@@ -27,27 +27,27 @@ type aiCandidate struct {
|
||||
modelOcid string
|
||||
}
|
||||
|
||||
// RespPassthrough 编排一次非流式直通调用:选渠道(priority→加权随机)→ 调用 →
|
||||
// 可重试错误换渠道(整请求上限 3 次)并维护熔断;group 非空时只在同分组渠道内路由。
|
||||
// 上游为 OpenAI-compatible /actions/v1/responses(实测可用,无 Oracle 文档合同)。
|
||||
func (s *AiGatewayService) RespPassthrough(ctx context.Context, raw []byte, modelName, group string) ([]byte, ChatMeta, error) {
|
||||
// routeRetry 统一编排「选渠道(priority→加权随机)→ 调用 → 可重试错误换渠道」,
|
||||
// 整请求上限 3 次并维护熔断;group 非空时只在同分组渠道内路由。
|
||||
func routeRetry[T any](ctx context.Context, s *AiGatewayService, modelName, group, capability string, once func(*aiCandidate) (T, error)) (T, ChatMeta, error) {
|
||||
var zero T
|
||||
meta := ChatMeta{}
|
||||
excluded := map[uint]bool{}
|
||||
var lastErr error
|
||||
for attempt := 0; attempt < 3; attempt++ {
|
||||
cand, err := s.pick(ctx, modelName, group, "CHAT", excluded)
|
||||
cand, err := s.pick(ctx, modelName, group, capability, excluded)
|
||||
if err != nil {
|
||||
return nil, meta, firstErr(lastErr, err)
|
||||
return zero, meta, firstErr(lastErr, err)
|
||||
}
|
||||
meta.ChannelID, meta.ChannelName = cand.ch.ID, cand.ch.Name
|
||||
payload, err := s.passthroughOnce(ctx, cand, raw)
|
||||
out, err := once(cand)
|
||||
if err == nil {
|
||||
s.markSuccess(ctx, cand.ch.ID)
|
||||
return payload, meta, nil
|
||||
return out, meta, nil
|
||||
}
|
||||
retry, penalize := switchable(err)
|
||||
if !retry {
|
||||
return nil, meta, err
|
||||
return zero, meta, err
|
||||
}
|
||||
if penalize {
|
||||
s.markFailure(ctx, cand.ch.ID)
|
||||
@@ -56,7 +56,15 @@ func (s *AiGatewayService) RespPassthrough(ctx context.Context, raw []byte, mode
|
||||
meta.Retries++
|
||||
lastErr = err
|
||||
}
|
||||
return nil, meta, lastErr
|
||||
return zero, meta, lastErr
|
||||
}
|
||||
|
||||
// RespPassthrough 编排一次非流式直通调用。
|
||||
// 上游为 OpenAI-compatible /actions/v1/responses(实测可用,无 Oracle 文档合同)。
|
||||
func (s *AiGatewayService) RespPassthrough(ctx context.Context, raw []byte, modelName, group string) ([]byte, ChatMeta, error) {
|
||||
return routeRetry(ctx, s, modelName, group, "CHAT", func(cand *aiCandidate) ([]byte, error) {
|
||||
return s.passthroughOnce(ctx, cand, raw)
|
||||
})
|
||||
}
|
||||
|
||||
func (s *AiGatewayService) passthroughOnce(ctx context.Context, cand *aiCandidate, raw []byte) ([]byte, error) {
|
||||
@@ -70,36 +78,13 @@ func (s *AiGatewayService) passthroughOnce(ctx context.Context, cand *aiCandidat
|
||||
// RespPassthroughStream 编排流式直通:流建立成功即绑定渠道,建立失败按 switchable
|
||||
// 换渠道重试;建立后的中断不重试、不计熔断(与 OpenStream 语义一致)。
|
||||
func (s *AiGatewayService) RespPassthroughStream(ctx context.Context, raw []byte, modelName, group string) (io.ReadCloser, ChatMeta, error) {
|
||||
meta := ChatMeta{}
|
||||
excluded := map[uint]bool{}
|
||||
var lastErr error
|
||||
for attempt := 0; attempt < 3; attempt++ {
|
||||
cand, err := s.pick(ctx, modelName, group, "CHAT", excluded)
|
||||
if err != nil {
|
||||
return nil, meta, firstErr(lastErr, err)
|
||||
}
|
||||
meta.ChannelID, meta.ChannelName = cand.ch.ID, cand.ch.Name
|
||||
return routeRetry(ctx, s, modelName, group, "CHAT", func(cand *aiCandidate) (io.ReadCloser, error) {
|
||||
cred, err := s.configs.credentialsByID(ctx, cand.ch.OciConfigID)
|
||||
if err != nil {
|
||||
return nil, meta, err
|
||||
return nil, err
|
||||
}
|
||||
stream, err := s.client.GenAiCompatResponsesStream(ctx, cred, cand.ch.Region, raw, s.UpstreamWait())
|
||||
if err == nil {
|
||||
s.markSuccess(ctx, cand.ch.ID)
|
||||
return stream, meta, nil
|
||||
}
|
||||
retry, penalize := switchable(err)
|
||||
if !retry {
|
||||
return nil, meta, err
|
||||
}
|
||||
if penalize {
|
||||
s.markFailure(ctx, cand.ch.ID)
|
||||
}
|
||||
excluded[cand.ch.ID] = true
|
||||
meta.Retries++
|
||||
lastErr = err
|
||||
}
|
||||
return nil, meta, lastErr
|
||||
return s.client.GenAiCompatResponsesStream(ctx, cred, cand.ch.Region, raw, s.UpstreamWait())
|
||||
})
|
||||
}
|
||||
|
||||
// firstErr 在换渠道后仍失败时优先返回上游错误(而非「无渠道」)。
|
||||
@@ -221,34 +206,11 @@ func weightedPick(chs []model.AiChannel) model.AiChannel {
|
||||
return chs[len(chs)-1]
|
||||
}
|
||||
|
||||
// Embeddings 编排向量化调用:按 EMBEDDING 能力选渠道,可重试错误换渠道(整请求上限 3 次)。
|
||||
// Embeddings 编排向量化调用:按 EMBEDDING 能力选渠道,可重试错误换渠道。
|
||||
func (s *AiGatewayService) Embeddings(ctx context.Context, req aiwire.EmbeddingsRequest, group string) (*aiwire.EmbeddingsResponse, ChatMeta, error) {
|
||||
meta := ChatMeta{}
|
||||
excluded := map[uint]bool{}
|
||||
var lastErr error
|
||||
for attempt := 0; attempt < 3; attempt++ {
|
||||
cand, err := s.pick(ctx, req.Model, group, "EMBEDDING", excluded)
|
||||
if err != nil {
|
||||
return nil, meta, firstErr(lastErr, err)
|
||||
}
|
||||
meta.ChannelID, meta.ChannelName = cand.ch.ID, cand.ch.Name
|
||||
resp, err := s.embedOnce(ctx, cand, req)
|
||||
if err == nil {
|
||||
s.markSuccess(ctx, cand.ch.ID)
|
||||
return resp, meta, nil
|
||||
}
|
||||
retry, penalize := switchable(err)
|
||||
if !retry {
|
||||
return nil, meta, err
|
||||
}
|
||||
if penalize {
|
||||
s.markFailure(ctx, cand.ch.ID)
|
||||
}
|
||||
excluded[cand.ch.ID] = true
|
||||
meta.Retries++
|
||||
lastErr = err
|
||||
}
|
||||
return nil, meta, lastErr
|
||||
return routeRetry(ctx, s, req.Model, group, "EMBEDDING", func(cand *aiCandidate) (*aiwire.EmbeddingsResponse, error) {
|
||||
return s.embedOnce(ctx, cand, req)
|
||||
})
|
||||
}
|
||||
|
||||
// embedOnce 调用渠道向量化并装配 OpenAI 形态响应。
|
||||
|
||||
Reference in New Issue
Block a user