AI网关新增TTS/重排/审核端点,xAI工具扩展,swagger修缺

- 新端点 /ai/v1/audio/speech(xai.grok-tts)、/rerank(cohere.rerank-v4)、/moderations(OCI Guardrails)
- Responses 放行 code_interpreter 与远程 mcp 工具,web_search/x_search 解除仅非流式限制
- 模型能力映射扩展:TEXT_RERANK→RERANK、TEXT_TO_AUDIO→TTS
- AI 网关文档独立 docs/ai-gateway.md,字段兼容矩阵只列支持项;README 精简引用
- swagger 修缺:135 处响应注解具体化,RawMessage/联合类型统一渲染 AnyJSON,overrides 迁至 docs/.swaggo
- CHANGELOG 0.4.0,版本段不再记日期;DASH_VERSION v0.4.0

internal/api/aigateway.go

@@ -165,8 +165,8 @@ func fillUsage(entry *model.AiCallLog, u *aiwire.Usage) {
 //
 // @Summary  OpenAI 兼容向量嵌入
 // @Tags     AI 网关
-// @Param    body body object true "OpenAI embeddings 请求体"
-// @Success  200 {object} map[string]any "OpenAI 兼容响应"
+// @Param    body body aiwire.EmbeddingsRequest true "OpenAI embeddings 请求体"
+// @Success  200 {object} aiwire.EmbeddingsResponse "OpenAI 兼容响应"
 // @Router   /ai/v1/embeddings [post]
 func (h *aiGatewayHandler) embeddings(c *gin.Context) {
 	var req aiwire.EmbeddingsRequest
@@ -218,8 +218,8 @@ const anthDefaultMaxTokens = 8192
 //
 // @Summary  Anthropic Messages 兼容端点
 // @Tags     AI 网关
-// @Param    body body object true "Anthropic messages 请求体(支持 stream;经 OCI OpenAI 兼容面直通;max_tokens 可缺省,默认 8192)"
-// @Success  200 {object} map[string]any "Anthropic 兼容响应(流式为 SSE)"
+// @Param    body body aiwire.MessagesRequest true "Anthropic messages 请求体(支持 stream;经 OCI OpenAI 兼容面直通;max_tokens 可缺省,默认 8192)"
+// @Success  200 {object} aiwire.MessagesResponse "Anthropic 兼容响应(非流式;流式为 SSE 事件序列)"
 // @Router   /ai/v1/messages [post]
 func (h *aiGatewayHandler) messages(c *gin.Context) {
 	var req aiwire.MessagesRequest
@@ -381,8 +381,8 @@ func writeAnthEvents(c *gin.Context, events []service.AnthEvent) {
 //
 // @Summary  OpenAI Chat Completions 兼容端点
 // @Tags     AI 网关
-// @Param    body body object true "OpenAI chat/completions 请求体(支持 stream;经 Responses 转换直通)"
-// @Success  200 {object} map[string]any "OpenAI 兼容响应(流式为 SSE,末尾 data: [DONE])"
+// @Param    body body aiwire.ChatRequest true "OpenAI chat/completions 请求体(支持 stream;经 Responses 转换直通)"
+// @Success  200 {object} aiwire.ChatResponse "OpenAI 兼容响应(非流式;流式为 SSE,末尾 data: [DONE])"
 // @Router   /ai/v1/chat/completions [post]
 func (h *aiGatewayHandler) chatCompletions(c *gin.Context) {
 	var req aiwire.ChatRequest
@@ -528,7 +528,7 @@ func writeChatChunks(c *gin.Context, chunks []aiwire.ChatChunk) {
 //
 // @Summary  可用模型列表
 // @Tags     AI 网关
-// @Success  200 {object} map[string]any "OpenAI 兼容 models 列表"
+// @Success  200 {object} aiwire.ModelList "OpenAI 兼容 models 列表"
 // @Router   /ai/v1/models [get]
 func (h *aiGatewayHandler) listModels(c *gin.Context) {
 	list, err := h.gw.GatewayModels(c.Request.Context(), keyGroup(c))
@@ -552,8 +552,8 @@ 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;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)"
+// @Param    body body aiwire.RespRequest true "OpenAI responses 请求体(支持 stream;服务端工具 web_search/x_search/code_interpreter/mcp 含流式;未列字段原样透传上游)"
+// @Success  200 {object} aiwire.RespResponse "OpenAI 兼容响应(非流式;流式为 SSE);直通仅建模常用字段,未列字段原样返回"
 // @Router   /ai/v1/responses [post]
 func (h *aiGatewayHandler) responses(c *gin.Context) {
 	raw, err := c.GetRawData()