responses 直通超时可配,流式去总超时,代理补阶段超时

internal/api/aiadmin.go

@@ -3,6 +3,7 @@ package api
 import (
 	"net/http"
 	"strconv"
+	"time"
 
 	"github.com/gin-gonic/gin"
 
@@ -450,6 +451,9 @@ type aiSettingsResponse struct {
 	// 请求 tools 已包含同名工具时不覆盖
 	GrokWebSearch bool `json:"grokWebSearch"`
 	GrokXSearch   bool `json:"grokXSearch"`
+	// UpstreamWaitSeconds 是 responses 直通的上游无响应预算(秒):非流式为单次
+	// 尝试总超时,流式为等待响应头预算;multi-agent/搜索类模型需远超 60s
+	UpstreamWaitSeconds int `json:"upstreamWaitSeconds"`
 }
 
 // currentAiSettings 汇总网关运行时设置为响应体。
@@ -457,11 +461,12 @@ func (h *aiAdminHandler) currentAiSettings() aiSettingsResponse {
 	guardOn, guardKB := h.gw.StreamGuard()
 	web, x := h.gw.GrokSearch()
 	return aiSettingsResponse{
-		FilterDeprecated:   h.gw.FilterDeprecated(),
-		StreamGuardEnabled: guardOn,
-		StreamGuardKB:      guardKB,
-		GrokWebSearch:      web,
-		GrokXSearch:        x,
+		FilterDeprecated:    h.gw.FilterDeprecated(),
+		StreamGuardEnabled:  guardOn,
+		StreamGuardKB:       guardKB,
+		GrokWebSearch:       web,
+		GrokXSearch:         x,
+		UpstreamWaitSeconds: int(h.gw.UpstreamWait() / time.Second),
 	}
 }
 
@@ -480,7 +485,7 @@ func (h *aiAdminHandler) aiSettings(c *gin.Context) {
 //
 // @Summary  更新 AI 网关全局设置
 // @Tags     AI 管理
-// @Param    body body aiSettingsResponse true "全量提交;保险丝阈值限 1..1024 KB"
+// @Param    body body aiSettingsResponse true "全量提交;保险丝阈值限 1..1024 KB,上游无响应预算限 30..900 秒"
 // @Success  200 {object} aiSettingsResponse
 // @Failure  400 {object} map[string]string
 // @Security BearerAuth
@@ -495,6 +500,10 @@ func (h *aiAdminHandler) updateAiSettings(c *gin.Context) {
 		c.JSON(http.StatusBadRequest, gin.H{"error": "streamGuardKB 须在 1..1024"})
 		return
 	}
+	if req.UpstreamWaitSeconds < 30 || req.UpstreamWaitSeconds > 900 {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "upstreamWaitSeconds 须在 30..900"})
+		return
+	}
 	ctx := c.Request.Context()
 	if err := h.gw.SetFilterDeprecated(ctx, req.FilterDeprecated); err != nil {
 		respondError(c, err)
@@ -508,5 +517,9 @@ func (h *aiAdminHandler) updateAiSettings(c *gin.Context) {
 		respondError(c, err)
 		return
 	}
+	if err := h.gw.SetUpstreamWait(ctx, req.UpstreamWaitSeconds); err != nil {
+		respondError(c, err)
+		return
+	}
 	c.JSON(http.StatusOK, h.currentAiSettings())
 }