设置页AI Tab:网关设置入库、保险丝改维度与grok工具注入

internal/api/aiadmin.go

@@ -422,9 +422,47 @@ func aiPathID(c *gin.Context) (uint, bool) {
 	return uint(id), true
 }
 
+// modelCatalog 返回启用渠道聚合去重后的模型目录(含能力),黑名单添加弹窗用。
+//
+// @Summary  聚合模型目录
+// @Tags     AI 管理
+// @Success  200 {object} itemsResponse[service.AggregatedModel]
+// @Security BearerAuth
+// @Router   /api/v1/ai-model-catalog [get]
+func (h *aiAdminHandler) modelCatalog(c *gin.Context) {
+	items, err := h.gw.AggregatedModels(c.Request.Context())
+	if err != nil {
+		respondError(c, err)
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{"items": items})
+}
+
 // aiSettingsResponse 是 AI 网关全局设置(文档与响应共用)。
 type aiSettingsResponse struct {
+	// FilterDeprecated 开启后已宣布弃用(即使未退役)的模型从列表与路由中排除
 	FilterDeprecated bool `json:"filterDeprecated"`
+	// StreamGuardEnabled / StreamGuardKB 是 Responses 流式保险丝:
+	// instructions+tools 合计超阈值(KB)的流式请求改非流式上游并合成 SSE
+	StreamGuardEnabled bool `json:"streamGuardEnabled"`
+	StreamGuardKB      int  `json:"streamGuardKB"`
+	// GrokWebSearch / GrokXSearch 是 xai. 模型服务端搜索工具默认注入开关;
+	// 请求 tools 已包含同名工具时不覆盖
+	GrokWebSearch bool `json:"grokWebSearch"`
+	GrokXSearch   bool `json:"grokXSearch"`
+}
+
+// currentAiSettings 汇总网关运行时设置为响应体。
+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,
+	}
 }
 
 // aiSettings 返回 AI 网关全局设置。
@@ -435,15 +473,16 @@ type aiSettingsResponse struct {
 // @Security BearerAuth
 // @Router   /api/v1/ai-settings [get]
 func (h *aiAdminHandler) aiSettings(c *gin.Context) {
-	c.JSON(http.StatusOK, aiSettingsResponse{FilterDeprecated: h.gw.FilterDeprecated()})
+	c.JSON(http.StatusOK, h.currentAiSettings())
 }
 
-// updateAiSettings 更新 AI 网关全局设置(当前仅「过滤弃用模型」开关)。
+// updateAiSettings 更新 AI 网关全局设置(过滤弃用/流式保险丝/grok 搜索工具默认注入)。
 //
 // @Summary  更新 AI 网关全局设置
 // @Tags     AI 管理
-// @Param    body body aiSettingsResponse true "开启后已宣布弃用(即使未退役)的模型从列表与路由中排除"
+// @Param    body body aiSettingsResponse true "全量提交;保险丝阈值限 1..1024 KB"
 // @Success  200 {object} aiSettingsResponse
+// @Failure  400 {object} map[string]string
 // @Security BearerAuth
 // @Router   /api/v1/ai-settings [put]
 func (h *aiAdminHandler) updateAiSettings(c *gin.Context) {
@@ -452,9 +491,22 @@ func (h *aiAdminHandler) updateAiSettings(c *gin.Context) {
 		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
 		return
 	}
-	if err := h.gw.SetFilterDeprecated(c.Request.Context(), req.FilterDeprecated); err != nil {
+	if req.StreamGuardKB < 1 || req.StreamGuardKB > 1024 {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "streamGuardKB 须在 1..1024"})
+		return
+	}
+	ctx := c.Request.Context()
+	if err := h.gw.SetFilterDeprecated(ctx, req.FilterDeprecated); err != nil {
 		respondError(c, err)
 		return
 	}
-	c.JSON(http.StatusOK, aiSettingsResponse{FilterDeprecated: h.gw.FilterDeprecated()})
+	if err := h.gw.SetStreamGuard(ctx, req.StreamGuardEnabled, req.StreamGuardKB); err != nil {
+		respondError(c, err)
+		return
+	}
+	if err := h.gw.SetGrokSearch(ctx, req.GrokWebSearch, req.GrokXSearch); err != nil {
+		respondError(c, err)
+		return
+	}
+	c.JSON(http.StatusOK, h.currentAiSettings())
 }

internal/api/aigateway.go

@@ -587,8 +587,13 @@ func (h *aiGatewayHandler) responsesPassthrough(c *gin.Context, raw []byte, req
 		return
 	}
 	logRespCompat(req.Model, compat)
+	web, x := h.gw.GrokSearch()
+	if injectedBody, injected := service.RespInjectGrokTools(body, req.Model, web, x); len(injected) > 0 {
+		body = injectedBody
+		log.Printf("responses 直通(model=%s): 默认注入 %s", req.Model, strings.Join(injected, ", "))
+	}
 	if req.Stream {
-		if len(body) > service.RespStreamUpgradeLimit {
+		if on, kb := h.gw.StreamGuard(); on && service.RespGuardBytes(body) > kb*1024 {
 			h.responsesStreamUpgrade(c, body, req, compat)
 			return
 		}
@@ -630,9 +635,9 @@ func logRespCompat(model string, compat service.RespCompat) {
 	log.Printf("responses 直通(model=%s): %s", model, strings.Join(parts, "; "))
 }
 
-// responsesStreamUpgrade 流式升级回退:上游对超大流式请求会在推理途中掐断
-// (实测 >~82KB,见 RespStreamUpgradeLimit),超限时改调非流式上游拿完整响应,
-// 本地合成最小 SSE 事件序列回给客户端;丢失增量输出,换会话不中断。
+// responsesStreamUpgrade 流式升级回退:instructions+tools 合计超过保险丝阈值
+// (设置页 AI Tab 配置,默认开 60KB;上游对 >≈64.5KB 会静默断流)时改调非流式
+// 上游拿完整响应,本地合成最小 SSE 事件序列回给客户端;丢失增量输出,换会话不中断。
 func (h *aiGatewayHandler) responsesStreamUpgrade(c *gin.Context, body []byte, req aiwire.RespRequest, compat service.RespCompat) {
 	start := time.Now()
 	nsBody, err := service.RespDisableStream(body)
@@ -640,7 +645,8 @@ func (h *aiGatewayHandler) responsesStreamUpgrade(c *gin.Context, body []byte, r
 		aiError(c, http.StatusBadRequest, "invalid_request_error", err.Error())
 		return
 	}
-	log.Printf("responses 直通(model=%s): 请求体 %dKB 超流式安全上限,改走非流式合成 SSE", req.Model, len(body)/1024)
+	log.Printf("responses 直通(model=%s): instructions+tools %dKB 超保险丝阈值,改走非流式合成 SSE",
+		req.Model, service.RespGuardBytes(body)/1024)
 	payload, meta, err := h.gw.RespPassthrough(c.Request.Context(), nsBody, req.Model, keyGroup(c))
 	entry := h.logEntry(c, "responses", req.Model, true, meta, start)
 	if err != nil {

internal/api/routes_ai.go

@@ -39,6 +39,7 @@ func registerAiAdmin(secured *gin.RouterGroup, aiGateway *service.AiGatewayServi
 	secured.GET("/ai-channels/:id/models", aiadmin.listChannelModels)
 	secured.POST("/ai-channels/:id/test-model", aiadmin.testChannelModel)
 	secured.GET("/ai-models", aiadmin.gatewayModels)
+	secured.GET("/ai-model-catalog", aiadmin.modelCatalog)
 	secured.GET("/ai-settings", aiadmin.aiSettings)
 	secured.PUT("/ai-settings", aiadmin.updateAiSettings)
 	secured.GET("/ai-blacklist", aiadmin.listBlacklist)