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

internal/oci/genai.go

@@ -2,13 +2,11 @@ package oci
 
 import (
 	"context"
+	"encoding/json"
 	"fmt"
-	"io"
 	"net/http"
-	"strings"
 	"time"
 
-	"github.com/oracle/oci-go-sdk/v65/common"
 	"github.com/oracle/oci-go-sdk/v65/generativeai"
 	"github.com/oracle/oci-go-sdk/v65/generativeaiinference"
 
@@ -30,12 +28,6 @@ type GenAiModel struct {
 	Retired *time.Time `json:"retired"`
 }
 
-// GenAiStream 逐事件读取流式聊天;Next 在流结束时返回 io.EOF。
-type GenAiStream interface {
-	Next() (aiwire.ChatChunk, error)
-	Close() error
-}
-
 func (c *RealClient) genAiClient(cred Credentials, region string) (generativeai.GenerativeAiClient, error) {
 	gc, err := generativeai.NewGenerativeAiClientWithConfigurationProvider(provider(cred))
 	if err != nil {
@@ -152,121 +144,15 @@ func capStrings(caps []generativeai.ModelCapabilityEnum) []string {
 	return out
 }
 
-// GenAiChat 实现 Client:非流式聊天;modelOcid 走 on-demand serving,
-// cohere.* 模型走 COHERE 请求格式,其余走 GENERIC。
-func (c *RealClient) GenAiChat(ctx context.Context, cred Credentials, region, modelOcid string, ir aiwire.ChatRequest) (*aiwire.ChatResponse, error) {
-	ic, err := c.genAiInferenceClient(cred, region)
-	if err != nil {
-		return nil, err
-	}
-	req, err := buildChatRequest(ir, false)
-	if err != nil {
-		return nil, err
-	}
-	resp, err := ic.Chat(ctx, chatRequest(cred, modelOcid, req))
-	if err != nil {
-		return nil, fmt.Errorf("genai chat: %w", err)
-	}
-	return chatResponseToIR(resp.ChatResult.ChatResponse, ir.Model)
-}
-
-// buildChatRequest 按模型 vendor 组装底层请求体。
-func buildChatRequest(ir aiwire.ChatRequest, stream bool) (generativeaiinference.BaseChatRequest, error) {
-	if isCohereModel(ir.Model) {
-		return irToCohereSDK(ir, stream)
-	}
-	return irToSDK(ir, stream), nil
-}
-
-// chatResponseToIR 按响应实际形态(GENERIC / COHERE)转回 IR。
-func chatResponseToIR(resp generativeaiinference.BaseChatResponse, model string) (*aiwire.ChatResponse, error) {
-	switch r := resp.(type) {
-	case generativeaiinference.GenericChatResponse:
-		return sdkToIR(r, model), nil
-	case generativeaiinference.CohereChatResponse:
-		return cohereSDKToIR(r, model), nil
-	default:
-		return nil, fmt.Errorf("genai chat: unexpected response format %T", resp)
-	}
-}
-
-func chatRequest(cred Credentials, modelOcid string, req generativeaiinference.BaseChatRequest) generativeaiinference.ChatRequest {
-	return generativeaiinference.ChatRequest{
-		ChatDetails: generativeaiinference.ChatDetails{
-			CompartmentId: &cred.TenancyOCID,
-			ServingMode:   generativeaiinference.OnDemandServingMode{ModelId: &modelOcid},
-			ChatRequest:   req,
-		},
-	}
-}
-
-// GenAiChatStream 实现 Client:流式聊天,返回逐事件读取器。
-// SDK 对 text/event-stream 跳过 unmarshal,原始流经 RawResponse 交由 SSEReader 消费。
-func (c *RealClient) GenAiChatStream(ctx context.Context, cred Credentials, region, modelOcid string, ir aiwire.ChatRequest) (GenAiStream, error) {
-	ic, err := c.genAiInferenceClient(cred, region)
-	if err != nil {
-		return nil, err
-	}
-	req, err := buildChatRequest(ir, true)
-	if err != nil {
-		return nil, err
-	}
-	resp, err := ic.Chat(ctx, chatRequest(cred, modelOcid, req))
-	if err != nil {
-		return nil, fmt.Errorf("genai chat stream: %w", err)
-	}
-	reader, err := common.NewSSEReader(resp.RawResponse)
-	if err != nil {
-		return nil, fmt.Errorf("genai chat stream: sse reader: %w", err)
-	}
-	return &genAiSSEStream{reader: reader, body: resp.RawResponse.Body, model: ir.Model}, nil
-}
-
-// genAiSSEStream 把 OCI SSE 事件流适配为 IR chunk 流。
-type genAiSSEStream struct {
-	reader *common.SseReader
-	body   io.ReadCloser
-	model  string
-}
-
-// Next 读取下一条有效事件;空事件与 [DONE] 哨兵跳过,流尽返回 io.EOF。
-func (s *genAiSSEStream) Next() (aiwire.ChatChunk, error) {
-	for {
-		data, err := s.reader.ReadNextEvent()
-		if err != nil {
-			return aiwire.ChatChunk{}, err
-		}
-		text := strings.TrimSpace(string(data))
-		if text == "" {
-			continue
-		}
-		if text == "[DONE]" {
-			return aiwire.ChatChunk{}, io.EOF
-		}
-		if chunk, ok := parseGenAiEvent([]byte(text), s.model); ok {
-			return chunk, nil
-		}
-	}
-}
-
-func (s *genAiSSEStream) Close() error {
-	if s.body != nil {
-		return s.body.Close()
-	}
-	return nil
-}
-
-// GenAiProbeChat 实现 Client:配额探测专用的最小聊天(maxTokens=1),返回 HTTP 状态码;
+// GenAiProbeChat 实现 Client:经 OpenAI 兼容面(直通同链路)发一次极小请求探测渠道;配额探测专用的最小聊天(maxTokens=1),返回 HTTP 状态码;
 // modelName 决定请求格式(cohere.* 走 COHERE)。
 func (c *RealClient) GenAiProbeChat(ctx context.Context, cred Credentials, region, modelOcid, modelName string) (int, error) {
-	one := 1
-	ir := aiwire.ChatRequest{
-		Model:     modelName,
-		Messages:  []aiwire.ChatMessage{{Role: "user", Content: aiwire.NewTextContent("hi")}},
-		MaxTokens: &one,
+	body, err := json.Marshal(map[string]any{"model": modelName, "input": "hi",
+		"max_output_tokens": 1, "store": false})
+	if err != nil {
+		return 0, err
 	}
-	_, err := c.GenAiChat(ctx, cred, region, modelOcid, ir)
-	if err == nil {
+	if _, err = c.GenAiCompatResponses(ctx, cred, region, body); err == nil {
 		return http.StatusOK, nil
 	}
 	if status, ok := ServiceStatus(err); ok {
@@ -275,6 +161,27 @@ func (c *RealClient) GenAiProbeChat(ctx context.Context, cred Credentials, regio
 	return 0, err
 }
 
+// sdkUsageToIR 把 SDK 用量转为内部记账结构(缓存命中挂 details,仅命中时出现)。
+func sdkUsageToIR(u *generativeaiinference.Usage) *aiwire.Usage {
+	if u == nil {
+		return nil
+	}
+	out := &aiwire.Usage{}
+	if u.PromptTokens != nil {
+		out.PromptTokens = *u.PromptTokens
+	}
+	if u.CompletionTokens != nil {
+		out.CompletionTokens = *u.CompletionTokens
+	}
+	if u.TotalTokens != nil {
+		out.TotalTokens = *u.TotalTokens
+	}
+	if u.PromptTokensDetails != nil && u.PromptTokensDetails.CachedTokens != nil && *u.PromptTokensDetails.CachedTokens > 0 {
+		out.PromptTokensDetails = &aiwire.PromptTokensDetails{CachedTokens: *u.PromptTokensDetails.CachedTokens}
+	}
+	return out
+}
+
 // GenAiEmbed 实现 Client:文本向量化(on-demand serving);dimensions 透传 OutputDimensions。
 func (c *RealClient) GenAiEmbed(ctx context.Context, cred Credentials, region, modelOcid string, inputs []string, dimensions *int) ([][]float32, *aiwire.Usage, error) {
 	ic, err := c.genAiInferenceClient(cred, region)