fix: retain source continuation and explain request reservation pauses
This commit is contained in:
@@ -23,7 +23,7 @@ export function checkModelDispatchBudget(store,session,run,config,body,overheadT
|
||||
const runRemainingTokens=remaining(run),taskRemainingTokens=remaining(task),remainingTokens=Math.min(runRemainingTokens,taskRemainingTokens);
|
||||
if(tokenReservation.reservedTokens>remainingTokens){
|
||||
const error=new BudgetExceeded(runRemainingTokens<=taskRemainingTokens?'token_limit':'task_token_limit','下一次模型请求的用量预留超过剩余预算,已在发送前暂停。原用量和已完成工具结果保留。');
|
||||
error.contextBudget={tokenReservation,remainingTokens,runRemainingTokens:Number.isFinite(runRemainingTokens)?runRemainingTokens:null,
|
||||
error.contextBudget={pauseKind:'request_reservation',tokenReservation,remainingTokens,runRemainingTokens:Number.isFinite(runRemainingTokens)?runRemainingTokens:null,
|
||||
taskRemainingTokens:Number.isFinite(taskRemainingTokens)?taskRemainingTokens:null};
|
||||
throw error;
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user