wangdefa/oci-portal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 18 Wiki Activity

responses 直通超时可配,流式去总超时,代理补阶段超时
CI / test (push) Successful in 31s
Details

Browse Source
This commit is contained in:
wangdefa
2026-07-16 21:20:02 +08:00
parent d56678e1de
commit cb66567256
13 changed files with 379 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/oci/client.go
+6 -4
View File
@@ -102,10 +102,12 @@ type Client interface {
ListGenAiModels(ctx context.Context, cred Credentials, region string) ([]GenAiModel, error)
GenAiProbeChat(ctx context.Context, cred Credentials, region, modelOcid, modelName string) (int, error)
GenAiEmbed(ctx context.Context, cred Credentials, region, modelOcid string, inputs []string, dimensions *int) ([][]float32, *aiwire.Usage, error)
// GenAiCompatResponses 直通 OpenAI Responses 请求体到 /actions/v1/responses(xAI 服务端工具通路)。
GenAiCompatResponses(ctx context.Context, cred Credentials, region string, body []byte) ([]byte, error)
// GenAiCompatResponsesStream 流式直通 /actions/v1/responses,建立成功返回 SSE body。
GenAiCompatResponsesStream(ctx context.Context, cred Credentials, region string, body []byte) (io.ReadCloser, error)
// GenAiCompatResponses 直通 OpenAI Responses 请求体到 /actions/v1/responses(xAI 服务端工具通路);
// wait 是上游无响应预算(整请求总超时),multi-agent/搜索类模型需远超 SDK 默认 60s。
GenAiCompatResponses(ctx context.Context, cred Credentials, region string, body []byte, wait time.Duration) ([]byte, error)
// GenAiCompatResponsesStream 流式直通 /actions/v1/responses,建立成功返回 SSE body;
// wait 仅约束等待响应头阶段,建立后的流生命周期由 ctx 决定。
GenAiCompatResponsesStream(ctx context.Context, cred Credentials, region string, body []byte, wait time.Duration) (io.ReadCloser, error)
// GenAiCompatSpeech 直通 OpenAI Audio Speech 请求体到 /openai/v1/audio/speech,返回音频与 Content-Type。
GenAiCompatSpeech(ctx context.Context, cred Credentials, region string, body []byte) ([]byte, string, error)
// GenAiRerank 文档重排,返回按相关度排序的下标与得分。