Agent-Intent/intent/registry.go

package intent

import (
	"context"
	"fmt"
	"io/fs"
	"math"
	"regexp"
	"sort"
	"strings"
	"sync"
	"sync/atomic"

	"logging-system/logsys"
)

// Options 注册表与识别器的共享选项。零值字段在构建时填入默认值；
// GuardDomains / ProtectedDomains 决定快照的阶段归属与 overlay 保护范围。
type Options struct {
	// ProtectedDomains 保护域：overlay 覆盖或禁用这些域内的 spec 会整批失败（fail-closed）。
	ProtectedDomains []string
	// GuardDomains 守卫域：这些域内的 spec 在 Stage 0 演练，命中即短路返回 GuardHit。
	GuardDomains []string
	// TopN 结果候选数上限（默认 5）。
	TopN int
	// AmbiguityMargin 前两名分差小于该值判 Ambiguous（默认 0.1）。
	AmbiguityMargin float64
	// MaxInputLen 输入字节长度上限（默认 4096），超过返回 InvalidArgument。
	MaxInputLen int
	// MaxSpecs 快照内 spec 总数上限，含禁用（默认 2048）。
	MaxSpecs int
	// MaxPatternsPerSpec 单 spec 正则数量上限（默认 32）。
	MaxPatternsPerSpec int
	// MaxSlotsPerSpec 单 spec 槽位数量上限（默认 16）。
	MaxSlotsPerSpec int
	// Log 可选日志器；nil 时使用 Nop。识别日志不记录原始输入。
	Log *logsys.Logger
	// SlotValidators 作用域槽位校验器。构建与校验时先查此表，查不到再回落
	// 已弃用的全局表（RegisterSlotValidator）。不同 Registry 的同名校验器互不影响。
	SlotValidators map[string]SlotValidator
	// NFKC 为真时，词条与输入先做兼容等价归一（全角 ASCII、组合字符），再按
	// case_sensitive 决定是否小写。NFKC 不做繁简转换。
	NFKC bool
}

// Options 字段默认值。
const (
	DefaultTopN            = 5
	DefaultAmbiguityMargin = 0.1
	DefaultMaxInputLen     = 4096
	DefaultMaxSpecs        = 2048
	DefaultMaxPatterns     = 32
	DefaultMaxSlots        = 16
)

func (o Options) normalized() Options {
	n := o
	if n.TopN <= 0 {
		n.TopN = DefaultTopN
	}
	if n.AmbiguityMargin <= 0 {
		n.AmbiguityMargin = DefaultAmbiguityMargin
	}
	if n.MaxInputLen <= 0 {
		n.MaxInputLen = DefaultMaxInputLen
	}
	if n.MaxSpecs <= 0 {
		n.MaxSpecs = DefaultMaxSpecs
	}
	if n.MaxPatternsPerSpec <= 0 {
		n.MaxPatternsPerSpec = DefaultMaxPatterns
	}
	if n.MaxSlotsPerSpec <= 0 {
		n.MaxSlotsPerSpec = DefaultMaxSlots
	}
	if n.Log == nil {
		n.Log = logsys.Nop()
	}
	if len(n.SlotValidators) > 0 {
		cp := make(map[string]SlotValidator, len(n.SlotValidators))
		for k, v := range n.SlotValidators {
			cp[k] = v
		}
		n.SlotValidators = cp
	}
	return n
}

func (o Options) protectedSet() map[string]bool {
	return domainSet(o.ProtectedDomains)
}

func (o Options) guardSet() map[string]bool {
	return domainSet(o.GuardDomains)
}

func domainSet(domains []string) map[string]bool {
	m := make(map[string]bool, len(domains))
	for _, d := range domains {
		m[d] = true
	}
	return m
}

func (o Options) limits() limits {
	return limits{maxSpecs: o.MaxSpecs, maxPatternsPerSpec: o.MaxPatternsPerSpec, maxSlotsPerSpec: o.MaxSlotsPerSpec}
}

// ---- 编译产物 ----
// 槽位的编译产物与抽取/校验逻辑见 slots.go。

type compiledSpec struct {
	spec      IntentSpec
	termsAny  []string // 已按 case_sensitive 折叠
	termsAll  []string
	termsEx   []string
	patterns  []*regexp.Regexp
	slots     []compiledSlot
	guard     bool
	index     int // 合并序，确定性次序裁决用
	base      float64
	bonus     float64
	threshold float64
}

// matchOutcome 单个 spec 对一次输入的评估结果。
type matchOutcome struct {
	score    float64
	passed   bool
	hitTerms []string
	hitPat   []string
	reject   string // 非 passed 时的排除原因
}

// evaluate 按文档化的计分规则评估。input 为原文，folded 为小写折叠后文本。
func (cs *compiledSpec) evaluate(input, folded string) matchOutcome {
	hay := input
	if !cs.spec.Matcher.CaseSensitive {
		hay = folded
	}
	for _, t := range cs.termsEx {
		if strings.Contains(hay, t) {
			return matchOutcome{reject: "excluded_term:" + t}
		}
	}
	for _, t := range cs.termsAll {
		if !strings.Contains(hay, t) {
			return matchOutcome{reject: "missing_includes_all:" + t}
		}
	}
	var hitTerms, hitPat []string
	positive := false
	for _, t := range cs.termsAny {
		if strings.Contains(hay, t) {
			positive = true
			hitTerms = append(hitTerms, t)
		}
	}
	for i, p := range cs.patterns {
		if p.MatchString(input) {
			positive = true
			hitPat = append(hitPat, cs.spec.Matcher.Patterns[i])
		}
	}
	if !positive && (len(cs.termsAny) > 0 || len(cs.patterns) > 0) {
		return matchOutcome{reject: "no_positive_match"}
	}
	score := cs.base
	if len(hitPat) > 0 {
		score += cs.bonus
	}
	if score > 1 {
		score = 1
	}
	// 固定精度舍入：避免浮点噪声进入结果与 margin 比较。
	return matchOutcome{score: math.Round(score*10000) / 10000, passed: score >= cs.threshold, hitTerms: hitTerms, hitPat: hitPat}
}

func compileSpec(spec IntentSpec, guard bool, index int, scoped map[string]SlotValidator, nfkc bool) (*compiledSpec, error) {
	m := spec.Matcher
	fold := func(terms []string) []string {
		out := make([]string, len(terms))
		for i, t := range terms {
			out[i] = foldMatchText(t, nfkc, m.CaseSensitive)
		}
		return out
	}
	cs := &compiledSpec{
		spec:      spec,
		termsAny:  fold(m.IncludesAny),
		termsAll:  fold(m.IncludesAll),
		termsEx:   fold(m.ExcludesAny),
		patterns:  make([]*regexp.Regexp, len(m.Patterns)),
		guard:     guard,
		index:     index,
		base:      spec.Confidence.Base,
		bonus:     spec.Confidence.PatternBonus,
		threshold: spec.Confidence.Threshold,
	}
	if cs.base == 0 {
		cs.base = DefaultBase
	}
	if cs.bonus == 0 {
		cs.bonus = DefaultPatternBonus
	}
	if cs.threshold == 0 {
		cs.threshold = DefaultThreshold
	}
	for i, p := range m.Patterns {
		re, err := regexp.Compile(p)
		if err != nil {
			return nil, newError(InvalidSpec, "pattern 编译失败", "field", fmt.Sprintf("matcher.patterns[%d]", i), "id", spec.ID, "error", err.Error())
		}
		cs.patterns[i] = re
	}
	for _, s := range spec.Slots {
		cs2, err := compileSlot(s, scoped)
		if err != nil {
			return nil, err.(*Error).with("id", spec.ID)
		}
		cs.slots = append(cs.slots, cs2)
	}
	return cs, nil
}

// ---- 快照 ----

// Snapshot 是合并产物的不可变快照：全部 matcher 已编译，识别全程无锁读。
// 同一快照对同样输入给出同样结果；revision 单调递增。
type Snapshot struct {
	rev      int64
	margin   float64
	topN     int
	maxInput int
	specs    []*compiledSpec // 仅启用 spec，按合并序
	byID     map[string]int
	guardIdx []int
	disabled []string // 已禁用 id（overlay disable 与 spec.disabled 两个入口）
	sources  map[string]string
	total    int // 含禁用
	nfkc     bool
}

// Revision 返回快照版本号，随每次成功 Reload 递增。
func (s *Snapshot) Revision() int64 { return s.rev }

// SpecIDs 返回启用中的 spec id，按合并序（确定性次序裁决的注册序）。
func (s *Snapshot) SpecIDs() []string {
	ids := make([]string, len(s.specs))
	for i, cs := range s.specs {
		ids[i] = cs.spec.ID
	}
	return ids
}

// DisabledIDs 返回被禁用的 spec id，字典序。
func (s *Snapshot) DisabledIDs() []string {
	out := make([]string, len(s.disabled))
	copy(out, s.disabled)
	sort.Strings(out)
	return out
}

// Source 返回 spec 的来源描述（"builtin" 或 "<file>#intents[i]"）。
func (s *Snapshot) Source(id string) (string, bool) {
	src, ok := s.sources[id]
	return src, ok
}

// SpecByID 返回指定 id 的启用 spec 定义副本。切片与 Metadata 深拷贝，
// 调用方改返回值不会改到快照。不存在或已禁用时第二个返回值为 false。
func (s *Snapshot) SpecByID(id string) (IntentSpec, bool) {
	if idx, ok := s.byID[id]; ok {
		return cloneIntentSpec(s.specs[idx].spec), true
	}
	return IntentSpec{}, false
}

// Conflict 诊断信息：两个启用 spec 共享同一 includes_any 词条。
// 共享不一定是错误（计分与确定性次序会裁决），用于配置评审提示。
type Conflict struct {
	Kind string
	A    string
	B    string
	Term string
}

// Conflicts 报告非守卫 spec 之间共享的 includes_any 词条，确定性排序。
func (s *Snapshot) Conflicts() []Conflict {
	termOwners := make(map[string][]string)
	for _, cs := range s.specs {
		if cs.guard {
			continue
		}
		for _, t := range cs.spec.Matcher.IncludesAny {
			termOwners[t] = append(termOwners[t], cs.spec.ID)
		}
	}
	terms := make([]string, 0, len(termOwners))
	for t, owners := range termOwners {
		if len(owners) > 1 {
			terms = append(terms, t)
		}
	}
	sort.Strings(terms)
	var out []Conflict
	for _, t := range terms {
		owners := append([]string(nil), termOwners[t]...)
		sort.Strings(owners)
		for i := 0; i < len(owners); i++ {
			for j := i + 1; j < len(owners); j++ {
				out = append(out, Conflict{Kind: "shared_term", A: owners[i], B: owners[j], Term: t})
			}
		}
	}
	return out
}

// specHit 规则阶段的内部命中记录。
type specHit struct {
	cs    *compiledSpec
	score float64
	terms []string
	pats  []string
}

func lessHit(a, b specHit) bool {
	if a.score != b.score {
		return a.score > b.score
	}
	if a.cs.spec.Priority != b.cs.spec.Priority {
		return a.cs.spec.Priority > b.cs.spec.Priority
	}
	return a.cs.index < b.cs.index
}

func sortHits(hits []specHit) {
	sort.SliceStable(hits, func(i, j int) bool { return lessHit(hits[i], hits[j]) })
}

// evalGuard 评估守卫域 spec，返回过阈命中（已排序）。
func (s *Snapshot) evalGuard(input, folded string) []specHit {
	var hits []specHit
	for _, idx := range s.guardIdx {
		cs := s.specs[idx]
		if o := cs.evaluate(input, folded); o.passed {
			hits = append(hits, specHit{cs: cs, score: o.score, terms: o.hitTerms, pats: o.hitPat})
		}
	}
	sortHits(hits)
	return hits
}

// evalIDs 按给定 id 列表评估（挂起预期阶段用），返回过阈命中（已排序）。
func (s *Snapshot) evalIDs(ids []string, input, folded string) []specHit {
	var hits []specHit
	for _, id := range ids {
		idx, ok := s.byID[id]
		if !ok {
			continue
		}
		cs := s.specs[idx]
		if o := cs.evaluate(input, folded); o.passed {
			hits = append(hits, specHit{cs: cs, score: o.score, terms: o.hitTerms, pats: o.hitPat})
		}
	}
	sortHits(hits)
	return hits
}

// evalRules 对全部非守卫 spec 做线性扫描，返回过阈命中（已排序）。
// 规模上限是 Options.MaxSpecs（默认 DefaultMaxSpecs = 2048）。倒排索引留到
// 超过该上限仍不够用时再做；构建期已经拒绝超过上限的快照。
func (s *Snapshot) evalRules(input, folded string) []specHit {
	var hits []specHit
	for _, cs := range s.specs {
		if cs.guard {
			continue
		}
		if o := cs.evaluate(input, folded); o.passed {
			hits = append(hits, specHit{cs: cs, score: o.score, terms: o.hitTerms, pats: o.hitPat})
		}
	}
	sortHits(hits)
	return hits
}

func (h specHit) reason() string {
	var parts []string
	if len(h.terms) > 0 {
		parts = append(parts, "terms="+strings.Join(h.terms, ","))
	}
	if len(h.pats) > 0 {
		parts = append(parts, "patterns="+strings.Join(h.pats, ","))
	}
	return strings.Join(parts, " ")
}

func (h specHit) candidate(input string, withSlots bool) Candidate {
	cs := h.cs
	c := Candidate{
		ID:              cs.spec.ID,
		Domain:          cs.spec.Domain,
		Version:         cs.spec.Version,
		Confidence:      h.score,
		Priority:        cs.spec.Priority,
		Risk:            cs.spec.Risk,
		RequiresConfirm: cs.spec.RequiresConfirm,
		Handler:         cs.spec.Handler,
		Reason:          h.reason(),
	}
	if c.Risk == "" {
		c.Risk = RiskLow
	}
	if len(cs.spec.Metadata) > 0 {
		c.Metadata = make(map[string]string, len(cs.spec.Metadata))
		for k, v := range cs.spec.Metadata {
			c.Metadata[k] = v
		}
	}
	if withSlots {
		c.Slots, c.MissingRequiredSlots, c.InvalidSlots = cs.extractSlots(input)
	}
	return c
}

// fillTopSlots 给裁决后的 Top 补抽槽位。Ambiguous 路径建候选时不抽槽位，
// 分类器选定 Top 之后才知道该抽哪一条。
func (s *Snapshot) fillTopSlots(c *Candidate, input string) {
	idx, ok := s.byID[c.ID]
	if !ok {
		return
	}
	slots, missing, invalid := s.specs[idx].extractSlots(input)
	c.Slots = slots
	c.MissingRequiredSlots = missing
	c.InvalidSlots = invalid
}

func candidatesOf(hits []specHit, input string, topSlots bool) []Candidate {
	out := make([]Candidate, 0, len(hits))
	for i, h := range hits {
		out = append(out, h.candidate(input, topSlots && i == 0))
	}
	return out
}

// ---- 构建与合并 ----

// RegistryBuilder 收集 Go 内置基线 spec 并构建 Registry。
type RegistryBuilder struct {
	opts    Options
	builtin []IntentSpec
	seen    map[string]bool
}

// NewRegistryBuilder 创建构建器。opts 零值字段填默认。
func NewRegistryBuilder(opts Options) *RegistryBuilder {
	return &RegistryBuilder{opts: opts.normalized(), seen: make(map[string]bool)}
}

// Register 登记内置基线 spec，立即校验；重复 id 报 InvalidSpec。
func (b *RegistryBuilder) Register(specs ...IntentSpec) error {
	lim := b.opts.limits()
	for _, spec := range specs {
		if b.seen[spec.ID] {
			return newError(InvalidSpec, "内置 spec id 重复", "id", spec.ID)
		}
		if err := validateSpec(spec, lim, b.opts.SlotValidators); err != nil {
			return err
		}
		b.seen[spec.ID] = true
		b.builtin = append(b.builtin, spec)
	}
	return nil
}

// Build 仅用内置基线构建（rev 1）。此后 Reload 会报错（无配置来源）。
func (b *RegistryBuilder) Build() (*Registry, error) {
	return b.buildWithSource(nil, nil)
}

// BuildFS 用内置基线 + JSON overlay 来源构建，并记住来源供 Reload 重读。
// roots 按给定顺序应用；目录 root 内按文件名字典序加载 *.json。
func (b *RegistryBuilder) BuildFS(ctx context.Context, fsys fs.FS, roots ...string) (*Registry, error) {
	if fsys == nil {
		return nil, newError(InvalidArgument, "fsys 为 nil")
	}
	if len(roots) == 0 {
		return nil, newError(InvalidArgument, "至少提供一个配置 root")
	}
	return b.buildWithSource(fsys, roots)
}

func (b *RegistryBuilder) buildWithSource(fsys fs.FS, roots []string) (*Registry, error) {
	var entries []overlayEntry
	if fsys != nil {
		var err error
		entries, err = loadOverlays(fsys, roots)
		if err != nil {
			return nil, err
		}
	}
	snap, err := buildSnapshot(b.opts, b.builtin, entries, 1)
	if err != nil {
		return nil, err
	}
	r := &Registry{
		opts:      b.opts,
		builtin:   append([]IntentSpec(nil), b.builtin...),
		fsys:      fsys,
		roots:     append([]string(nil), roots...),
		hasSource: fsys != nil,
		log:       b.opts.Log,
	}
	r.snap.Store(snap)
	return r, nil
}

// Registry 持有当前快照与配置来源，支持原子 Reload。
type Registry struct {
	opts      Options
	builtin   []IntentSpec
	fsys      fs.FS
	roots     []string
	hasSource bool
	mu        sync.Mutex // 串行化 Reload
	snap      atomic.Pointer[Snapshot]
	log       *logsys.Logger
}

// Snapshot 返回当前生效快照。永不为 nil。
func (r *Registry) Snapshot() *Snapshot { return r.snap.Load() }

// Options 返回生效选项（已填默认值）。
func (r *Registry) Options() Options { return r.opts }

// Reload 重读配置来源并构建新快照；成功后原子替换并返回新快照。
// 任一步失败保留旧快照，revision 不变，返回带来源与原因的错误。
func (r *Registry) Reload(ctx context.Context) (*Snapshot, error) {
	r.mu.Lock()
	defer r.mu.Unlock()
	old := r.snap.Load()
	if !r.hasSource {
		err := newError(LoadFailed, "没有登记配置来源；用 BuildFS 构建后才能 Reload", "revision", old.rev)
		r.log.Module("intent").Error("intent config rejected", err)
		return nil, err
	}
	entries, err := loadOverlays(r.fsys, r.roots)
	if err != nil {
		r.log.Module("intent").Error("intent config rejected", err)
		return nil, err
	}
	ns, err := buildSnapshot(r.opts, r.builtin, entries, old.rev+1)
	if err != nil {
		r.log.Module("intent").Error("intent config rejected", err)
		return nil, err
	}
	r.snap.Store(ns)
	r.log.Module("intent").Info("intent snapshot reloaded",
		"revision", ns.rev, "specs", len(ns.specs), "disabled", len(ns.disabled))
	return ns, nil
}

// buildSnapshot 执行双源合并与编译。任一错误整批失败，不产生半套快照。
func buildSnapshot(opts Options, baseline []IntentSpec, entries []overlayEntry, rev int64) (*Snapshot, error) {
	opts = opts.normalized()
	protected := opts.protectedSet()
	guards := opts.guardSet()
	lim := opts.limits()

	ordered := append([]IntentSpec(nil), baseline...)
	pos := make(map[string]int, len(ordered))
	sources := make(map[string]string, len(ordered))
	for i, spec := range ordered {
		pos[spec.ID] = i
		sources[spec.ID] = "builtin"
	}
	var disabledList []string

	for _, e := range entries {
		if e.disable {
			idx, ok := pos[e.id]
			if !ok {
				return nil, newError(InvalidSpec, "disable 目标不存在", "id", e.id, "source", e.source)
			}
			if protected[ordered[idx].Domain] {
				return nil, newError(SpecProtected, "overlay 试图禁用保护域 spec",
					"id", e.id, "domain", ordered[idx].Domain, "source", e.source)
			}
			ordered = append(ordered[:idx], ordered[idx+1:]...)
			for id, p := range pos {
				if p > idx {
					pos[id] = p - 1
				}
			}
			delete(pos, e.id)
			disabledList = append(disabledList, e.id)
			sources[e.id] = e.source + " (disabled)"
			continue
		}
		spec := e.spec
		if err := validateSpec(spec, lim, opts.SlotValidators); err != nil {
			return nil, err.(*Error).with("source", e.source)
		}
		if idx, ok := pos[spec.ID]; ok {
			old := ordered[idx]
			if protected[old.Domain] {
				return nil, newError(SpecProtected, "overlay 试图覆盖保护域 spec",
					"id", spec.ID, "domain", old.Domain, "source", e.source)
			}
			if spec.Version <= old.Version {
				return nil, newError(InvalidSpec, "覆盖必须递增 version",
					"id", spec.ID, "old_version", old.Version, "new_version", spec.Version, "source", e.source)
			}
			ordered[idx] = spec
		} else {
			ordered = append(ordered, spec)
			pos[spec.ID] = len(ordered) - 1
		}
		sources[spec.ID] = e.source
	}

	total := len(ordered) + len(disabledList)
	if total > lim.maxSpecs {
		return nil, newError(InvalidSpec, "spec 总数超过上限", "total", total, "max", lim.maxSpecs)
	}

	snap := &Snapshot{
		rev:      rev,
		margin:   opts.AmbiguityMargin,
		topN:     opts.TopN,
		maxInput: opts.MaxInputLen,
		byID:     make(map[string]int, len(ordered)),
		disabled: disabledList,
		sources:  sources,
		total:    total,
		nfkc:     opts.NFKC,
	}
	nextIndex := 0
	for _, spec := range ordered {
		if spec.Disabled {
			snap.disabled = append(snap.disabled, spec.ID)
			continue
		}
		cs, err := compileSpec(spec, guards[spec.Domain], nextIndex, opts.SlotValidators, opts.NFKC)
		if err != nil {
			return nil, err
		}
		snap.specs = append(snap.specs, cs)
		snap.byID[spec.ID] = len(snap.specs) - 1
		if cs.guard {
			snap.guardIdx = append(snap.guardIdx, len(snap.specs)-1)
		}
		nextIndex++
	}
	return snap, nil
}