paliad/internal/services/paliadin_remote.go

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
	SessionPrefix  string // tmux session prefix; per-user session is "<prefix>-<userid8>"
}

// RemotePaliadinService implements Paliadin against a remote
// paliadin-shim over SSH.
type RemotePaliadinService struct {
	paliadinDB
	cfg RemotePaliadinConfig

	// Serialise turns across all users. mRiver's host has finite tmux
	// concurrency anyway, and Paliadin turns are short. Per-user
	// fan-out can ship in v2 if it ever bottlenecks.
	turnMu sync.Mutex

	// Health-check cache, keyed by per-user session name. Avoids
	// probing mRiver on every turn — once a session's cache is warm,
	// RunTurn skips the probe for 10 seconds.
	healthMu sync.Mutex
	health   map[string]healthCacheEntry

	// 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)
}

// healthCacheEntry is one row in the health cache, keyed off tmux
// session name. We cache success only — failures re-probe so a flap
// surfaces immediately when paliad reboots into a healthy mRiver.
type healthCacheEntry struct {
	ok        bool
	checkedAt time.Time
}

// 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"
	}
	if cfg.SessionPrefix == "" {
		cfg.SessionPrefix = "paliad-paliadin"
	}
	return &RemotePaliadinService{
		paliadinDB: paliadinDB{db: db, users: users},
		cfg:        cfg,
		health:     make(map[string]healthCacheEntry),
	}
}

// sessionNameFor returns the per-user tmux session name. Per-user
// keying (t-paliad-155): one persistent session per Paliad user keyed
// on the first 8 hex chars of their UUID. Conversation history piles
// up across visits; ResetSession is the user-driven escape hatch.
func (s *RemotePaliadinService) sessionNameFor(userID uuid.UUID) string {
	short := userID.String()
	if len(short) >= 8 {
		short = short[:8]
	}
	return s.cfg.SessionPrefix + "-" + short
}

// 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)
	}

	session := s.sessionNameFor(req.UserID)

	// Health-gate before paying the cost of a real turn. Caches OK for
	// 10 s per session so a fast back-to-back chat doesn't probe every
	// time.
	if err := s.healthGate(ctx, session); err != nil {
		_ = s.markTurnError(ctx, turnID, "mriver_unreachable")
		return nil, err
	}

	// Persona + response protocol live in the Paliadin skill at
	// ~/.claude/skills/paliadin/SKILL.md on mRiver. Claude's skill
	// router auto-matches the [PALIADIN: envelope so no in-process
	// bootstrap (system-prompt-via-tmux-keystroke) is needed any more.

	msg := sanitiseForTmux(req.UserMessage)
	msgB64 := base64.StdEncoding.EncodeToString([]byte(msg))

	body, err := s.callShim(ctx, "run-turn", session, 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 kills the user's tmux session on mRiver entirely so the
// next RunTurn boots a fresh claude pane. Skill-based persona load
// means the new pane re-acquires the Paliadin protocol contract on
// first turn — no system-prompt re-send needed.
func (s *RemotePaliadinService) ResetSession(ctx context.Context, userID uuid.UUID) error {
	session := s.sessionNameFor(userID)

	// Drop the cached health entry so the next turn re-probes against
	// the fresh session.
	s.healthMu.Lock()
	delete(s.health, session)
	s.healthMu.Unlock()

	if _, err := s.callShim(ctx, "reset", session); err != nil {
		return fmt.Errorf("paliadin: reset %s: %w", session, err)
	}
	return nil
}

// healthGate runs the shim's `health <session>` verb at most once per
// 10 s per session. Returns ErrMRiverUnreachable wrapping the
// underlying error on miss.
func (s *RemotePaliadinService) healthGate(ctx context.Context, session string) error {
	s.healthMu.Lock()
	defer s.healthMu.Unlock()

	if entry, ok := s.health[session]; ok && entry.ok && time.Since(entry.checkedAt) < 10*time.Second {
		return nil
	}

	probeCtx, cancel := context.WithTimeout(ctx, 3*time.Second)
	defer cancel()
	out, err := s.callShim(probeCtx, "health", session)
	if err != nil {
		// Don't cache failures — re-probe on every miss so a recovery
		// surfaces immediately.
		delete(s.health, session)
		return fmt.Errorf("%w: %v", ErrMRiverUnreachable, err)
	}
	if strings.TrimSpace(string(out)) != "ok" {
		delete(s.health, session)
		return fmt.Errorf("%w: shim returned %q", ErrMRiverUnreachable, string(out))
	}
	s.health[session] = healthCacheEntry{ok: true, checkedAt: time.Now()}
	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 120 s (cold start = claude boot + skill
	// load + MCP discovery + first reasoning); +10 s gives SSH overhead.
	c, cancel := context.WithTimeout(ctx, 130*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, userID uuid.UUID) 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)
)