tiny-forge/internal/stack/manager.go

package stack

import (
	"context"
	"fmt"
	"log/slog"
	"os"
	"path/filepath"
	"regexp"
	"strings"
	"time"

	"github.com/alexei/tinyforge/internal/events"
	"github.com/alexei/tinyforge/internal/store"
)

// Manager orchestrates the stack deployment pipeline: validate YAML, persist
// a revision, write YAML to disk, run `docker compose up`, update status.
type Manager struct {
	store    *store.Store
	compose  *Compose
	eventBus *events.Bus
	workDir  string // where per-stack YAML files are written
}

// NewManager constructs a stack Manager. workDir is the directory where
// per-stack YAML files are written; it is created if missing.
func NewManager(st *store.Store, compose *Compose, eventBus *events.Bus, workDir string) (*Manager, error) {
	if workDir == "" {
		workDir = filepath.Join(os.TempDir(), "tinyforge-stacks")
	}
	if err := os.MkdirAll(workDir, 0o755); err != nil {
		return nil, fmt.Errorf("create stack workdir: %w", err)
	}
	return &Manager{
		store:    st,
		compose:  compose,
		eventBus: eventBus,
		workDir:  workDir,
	}, nil
}

// Available reports whether the underlying `docker compose` CLI is usable.
func (m *Manager) Available(ctx context.Context) error {
	return m.compose.Available(ctx)
}

// Create inserts a new stack + its initial revision. Does NOT deploy.
func (m *Manager) Create(ctx context.Context, name, description, yamlText, author string) (store.Stack, store.StackRevision, error) {
	if strings.TrimSpace(name) == "" {
		return store.Stack{}, store.StackRevision{}, fmt.Errorf("name is required")
	}
	spec, err := Parse(yamlText)
	if err != nil {
		return store.Stack{}, store.StackRevision{}, err
	}
	if err := Validate(spec); err != nil {
		return store.Stack{}, store.StackRevision{}, err
	}

	st := store.Stack{
		Name:               name,
		Description:        description,
		ComposeProjectName: composeProjectName(name),
		Status:             "stopped",
	}
	st, err = m.store.CreateStack(st)
	if err != nil {
		return store.Stack{}, store.StackRevision{}, err
	}

	rev, err := m.store.CreateStackRevision(store.StackRevision{
		StackID: st.ID,
		YAML:    yamlText,
		Author:  author,
	})
	if err != nil {
		// Best-effort cleanup of the stack row.
		_ = m.store.DeleteStack(st.ID)
		return store.Stack{}, store.StackRevision{}, err
	}
	return st, rev, nil
}

// Deploy brings up the stack for the given revision. Updates stack + revision
// status transitions: deploying → running | failed. Blocking.
func (m *Manager) Deploy(ctx context.Context, stackID, revisionID string) error {
	st, err := m.store.GetStackByID(stackID)
	if err != nil {
		return err
	}
	rev, err := m.store.GetStackRevisionByID(revisionID)
	if err != nil {
		return err
	}
	if rev.StackID != stackID {
		return fmt.Errorf("revision %s does not belong to stack %s", revisionID, stackID)
	}

	deploy, err := m.store.CreateStackDeploy(store.StackDeploy{
		StackID:    stackID,
		RevisionID: revisionID,
		Status:     "deploying",
	})
	if err != nil {
		return err
	}
	_ = m.store.UpdateStackRevisionStatus(rev.ID, "deploying", deploy.ID)
	m.setStatus(st, "deploying", "")

	yamlPath, err := m.writeYAML(st.ID, rev.Revision, rev.YAML)
	if err != nil {
		m.failDeploy(st, deploy, rev, fmt.Sprintf("write yaml: %v", err))
		return err
	}

	out, upErr := m.compose.Up(ctx, st.ComposeProjectName, yamlPath)
	if upErr != nil {
		m.failDeploy(st, deploy, rev, fmt.Sprintf("compose up: %v\n%s", upErr, out))
		return upErr
	}

	// Success.
	deploy.Status = "success"
	deploy.Log = out
	deploy.FinishedAt = store.Now()
	_ = m.store.UpdateStackDeploy(deploy)
	_ = m.store.UpdateStackRevisionStatus(rev.ID, "success", deploy.ID)
	_ = m.store.SetStackCurrentRevision(st.ID, rev.ID)
	m.setStatus(st, "running", "")
	m.syncContainerRows(ctx, st, yamlPath)
	return nil
}

// NewRevisionAndDeploy appends a new revision (validating YAML first) and deploys it.
func (m *Manager) NewRevisionAndDeploy(ctx context.Context, stackID, yamlText, author string) (store.StackRevision, error) {
	spec, err := Parse(yamlText)
	if err != nil {
		return store.StackRevision{}, err
	}
	if err := Validate(spec); err != nil {
		return store.StackRevision{}, err
	}
	rev, err := m.store.CreateStackRevision(store.StackRevision{
		StackID: stackID,
		YAML:    yamlText,
		Author:  author,
	})
	if err != nil {
		return store.StackRevision{}, err
	}
	if err := m.Deploy(ctx, stackID, rev.ID); err != nil {
		return rev, err
	}
	return rev, nil
}

// NewRevisionAndDeployAsync creates a revision and triggers deploy in a goroutine.
// Returns the created revision immediately.
func (m *Manager) NewRevisionAndDeployAsync(ctx context.Context, stackID, yamlText, author string) (store.StackRevision, error) {
	spec, err := Parse(yamlText)
	if err != nil {
		return store.StackRevision{}, err
	}
	if err := Validate(spec); err != nil {
		return store.StackRevision{}, err
	}
	rev, err := m.store.CreateStackRevision(store.StackRevision{
		StackID: stackID,
		YAML:    yamlText,
		Author:  author,
	})
	if err != nil {
		return store.StackRevision{}, err
	}
	go func(stackID, revID string) {
		bgCtx, cancel := context.WithTimeout(context.Background(), 10*time.Minute)
		defer cancel()
		if err := m.Deploy(bgCtx, stackID, revID); err != nil {
			slog.Warn("stack: async deploy failed", "stack", stackID, "revision", revID, "error", err)
		}
	}(stackID, rev.ID)
	return rev, nil
}

// RollbackAsync creates a copy-revision from a target and deploys asynchronously.
func (m *Manager) RollbackAsync(ctx context.Context, stackID, targetRevisionID, author string) (store.StackRevision, error) {
	target, err := m.store.GetStackRevisionByID(targetRevisionID)
	if err != nil {
		return store.StackRevision{}, err
	}
	if target.StackID != stackID {
		return store.StackRevision{}, fmt.Errorf("revision %s does not belong to stack %s", targetRevisionID, stackID)
	}
	return m.NewRevisionAndDeployAsync(ctx, stackID, target.YAML, author+" (rollback to rev "+itoa(target.Revision)+")")
}

// Rollback creates a new revision whose YAML is copied from the given prior
// revision, then deploys it. Keeps history append-only.
func (m *Manager) Rollback(ctx context.Context, stackID, targetRevisionID, author string) (store.StackRevision, error) {
	target, err := m.store.GetStackRevisionByID(targetRevisionID)
	if err != nil {
		return store.StackRevision{}, err
	}
	if target.StackID != stackID {
		return store.StackRevision{}, fmt.Errorf("revision %s does not belong to stack %s", targetRevisionID, stackID)
	}
	return m.NewRevisionAndDeploy(ctx, stackID, target.YAML, author+" (rollback to rev "+itoa(target.Revision)+")")
}

// Stop runs `docker compose stop` without removing containers.
func (m *Manager) Stop(ctx context.Context, stackID string) error {
	st, err := m.store.GetStackByID(stackID)
	if err != nil {
		return err
	}
	if _, err := m.compose.Stop(ctx, st.ComposeProjectName); err != nil {
		return err
	}
	m.setStatus(st, "stopped", "")
	m.markStackContainersState(stackID, "stopped")
	return nil
}

// Start runs `docker compose start` on existing containers.
func (m *Manager) Start(ctx context.Context, stackID string) error {
	st, err := m.store.GetStackByID(stackID)
	if err != nil {
		return err
	}
	if _, err := m.compose.Start(ctx, st.ComposeProjectName); err != nil {
		return err
	}
	m.setStatus(st, "running", "")
	m.markStackContainersState(stackID, "running")
	return nil
}

// Delete tears down the stack and removes the DB row. If removeVolumes is
// true, named volumes are also deleted (`compose down -v`). Destructive.
func (m *Manager) Delete(ctx context.Context, stackID string, removeVolumes bool) error {
	st, err := m.store.GetStackByID(stackID)
	if err != nil {
		return err
	}
	if _, err := m.compose.Down(ctx, st.ComposeProjectName, removeVolumes); err != nil {
		// Log but continue — DB row must not be orphaned.
		slog.Warn("stack: compose down failed", "stack", st.Name, "error", err)
	}
	// Best-effort YAML cleanup.
	_ = os.RemoveAll(filepath.Join(m.workDir, st.ID))
	return m.store.DeleteStack(stackID)
}

// Services returns current service state for a stack.
func (m *Manager) Services(ctx context.Context, stackID string) ([]Service, error) {
	st, err := m.store.GetStackByID(stackID)
	if err != nil {
		return nil, err
	}
	yamlPath := ""
	if st.CurrentRevisionID != "" {
		if rev, err := m.store.GetStackRevisionByID(st.CurrentRevisionID); err == nil {
			yamlPath, _ = m.writeYAML(st.ID, rev.Revision, rev.YAML)
		}
	}
	ctx, cancel := context.WithTimeout(ctx, 15*time.Second)
	defer cancel()
	return m.compose.Ps(ctx, st.ComposeProjectName, yamlPath)
}

// Logs returns the last `tail` log lines for a service (or all services if empty).
func (m *Manager) Logs(ctx context.Context, stackID, service string, tail int) (string, error) {
	st, err := m.store.GetStackByID(stackID)
	if err != nil {
		return "", err
	}
	if tail <= 0 {
		tail = 200
	}
	return m.compose.Logs(ctx, st.ComposeProjectName, service, tail)
}

// --- internals ---

// syncContainerRows upserts one Container row per compose service for this
// stack so the global container index stays in sync after every deploy. The
// Docker container ID is left empty here — the reconciler resolves it from
// `docker ps` via the `com.docker.compose.project` label. Best-effort: a
// failure here is logged but does not affect deploy outcome.
func (m *Manager) syncContainerRows(ctx context.Context, st store.Stack, yamlPath string) {
	w, err := m.store.GetWorkloadByRef(store.WorkloadKindStack, st.ID)
	if err != nil {
		slog.Warn("stack: resolve workload", "stack", st.ID, "error", err)
		return
	}
	psCtx, cancel := context.WithTimeout(ctx, 10*time.Second)
	defer cancel()
	services, err := m.compose.Ps(psCtx, st.ComposeProjectName, yamlPath)
	if err != nil {
		slog.Warn("stack: compose ps for container sync", "stack", st.ID, "error", err)
		return
	}
	for _, svc := range services {
		state := svc.State
		if state == "" {
			state = svc.Status
		}
		m.upsertStackContainer(w.ID, svc, state)
	}
}

// upsertStackContainer writes a Container row for one compose service. The
// row ID is deterministic — `<workloadID>:<service>` — so re-deploys update
// the same row instead of accumulating rows.
func (m *Manager) upsertStackContainer(workloadID string, svc Service, state string) {
	role := svc.Service
	if role == "" {
		role = svc.Name
	}
	if err := m.store.UpsertContainer(store.Container{
		ID:           workloadID + ":" + role,
		WorkloadID:   workloadID,
		WorkloadKind: string(store.WorkloadKindStack),
		Role:         role,
		ContainerID:  "", // reconciler fills in from docker ps
		Host:         "local",
		State:        state,
		LastSeenAt:   store.Now(),
	}); err != nil {
		slog.Warn("stack: upsert container row", "workload_id", workloadID, "service", role, "error", err)
	}
}

// markStackContainersState bulk-updates the state of every container row for
// this stack (used by Stop/Start which don't go through compose ps).
func (m *Manager) markStackContainersState(stackID, state string) {
	w, err := m.store.GetWorkloadByRef(store.WorkloadKindStack, stackID)
	if err != nil {
		return
	}
	rows, err := m.store.ListContainersByWorkload(w.ID)
	if err != nil {
		slog.Warn("stack: list containers for state update", "workload_id", w.ID, "error", err)
		return
	}
	for _, r := range rows {
		if err := m.store.UpdateContainerState(r.ID, state); err != nil {
			slog.Warn("stack: update container state", "container_row", r.ID, "error", err)
		}
	}
}

func (m *Manager) setStatus(st store.Stack, status, errMsg string) {
	_ = m.store.UpdateStackStatus(st.ID, status, errMsg)
	if m.eventBus != nil {
		m.eventBus.Publish(events.Event{
			Type: events.EventStackStatus,
			Payload: events.StackStatusPayload{
				StackID: st.ID,
				Name:    st.Name,
				Status:  status,
				Error:   errMsg,
			},
		})
	}
}

func (m *Manager) failDeploy(st store.Stack, d store.StackDeploy, rev store.StackRevision, errMsg string) {
	d.Status = "failed"
	d.Error = errMsg
	d.FinishedAt = store.Now()
	_ = m.store.UpdateStackDeploy(d)
	_ = m.store.UpdateStackRevisionStatus(rev.ID, "failed", d.ID)
	m.setStatus(st, "failed", errMsg)
}

// writeYAML writes yaml to <workDir>/<stackID>/rev-<n>.yml and returns the path.
func (m *Manager) writeYAML(stackID string, revision int, yamlText string) (string, error) {
	dir := filepath.Join(m.workDir, stackID)
	if err := os.MkdirAll(dir, 0o755); err != nil {
		return "", err
	}
	path := filepath.Join(dir, fmt.Sprintf("rev-%d.yml", revision))
	if err := os.WriteFile(path, []byte(yamlText), 0o644); err != nil {
		return "", err
	}
	return path, nil
}

// composeProjectName sanitises a user-provided stack name into something
// `docker compose -p` will accept: lowercase, digits, dashes only.
func composeProjectName(name string) string {
	name = strings.ToLower(name)
	name = nonProjectChars.ReplaceAllString(name, "-")
	name = strings.Trim(name, "-")
	if name == "" {
		name = "stack"
	}
	return "tinyforge-" + name
}

var nonProjectChars = regexp.MustCompile(`[^a-z0-9-]+`)

func itoa(n int) string { return fmt.Sprintf("%d", n) }