AI 网关切换 OpenAI 兼容面并移除 chat 端点,新增模型黑白名单

internal/api/aiadmin.go

@@ -40,15 +40,16 @@ func (h *aiAdminHandler) listKeys(c *gin.Context) {
 // @Router   /api/v1/ai-keys [post]
 func (h *aiAdminHandler) createKey(c *gin.Context) {
 	var req struct {
-		Name  string `json:"name" binding:"required"`
-		Value string `json:"value"`
-		Group string `json:"group"`
+		Name   string   `json:"name" binding:"required"`
+		Value  string   `json:"value"`
+		Group  string   `json:"group"`
+		Models []string `json:"models"`
 	}
 	if err := c.ShouldBindJSON(&req); err != nil {
 		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
 		return
 	}
-	plaintext, key, err := h.gw.CreateKey(c.Request.Context(), req.Name, req.Value, req.Group)
+	plaintext, key, err := h.gw.CreateKey(c.Request.Context(), req.Name, req.Value, req.Group, req.Models)
 	if err != nil {
 		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
 		return
@@ -69,15 +70,16 @@ func (h *aiAdminHandler) updateKey(c *gin.Context) {
 		return
 	}
 	var req struct {
-		Name    string  `json:"name"`
-		Enabled *bool   `json:"enabled"`
-		Group   *string `json:"group"`
+		Name    string    `json:"name"`
+		Enabled *bool     `json:"enabled"`
+		Group   *string   `json:"group"`
+		Models  *[]string `json:"models"`
 	}
 	if err := c.ShouldBindJSON(&req); err != nil {
 		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
 		return
 	}
-	if err := h.gw.UpdateKey(c.Request.Context(), id, req.Name, req.Enabled, req.Group); err != nil {
+	if err := h.gw.UpdateKey(c.Request.Context(), id, req.Name, req.Enabled, req.Group, req.Models); err != nil {
 		respondError(c, err)
 		return
 	}
@@ -285,6 +287,64 @@ func (h *aiAdminHandler) gatewayModels(c *gin.Context) {
 	c.JSON(http.StatusOK, gin.H{"items": list.Data})
 }
 
+// ---- 模型黑名单 ----
+
+// @Summary  模型黑名单列表
+// @Tags     AI 管理
+// @Success  200 {object} map[string]any
+// @Security BearerAuth
+// @Router   /api/v1/ai-blacklist [get]
+func (h *aiAdminHandler) listBlacklist(c *gin.Context) {
+	items, err := h.gw.Blacklist(c.Request.Context())
+	if err != nil {
+		respondError(c, err)
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{"items": items})
+}
+
+// addBlacklist 拉黑模型:删除全部渠道缓存中的同名条目,后续同步 / 探测均过滤。
+//
+// @Summary  添加模型黑名单
+// @Tags     AI 管理
+// @Param    body body object true "请求体:{name: 模型名}"
+// @Success  201 {object} map[string]any
+// @Security BearerAuth
+// @Router   /api/v1/ai-blacklist [post]
+func (h *aiAdminHandler) addBlacklist(c *gin.Context) {
+	var req struct {
+		Name string `json:"name" binding:"required"`
+	}
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+		return
+	}
+	item, err := h.gw.AddBlacklist(c.Request.Context(), req.Name)
+	if err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+		return
+	}
+	c.JSON(http.StatusCreated, gin.H{"item": item})
+}
+
+// @Summary  移除模型黑名单(重新同步后模型恢复入池)
+// @Tags     AI 管理
+// @Param    id path int true "黑名单条目 ID"
+// @Success  204 "无内容"
+// @Security BearerAuth
+// @Router   /api/v1/ai-blacklist/{id} [delete]
+func (h *aiAdminHandler) removeBlacklist(c *gin.Context) {
+	id, ok := aiPathID(c)
+	if !ok {
+		return
+	}
+	if err := h.gw.RemoveBlacklist(c.Request.Context(), id); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+		return
+	}
+	c.Status(http.StatusNoContent)
+}
+
 // @Summary  AI 调用日志列表
 // @Tags     AI 管理
 // @Success  200 {object} map[string]any

internal/api/aigateway.go

@@ -1,13 +1,15 @@
 package api
 
 import (
+	"bufio"
+	"bytes"
 	"crypto/rand"
 	"encoding/hex"
 	"encoding/json"
 	"errors"
-	"fmt"
 	"io"
 	"net/http"
+	"slices"
 	"strings"
 	"time"
 
@@ -86,6 +88,25 @@ func keyGroup(c *gin.Context) string {
 	return ""
 }
 
+// keyModels 取当前请求密钥的模型白名单(空 = 不限模型)。
+func keyModels(c *gin.Context) []string {
+	if key, ok := c.Get(aiKeyCtx); ok {
+		return key.(*model.AiKey).Models
+	}
+	return nil
+}
+
+// checkKeyModel 校验请求模型是否在密钥白名单内;拒绝时按端点协议返回
+// 404 model_not_found(与未知模型同口径,不泄露密钥配置细节)并返回 false。
+func checkKeyModel(c *gin.Context, modelName string) bool {
+	allowed := keyModels(c)
+	if len(allowed) == 0 || slices.Contains(allowed, modelName) {
+		return true
+	}
+	aiError(c, http.StatusNotFound, "model_not_found", "模型不存在或无权访问: "+modelName)
+	return false
+}
+
 // logEntry 组装调用日志骨架;usage / status 由调用方补齐。
 func (h *aiGatewayHandler) logEntry(c *gin.Context, endpoint, modelName string, stream bool, meta service.ChatMeta, start time.Time) model.AiCallLog {
 	entry := model.AiCallLog{
@@ -102,21 +123,6 @@ func (h *aiGatewayHandler) logEntry(c *gin.Context, endpoint, modelName string,
 }
 
 // validateIR 做协议无关的入参检查(模型名、消息、不支持的内容块)。
-func validateIR(ir aiwire.ChatRequest) error {
-	if strings.TrimSpace(ir.Model) == "" {
-		return fmt.Errorf("model 不能为空")
-	}
-	if len(ir.Messages) == 0 {
-		return fmt.Errorf("messages 不能为空")
-	}
-	for _, m := range ir.Messages {
-		if m.Content.HasUnsupported() {
-			return service.ErrAiUnsupportedBlock
-		}
-	}
-	return nil
-}
-
 // maybeLogContent 在调用密钥显式开启内容日志且未过期时写正文(红线例外);
 // respBody 为 nil 时只记请求(流式响应与向量结果不记录);callLogID 关联同次调用日志。
 func (h *aiGatewayHandler) maybeLogContent(c *gin.Context, callLogID uint, endpoint, modelName string, stream bool, reqBody, respBody any) {
@@ -147,47 +153,6 @@ func (h *aiGatewayHandler) logFailure(c *gin.Context, entry model.AiCallLog, req
 	h.maybeLogContent(c, callID, entry.Endpoint, entry.Model, entry.Stream, reqBody, nil)
 }
 
-// chatCompletions 是 OpenAI /ai/v1/chat/completions 端点。
-//
-// @Summary  OpenAI 兼容对话补全
-// @Tags     AI 网关
-// @Param    body body object true "OpenAI chat/completions 请求体(支持 stream)"
-// @Success  200 {object} map[string]any "OpenAI 兼容响应(流式为 SSE)"
-// @Router   /ai/v1/chat/completions [post]
-func (h *aiGatewayHandler) chatCompletions(c *gin.Context) {
-	var ir aiwire.ChatRequest
-	if err := c.ShouldBindJSON(&ir); err != nil {
-		aiError(c, http.StatusBadRequest, "invalid_request_error", err.Error())
-		return
-	}
-	if err := validateIR(ir); err != nil {
-		aiError(c, http.StatusBadRequest, "invalid_request_error", err.Error())
-		return
-	}
-	if ir.Stream {
-		h.streamOpenAI(c, ir)
-		return
-	}
-	start := time.Now()
-	resp, meta, err := h.gw.Chat(c.Request.Context(), ir, keyGroup(c))
-	entry := h.logEntry(c, "openai", ir.Model, false, meta, start)
-	if err != nil {
-		upstreamError(c, err)
-		entry.ErrMsg = err.Error()
-		h.logFailure(c, entry, ir)
-		return
-	}
-	resp.ID = aiRandID("chatcmpl-")
-	if resp.Created == 0 {
-		resp.Created = time.Now().Unix()
-	}
-	entry.Status = http.StatusOK
-	fillUsage(&entry, resp.Usage)
-	callID := h.gw.LogCall(entry)
-	h.maybeLogContent(c, callID, "openai", ir.Model, false, ir, resp)
-	c.JSON(http.StatusOK, resp)
-}
-
 func fillUsage(entry *model.AiCallLog, u *aiwire.Usage) {
 	if u == nil {
 		return
@@ -217,6 +182,9 @@ func (h *aiGatewayHandler) embeddings(c *gin.Context) {
 		aiError(c, http.StatusBadRequest, "invalid_request_error", "仅支持 encoding_format=float")
 		return
 	}
+	if !checkKeyModel(c, req.Model) {
+		return
+	}
 	start := time.Now()
 	resp, meta, err := h.gw.Embeddings(c.Request.Context(), req, keyGroup(c))
 	entry := h.logEntry(c, "embeddings", req.Model, false, meta, start)
@@ -235,44 +203,6 @@ func (h *aiGatewayHandler) embeddings(c *gin.Context) {
 	c.JSON(http.StatusOK, resp)
 }
 
-// streamOpenAI 以 OpenAI SSE 直通流式响应,末尾发 [DONE]。
-func (h *aiGatewayHandler) streamOpenAI(c *gin.Context, ir aiwire.ChatRequest) {
-	start := time.Now()
-	stream, meta, err := h.gw.OpenStream(c.Request.Context(), ir, keyGroup(c))
-	entry := h.logEntry(c, "openai", ir.Model, true, meta, start)
-	if err != nil {
-		upstreamError(c, err)
-		entry.ErrMsg = err.Error()
-		h.logFailure(c, entry, ir)
-		return
-	}
-	defer stream.Close()
-	sseHeaders(c)
-	id, created := aiRandID("chatcmpl-"), time.Now().Unix()
-	var usage *aiwire.Usage
-	for {
-		chunk, err := stream.Next()
-		if err != nil {
-			if !errors.Is(err, io.EOF) {
-				entry.ErrMsg = err.Error()
-			}
-			break
-		}
-		chunk.ID, chunk.Created = id, created
-		if chunk.Usage != nil {
-			usage = chunk.Usage
-		}
-		writeSSEData(c, chunk)
-	}
-	c.Writer.WriteString("data: [DONE]\n\n")
-	c.Writer.Flush()
-	entry.Status = http.StatusOK
-	entry.LatencyMs = time.Since(start).Milliseconds()
-	fillUsage(&entry, usage)
-	callID := h.gw.LogCall(entry)
-	h.maybeLogContent(c, callID, "openai", ir.Model, true, ir, nil)
-}
-
 func sseHeaders(c *gin.Context) {
 	c.Header("Content-Type", "text/event-stream")
 	c.Header("Cache-Control", "no-cache")
@@ -280,22 +210,11 @@ func sseHeaders(c *gin.Context) {
 	c.Writer.Flush()
 }
 
-func writeSSEData(c *gin.Context, v any) {
-	b, err := json.Marshal(v)
-	if err != nil {
-		return
-	}
-	c.Writer.WriteString("data: ")
-	c.Writer.Write(b)
-	c.Writer.WriteString("\n\n")
-	c.Writer.Flush()
-}
-
 // messages 是 Anthropic /ai/v1/messages 端点。
 //
 // @Summary  Anthropic Messages 兼容端点
 // @Tags     AI 网关
-// @Param    body body object true "Anthropic messages 请求体(支持 stream)"
+// @Param    body body object true "Anthropic messages 请求体(支持 stream;经 OCI OpenAI 兼容面直通)"
 // @Success  200 {object} map[string]any "Anthropic 兼容响应(流式为 SSE)"
 // @Router   /ai/v1/messages [post]
 func (h *aiGatewayHandler) messages(c *gin.Context) {
@@ -308,69 +227,92 @@ func (h *aiGatewayHandler) messages(c *gin.Context) {
 		aiError(c, http.StatusBadRequest, "invalid_request_error", "max_tokens 必填且需大于 0")
 		return
 	}
-	ir, err := service.AnthropicToIR(req)
+	if len(req.Messages) == 0 {
+		aiError(c, http.StatusBadRequest, "invalid_request_error", "messages 不能为空")
+		return
+	}
+	if !checkKeyModel(c, req.Model) {
+		return
+	}
+	body, err := service.AnthropicToResponsesBody(req)
 	if err != nil {
 		aiError(c, http.StatusBadRequest, "invalid_request_error", err.Error())
 		return
 	}
-	if err := validateIR(ir); err != nil {
-		aiError(c, http.StatusBadRequest, "invalid_request_error", err.Error())
-		return
-	}
 	if req.Stream {
-		h.streamAnthropic(c, ir)
+		h.streamAnthropic(c, body, req)
 		return
 	}
 	start := time.Now()
-	resp, meta, err := h.gw.Chat(c.Request.Context(), ir, keyGroup(c))
-	entry := h.logEntry(c, "anthropic", ir.Model, false, meta, start)
+	payload, meta, err := h.gw.RespPassthrough(c.Request.Context(), body, req.Model, keyGroup(c))
+	entry := h.logEntry(c, "anthropic", req.Model, false, meta, start)
 	if err != nil {
 		upstreamError(c, err)
 		entry.ErrMsg = err.Error()
 		h.logFailure(c, entry, req)
 		return
 	}
+	out, err := service.ResponsesToAnthropic(payload, aiRandID("msg_"))
+	if err != nil {
+		aiError(c, http.StatusBadGateway, "api_error", err.Error())
+		entry.ErrMsg = err.Error()
+		h.logFailure(c, entry, req)
+		return
+	}
 	entry.Status = http.StatusOK
-	fillUsage(&entry, resp.Usage)
+	fillUsage(&entry, service.RespPassthroughUsage(payload))
 	callID := h.gw.LogCall(entry)
-	out := service.IRRespToAnthropic(resp, aiRandID("msg_"))
-	h.maybeLogContent(c, callID, "anthropic", ir.Model, false, req, out)
+	h.maybeLogContent(c, callID, "anthropic", req.Model, false, req, out)
 	c.JSON(http.StatusOK, out)
 }
 
-// streamAnthropic 经状态机把 IR chunk 流聚合为 Anthropic SSE 事件流。
-func (h *aiGatewayHandler) streamAnthropic(c *gin.Context, ir aiwire.ChatRequest) {
+// streamAnthropic 流式直通并桥接:上游 Responses SSE 事件经 AnthRespBridge
+// 转为 Anthropic 事件序列逐块写出;usage 从 completed 事件记账。
+func (h *aiGatewayHandler) streamAnthropic(c *gin.Context, body []byte, req aiwire.MessagesRequest) {
 	start := time.Now()
-	stream, meta, err := h.gw.OpenStream(c.Request.Context(), ir, keyGroup(c))
-	entry := h.logEntry(c, "anthropic", ir.Model, true, meta, start)
+	upstream, meta, err := h.gw.RespPassthroughStream(c.Request.Context(), body, req.Model, keyGroup(c))
+	entry := h.logEntry(c, "anthropic", req.Model, true, meta, start)
 	if err != nil {
 		upstreamError(c, err)
 		entry.ErrMsg = err.Error()
-		h.logFailure(c, entry, ir)
+		h.logFailure(c, entry, req)
 		return
 	}
-	defer stream.Close()
+	defer upstream.Close()
 	sseHeaders(c)
-	st := service.NewAnthStream(aiRandID("msg_"), ir.Model)
-	for {
-		chunk, err := stream.Next()
-		if err != nil {
-			if !errors.Is(err, io.EOF) {
-				entry.ErrMsg = err.Error()
-			}
-			break
-		}
-		writeAnthEvents(c, st.Feed(chunk))
+	bridge := service.NewAnthRespBridge(aiRandID("msg_"), req.Model)
+	if err := forwardAnthSSE(c, upstream, bridge); err != nil {
+		entry.ErrMsg = err.Error()
 	}
-	writeAnthEvents(c, st.Finish())
+	writeAnthEvents(c, bridge.Finish())
 	entry.Status = http.StatusOK
 	entry.LatencyMs = time.Since(start).Milliseconds()
-	usage := st.Usage()
+	usage := bridge.Usage()
 	entry.PromptTokens, entry.CompletionTokens = usage.InputTokens, usage.OutputTokens
 	entry.TotalTokens = usage.InputTokens + usage.OutputTokens
 	entry.CachedTokens = usage.CacheReadInputTokens
 	callID := h.gw.LogCall(entry)
-	h.maybeLogContent(c, callID, "anthropic", ir.Model, true, ir, nil)
+	h.maybeLogContent(c, callID, "anthropic", req.Model, true, req, nil)
+}
+
+// forwardAnthSSE 逐行读上游 SSE,把 data 行喂给桥并即时写出转换后的事件。
+func forwardAnthSSE(c *gin.Context, upstream io.Reader, bridge *service.AnthRespBridge) error {
+	reader := bufio.NewReader(upstream)
+	for {
+		line, err := reader.ReadBytes('\n')
+		if len(line) > 0 {
+			trimmed := bytes.TrimSpace(line)
+			if data, ok := bytes.CutPrefix(trimmed, []byte("data: ")); ok {
+				writeAnthEvents(c, bridge.Feed(data))
+			}
+		}
+		if err != nil {
+			if errors.Is(err, io.EOF) {
+				return nil
+			}
+			return err
+		}
+	}
 }
 
 func writeAnthEvents(c *gin.Context, events []service.AnthEvent) {
@@ -398,6 +340,15 @@ func (h *aiGatewayHandler) listModels(c *gin.Context) {
 		aiError(c, http.StatusInternalServerError, "api_error", "查询模型列表失败")
 		return
 	}
+	if allowed := keyModels(c); len(allowed) > 0 {
+		kept := make([]aiwire.Model, 0, len(list.Data))
+		for _, m := range list.Data {
+			if slices.Contains(allowed, m.ID) {
+				kept = append(kept, m)
+			}
+		}
+		list.Data = kept
+	}
 	c.JSON(http.StatusOK, list)
 }
 
@@ -405,31 +356,45 @@ func (h *aiGatewayHandler) listModels(c *gin.Context) {
 //
 // @Summary  OpenAI Responses 兼容端点
 // @Tags     AI 网关
-// @Param    body body object true "OpenAI responses 请求体(支持 stream)"
+// @Param    body body object true "OpenAI responses 请求体(支持 stream;web_search/x_search 服务端工具仅非流式)"
 // @Success  200 {object} map[string]any "OpenAI 兼容响应(流式为 SSE)"
 // @Router   /ai/v1/responses [post]
 func (h *aiGatewayHandler) responses(c *gin.Context) {
-	var req aiwire.RespRequest
-	if err := c.ShouldBindJSON(&req); err != nil {
-		aiError(c, http.StatusBadRequest, "invalid_request_error", err.Error())
-		return
-	}
-	ir, err := service.ResponsesToIR(req)
+	raw, err := c.GetRawData()
 	if err != nil {
 		aiError(c, http.StatusBadRequest, "invalid_request_error", err.Error())
 		return
 	}
-	if err := validateIR(ir); err != nil {
+	var req aiwire.RespRequest
+	if err := json.Unmarshal(raw, &req); err != nil {
+		aiError(c, http.StatusBadRequest, "invalid_request_error", err.Error())
+		return
+	}
+	if !checkKeyModel(c, req.Model) {
+		return
+	}
+	h.responsesPassthrough(c, raw, req)
+}
+
+// responsesPassthrough 直通链路(唯一上游):原始 body 改写后直达
+// OCI /actions/v1/responses,响应原样透传。
+func (h *aiGatewayHandler) responsesPassthrough(c *gin.Context, raw []byte, req aiwire.RespRequest) {
+	if err := service.RespPassthroughValidate(req); err != nil {
+		aiError(c, http.StatusBadRequest, "invalid_request_error", err.Error())
+		return
+	}
+	body, err := service.RespPassthroughBody(raw)
+	if err != nil {
 		aiError(c, http.StatusBadRequest, "invalid_request_error", err.Error())
 		return
 	}
 	if req.Stream {
-		h.streamResponses(c, ir)
+		h.responsesPassthroughStream(c, body, req)
 		return
 	}
 	start := time.Now()
-	resp, meta, err := h.gw.Chat(c.Request.Context(), ir, keyGroup(c))
-	entry := h.logEntry(c, "responses", ir.Model, false, meta, start)
+	payload, meta, err := h.gw.RespPassthrough(c.Request.Context(), body, req.Model, keyGroup(c))
+	entry := h.logEntry(c, "responses", req.Model, false, meta, start)
 	if err != nil {
 		upstreamError(c, err)
 		entry.ErrMsg = err.Error()
@@ -437,54 +402,61 @@ func (h *aiGatewayHandler) responses(c *gin.Context) {
 		return
 	}
 	entry.Status = http.StatusOK
-	fillUsage(&entry, resp.Usage)
+	fillUsage(&entry, service.RespPassthroughUsage(payload))
 	callID := h.gw.LogCall(entry)
-	out := service.IRRespToResponses(resp, aiRandID("resp_"), time.Now().Unix())
-	h.maybeLogContent(c, callID, "responses", ir.Model, false, req, out)
-	c.JSON(http.StatusOK, out)
+	h.maybeLogContent(c, callID, "responses", req.Model, false, req, json.RawMessage(payload))
+	c.Data(http.StatusOK, "application/json; charset=utf-8", payload)
 }
 
-// streamResponses 经状态机把 IR chunk 流聚合为 Responses 语义事件流。
-func (h *aiGatewayHandler) streamResponses(c *gin.Context, ir aiwire.ChatRequest) {
+// responsesPassthroughStream 流式直通:SSE 事件原样转发(推理增量等直达客户端),
+// 逐行扫描 completed 事件提取 usage 记账。
+func (h *aiGatewayHandler) responsesPassthroughStream(c *gin.Context, body []byte, req aiwire.RespRequest) {
 	start := time.Now()
-	stream, meta, err := h.gw.OpenStream(c.Request.Context(), ir, keyGroup(c))
-	entry := h.logEntry(c, "responses", ir.Model, true, meta, start)
+	upstream, meta, err := h.gw.RespPassthroughStream(c.Request.Context(), body, req.Model, keyGroup(c))
+	entry := h.logEntry(c, "responses", req.Model, true, meta, start)
 	if err != nil {
 		upstreamError(c, err)
 		entry.ErrMsg = err.Error()
-		h.logFailure(c, entry, ir)
+		h.logFailure(c, entry, req)
 		return
 	}
-	defer stream.Close()
+	defer upstream.Close()
 	sseHeaders(c)
-	st := service.NewRespStream(aiRandID("resp_"), ir.Model, time.Now().Unix())
-	for {
-		chunk, err := stream.Next()
-		if err != nil {
-			if !errors.Is(err, io.EOF) {
-				entry.ErrMsg = err.Error()
-			}
-			break
-		}
-		writeRespEvents(c, st.Feed(chunk))
+	usage, err := forwardSSE(c, upstream)
+	if err != nil {
+		entry.ErrMsg = err.Error()
 	}
-	writeRespEvents(c, st.Finish())
 	entry.Status = http.StatusOK
 	entry.LatencyMs = time.Since(start).Milliseconds()
-	fillUsage(&entry, st.Usage())
+	fillUsage(&entry, usage)
 	callID := h.gw.LogCall(entry)
-	h.maybeLogContent(c, callID, "responses", ir.Model, true, ir, nil)
+	h.maybeLogContent(c, callID, "responses", req.Model, true, req, nil)
 }
 
-func writeRespEvents(c *gin.Context, events []service.RespEvent) {
-	for _, ev := range events {
-		b, err := json.Marshal(ev.Data)
+// forwardSSE 把上游 SSE 逐行转发给客户端,空行(事件边界)即 flush;
+// 顺带从 data 行提取 response.completed 的 usage。
+func forwardSSE(c *gin.Context, upstream io.Reader) (*aiwire.Usage, error) {
+	reader := bufio.NewReader(upstream)
+	var usage *aiwire.Usage
+	for {
+		line, err := reader.ReadBytes('\n')
+		if len(line) > 0 {
+			c.Writer.Write(line)
+			trimmed := bytes.TrimSpace(line)
+			if len(trimmed) == 0 {
+				c.Writer.Flush()
+			} else if data, ok := bytes.CutPrefix(trimmed, []byte("data: ")); ok {
+				if u := service.RespStreamCompletedUsage(data); u != nil {
+					usage = u
+				}
+			}
+		}
 		if err != nil {
-			continue
+			c.Writer.Flush()
+			if errors.Is(err, io.EOF) {
+				return usage, nil
+			}
+			return usage, err
 		}
-		c.Writer.WriteString("event: " + ev.Event + "\ndata: ")
-		c.Writer.Write(b)
-		c.Writer.WriteString("\n\n")
 	}
-	c.Writer.Flush()
 }

internal/api/aigateway_test.go

@@ -0,0 +1,206 @@
+package api
+
+import (
+	"context"
+	"encoding/json"
+	"net/http"
+	"strconv"
+	"strings"
+	"testing"
+	"time"
+
+	"gorm.io/gorm"
+
+	"oci-portal/internal/model"
+)
+
+// seedGatewayModel 直插启用渠道与模型缓存,绕过云同步。
+func seedGatewayModel(t *testing.T, db *gorm.DB, name string) {
+	t.Helper()
+	ch := &model.AiChannel{Name: "t-" + name, OciConfigID: 1, Region: "r-" + name, Enabled: true, Priority: 1, Weight: 1}
+	if err := db.Create(ch).Error; err != nil {
+		t.Fatalf("seed channel: %v", err)
+	}
+	cache := &model.AiModelCache{ChannelID: ch.ID, ModelOcid: "ocid1.." + name, Name: name, Vendor: "v", SyncedAt: time.Now()}
+	if err := db.Create(cache).Error; err != nil {
+		t.Fatalf("seed model cache: %v", err)
+	}
+}
+
+func TestAiGatewayKeyModelRestrict(t *testing.T) {
+	r, auth, _, db := newTestRouterDB(t)
+	token, _, err := auth.Login(context.Background(), "admin", "pass123", "127.0.0.1", "")
+	if err != nil {
+		t.Fatalf("login: %v", err)
+	}
+
+	// 受限密钥:白名单含脏输入,入库应规范化为 2 项(cohere + ghost)
+	w := doRequest(t, r, http.MethodPost, "/api/v1/ai-keys", token,
+		`{"name":"limited","value":"limited-key-1234","models":[" cohere.command-a-03-2025 ","cohere.command-a-03-2025","","ghost-model"]}`)
+	if w.Code != http.StatusCreated {
+		t.Fatalf("创建受限密钥 status = %d, body %s", w.Code, w.Body.String())
+	}
+	var created struct {
+		Item model.AiKey `json:"item"`
+	}
+	if err := json.Unmarshal(w.Body.Bytes(), &created); err != nil {
+		t.Fatalf("decode: %v", err)
+	}
+	if len(created.Item.Models) != 2 || created.Item.Models[0] != "cohere.command-a-03-2025" {
+		t.Fatalf("创建后 models 未规范化: %v", created.Item.Models)
+	}
+	// 不限密钥对照
+	w = doRequest(t, r, http.MethodPost, "/api/v1/ai-keys", token, `{"name":"open","value":"open-key-12345"}`)
+	if w.Code != http.StatusCreated {
+		t.Fatalf("创建不限密钥 status = %d, body %s", w.Code, w.Body.String())
+	}
+
+	seedGatewayModel(t, db, "cohere.command-a-03-2025")
+	seedGatewayModel(t, db, "meta.llama-3.3-70b-instruct")
+
+	deny := []string{"model_not_found", "无权访问"}
+	pass := []string{"未知模型"} // 穿过白名单闸门,由编排层以「未知模型」拒绝(池内无 ghost-model)
+	tests := []struct {
+		name     string
+		key      string
+		path     string
+		body     string
+		wantCode int
+		wantSub  []string
+	}{
+		{"responses 流式同样拦截", "limited-key-1234", "/ai/v1/responses",
+			`{"model":"meta.llama-3.3-70b-instruct","stream":true,"input":"hi"}`, 404, deny},
+		{"responses 白名单内穿透", "limited-key-1234", "/ai/v1/responses",
+			`{"model":"ghost-model","input":"hi"}`, 404, pass},
+		{"embeddings 白名单外拦截", "limited-key-1234", "/ai/v1/embeddings",
+			`{"model":"meta.llama-3.3-70b-instruct","input":["hi"]}`, 404, deny},
+		{"messages 白名单外拦截为 Anthropic 体", "limited-key-1234", "/ai/v1/messages",
+			`{"model":"meta.llama-3.3-70b-instruct","max_tokens":16,"messages":[{"role":"user","content":"hi"}]}`, 404,
+			[]string{`"type":"error"`, "model_not_found", "无权访问"}},
+		{"responses 白名单外拦截", "limited-key-1234", "/ai/v1/responses",
+			`{"model":"meta.llama-3.3-70b-instruct","input":"hi"}`, 404, deny},
+		{"不限密钥穿透闸门", "open-key-12345", "/ai/v1/responses",
+			`{"model":"ghost-model","input":"hi"}`, 404, pass},
+		{"chat completions 端点已删除", "open-key-12345", "/ai/v1/chat/completions",
+			`{"model":"ghost-model","messages":[{"role":"user","content":"hi"}]}`, 404, []string{"not found"}},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			w := doRequest(t, r, http.MethodPost, tt.path, tt.key, tt.body)
+			if w.Code != tt.wantCode {
+				t.Fatalf("status = %d, want %d, body %s", w.Code, tt.wantCode, w.Body.String())
+			}
+			for _, sub := range tt.wantSub {
+				if !strings.Contains(w.Body.String(), sub) {
+					t.Errorf("body 缺少 %q: %s", sub, w.Body.String())
+				}
+			}
+		})
+	}
+}
+
+func TestAiGatewayModelsFilteredByKey(t *testing.T) {
+	r, auth, _, db := newTestRouterDB(t)
+	token, _, err := auth.Login(context.Background(), "admin", "pass123", "127.0.0.1", "")
+	if err != nil {
+		t.Fatalf("login: %v", err)
+	}
+	seedGatewayModel(t, db, "cohere.command-a-03-2025")
+	seedGatewayModel(t, db, "meta.llama-3.3-70b-instruct")
+	w := doRequest(t, r, http.MethodPost, "/api/v1/ai-keys", token,
+		`{"name":"limited","value":"limited-key-1234","models":["cohere.command-a-03-2025"]}`)
+	if w.Code != http.StatusCreated {
+		t.Fatalf("创建密钥 status = %d", w.Code)
+	}
+	w = doRequest(t, r, http.MethodPost, "/api/v1/ai-keys", token, `{"name":"open","value":"open-key-12345"}`)
+	if w.Code != http.StatusCreated {
+		t.Fatalf("创建密钥 status = %d", w.Code)
+	}
+
+	tests := []struct {
+		name    string
+		key     string
+		want    []string
+		notWant []string
+	}{
+		{"受限密钥仅见交集", "limited-key-1234", []string{"cohere.command-a-03-2025"}, []string{"meta.llama-3.3-70b-instruct"}},
+		{"不限密钥全量可见", "open-key-12345", []string{"cohere.command-a-03-2025", "meta.llama-3.3-70b-instruct"}, nil},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			w := doRequest(t, r, http.MethodGet, "/ai/v1/models", tt.key, "")
+			if w.Code != http.StatusOK {
+				t.Fatalf("status = %d, body %s", w.Code, w.Body.String())
+			}
+			for _, sub := range tt.want {
+				if !strings.Contains(w.Body.String(), sub) {
+					t.Errorf("应包含 %q: %s", sub, w.Body.String())
+				}
+			}
+			for _, sub := range tt.notWant {
+				if strings.Contains(w.Body.String(), sub) {
+					t.Errorf("不应包含 %q: %s", sub, w.Body.String())
+				}
+			}
+		})
+	}
+}
+
+func TestAiKeyModelsUpdateRoundTrip(t *testing.T) {
+	r, auth, _, _ := newTestRouterDB(t)
+	token, _, err := auth.Login(context.Background(), "admin", "pass123", "127.0.0.1", "")
+	if err != nil {
+		t.Fatalf("login: %v", err)
+	}
+	w := doRequest(t, r, http.MethodPost, "/api/v1/ai-keys", token, `{"name":"k","value":"round-key-1234"}`)
+	if w.Code != http.StatusCreated {
+		t.Fatalf("创建 status = %d", w.Code)
+	}
+	var created struct {
+		Item model.AiKey `json:"item"`
+	}
+	_ = json.Unmarshal(w.Body.Bytes(), &created)
+	id := created.Item.ID
+
+	listModels := func() []string {
+		w := doRequest(t, r, http.MethodGet, "/api/v1/ai-keys", token, "")
+		var resp struct {
+			Items []model.AiKey `json:"items"`
+		}
+		_ = json.Unmarshal(w.Body.Bytes(), &resp)
+		for _, k := range resp.Items {
+			if k.ID == id {
+				return k.Models
+			}
+		}
+		t.Fatalf("密钥 %d 不在列表中", id)
+		return nil
+	}
+
+	tests := []struct {
+		name string
+		body string
+		want []string
+	}{
+		{"设置白名单", `{"models":[" a-model ","a-model","b-model"]}`, []string{"a-model", "b-model"}},
+		{"不传 models 保持不变", `{"name":"k2"}`, []string{"a-model", "b-model"}},
+		{"空数组清空恢复不限", `{"models":[]}`, nil},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			w := doRequest(t, r, http.MethodPut, "/api/v1/ai-keys/"+strconv.Itoa(int(id)), token, tt.body)
+			if w.Code != http.StatusNoContent {
+				t.Fatalf("update status = %d, body %s", w.Code, w.Body.String())
+			}
+			got := listModels()
+			if len(got) != len(tt.want) {
+				t.Fatalf("models = %v, want %v", got, tt.want)
+			}
+			for i := range tt.want {
+				if got[i] != tt.want[i] {
+					t.Fatalf("models = %v, want %v", got, tt.want)
+				}
+			}
+		})
+	}
+}

internal/api/router_test.go

@@ -57,6 +57,13 @@ func (nullClient) GetSubscription(context.Context, oci.Credentials, string) (oci
 }
 
 func newTestRouter(t *testing.T) (*gin.Engine, *service.AuthService, *service.SystemLogService) {
+	t.Helper()
+	r, auth, systemLogs, _ := newTestRouterDB(t)
+	return r, auth, systemLogs
+}
+
+// newTestRouterDB 额外回传 db 句柄,供需要直插数据(如网关模型缓存)的测试使用。
+func newTestRouterDB(t *testing.T) (*gin.Engine, *service.AuthService, *service.SystemLogService, *gorm.DB) {
 	t.Helper()
 	gin.SetMode(gin.TestMode)
 	db, err := gorm.Open(sqlite.Open(":memory:"), &gorm.Config{
@@ -90,7 +97,7 @@ func newTestRouter(t *testing.T) (*gin.Engine, *service.AuthService, *service.Sy
 	logEvents := service.NewLogEventService(db)
 	oauth := service.NewOAuthService(db, settings, auth)
 	r := NewRouter(auth, oauth, ociConfigs, tasks, service.NewConsoleService(ociConfigs), settings, notifier, systemLogs, logEvents, service.NewProxyService(db, cipher), service.NewAiGatewayService(db, ociConfigs, nullClient{}))
-	return r, auth, systemLogs
+	return r, auth, systemLogs, db
 }
 
 func doRequest(t *testing.T, r *gin.Engine, method, path, token, body string) *httptest.ResponseRecorder {

internal/api/routes_ai.go

@@ -11,7 +11,6 @@ import (
 func registerAiGateway(r *gin.Engine, aiGateway *service.AiGatewayService) {
 	aih := &aiGatewayHandler{gw: aiGateway}
 	ai := r.Group("/ai/v1", bodyLimit(10<<20), aih.auth)
-	ai.POST("/chat/completions", aih.chatCompletions)
 	ai.POST("/responses", aih.responses)
 	ai.POST("/messages", aih.messages)
 	ai.POST("/embeddings", aih.embeddings)
@@ -33,6 +32,9 @@ func registerAiAdmin(secured *gin.RouterGroup, aiGateway *service.AiGatewayServi
 	secured.POST("/ai-channels/:id/probe", aiadmin.probeChannel)
 	secured.POST("/ai-channels/:id/sync-models", aiadmin.syncChannelModels)
 	secured.GET("/ai-models", aiadmin.gatewayModels)
+	secured.GET("/ai-blacklist", aiadmin.listBlacklist)
+	secured.POST("/ai-blacklist", aiadmin.addBlacklist)
+	secured.DELETE("/ai-blacklist/:id", aiadmin.removeBlacklist)
 	secured.GET("/ai-logs", aiadmin.listLogs)
 	secured.GET("/ai-content-logs", aiadmin.listContentLogs)
 }