oikos/internal/actuator/ssh.go

// Package actuator provides SSH-based skill procedure execution for the Oikos
// Phase 3 actuator loop. It runs stored skill procedures over SSH with a
// restricted key, classifies SSH errors into retryable/fatal/timeout, and
// supports step-by-step procedure verification.
package actuator

import (
	"context"
	"encoding/json"
	"errors"
	"fmt"
	"log/slog"
	"net"
	"os"
	"strings"
	"sync"
	"time"

	"golang.org/x/crypto/ssh"
)

// ─── Procedure types ──────────────────────────────────────────────────────

// Procedure represents a parsed skill procedure from JSON config.
type Procedure struct {
	Steps []Step `json:"steps"`
}

// Step is a single step within a procedure.
type Step struct {
	Runner   string `json:"runner"`             // "shell", "script", "verify"
	Target   string `json:"target,omitempty"`   // hostname/IP (empty = local)
	Command  string `json:"command"`            // shell command or script path
	TimeoutS int    `json:"timeout_s,omitempty"` // per-step timeout in seconds
}

// SSHResult holds the outcome of an SSH execution.
type SSHResult struct {
	Output   string `json:"output"`
	Duration time.Duration `json:"duration"`
	Verified bool   `json:"verified"`
	Err      error  `json:"error,omitempty"`
}

// ─── Error classification ─────────────────────────────────────────────────

// SSHErrorClass categorises SSH errors.
type SSHErrorClass int

const (
	SSHErrorUnknown  SSHErrorClass = iota
	SSHErrorNetwork               // dial/connect timeout — retryable
	SSHErrorAuth                  // auth failure — fatal
	SSHErrorTimeout               // command timed out
	SSHErrorRemote                // remote command returned non-zero
	SSHErrorOther                 // other non-retryable
)

func (c SSHErrorClass) String() string {
	switch c {
	case SSHErrorNetwork:
		return "network"
	case SSHErrorAuth:
		return "auth"
	case SSHErrorTimeout:
		return "timed_out"
	case SSHErrorRemote:
		return "remote"
	case SSHErrorOther:
		return "other"
	default:
		return "unknown"
	}
}

// classifySSHError maps an SSH error to a class for retry/fatal decisions.
func classifySSHError(err error) SSHErrorClass {
	if err == nil {
		return SSHErrorOther
	}

	if errors.Is(err, context.DeadlineExceeded) {
		return SSHErrorTimeout
	}

	var netErr net.Error
	if errors.As(err, &netErr) {
		if netErr.Timeout() {
			return SSHErrorNetwork
		}
		return SSHErrorNetwork
	}

	if strings.Contains(err.Error(), "unable to authenticate") ||
		strings.Contains(err.Error(), "no supported methods remain") ||
		strings.Contains(err.Error(), "ssh: handshake failed") ||
		strings.Contains(err.Error(), "publickey") ||
		strings.Contains(err.Error(), "permission denied") {
		return SSHErrorAuth
	}

	var exitErr *ssh.ExitError
	if errors.As(err, &exitErr) {
		return SSHErrorRemote
	}

	return SSHErrorOther
}

// ─── SSH execution ────────────────────────────────────────────────────────

// SSHConfig holds connection parameters for SSH sessions.
type SSHConfig struct {
	Host     string
	Port     int
	User     string
	KeyPath  string
	Timeout  time.Duration
}

// ExecuteProcedure runs a complete procedure over SSH, step by step.
// Returns the combined result, duration, and verified status.
//
// Context cancellation aborts the running session. Returns the last
// successfully completed step's output on partial failure.
func ExecuteProcedure(
	ctx context.Context,
	cfg SSHConfig,
	proc Procedure,
) SSHResult {
	start := time.Now()

	// Parse the SSH key
	key, err := os.ReadFile(cfg.KeyPath)
	if err != nil {
		return SSHResult{
			Err:      fmt.Errorf("read ssh key: %w", err),
			Duration: time.Since(start),
			Verified: false,
		}
	}

	signer, err := ssh.ParsePrivateKey(key)
	if err != nil {
		return SSHResult{
			Err:      fmt.Errorf("parse ssh key: %w", err),
			Duration: time.Since(start),
			Verified: false,
		}
	}

	addr := net.JoinHostPort(cfg.Host, fmt.Sprintf("%d", cfg.Port))
	if cfg.Port == 0 {
		addr = net.JoinHostPort(cfg.Host, "22")
	}

	clientCfg := &ssh.ClientConfig{
		User:            cfg.User,
		Auth:            []ssh.AuthMethod{ssh.PublicKeys(signer)},
		HostKeyCallback: ssh.InsecureIgnoreHostKey(), // restricted key; host trust via inventory
		Timeout:         cfg.Timeout,
	}

	client, err := ssh.Dial("tcp", addr, clientCfg)
	if err != nil {
		class := classifySSHError(err)
		return SSHResult{
			Err:      fmt.Errorf("ssh dial (%s): %w", class, err),
			Duration: time.Since(start),
			Verified: false,
		}
	}
	defer client.Close()

	// Execute each step in sequence
	var lastOutput string
	verified := true

	for i, step := range proc.Steps {
		// Check context before each step
		if ctx.Err() != nil {
			return SSHResult{
				Output:   lastOutput,
				Duration: time.Since(start),
				Verified: false,
				Err:      fmt.Errorf("cancelled before step %d: %w", i, ctx.Err()),
			}
		}

		timeout := time.Duration(step.TimeoutS) * time.Second
		if timeout <= 0 {
			timeout = 30 * time.Second
		}

		stepCtx, cancel := context.WithTimeout(ctx, timeout)
		defer cancel()

		output, err := runSSHCommand(stepCtx, client, step.Command)
		if err != nil {
			class := classifySSHError(err)
			// Verify steps that fail are not counted as verified failures
			if step.Runner == "verify" {
				verified = false
			}

			// Non-verify step failure is a real failure
			if step.Runner != "verify" {
				return SSHResult{
					Output:   lastOutput,
					Duration: time.Since(start),
					Err:      fmt.Errorf("step %d (%s) failed (%s): %w", i, step.Runner, class, err),
					Verified: false,
				}
			}
		}
		lastOutput = output

		slog.Debug("ssh step completed",
			"step", i,
			"runner", step.Runner,
			"duration", time.Since(start).Round(time.Millisecond),
		)
	}

	return SSHResult{
		Output:   lastOutput,
		Duration: time.Since(start),
		Verified: verified,
	}
}

// runSSHCommand executes a single command over an established SSH session.
// Uses context-aware goroutines: ctx.Done() closes the session.
func runSSHCommand(ctx context.Context, client *ssh.Client, command string) (string, error) {
	session, err := client.NewSession()
	if err != nil {
		return "", fmt.Errorf("create session: %w", err)
	}
	defer session.Close()

	// Wrap in goroutine so we can abort on ctx.Done()
	type result struct {
		output string
		err    error
	}

	ch := make(chan result, 1)
	go func() {
		out, err := session.CombinedOutput(command)
		ch <- result{output: string(out), err: err}
	}()

	select {
	case <-ctx.Done():
		// Close the session to abort the SSH command
		session.Close()
		return "", ctx.Err()
	case res := <-ch:
		if res.err != nil {
			return res.output, fmt.Errorf("command: %w", res.err)
		}
		return res.output, nil
	}
}

// ─── Procedure parsing ────────────────────────────────────────────────────

// ParseProcedure deserialises a JSON procedure (from skill.procedure).
func ParseProcedure(data []byte) (Procedure, error) {
	var proc Procedure
	if err := json.Unmarshal(data, &proc); err != nil {
		return Procedure{}, fmt.Errorf("parse procedure: %w", err)
	}
	return proc, nil
}

// ─── Global SSH client options ────────────────────────────────────────────

var (
	mu sync.Mutex
	// defaultSSHTimeout is the default dial timeout for SSH connections.
	defaultSSHTimeout = 10 * time.Second
)

// SetDefaultSSHTimeout overrides the default SSH dial timeout. Not safe for
// concurrent use during active execution.
func SetDefaultSSHTimeout(d time.Duration) {
	mu.Lock()
	defer mu.Unlock()
	defaultSSHTimeout = d
}