claude-failover/internal/lifecycle/manager.go

// Package lifecycle provides the SessionLifecycleManager, which continuously
// monitors tmux sessions and recreates any that have died unexpectedly.
package lifecycle

import (
	"context"
	"log"
	"time"

	"forge.secuaas.ovh/olivier/claude-failover/internal/config"
	"forge.secuaas.ovh/olivier/claude-failover/internal/state"
	"forge.secuaas.ovh/olivier/claude-failover/internal/tmux"
)

// Manager reconciles the desired pool state (from config) against the actual
// tmux sessions, recreating any that have disappeared.
type Manager struct {
	tmux     tmux.Client
	state    *state.State
	config   *config.Config
	logger   *log.Logger
	interval time.Duration
}

// New creates a Manager with a default reconciliation interval of 15 seconds.
func New(tc tmux.Client, s *state.State, cfg *config.Config) *Manager {
	return &Manager{
		tmux:     tc,
		state:    s,
		config:   cfg,
		logger:   log.Default(),
		interval: 15 * time.Second,
	}
}

// Run starts the reconciliation loop, ticking every m.interval until ctx is cancelled.
func (m *Manager) Run(ctx context.Context) {
	ticker := time.NewTicker(m.interval)
	defer ticker.Stop()
	for {
		select {
		case <-ctx.Done():
			return
		case <-ticker.C:
			m.reconcile()
		}
	}
}

// EnsureAllSessions creates all configured sessions that are not yet present in tmux.
// It is intended to be called once at daemon startup before Run is launched.
func (m *Manager) EnsureAllSessions() {
	for _, ds := range m.config.Pool.Dedicated {
		if !m.tmux.HasSession(ds.Name) {
			if err := m.tmux.CreateSession(ds.Name, ds.Project); err != nil {
				m.logger.Printf("[lifecycle] EnsureAllSessions: failed to create session %q: %v", ds.Name, err)
			} else {
				m.logger.Printf("[lifecycle] EnsureAllSessions: created session %q (workdir=%s)", ds.Name, ds.Project)
				m.state.SetIdle(ds.Name)
			}
		}
	}

	// Ensure autonomous pool sessions (prefix + index, starting at StartIndex).
	prefix := m.config.Pool.Autonomous.Prefix
	if prefix == "" {
		prefix = "ccl-auto-"
	}
	start := m.config.Pool.Autonomous.StartIndex
	for i := start; i < start+m.config.Pool.Autonomous.Min; i++ {
		name := sessionName(prefix, i)
		if !m.tmux.HasSession(name) {
			if err := m.tmux.CreateSession(name, ""); err != nil {
				m.logger.Printf("[lifecycle] EnsureAllSessions: failed to create autonomous session %q: %v", name, err)
			} else {
				m.logger.Printf("[lifecycle] EnsureAllSessions: created autonomous session %q", name)
				m.state.SetIdle(name)
			}
		}
	}
}

// reconcile checks every configured session and repairs missing ones.
func (m *Manager) reconcile() {
	// Reconcile dedicated sessions.
	for _, ds := range m.config.Pool.Dedicated {
		m.reconcileSession(ds.Name, ds.Project)
	}

	// Reconcile the autonomous pool (min sessions, starting at StartIndex).
	prefix := m.config.Pool.Autonomous.Prefix
	if prefix == "" {
		prefix = "ccl-auto-"
	}
	start := m.config.Pool.Autonomous.StartIndex
	for i := start; i < start+m.config.Pool.Autonomous.Min; i++ {
		name := sessionName(prefix, i)
		m.reconcileSession(name, "")
	}
}

// reconcileSession handles a single named session.
func (m *Manager) reconcileSession(name, workdir string) {
	has := m.tmux.HasSession(name)
	st := m.state.GetSession(name)

	if has {
		// Session exists — if it's supposed to be working, verify it still looks active.
		if st != nil && st.State == "working" {
			tail, err := m.tmux.CapturePaneTail(name, 5)
			if err != nil {
				m.logger.Printf("[lifecycle] reconcile: cannot capture pane for %q: %v", name, err)
			}
			// A session that has exited to the shell prompt after a Claude process crash
			// will show a shell prompt. We just log a warning here; deeper heuristics can
			// be added in future phases.
			_ = tail
		}
		return
	}

	// Session is missing.
	if st == nil || st.State == "idle" || st.State == "" {
		m.logger.Printf("[lifecycle] RECREATED: session %q was absent (state=idle) — creating", name)
		if err := m.tmux.CreateSession(name, workdir); err != nil {
			m.logger.Printf("[lifecycle] reconcile: failed to recreate %q: %v", name, err)
			return
		}
		m.state.SetIdle(name)
	} else if st.State == "working" {
		m.logger.Printf("[lifecycle] RECOVERED: session %q crashed while working (task=%v) — marking failed and recreating",
			name, deref(st.Task))
		m.state.SetFailed(name)
		if err := m.tmux.CreateSession(name, workdir); err != nil {
			m.logger.Printf("[lifecycle] reconcile: failed to recreate %q after recovery: %v", name, err)
			return
		}
		m.state.SetIdle(name)
	}
}

// sessionName builds a session name from a prefix and a zero-based index.
func sessionName(prefix string, i int) string {
	return prefix + itoa(i)
}

// itoa converts an integer to its decimal string representation without importing strconv.
func itoa(n int) string {
	if n == 0 {
		return "0"
	}
	b := make([]byte, 0, 10)
	for n > 0 {
		b = append([]byte{byte('0' + n%10)}, b...)
		n /= 10
	}
	return string(b)
}

// deref safely dereferences a *string, returning "<nil>" if nil.
func deref(s *string) string {
	if s == nil {
		return "<nil>"
	}
	return *s
}