mirror of
https://github.com/QuantumNous/new-api.git
synced 2026-04-18 10:37:28 +00:00
feat(task): add model redirection, per-call billing, and multipart retry fix for async tasks
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:
@@ -9,6 +9,7 @@ import (
|
||||
"github.com/QuantumNous/new-api/model"
|
||||
"github.com/QuantumNous/new-api/relay"
|
||||
"github.com/QuantumNous/new-api/service"
|
||||
"github.com/QuantumNous/new-api/types"
|
||||
|
||||
"github.com/gin-gonic/gin"
|
||||
)
|
||||
@@ -37,7 +38,7 @@ func GetAllTask(c *gin.Context) {
|
||||
items := model.TaskGetAllTasks(pageInfo.GetStartIdx(), pageInfo.GetPageSize(), queryParams)
|
||||
total := model.TaskCountAllTasks(queryParams)
|
||||
pageInfo.SetTotal(int(total))
|
||||
pageInfo.SetItems(tasksToDto(items))
|
||||
pageInfo.SetItems(tasksToDto(items, true))
|
||||
common.ApiSuccess(c, pageInfo)
|
||||
}
|
||||
|
||||
@@ -61,13 +62,32 @@ func GetUserTask(c *gin.Context) {
|
||||
items := model.TaskGetAllUserTask(userId, pageInfo.GetStartIdx(), pageInfo.GetPageSize(), queryParams)
|
||||
total := model.TaskCountAllUserTask(userId, queryParams)
|
||||
pageInfo.SetTotal(int(total))
|
||||
pageInfo.SetItems(tasksToDto(items))
|
||||
pageInfo.SetItems(tasksToDto(items, false))
|
||||
common.ApiSuccess(c, pageInfo)
|
||||
}
|
||||
|
||||
func tasksToDto(tasks []*model.Task) []*dto.TaskDto {
|
||||
func tasksToDto(tasks []*model.Task, fillUser bool) []*dto.TaskDto {
|
||||
var userIdMap map[int]*model.UserBase
|
||||
if fillUser {
|
||||
userIdMap = make(map[int]*model.UserBase)
|
||||
userIds := types.NewSet[int]()
|
||||
for _, task := range tasks {
|
||||
userIds.Add(task.UserId)
|
||||
}
|
||||
for _, userId := range userIds.Items() {
|
||||
cacheUser, err := model.GetUserCache(userId)
|
||||
if err == nil {
|
||||
userIdMap[userId] = cacheUser
|
||||
}
|
||||
}
|
||||
}
|
||||
result := make([]*dto.TaskDto, len(tasks))
|
||||
for i, task := range tasks {
|
||||
if fillUser {
|
||||
if user, ok := userIdMap[task.UserId]; ok {
|
||||
task.Username = user.Username
|
||||
}
|
||||
}
|
||||
result[i] = relay.TaskModel2Dto(task)
|
||||
}
|
||||
return result
|
||||
|
||||
Reference in New Issue
Block a user