "run-turn", turnID.String(), msgB64)
+	if err != nil {
+		_ = s.markTurnError(ctx, turnID, classifySSHError(err))
+		return nil, err
+	}
+
+	// Same trailer parse + audit completion as the local path.
+	cleanBody, meta := splitTrailer(string(body))
+	tokens := approxTokenCount(cleanBody)
+	chipCount := countChips(cleanBody)
+	finished := time.Now().UTC()
+	durationMS := int(finished.Sub(startedAt) / time.Millisecond)
+
+	if err := s.completeTurn(ctx, turnID, finished, durationMS, cleanBody, tokens, meta, chipCount); err != nil {
+		log.Printf("paliadin: complete turn %s: %v", turnID, err)
+	}
+
+	return &TurnResult{
+		TurnID:        turnID,
+		Response:      cleanBody,
+		UsedTools:     meta.UsedTools,
+		RowsSeen:      meta.RowsSeen,
+		ChipCount:     chipCount,
+		ClassifierTag: meta.ClassifierTag,
+		DurationMS:    durationMS,
+	}, nil
+}
+
+// ResetSession sends `/clear` to the remote claude pane.
+func (s *RemotePaliadinService) ResetSession(ctx context.Context) error {
+	if _, err := s.callShim(ctx, "reset"); err != nil {
+		return fmt.Errorf("paliadin: reset: %w", err)
+	}
+	return nil
+}
+
+// healthGate runs the shim's `health` verb at most once per 10 s.
+// Returns ErrMRiverUnreachable wrapping the underlying error on miss.
+func (s *RemotePaliadinService) healthGate(ctx context.Context) error {
+	s.healthMu.Lock()
+	defer s.healthMu.Unlock()
+
+	if s.healthOK && time.Since(s.healthCheckedAt) < 10*time.Second {
+		return nil
+	}
+
+	probeCtx, cancel := context.WithTimeout(ctx, 3*time.Second)
+	defer cancel()
+	out, err := s.callShim(probeCtx, "health")
+	s.healthCheckedAt = time.Now()
+	if err != nil {
+		s.healthOK = false
+		return fmt.Errorf("%w: %v", ErrMRiverUnreachable, err)
+	}
+	if strings.TrimSpace(string(out)) != "ok" {
+		s.healthOK = false
+		return fmt.Errorf("%w: shim returned %q", ErrMRiverUnreachable, string(out))
+	}
+	s.healthOK = true
+	return nil
+}
+
+// ensureBootstrapped sends the Paliadin system prompt to the remote
+// claude pane on first call. Idempotent — subsequent calls return nil
+// without doing any work.
+func (s *RemotePaliadinService) ensureBootstrapped(ctx context.Context) error {
+	s.bootstrapMu.Lock()
+	defer s.bootstrapMu.Unlock()
+	if s.bootstrapped {
+		return nil
+	}
+	prompt := paliadinSystemPrompt("/tmp/paliadin")
+	promptB64 := base64.StdEncoding.EncodeToString([]byte(prompt))
+	if _, err := s.callShim(ctx, "bootstrap", promptB64); err != nil {
+		return fmt.Errorf("paliadin: bootstrap: %w", err)
+	}
+	s.bootstrapped = true
+	return nil
+}
+
+// callShim runs `ssh <user>@<host> -- <verb> <args...>` against the
+// paliadin-shim. The shim's authorized_keys command= directive ensures
+// the verb + args are passed via $SSH_ORIGINAL_COMMAND regardless of
+// what we put after the `--`; we keep the explicit argv form anyway so
+// reading the code at the call site is unambiguous.
+//
+// Tests set callShimHook to bypass exec.
+func (s *RemotePaliadinService) callShim(ctx context.Context, args ...string) ([]byte, error) {
+	if s.callShimHook != nil {
+		return s.callShimHook(ctx, args...)
+	}
+
+	sshArgs := []string{
+		"-F", "/dev/null", // ignore /etc/ssh/ssh_config + ~/.ssh/config
+		"-i", s.cfg.SSHKeyPath,
+		"-p", strconv.Itoa(s.cfg.SSHPort), // 22022 — bypasses Tailscale SSH on :22
+		"-o", "IdentitiesOnly=yes",
+		"-o", "UserKnownHostsFile=" + s.cfg.KnownHostsPath,
+		"-o", "StrictHostKeyChecking=yes",
+		"-o", "BatchMode=yes",
+		"-o", "ConnectTimeout=3",
+		"-o", "ServerAliveInterval=10",
+		"-o", "ServerAliveCountMax=3",
+		s.cfg.SSHUser + "@" + s.cfg.SSHHost,
+		"--",
+	}
+	sshArgs = append(sshArgs, args...)
+
+	// Shim's run-turn timeout is 60 s; +10 s gives SSH some overhead.
+	c, cancel := context.WithTimeout(ctx, 70*time.Second)
+	defer cancel()
+
+	cmd := exec.CommandContext(c, "ssh", sshArgs...)
+	var stdout, stderr bytes.Buffer
+	cmd.Stdout = &stdout
+	cmd.Stderr = &stderr
+	if err := cmd.Run(); err != nil {
+		return nil, fmt.Errorf("ssh %s: %w (stderr: %s)", strings.Join(args, " "), err, strings.TrimSpace(stderr.String()))
+	}
+	return stdout.Bytes(), nil
+}
+
+// classifySSHError turns a callShim error into one of the audit-row
+// error codes. Codes are stable strings shown on the admin dashboard
+// and used by the frontend's friendlyErrorMessage to localise.
+func classifySSHError(err error) string {
+	if err == nil {
+		return ""
+	}
+	if errors.Is(err, ErrMRiverUnreachable) {
+		return "mriver_unreachable"
+	}
+	if errors.Is(err, context.DeadlineExceeded) {
+		return "timeout"
+	}
+	msg := err.Error()
+	switch {
+	case strings.Contains(msg, "Connection timed out"),
+		strings.Contains(msg, "Connection refused"),
+		strings.Contains(msg, "Could not resolve hostname"),
+		strings.Contains(msg, "Network is unreachable"):
+		return "mriver_unreachable"
+	case strings.Contains(msg, "exit status 124"):
+		// Shim's run-turn 60 s timeout — Claude didn't write the
+		// response file in time.
+		return "timeout"
+	case strings.Contains(msg, "Permission denied"):
+		return "shim_auth_failed"
+	default:
+		return "shim_error"
+	}
+}
+
+// DisabledPaliadinService is a stub that always returns
+// ErrPaliadinDisabled. cmd/server/main.go constructs one when neither
+// PALIADIN_REMOTE_HOST is set nor a local tmux is available; without
+// the stub, the handler would have to nil-check on every entry point.
+type DisabledPaliadinService struct {
+	paliadinDB
+}
+
+// NewDisabledPaliadinService wires the stub. DB methods (IsOwner /
+// ListRecentTurns / Stats) still work; only RunTurn / ResetSession
+// return ErrPaliadinDisabled.
+func NewDisabledPaliadinService(db *sqlx.DB, users *UserService) *DisabledPaliadinService {
+	return &DisabledPaliadinService{paliadinDB: paliadinDB{db: db, users: users}}
+}
+
+func (s *DisabledPaliadinService) RunTurn(ctx context.Context, req TurnRequest) (*TurnResult, error) {
+	return nil, ErrPaliadinDisabled
+}
+
+func (s *DisabledPaliadinService) ResetSession(ctx context.Context) error {
+	return ErrPaliadinDisabled
+}
+
+// Compile-time interface conformance checks — fail the build, not a
+// runtime test, if a method drifts off any backend.
+var (
+	_ Paliadin = (*LocalPaliadinService)(nil)
+	_ Paliadin = (*RemotePaliadinService)(nil)
+	_ Paliadin = (*DisabledPaliadinService)(nil)
+)