fix: 避免中转 Key 按透传的 ChatGPT 周限额长期冷却

README.md

@@ -108,6 +108,12 @@ gateway:
 - 修改 Compose `.env` 后需要重建容器以更新环境变量。调大等待时间时，需要确认客户端及反向代理的首字节超时。
 - 升级自动应用 `237_add_api_key_concurrency_limit.sql`，旧 Key 默认为 `0`。回退二进制不会撤销数据库新增字段。
 
+### 中转 API Key 的上游 429
+
+- OpenAI 平台普通 API Key 收到上游 429 时，使用管理端已有的“429 兜底冷却”设置（默认启用、5 秒），不再把透传的 ChatGPT/Codex 周窗口、`resets_at` 或使用率快照写成整个 Key 的配额状态。关闭该设置时不新增本地兜底冷却，上游错误仍按原有响应与故障转移逻辑处理。
+- OAuth / Setup Token 保留真实配额窗口；Ollama Cloud、国产供应商和 OpenCode Go 的已识别专用配额逻辑，以及池模式、自定义错误策略和显式临时停调规则，仍按原有优先级处理。
+- 管理端测试 API Key 时，不再用透传的 ChatGPT 429 重置时间更新 Key 的调度状态。升级不会自动清理此前已写入的长冷却；核实状态后可使用管理端恢复功能处理。
+
 ## 技术栈
 
 | 组件 | 技术 |

backend/internal/service/account_test_service.go

@@ -2641,6 +2641,12 @@ func (s *AccountTestService) reconcileOpenAI429State(ctx context.Context, accoun
 		return
 	}
 
+	// A relayed ChatGPT quota window is not the API key's own quota. Manual
+	// tests must not turn it into a persistent key-wide scheduling block.
+	if !account.IsOpenAIOAuthLike() {
+		return
+	}
+
 	persistOpenAI429PlanType(ctx, s.accountRepo, account, body)
 
 	var resetAt *time.Time

backend/internal/service/account_test_service_openai_test.go

@@ -444,9 +444,9 @@ func TestAccountTestService_OpenAIAPIKey429DoesNotSyncUpstreamPlanType(t *testin
 				}
 				require.Equal(t, AccountTypeAPIKey, account.Type)
 				require.Equal(t, "test-key", account.GetCredential("api_key"))
-				require.Equal(t, account.ID, repo.rateLimitedID)
-				require.NotNil(t, account.RateLimitResetAt)
-				require.Equal(t, int64(4102444800), account.RateLimitResetAt.Unix())
+				require.Zero(t, repo.rateLimitedID)
+				require.Nil(t, account.RateLimitedAt)
+				require.Nil(t, account.RateLimitResetAt)
 			})
 		}
 	}

backend/internal/service/openai_account_runtime_block_fastpath_test.go

@@ -371,8 +371,10 @@ func TestOpenAI429FastPath_OpenCodeGoUsageLimitUsesMessageResetDuration(t *testi
 	repo := &rateLimit429AccountRepoStub{}
 	rateLimitService := NewRateLimitService(repo, nil, &config.Config{}, nil, nil)
 	svc := &OpenAIGatewayService{rateLimitService: rateLimitService}
-	rateLimitService.SetAccountRuntimeBlocker(svc)
-	account := &Account{ID: 44, Platform: PlatformOpenAI, Type: AccountTypeAPIKey}
+	blocker := &runtimeBlockRecorder{}
+	rateLimitService.SetAccountRuntimeBlocker(blocker)
+	// Only an identified provider owns this quota; generic relayed OpenAI keys use fallback.
+	account := &Account{ID: 44, Platform: PlatformOpenCodeGo, Type: AccountTypeAPIKey}
 	body := []byte(`{"type":"error","error":{"type":"GoUsageLimitError","message":"5-hour usage limit reached. Resets in 4hr 59min. To continue using this model now, enable usage from your available balance: https://opencode.ai/workspace/wrk_test/go"},"metadata":{"workspace":"wrk_test","limitName":"5 hour"}}`)
 
 	before := time.Now()
@@ -391,7 +393,8 @@ func TestOpenAI429FastPath_OpenCodeGoUsageLimitUsesMessageResetDuration(t *testi
 	expectedResetAfter := 4*time.Hour + 59*time.Minute
 	require.False(t, repo.lastRateLimitReset.Before(before.Add(expectedResetAfter-time.Second)))
 	require.False(t, repo.lastRateLimitReset.After(after.Add(expectedResetAfter)))
-	require.True(t, svc.isOpenAIAccountRuntimeBlocked(account))
+	require.Equal(t, []*Account{account}, blocker.accounts)
+	require.Equal(t, []time.Time{repo.lastRateLimitReset}, blocker.until)
 }
 
 // TestOpenAI429FastPath_SkipsSparkShadow 外审第8轮 P1:spark 影子被选中后若 /responses 返回 429,

backend/internal/service/openai_oauth_passthrough_test.go

@@ -1635,10 +1635,10 @@ func TestOpenAIGatewayService_OpenAIPassthrough_RetryableStatusesTriggerFailover
 				return fmt.Sprintf(`{"error":{"message":"The usage limit has been reached","type":"usage_limit_reached","resets_at":%d}}`, resetAt)
 			}(),
 			expectFailover: true,
-			assertRepo: func(t *testing.T, repo *openAIPassthroughFailoverRepo, _ time.Time) {
+			assertRepo: func(t *testing.T, repo *openAIPassthroughFailoverRepo, start time.Time) {
 				require.Len(t, repo.rateLimitCalls, 1)
 				require.Empty(t, repo.overloadCalls)
-				require.True(t, time.Until(repo.rateLimitCalls[0]) > 24*time.Hour)
+				requireOpenAIWSQuotaCooldown(t, AccountTypeAPIKey, repo.rateLimitCalls[0], start, time.Now(), time.Time{})
 			},
 		},
 		{