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/oci/genai_speech.go

@@ -0,0 +1,44 @@
+package oci
+
+import (
+	"bytes"
+	"context"
+	"fmt"
+	"io"
+	"net/http"
+
+	"github.com/oracle/oci-go-sdk/v65/common"
+)
+
+// compatSpeechLimit 限制 TTS 音频响应体大小(长文本 mp3 给足余量)。
+const compatSpeechLimit = int64(64 << 20)
+
+// GenAiCompatSpeech 实现 Client:把 OpenAI Audio Speech 请求体直通到 OCI
+// 兼容面 `/openai/v1/audio/speech`(IAM 签名,BasePath 置空——该面与
+// /20231130/actions 面并存,实测仅前者承载 TTS)。返回音频字节与 Content-Type。
+func (c *RealClient) GenAiCompatSpeech(ctx context.Context, cred Credentials, region string, body []byte) ([]byte, string, error) {
+	ic, err := c.genAiInferenceClient(cred, region)
+	if err != nil {
+		return nil, "", err
+	}
+	client := ic.BaseClient
+	common.UpdateEndpointTemplateForOptions(&client)
+	common.SetMissingTemplateParams(&client)
+	client.BasePath = ""
+	request, err := http.NewRequestWithContext(ctx, http.MethodPost, "/openai/v1/audio/speech", bytes.NewReader(body))
+	if err != nil {
+		return nil, "", fmt.Errorf("build compat speech request: %w", err)
+	}
+	request.Header.Set("Content-Type", "application/json")
+	request.Header.Set("opc-compartment-id", cred.TenancyOCID)
+	response, err := client.Call(ctx, request)
+	if err != nil {
+		return nil, "", err
+	}
+	defer response.Body.Close()
+	payload, err := io.ReadAll(io.LimitReader(response.Body, compatSpeechLimit))
+	if err != nil {
+		return nil, "", fmt.Errorf("read compat speech body: %w", err)
+	}
+	return payload, response.Header.Get("Content-Type"), nil
+}