Cyrene_v2/cmd/cyrene/wire.go

package main

import (
	"context"
	"database/sql"
	"encoding/json"
	"fmt"
	"log/slog"
	"os"
	"path/filepath"
	"strings"
	"time"

	"git.yeij.top/AskaEth/Cyrene_v2/internal/auth"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/bus"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/capability/mcp"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/capability/registry"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/channel/session"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/config"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/db"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/iot"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/logger"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/persona/loader"
	personareg "git.yeij.top/AskaEth/Cyrene_v2/internal/persona/registry"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/platform"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/agent"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/capacity"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/embedding"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/exec"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/guardrail"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/knowledge"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/loop"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/memory"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/memory/projectindex"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/memory/vector"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/model"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/multimodal/vision"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/multimodal/voice"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/orchestration"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/orchestration/audit"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/persist"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/task"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/tool"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/trace"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/services/automations"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/services/backthink"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/services/channelbridge"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/services/gateway"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/user"
	"git.yeij.top/AskaEth/Cyrene_v2/plugins/tools/basic"
	iotools "git.yeij.top/AskaEth/Cyrene_v2/plugins/tools/io"
)

// defaultOwnerPath and defaultPersonasDir point at the on-disk persona/owner
// definitions shipped with the repo; they are relative to the working directory.
const (
	defaultOwnerPath    = "configs/users/owner.yaml"
	defaultPersonasDir  = "configs/personas"
	defaultSQLitePath   = "./data/cyrene.db"
	fallbackInstruction = "You are Cyrene, a warm and attentive companion."

	// Bound/knob constants. Compile-time so no bare magic number appears in the
	// runtime path (project rule §10).
	defaultMaxRounds   = 8
	defaultMaxParallel = 4
	defaultAgentID     = "orchestrator"
	defaultToolTimeout = 30 * time.Second
)

// app holds every subsystem the single Cyrene binary assembles. It is built by
// newApp and torn down by close on shutdown.
type app struct {
	cfg           *config.Config
	log           *slog.Logger
	db            *sql.DB
	bus           bus.Bus
	personas      *personareg.Registry
	caps          *registry.Registry
	dispatcher    *tool.Dispatcher
	memStore      *memory.Store
	retriever     *memory.Retriever
	projStore     *projectindex.Store
	loop          *loop.Loop
	scheduler     *orchestration.Scheduler
	tasks         *task.Manager
	execProv      exec.Provider
	iot           *iot.Manager
	voice         *voice.Chain
	mcpRegs       []*mcp.Registry
	sessions      *session.SessionManager
	automation    *automations.Service
	backthink     *backthink.Backthink
	vindex        vector.Index
	owner         *user.OwnerProfile
	gw            *gateway.Server
	channelBridge *channelbridge.Bridge
}

// newApp assembles the full Cyrene runtime from cfg and log. It opens the
// database, migrates the schema, wires the persona registry, model adapter, tool
// dispatcher, memory stack, agent loop, orchestration, execution, IoT, channel
// sessions/adapters and the gateway, and returns the ready app.
//
// Fatal wiring failures (database open/migrate, required auth, gateway) are
// returned as errors; optional subsystems degrade gracefully so the binary can
// boot even when a model key or external channel is not configured.
func newApp(ctx context.Context, cfg *config.Config, log *slog.Logger) (*app, error) {
	dataDir := resolveDataDir(cfg)
	databasePath := resolveSQLitePath(cfg, dataDir)
	dbCfg := cfg.DB
	dbCfg.SQLitePath = databasePath

	sqlDB, err := db.Open(ctx, databasePath, log)
	if err != nil {
		return nil, fmt.Errorf("open database: %w", err)
	}
	if err := db.MigrateUp(ctx, sqlDB, log); err != nil {
		_ = sqlDB.Close()
		return nil, fmt.Errorf("migrate database: %w", err)
	}

	eventBus := bus.New()
	a := &app{
		cfg:  cfg,
		log:  log,
		db:   sqlDB,
		bus:  eventBus,
		caps: registry.New(),
	}

	// Release already-opened resources if any later wiring step fails, without
	// the full-service shutdown log (a partial boot is not a clean shutdown).
	completed := false
	defer func() {
		if completed {
			return
		}
		if a.vindex != nil {
			_ = a.vindex.Close()
		}
		if a.tasks != nil {
			_ = a.tasks.Close()
		}
		if a.bus != nil {
			_ = a.bus.Close()
		}
		if a.db != nil {
			_ = a.db.Close()
		}
	}()

	if err := a.buildPersonas(); err != nil {
		return a, err
	}
	if err := a.wireMemory(ctx); err != nil {
		return a, err
	}
	if err := a.wireRuntime(); err != nil {
		return a, err
	}
	if err := a.wireAuxiliary(); err != nil {
		return a, err
	}
	if err := a.wireChannels(); err != nil {
		return a, err
	}
	if err := a.wireFrontend(); err != nil {
		return a, err
	}
	completed = true
	return a, nil
}

// buildPersonas loads the persona definitions and registers them, plus the
// default character and the owner profile used by channel identity resolution.
func (a *app) buildPersonas() error {
	a.personas = personareg.New()

	dirPersonas, err := loader.LoadDir(defaultPersonasDir)
	if err != nil {
		a.log.Warn("persona dir load skipped", "error", err)
	} else {
		for _, p := range dirPersonas {
			if rerr := a.personas.RegisterPersona(p); rerr != nil {
				a.log.Warn("persona register skipped", "persona", p.ID, "error", rerr)
			}
		}
	}

	if owner, oerr := user.LoadOwnerProfile(defaultOwnerPath); oerr == nil {
		a.owner = owner
	} else {
		a.log.Warn("owner profile load skipped", "error", oerr)
	}

	// Load the default persona explicitly if it was not under the personas dir.
	defaultID := "cyrene"
	if a.owner != nil && a.owner.DefaultPersona != "" {
		defaultID = a.owner.DefaultPersona
	}
	if _, ok := a.personas.Persona(defaultID); !ok {
		if p, lerr := loader.Load(filepath.Join(defaultPersonasDir, defaultID+".yaml")); lerr == nil {
			_ = a.personas.RegisterPersona(p)
		} else {
			a.log.Warn("default persona load skipped", "persona", defaultID, "error", lerr)
		}
	}
	if p, ok := a.personas.Persona(defaultID); ok {
		char := &personareg.Character{ID: p.ID, Name: p.Name, Default: true, PersonaID: p.ID}
		if cerr := a.personas.RegisterCharacter(char); cerr != nil {
			a.log.Warn("default character register skipped", "error", cerr)
		}
	}
	a.log.Info("personas ready", "count", a.personas.CountPersonas(), "default", defaultID)
	return nil
}

// wireMemory builds the long-term memory stack: store, embedding manager, vector
// index, project index and the retriever wired into the io knowledge tool.
func (a *app) wireMemory(ctx context.Context) error {
	store, err := memory.NewStore(ctx, a.db, a.log)
	if err != nil {
		return fmt.Errorf("memory store: %w", err)
	}
	a.memStore = store

	embedManager := embedding.New(a.cfg.Embedding)
	embedder := embedManager.Embedder()

	index, err := vector.New(a.dbCfgForEmbed(), embedder, a.log)
	if err != nil {
		a.log.Warn("vector index unavailable, falling back to in-memory semantic", "error", err)
	} else {
		a.vindex = index
	}

	projStore, err := projectindex.New(ctx, a.db, a.log)
	if err != nil {
		a.log.Warn("project index unavailable", "error", err)
		projStore = nil
	}
	a.projStore = projStore

	opts := []memory.RetrieverOption{memory.WithEmbedder(embedder)}
	if a.vindex != nil {
		opts = append(opts, memory.WithVectorIndex(a.vindex))
	}
	if projStore != nil {
		opts = append(opts, memory.WithProjectIndex(projStore))
	}
	a.retriever = memory.NewRetriever(store, opts...)
	return nil
}

// wireRuntime builds the model adapter, tool dispatcher, guardrails, the agent
// and its loop, tracing, persistence and the orchestration scheduler.
func (a *app) wireRuntime() error {
	adapter, aerr := model.NewChatChain(a.cfg.LLM)
	if aerr != nil {
		a.log.Warn("llm adapter unavailable", "error", aerr)
		adapter = nil
	}
	router := model.NewRouter(model.DefaultModelForProvider(a.cfg.LLM),
		model.WithVisionModel(a.cfg.LLM.VisionModel))

	dispatcher, derr := tool.New(a.caps, tool.WithDefaultTimeout(defaultToolTimeout))
	if derr != nil {
		return fmt.Errorf("tool dispatcher: %w", derr)
	}
	a.dispatcher = dispatcher

	if err := basic.Register(a.caps); err != nil {
		return fmt.Errorf("register basic tools: %w", err)
	}
	ioTools, ioErr := iotools.New(a.cfg, iotools.WithKnowledgeRetriever(a.retriever), iotools.WithLogger(a.log))
	if ioErr != nil {
		return fmt.Errorf("build io tools: %w", ioErr)
	}
	for _, t := range ioTools {
		if rerr := a.dispatcher.Register(t); rerr != nil {
			a.log.Warn("io tool register skipped", "tool", t.Name(), "error", rerr)
		}
	}
	a.wireVision()

	guards := guardrail.New()
	instructions := a.defaultInstructions()
	ag, aerr := agent.New(instructions, a.dispatcher, guards,
		agent.WithModel(adapter, router),
		agent.WithOptions(agent.Options{MaxRounds: defaultMaxRounds, Purpose: "chat"}))
	if aerr != nil {
		return fmt.Errorf("agent: %w", aerr)
	}

	personaID := a.defaultPersonaID()
	store := a.memStore

	tracer := trace.New(trace.NewJSONRecorder(os.Stderr))
	checkpoint, perr := persist.New(context.Background(), a.db, a.log)
	if perr != nil {
		return fmt.Errorf("checkpoint store: %w", perr)
	}

	// Vision routing: the loop rewrites an image-bearing user message per the
	// vision Router — a vision-capable main model sees the image directly,
	// otherwise the vision/OCR tool's text description replaces it (design/06 §0).
	visionRouter := vision.NewRouter(
		vision.WithVisionTool(visionToolName),
		vision.WithOCRTool(ocrToolName),
	)
	visionResolver := vision.NewMessageResolver(
		visionRouter,
		func() vision.ModelInfo {
			return vision.ModelInfo{Name: a.cfg.LLM.VisionModel, SupportsVision: a.cfg.LLM.VisionModel != ""}
		},
		a.dispatcher.Invoke,
	)

	capDecider := a.buildCapacity()

	a.loop = loop.New(loop.Options{
		Agent:         ag,
		Tools:         a.dispatcher,
		Capacity:      capDecider,
		OnCapacity:    a.onCapacity,
		Memory:        store,
		Retriever:     a.retriever,
		Extractor:     memory.NewManualExtractor(personaID, "owner"),
		Checkpoint:    checkpoint,
		Tracer:        tracer,
		Guards:        guards,
		PersonaID:     personaID,
		Timezone:      a.cfg.Timezone,
		MaxRounds:     defaultMaxRounds,
		WorkingMemory: memory.NewWorkingMemory(0),
		OnStream:      a.streamChunk,
		Vision:        visionResolver,
		Log:           logger.WithSource(a.log, "runtime/loop"),
	})

	a.scheduler = orchestration.New(orchestration.Options{
		MaxParallel: defaultMaxParallel,
		Loop:        a.loop,
		Bus:         a.bus,
		Memory:      store,
		Tracer:      tracer,
		Approver:    audit.NewApprover(a.log),
		Logger:      logger.WithSource(a.log, "orchestration"),
		AgentID:     defaultAgentID,
	})
	return nil
}

// buildCapacity constructs the awakened-capacity decider when enabled, or nil
// (which keeps the loop's default all-tools behavior). It is opt-in via
// CAPACITY_ENABLED; the allowed-set mapping comes from CAPACITY_TOOL_SETS and
// falls back to built-in defaults on a parse error.
func (a *app) buildCapacity() *capacity.Decider {
	if !a.cfg.Capacity.Enabled {
		return nil
	}
	sets, err := parseCapacityToolSets(a.cfg.Capacity.ToolSetsJSON)
	if err != nil {
		a.log.Warn("capacity tool sets parse failed, using built-in defaults", "error", err)
		sets = nil
	}
	return capacity.New(capacity.Config{
		Enabled:       true,
		MinConfidence: a.cfg.Capacity.MinConfidence,
		ToolSets:      sets,
	}, capacity.WithLogger(a.log))
}

// onCapacity is the loop's OnCapacity sink: it observes a capacity_awaken
// transition for observability. A future frontend wire (design/14 §5) will render
// the "能力点亮" progression from these events.
func (a *app) onCapacity(ev capacity.Event) {
	a.log.Debug("capacity event",
		"type", ev.Type, "from", ev.FromState, "to", ev.ToState,
		"tool", ev.Tool, "at", ev.At)
}

// parseCapacityToolSets decodes the CAPACITY_TOOL_SETS JSON map of
// state→allowed tool name list. A blank string yields nil (built-in defaults); a
// null value for a state means unrestricted (all tools).
func parseCapacityToolSets(raw string) (map[capacity.State][]string, error) {
	if strings.TrimSpace(raw) == "" {
		return nil, nil
	}
	var m map[string][]string
	if err := json.Unmarshal([]byte(raw), &m); err != nil {
		return nil, fmt.Errorf("capacity tool sets: %w", err)
	}
	out := make(map[capacity.State][]string, len(m))
	for k, v := range m {
		out[capacity.State(k)] = v
	}
	return out, nil
}

// wireAuxiliary builds the execution provider, task manager, IoT manager,
// channel session manager, automations and background thinking services.
func (a *app) wireAuxiliary() error {
	provider, err := exec.New(a.cfg.ExecSandbox, a.log)
	if err != nil {
		return fmt.Errorf("exec provider: %w", err)
	}
	a.execProv = provider
	tmgr, err := task.New(a.cfg, provider, a.log, task.WithBus(a.bus))
	if err != nil {
		return fmt.Errorf("task manager: %w", err)
	}
	a.tasks = tmgr

	iotMgr, err := iot.New(a.cfg.IoT, a.log, iot.WithBus(a.bus))
	if err != nil {
		return fmt.Errorf("iot: %w", err)
	}
	a.iot = iotMgr

	sess, err := session.New(context.Background(), a.db, a.log)
	if err != nil {
		return fmt.Errorf("session manager: %w", err)
	}
	a.sessions = sess

	automation, err := automations.NewService(automations.Config{}, automations.Deps{
		Bus:  a.bus,
		Loop: a.loop,
		Log:  logger.WithSource(a.log, "services/automations"),
	})
	if err != nil {
		return fmt.Errorf("automations: %w", err)
	}
	a.automation = automation

	bt, err := backthink.New(backthink.ConfigFromBackground(a.cfg.Background), backthink.Deps{
		Bus:     a.bus,
		Thinker: backthink.NewLoopThinker(a.loop),
		State:   backthink.NewIoTStateProvider(iotMgr, a.log),
		DB:      a.db,
		Log:     logger.WithSource(a.log, "services/backthink"),
	})
	if err != nil {
		return fmt.Errorf("backthink: %w", err)
	}
	a.backthink = bt

	a.wireVoice()
	a.wireMCP()
	a.wireSkills()
	a.wireTerminalTool()
	return nil
}

// wireChannels constructs the four IM channel adapters from environment
// configuration, registers them so the admin API can enumerate them, and wires
// them into the channel bridge so a configured adapter connects and routes
// inbound messages through session→actor→loop→reply. Adapters without
// credentials stay disconnected (logged, never fatal): connecting with an empty
// config would either fail or, for weixin-ilink, trigger a blocking scan-code
// login.
func (a *app) wireChannels() error {
	adapters := buildChannelAdapters(a.log)
	for _, ch := range adapters {
		capp := registry.Capability{
			Name:        ch.Name(),
			Kind:        registry.KindChannel,
			Description: ch.Name(),
			Value:       ch,
		}
		if err := a.caps.Register(capp); err != nil {
			a.log.Warn("channel register skipped", "channel", ch.Name(), "error", err)
		}
	}

	bridge, berr := channelbridge.New(channelbridge.Options{
		Log:      logger.WithSource(a.log, "services/channelbridge"),
		Loop:     a.loop,
		Sessions: a.sessions,
		Owner:    a.owner,
	})
	if berr != nil {
		return fmt.Errorf("channel bridge: %w", berr)
	}
	for _, ch := range adapters {
		bridge.Add(ch)
	}
	bridge.Start()
	a.channelBridge = bridge
	a.log.Info("channel adapters registered", "count", len(adapters))
	return nil
}

// wireFrontend builds the gateway with the embedded/external SPA filesystem and
// the JWT/RBAC authenticator. Session/Persona/Memories are wired to the concrete
// managers so the admin/user list endpoints return real data.
func (a *app) wireFrontend() error {
	jwt := auth.New(a.cfg.Auth)
	apiKeys := auth.NewAPIKey(a.cfg.Auth)
	ragStore := knowledge.New(knowledge.Deps{
		Projects:       a.projStore,
		Retriever:      a.retriever,
		DefaultPersona: a.defaultPersonaID(),
		VectorOn:       a.vindex != nil,
		Log:            a.log,
	})
	auditStore, aerr := gateway.NewSQLiteAuditStore(context.Background(), a.db, a.log)
	if aerr != nil {
		a.log.Warn("audit store unavailable, falling back to in-memory", "error", aerr)
		auditStore = nil
	}
	gw, err := gateway.New(a.cfg, gateway.Deps{
		Log:         logger.WithSource(a.log, "gateway"),
		Auth:        jwt,
		Bus:         a.bus,
		Registry:    a.caps,
		Loop:        a.loop,
		Session:     a.sessions,
		Personas:    a.personas,
		Memories:    a.memStore,
		IoT:         a.iot,
		Scheduler:   a.scheduler,
		Tasks:       a.tasks,
		Automations: a.automation,
		Users:       apiKeys,
		Backthink:   a.backthink,
		RAG:         ragStore,
		AuditStore:  auditStore,
		Streaming:   true,
		Frontend:    resolveFrontendFS(a.log),
		Webhooks:    a.channelBridge.WebhookHandlers(),
	})
	if err != nil {
		return fmt.Errorf("gateway: %w", err)
	}
	gw.SetVoice(a.voice)
	a.gw = gw
	return nil
}

// dbCfgForEmbed returns the DB config used by the vector index, which opens the
// same SQLite file as the primary pool.
func (a *app) dbCfgForEmbed() config.DBConfig {
	cfg := a.cfg.DB
	cfg.SQLitePath = resolveSQLitePath(a.cfg, resolveDataDir(a.cfg))
	return cfg
}

// defaultPersonaID returns the id of the default persona, falling back to
// "cyrene".
func (a *app) defaultPersonaID() string {
	if c, ok := a.personas.DefaultCharacter(); ok {
		return c.PersonaID
	}
	return "cyrene"
}

// defaultInstructions returns the default persona's system prompt, falling back
// to its role text or a minimal instruction when neither is set.
func (a *app) defaultInstructions() string {
	if c, ok := a.personas.DefaultCharacter(); ok {
		if p, ok := a.personas.Persona(c.PersonaID); ok {
			if p.Identity.SystemPrompt != "" {
				return p.Identity.SystemPrompt
			}
			if p.Identity.Role != "" {
				return p.Identity.Role
			}
		}
	}
	return fallbackInstruction
}

// close shuts down every subsystem in dependency order and releases resources.
func (a *app) close(ctx context.Context) {
	if a.backthink != nil {
		_ = a.backthink.Stop(ctx)
	}
	if a.automation != nil {
		_ = a.automation.Stop(ctx)
	}
	if a.channelBridge != nil {
		a.channelBridge.Stop(ctx)
	}
	if a.scheduler != nil {
		_ = a.scheduler.CancelAll(ctx)
	}
	if a.gw != nil {
		a.gw.Close()
	}
	for _, reg := range a.mcpRegs {
		_ = reg.Unregister(ctx)
	}
	if a.tasks != nil {
		_ = a.tasks.Close()
	}
	if a.vindex != nil {
		_ = a.vindex.Close()
	}
	if a.bus != nil {
		_ = a.bus.Close()
	}
	if a.db != nil {
		_ = a.db.Close()
	}
	a.log.Info("cyrene shutdown complete")
}

// resolveDataDir returns the configured data directory (from .env / env, via
// cfg.DataDir), falling back to the OS-appropriate default only when no
// directory is configured.
func resolveDataDir(cfg *config.Config) string {
	if cfg.DataDir != "" {
		return cfg.DataDir
	}
	return platform.DefaultDataDir()
}

// resolveSQLitePath returns the SQLite path to use, deriving it under the data
// directory when the configured default is left untouched.
func resolveSQLitePath(cfg *config.Config, dataDir string) string {
	p := cfg.DB.SQLitePath
	if strings.TrimSpace(p) == "" || p == defaultSQLitePath {
		return filepath.Join(dataDir, "cyrene.db")
	}
	return p
}