feat(harness): 评测闭环 —— 评测结果落库 + 分级 + 告警 + 可查(测温计→恒温器)

此前 eval 只打日志、不闭环。现在:
- 分级:evalLevel 据综合分+忠实度 → ok(≥0.75) / warn(≥0.5 或忠实<0.6) / poor(<0.5);poor 出 slog.Warn 告警。
- 落库:dispatcher 评完经 NATS(SubjectEval) 广播 EvalEvent → 网关订阅写 PG(新表 sundynix_eval,
  按 task_id upsert)。沿用任务状态回写那套(dispatcher 无 DB,经 bus→gateway 落库)。
- 可查:GET /api/v1/tasks/:id/eval 返回 overall/rule/llm/faithful/level/flags/reason/sources。
- 契约 EvalEvent + EvalOK/Warn/Poor;bus PublishEval/SubscribeEval;dispatcher EvalSink(NewOrchestrator 第9参)。

验证:三模块 build+vet+test 全绿;live RAG 任务评测落库,端点返回 overall~1.0 / level=ok / faithful=1 / sources=1。
剩:桌面端质量面板、低分自动重试(P3)。project_analysis 勾掉该项。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Blizzard
2026-06-25 15:26:19 +08:00
parent 446b784fc6
commit 10f08ffb14
12 changed files with 173 additions and 10 deletions
+14
View File
@@ -3,6 +3,7 @@ package main
import (
"context"
"encoding/json"
"log"
"os"
@@ -64,6 +65,19 @@ func main() {
log.Printf("[gateway] subscribe task status: %v", err)
}
// 评测闭环:订阅 dispatcher 回写的自动化评测结果,落 PG 供 UI 查询 / 质量趋势 / 门控。
if _, err := bus.SubscribeEval(func(ev *contract.EvalEvent) {
flags, _ := json.Marshal(ev.Flags)
if err := db.SaveEval(context.Background(), &store.Eval{
TaskID: ev.TaskID, Overall: ev.Overall, Rule: ev.Rule, LLM: ev.LLM, Faithful: ev.Faithful,
Level: ev.Level, Flags: string(flags), Reason: ev.Reason, Sources: ev.Sources,
}); err != nil {
log.Printf("[gateway] 落库评测 %s 失败: %v", ev.TaskID, err)
}
}); err != nil {
log.Printf("[gateway] subscribe eval: %v", err)
}
r := router.New(db, cache, bus, blobStore)
addr := envOr("GATEWAY_ADDR", ":8080")
log.Printf("[gateway] listening on %s", addr)