huangzhenpc/newapi-yx-diy
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(task): add model redirection, per-call billing, and multipart retry fix for async tasks

Browse Source 
1. Async task model redirection (aligned with sync tasks):
   - Integrate ModelMappedHelper in RelayTaskSubmit after model name
     determination, populating OriginModelName / UpstreamModelName on RelayInfo.
   - All task adaptors now send UpstreamModelName to upstream providers:
     - Gemini & Vertex: BuildRequestURL uses UpstreamModelName.
     - Doubao & Ali: BuildRequestBody conditionally overwrites body.Model.
     - Vidu, Kling, Hailuo, Jimeng: convertToRequestPayload accepts RelayInfo
       and unconditionally uses info.UpstreamModelName.
     - Sora: BuildRequestBody parses JSON and multipart bodies to replace
       the "model" field with UpstreamModelName.
   - Frontend log visibility: LogTaskConsumption and taskBillingOther now
     emit is_model_mapped / upstream_model_name in the "other" JSON field.
   - Billing safety: RecalculateTaskQuotaByTokens reads model name from
     BillingContext.OriginModelName (via taskModelName) instead of
     task.Data["model"], preventing billing leaks from upstream model names.

2. Per-call billing (TaskPricePatches lifecycle):
   - Rename TaskBillingContext.ModelName → OriginModelName; add PerCallBilling
     bool field, populated from TaskPricePatches at submission time.
   - settleTaskBillingOnComplete short-circuits when PerCallBilling is true,
     skipping both adaptor adjustments and token-based recalculation.
   - Remove ModelName from TaskSubmitResult; use relayInfo.OriginModelName
     consistently in controller/relay.go for billing context and logging.

3. Multipart retry boundary mismatch fix:
   - Root cause: after Sora (or OpenAI audio) rebuilds a multipart body with a
     new boundary and overwrites c.Request.Header["Content-Type"], subsequent
     calls to ParseMultipartFormReusable on retry would parse the cached
     original body with the wrong boundary, causing "NextPart: EOF".
   - Fix: ParseMultipartFormReusable now caches the original Content-Type in
     gin context key "_original_multipart_ct" on first call and reuses it for
     all subsequent parses, making multipart parsing retry-safe globally.
   - Sora adaptor reverted to the standard pattern (direct header set/get),
     which is now safe thanks to the root fix.

4. Tests:
   - task_billing_test.go: update makeTask to use OriginModelName; add
     PerCallBilling settlement tests (skip adaptor adjust, skip token recalc);
     add non-per-call adaptor adjustment test with refund verification.
This commit is contained in:
CaIon
2026-02-22 15:32:33 +08:00
parent 9976b311ef
commit ec5c6b28ea
19 changed files with 277 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
relay/channel/task/ali/adaptor.go
View File

@@ -253,8 +253,12 @@ func ProcessAliOtherRatios(aliReq *AliVideoRequest) (map[string]float64, error)
}
func (a *TaskAdaptor) convertToAliRequest(info *relaycommon.RelayInfo, req relaycommon.TaskSubmitReq) (*AliVideoRequest, error) {
upstreamModel := req.Model
if info.IsModelMapped {
upstreamModel = info.UpstreamModelName
}
aliReq := &AliVideoRequest{
Model: req.Model,
Model: upstreamModel,
Input: AliVideoInput{
Prompt: req.Prompt,
ImgURL: req.InputReference,
@@ -332,7 +336,7 @@ func (a *TaskAdaptor) convertToAliRequest(info *relaycommon.RelayInfo, req relay
}
}
if aliReq.Model != req.Model {
if aliReq.Model != upstreamModel {
return nil, errors.New("can't change model with metadata")
}