fix(cag): resolve data races, add queue observability, fix test coverage

Cycle 2 fixes from reviewer-sre + reviewer-quality:

- scheduler.go: remove delete() under RLock (data race); expired entries
  skipped on read, cleaned lazily by next MarkFailed write
- proxy.go: pre-populate transports for scheduler backends at startup to
  prevent concurrent map writes from ServeHTTP goroutines
- proxy.go: log + IncrQueueFull() on queue-full 503 path (was silent)
- proxy.go: remove stub total_tokens/hit_rate from cache-hit log event
- serviceadapter/router.go: Warnf when Auth.Required but jwtValidator nil
- observability: add queue_full_requests_total counter + Prometheus export
- scheduler_test.go: TestBackendAcquireCancelledContext (ctx cancel branch)
- proxy_test.go: implement TestWarmupHeaderHandling (remove t.Skip)
- router_test.go: TestAuthenticate_MethodCapabilityOverrideDirect (auth coverage)
This commit is contained in:
Admin Bot
2026-09-27 18:39:45 +08:00
parent fc5c0e967d
commit a731185588
8 changed files with 184 additions and 27 deletions
+6 -4
View File
@@ -128,10 +128,12 @@ func (s *Scheduler) selectRendezvous(cacheKey string) *Backend {
return scores[i].score > scores[j].score
})
for _, sc := range scores {
if t, failed := s.failedUntil[sc.b.Address]; !failed || now.After(t) {
if now.After(t) {
delete(s.failedUntil, sc.b.Address)
}
_, failed := s.failedUntil[sc.b.Address]
if !failed {
return sc.b
}
expiry := s.failedUntil[sc.b.Address]
if now.After(expiry) {
return sc.b
}
}