claude-failover/internal/state/state.go

// Package state manages the in-memory + on-disk representation of all
// session and quota state for the claude-failover daemon.
package state

import (
	"encoding/json"
	"fmt"
	"os"
	"sync"
	"time"
)

// SessionState captures the runtime status of a single tmux session.
type SessionState struct {
	State      string     `json:"state"`
	Project    *string    `json:"project,omitempty"`
	AssignedAt *time.Time `json:"assigned_at,omitempty"`
	Task       *string    `json:"task,omitempty"`
	LastFail   *time.Time `json:"last_fail,omitempty"`
}

// QuotaState tracks which account is active and whether dispatching is paused.
type QuotaState struct {
	Paused        bool       `json:"paused"`
	ActiveAccount string     `json:"active_account"`
	ResumeAt      *time.Time `json:"resume_at,omitempty"`
}

// State is the thread-safe runtime state persisted to a JSON file.
type State struct {
	mu        sync.RWMutex
	Sessions  map[string]*SessionState `json:"sessions"`
	Quota     QuotaState               `json:"quota"`
	UpdatedAt time.Time                `json:"updated_at"`
	filePath  string
}

// New creates an empty State that will be flushed to filePath.
func New(filePath string) *State {
	return &State{
		Sessions:  make(map[string]*SessionState),
		UpdatedAt: time.Now().UTC(),
		filePath:  filePath,
	}
}

// LoadFromFile reads an existing state JSON file. Returns a new empty
// State if the file does not exist.
func LoadFromFile(path string) (*State, error) {
	data, err := os.ReadFile(path)
	if os.IsNotExist(err) {
		return New(path), nil
	}
	if err != nil {
		return nil, fmt.Errorf("reading state file %s: %w", path, err)
	}

	s := New(path)
	if err := json.Unmarshal(data, s); err != nil {
		return nil, fmt.Errorf("parsing state file %s: %w", path, err)
	}
	s.filePath = path
	return s, nil
}

// Flush serialises the state to disk atomically (write to tmp then rename).
func (s *State) Flush() error {
	if s.filePath == "" {
		return nil
	}
	s.mu.RLock()
	data, err := json.MarshalIndent(s, "", "  ")
	s.mu.RUnlock()
	if err != nil {
		return fmt.Errorf("marshalling state: %w", err)
	}

	tmp := s.filePath + ".tmp"
	if err := os.WriteFile(tmp, data, 0600); err != nil {
		return fmt.Errorf("writing state tmp: %w", err)
	}
	return os.Rename(tmp, s.filePath)
}

// JSON returns the current state as a JSON byte slice (for HTTP /status).
func (s *State) JSON() []byte {
	s.mu.RLock()
	defer s.mu.RUnlock()
	data, _ := json.Marshal(s)
	return data
}

// GetSession returns the state for the named session, or nil.
func (s *State) GetSession(name string) *SessionState {
	s.mu.RLock()
	defer s.mu.RUnlock()
	return s.Sessions[name]
}

// touch updates the UpdatedAt timestamp. Must be called with write lock held.
func (s *State) touch() {
	s.UpdatedAt = time.Now().UTC()
}

// SetIdle marks the named session as idle and clears task metadata.
func (s *State) SetIdle(name string) {
	s.mu.Lock()
	defer s.mu.Unlock()
	sess, ok := s.Sessions[name]
	if !ok {
		sess = &SessionState{}
		s.Sessions[name] = sess
	}
	sess.State = "idle"
	sess.Task = nil
	sess.AssignedAt = nil
	s.touch()
}

// SetWorking marks the named session as busy with the given task ID.
func (s *State) SetWorking(name, task string) {
	s.mu.Lock()
	defer s.mu.Unlock()
	now := time.Now().UTC()
	sess, ok := s.Sessions[name]
	if !ok {
		sess = &SessionState{}
		s.Sessions[name] = sess
	}
	sess.State = "working"
	sess.Task = &task
	sess.AssignedAt = &now
	s.touch()
}

// SetFailed marks the named session as failed and records the failure timestamp.
// The task is preserved for potential requeue by the caller.
func (s *State) SetFailed(name string) {
	s.mu.Lock()
	defer s.mu.Unlock()
	now := time.Now().UTC()
	sess, ok := s.Sessions[name]
	if !ok {
		sess = &SessionState{}
		s.Sessions[name] = sess
	}
	sess.State = "failed"
	sess.LastFail = &now
	s.touch()
}