Files
Cyrene_v2/internal/services/automations/service.go
T
AskaEth 003d12a712 feat(trace): M40 span 写侧脱敏 + 共享上游错误收敛 helper
stderr 的 JSONL 是无主人在场的落盘面,却在此前原样落工具结果(result)、
子代理回复(text/summary)与上游报文,等于一次 tail 就能拷走整段对话。
本切片交付两件地基:

1) 写侧脱敏(trace.JSONRecorder)
   - 新增 trace/span_props.go:safePropKeys 白名单与 projectSpanProps 投影,
     读侧(safeSpanProps)与写侧共用同一张表、同一个投影函数;
   - WriteSpan 落盘前经 trace.SanitizeRecord 投影:白名单键清洗,表外键只留
     Digest(bytes/runes/sha256 前缀,收进 omitted),事件先 RedactEvent 再把
     正文键折成 Digest。落到磁盘的只有元数据,正文一个字节都不留;
   - 新增 trace/digest.go:Digest/DigestOf/DigestOfValue,给「脱敏后仍要能诊断」
     一个构造上不含正文的取值形态(体积 + 指纹),两条投影都按类型放行它。

2) 共享上游错误体收敛 helper(给 M41/M42,禁止三家各写一份)
   - trace.UpstreamError(upstream, status, contentType, body):只保留 status /
     contentType / bodyLen / body sha256 前缀 / 上游 JSON 的 error.code /
     error.type / 截断 128 rune 的 error.message,其余一律丢弃,响应体原文绝不
     进 error 或日志;*UpstreamErrorInfo 提供 Error()/Attrs()/Unwrap()(errors.Is
     可判 ErrUpstream 走降级链);
   - trace.HostOf / trace.MaskQuery:日志里的 URL 只回来源,凭据类 query 与
     fragment 值打码为 ***,user:pass@ 整段打码。

3) 剥掉三处正文上 span
   - loop:tool span 不再放 result,改放 result_summary(与 tool_execution.end
     帧同源、已脱敏截断)与 result_digest;
   - orchestration:subagent span 不再放 text,subagent.done 事件不再放 summary,
     改记 status/steps/chars/sha256;
   - automations:AddRuleByName 不再 %v 整个 payload,改记 subject/type/bytes/sha256。

测试:以哨兵正文在落盘字节上断言(JSONL / slog 输出),并分别对「编排层收到的
原始 span」与「写侧投影」两层各钉一遍;UpstreamError 用回显 input 的 422 报文
与 HTML 错误页各钉一条;解析出/未解析出 JSON 都不回原文。以上均做过变异验证
(去掉保护即变红)。

验收:go build ./... + go vet ./... + go test -count=1 ./... 全绿;
trace/loop/orchestration 另跑 -race 全绿。
2026-10-26 13:17:42 +08:00

267 lines
7.8 KiB
Go

package automations
import (
"context"
"errors"
"fmt"
"log/slog"
"sync"
"time"
"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/trace"
)
// Service composes the Scheduler (cron), the Engine (event rules) and the
// ReminderStore into a single automation engine with one lifecycle. It routes
// event rules to the Engine and cron rules to the Scheduler by Trigger kind.
type Service struct {
cfg Config
deps Deps
log *slog.Logger
sched *Scheduler
engine *Engine
remind *ReminderStore
mu sync.RWMutex
cronRules map[string]ScheduleID // rule id -> schedule id
cronMeta map[string]Rule // rule id -> cron rule (name/expression for listing)
}
// NewService builds an automation engine from cfg and deps. The bus in deps is
// required. It also resolves the AI pipeline used by AIAction construction.
func NewService(cfg Config, deps Deps) (*Service, error) {
if deps.Bus == nil {
return nil, fmt.Errorf("automations: new service: %w", ErrNilBus)
}
sched, err := New(cfg, deps)
if err != nil {
return nil, err
}
engine, err := NewEngine(cfg, deps)
if err != nil {
return nil, err
}
remind, err := NewReminder(cfg, deps)
if err != nil {
return nil, err
}
return &Service{
cfg: cfg,
deps: deps,
log: sourcedLog(deps.Log),
sched: sched,
engine: engine,
remind: remind,
cronRules: make(map[string]ScheduleID),
cronMeta: make(map[string]Rule),
}, nil
}
// Pipeline returns the service's resolved AI pipeline, or nil when neither a loop
// nor an agent is configured.
func (s *Service) Pipeline() Pipeline { return s.deps.pipeline() }
// Scheduler returns the underlying cron scheduler.
func (s *Service) Scheduler() *Scheduler { return s.sched }
// Engine returns the underlying event rule engine.
func (s *Service) Engine() *Engine { return s.engine }
// ReminderStore returns the underlying reminder store.
func (s *Service) ReminderStore() *ReminderStore { return s.remind }
// AddSchedule delegates to the Scheduler.
func (s *Service) AddSchedule(ctx context.Context, cronExpr string, action Action) (ScheduleID, error) {
return s.sched.AddSchedule(ctx, cronExpr, action)
}
// AddRule routes an event rule to the Engine and a cron rule to the Scheduler. A
// malformed rule returns an error wrapping ErrInvalidRule.
func (s *Service) AddRule(ctx context.Context, r Rule) error {
if !r.valid() {
return fmt.Errorf("automations: add rule %q: %w", r.ID, ErrInvalidRule)
}
switch r.Trigger {
case TriggerEvent:
return s.engine.AddEvent(ctx, r)
case TriggerCron:
id, err := s.sched.AddSchedule(ctx, r.Expression, r.Action)
if err != nil {
return err
}
s.mu.Lock()
s.cronRules[r.ID] = id
s.cronMeta[r.ID] = r
s.mu.Unlock()
return nil
default:
return fmt.Errorf("automations: add rule %q: %w", r.ID, ErrInvalidRule)
}
}
// RemoveRule removes an event or cron rule by id. It returns an error wrapping
// ErrNotFound when no such rule exists.
func (s *Service) RemoveRule(ctx context.Context, id string) error {
s.mu.Lock()
if schedID, ok := s.cronRules[id]; ok {
delete(s.cronRules, id)
delete(s.cronMeta, id)
s.mu.Unlock()
s.sched.RemoveSchedule(schedID)
return nil
}
s.mu.Unlock()
return s.engine.RemoveRule(ctx, id)
}
// AddReminder delegates to the ReminderStore.
func (s *Service) AddReminder(ctx context.Context, r Reminder) error {
return s.remind.Add(ctx, r)
}
// Reminders returns a sorted snapshot of registered reminders.
func (s *Service) Reminders() []Reminder { return s.remind.List() }
// List returns a read-only snapshot of every registered automation and reminder
// for the admin panel, composing the reminder store, the event rules and the
// cron schedules. It never mutates state and is safe for concurrent use. Cron
// entries' LastRun/NextRun are zero until the scheduler has run.
func (s *Service) List() []AutomationRecord {
out := make([]AutomationRecord, 0)
for _, r := range s.remind.List() {
at := r.At
out = append(out, AutomationRecord{
ID: r.ID,
Name: r.Message,
Kind: "reminder",
Enabled: true,
NextRun: at,
})
}
for _, r := range s.engine.Rules() {
out = append(out, AutomationRecord{
ID: r.ID,
Name: r.Name,
Kind: string(r.Trigger),
Enabled: true,
})
}
s.mu.RLock()
for id, rule := range s.cronMeta {
entry := s.sched.Entry(s.cronRules[id])
out = append(out, AutomationRecord{
ID: id,
Name: rule.Name,
Kind: string(rule.Trigger),
Cron: rule.Expression,
Enabled: true,
LastRun: entry.Prev,
NextRun: entry.Next,
})
}
s.mu.RUnlock()
return out
}
// CancelReminder delegates to the ReminderStore.
func (s *Service) CancelReminder(ctx context.Context, id string) error {
return s.remind.Cancel(ctx, id)
}
// AddRuleByName registers a named cron/event automation whose action records its
// fire on the service logger (a real, observable side effect) and returns the
// generated rule id. kind must be "cron" or "event"; expression is a cron spec
// for cron rules or a bus subject pattern for event rules. A malformed rule or
// expression returns an error wrapping ErrInvalidRule / ErrInvalidCron so the
// admin handler can answer honestly instead of fabricating a success.
//
// 🔴 日志只记触发面的元数据(规则名 / 订阅的 subject / payload 的类型、体积与
// 指纹),绝不记 payload 本身:绑到 `ws.chat`、`subagent.result` 这类 subject
// 上时,payload 里就是**她的正文**。原先这里 `%v` 整个 payload 打日志,等于把
// 一次对话原样抄进日志(M40 修掉的泄漏之一)。
func (s *Service) AddRuleByName(ctx context.Context, name, kind, expression string) (string, error) {
act, err := NewFuncAction(name, func(_ context.Context, payload any) (any, error) {
digest := trace.DigestOfValue(payload)
s.log.Info("admin automation fired",
"name", name,
"subject", expression,
"payload_type", payloadKind(payload),
"payload_bytes", digest.Bytes,
"payload_sha256", digest.SHA256,
)
return map[string]any{"fired": name, "payload": payload}, nil
})
if err != nil {
return "", err
}
rule := Rule{
ID: fmt.Sprintf("auto-%d", time.Now().UnixNano()),
Name: name,
Trigger: TriggerKind(kind),
Expression: expression,
Action: act,
}
if err := s.AddRule(ctx, rule); err != nil {
return "", err
}
return rule.ID, nil
}
// RunRule executes one registered rule's action once and returns its output. It
// is the manual "run now" path for the admin panel. It returns an error wrapping
// ErrNotFound when no rule or reminder carries id.
func (s *Service) RunRule(ctx context.Context, id string) (any, error) {
if id == "" {
return nil, fmt.Errorf("automations: run rule: %w", ErrInvalidRule)
}
for _, r := range s.engine.Rules() {
if r.ID == id {
return r.Action.Execute(ctx, nil)
}
}
s.mu.RLock()
r, ok := s.cronMeta[id]
s.mu.RUnlock()
if ok {
return r.Action.Execute(ctx, nil)
}
for _, rem := range s.remind.List() {
if rem.ID == id {
return map[string]any{"reminder": rem.ID, "message": rem.Message, "at": rem.At}, nil
}
}
return nil, fmt.Errorf("automations: run rule %q: %w", id, ErrNotFound)
}
// Start starts the scheduler, the event engine and the reminder loop.
func (s *Service) Start(ctx context.Context) error {
if err := s.sched.Start(ctx); err != nil {
return err
}
if err := s.engine.Start(ctx); err != nil {
return err
}
return s.remind.Start(ctx)
}
// Stop stops the reminder loop, the event engine and the scheduler, collecting
// errors from each.
func (s *Service) Stop(ctx context.Context) error {
var errs []error
if err := s.remind.Stop(ctx); err != nil {
errs = append(errs, err)
}
if err := s.engine.Stop(ctx); err != nil {
errs = append(errs, err)
}
if err := s.sched.Stop(ctx); err != nil {
errs = append(errs, err)
}
return errors.Join(errs...)
}