Thread last-request and cache usage fields through the exec event bridge (N3 WP6) #38
@@ -409,6 +409,10 @@ func (b *Backend) run(ctx context.Context, model string, budget *runtime.Budget,
|
||||
Detail: ev.Detail,
|
||||
PromptTokens: ev.PromptTokens,
|
||||
CompletionTokens: ev.CompletionTokens,
|
||||
LastPromptTokens: ev.LastPromptTokens,
|
||||
LastCompletionTokens: ev.LastCompletionTokens,
|
||||
CacheReadTokens: ev.CacheReadTokens,
|
||||
CacheWriteTokens: ev.CacheWriteTokens,
|
||||
})
|
||||
}
|
||||
},
|
||||
|
||||
@@ -57,6 +57,11 @@ type ProcessEvent struct {
|
||||
// PromptTokens / CompletionTokens 在 Type=usage 时填写。
|
||||
PromptTokens int
|
||||
CompletionTokens int
|
||||
// 以下在 Type=usage 或 message_end 时填写(N3 WP6:上一请求与缓存命中拆分)。
|
||||
LastPromptTokens int
|
||||
LastCompletionTokens int
|
||||
CacheReadTokens int
|
||||
CacheWriteTokens int
|
||||
}
|
||||
|
||||
const (
|
||||
|
||||
Reference in New Issue
Block a user