- 03.4.1:per-persona 路由载体选 models.json(组内新增 personaModels/personaProviders + 校验 + PersonaRoute()), Router/RuntimeLLM 快照绑定、loop 流式路径按该 turn 的 persona 路由;主步用路由结果、降级步钉自己的模型 - 03.4.3:本地第三级降级链(LLM_LOCAL_*,Configured() 含 Enabled ⇒ **默认关**),warn 标注来源 - 14.4.4:capacity 接入 L3(分类器接口 + TTL 缓存 + 严格 JSON 解析),CAPACITY_L3_ENABLED **默认 false** - 14.4.1:语义修正 —— group.multimodal 才是「主模型能否收图」(env 路径不再臆断),LLM_VISION_MODEL 只配视觉工具; vision/OCR 可各用不同模型;runtime 不再因有图抢路由(vision.Router 是唯一分层权威) - 14.4.5:新增 image-crop 工具(工具数 5→6,策略默认 owner-only),schema 支持按区域裁切 - 组合根:wire_runtime 读 group.Multimodal;capacity 装配拆出 wire_capacity.go(守 500 行) - 复核:`go build`/`go vet`/各包 `go test -count=1` 全绿;**6 条变异反证**先红后还原(含作者自查出的 2 条假阳性变异) - 未落:按 provider 的 thinking 开关(需 openai_encode.go/openai.go 文件面)、persona awakening(需 loader 文件面)
135 lines
4.1 KiB
Go
135 lines
4.1 KiB
Go
package capacity
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"strings"
|
|
"sync"
|
|
"time"
|
|
)
|
|
|
|
// IntentClassifier is the model-assisted intent classifier behind the L3 layer
|
|
// (design/14 §2.2 L3; 裁决 14.4.4). It is an interface so the decision engine
|
|
// stays testable without a model: the wiring supplies the LLM-backed
|
|
// implementation (NewLLMClassifier), a test supplies a stub.
|
|
//
|
|
// Classify returns the raw judgment for one turn's text — {isTask, taskKind,
|
|
// confidence} plus nothing else. An error means "no verdict": the caller keeps
|
|
// the conservative default rather than guessing.
|
|
type IntentClassifier interface {
|
|
Classify(ctx context.Context, text string) (Judgment, error)
|
|
}
|
|
|
|
// maxL3CacheEntries bounds the L3 verdict cache so a long-lived process cannot
|
|
// grow it without limit. Past the bound, expired entries are dropped first and
|
|
// the cache is cleared if every entry is still fresh.
|
|
const maxL3CacheEntries = 256
|
|
|
|
// ErrEmptyTurn is returned when the L3 classifier is asked to judge empty turn
|
|
// text. It is a sentinel so callers (and tests) can test the category without
|
|
// matching on the message text.
|
|
var ErrEmptyTurn = errors.New("capacity: empty turn text for L3 classification")
|
|
|
|
// DefaultL3CacheTTL is the default reuse window for an L3 verdict — the landing
|
|
// suggestion of 裁决 14.4.4 (5m): long enough that a repeated phrase inside one
|
|
// conversation costs one model call, short enough that a changed habit re-learns.
|
|
const DefaultL3CacheTTL = 5 * time.Minute
|
|
|
|
// l3Cache memoizes classifier verdicts per turn text for a bounded TTL, so the
|
|
// same phrase does not cost a model call on every round. A zero TTL disables
|
|
// reuse. The classifier call happens outside the lock: two concurrent turns must
|
|
// not serialize on each other's model call.
|
|
type l3Cache struct {
|
|
classifier IntentClassifier
|
|
ttl time.Duration
|
|
|
|
mu sync.Mutex
|
|
entries map[string]l3Entry
|
|
}
|
|
|
|
// l3Entry is one cached verdict with the time it was produced.
|
|
type l3Entry struct {
|
|
judgment Judgment
|
|
at time.Time
|
|
}
|
|
|
|
// newL3Cache builds the cache. A nil classifier yields nil, which the decider
|
|
// treats as "L3 not available".
|
|
func newL3Cache(classifier IntentClassifier, ttl time.Duration) *l3Cache {
|
|
if classifier == nil {
|
|
return nil
|
|
}
|
|
return &l3Cache{classifier: classifier, ttl: ttl, entries: map[string]l3Entry{}}
|
|
}
|
|
|
|
// classify returns the verdict for text, reusing a fresh cached one when
|
|
// possible. The bool reports whether a verdict was produced; an error is returned
|
|
// to the caller for reporting instead of being swallowed here.
|
|
func (c *l3Cache) classify(ctx context.Context, text string) (Judgment, error) {
|
|
key := l3CacheKey(text)
|
|
if key == "" {
|
|
return Judgment{}, ErrEmptyTurn
|
|
}
|
|
if j, ok := c.lookup(key, time.Now()); ok {
|
|
return j, nil
|
|
}
|
|
j, err := c.classifier.Classify(ctx, text)
|
|
if err != nil {
|
|
return Judgment{}, err
|
|
}
|
|
c.store(key, j, time.Now())
|
|
return j, nil
|
|
}
|
|
|
|
// lookup returns a fresh cached verdict, if any.
|
|
func (c *l3Cache) lookup(key string, now time.Time) (Judgment, bool) {
|
|
if c.ttl <= 0 {
|
|
return Judgment{}, false
|
|
}
|
|
c.mu.Lock()
|
|
defer c.mu.Unlock()
|
|
e, ok := c.entries[key]
|
|
if !ok {
|
|
return Judgment{}, false
|
|
}
|
|
if now.Sub(e.at) > c.ttl {
|
|
return Judgment{}, false
|
|
}
|
|
return e.judgment, true
|
|
}
|
|
|
|
// store records a verdict, evicting expired entries (and, if the bound is still
|
|
// exceeded, the whole map) so the cache cannot grow without limit.
|
|
func (c *l3Cache) store(key string, j Judgment, now time.Time) {
|
|
if c.ttl <= 0 {
|
|
return
|
|
}
|
|
c.mu.Lock()
|
|
defer c.mu.Unlock()
|
|
if len(c.entries) >= maxL3CacheEntries {
|
|
c.evictExpired(now)
|
|
}
|
|
c.entries[key] = l3Entry{judgment: j, at: now}
|
|
}
|
|
|
|
// evictExpired drops entries past their TTL; when none expired, it clears the
|
|
// map so a burst of distinct turns cannot pin the memory.
|
|
func (c *l3Cache) evictExpired(now time.Time) {
|
|
dropped := 0
|
|
for k, e := range c.entries {
|
|
if now.Sub(e.at) > c.ttl {
|
|
delete(c.entries, k)
|
|
dropped++
|
|
}
|
|
}
|
|
if dropped == 0 {
|
|
c.entries = map[string]l3Entry{}
|
|
}
|
|
}
|
|
|
|
// l3CacheKey normalizes a turn's text into the cache key. Empty text (nothing to
|
|
// classify) yields "".
|
|
func l3CacheKey(text string) string {
|
|
return strings.TrimSpace(text)
|
|
}
|