i/Aether
1
0
Fork 0
mirror of https://github.com/fawney19/Aether.git synced 2026-09-03 01:40:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: 扩展 cache creation token 细分统计与 effective_input_tokens 计费逻辑

Browse Source 
- 新增 cache_creation_ephemeral_5m/1h_input_tokens 字段，区分不同 TTL 的缓存写入 token
- 引入 effective_input_tokens（扣除 cache read 后的有效输入 token），暴露给 usage 接口
- billing 规则生成器支持 5m/1h ephemeral cache 独立定价与分级计费
- usage_mapper 增加 Claude/Anthropic 格式映射，修复 OpenAI responses 格式字段兼容性
- 迁移逻辑增强：支持 checksum 容错、applied/pending 数量日志、逐步执行信息输出
- executor 抽离 LocalExecutionRequestOutcome 类型，统一 sync/stream 路径返回语义
- provider-transport auth 层新增 complete passthrough headers 构建逻辑
- 前端 usage 类型全面补充 effective_input_tokens、cache_creation_tokens、total_input_context 字段
This commit is contained in:
fawney19
2026-04-10 17:44:55 +08:00
parent 5014e2f5fd
commit 010ab127e2
64 changed files with 4217 additions and 477 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
apps/aether-gateway/src/control/execute.rs
View File

@@ -3,7 +3,9 @@ use axum::http::{HeaderName, HeaderValue, Response};
use crate::constants::CONTROL_EXECUTED_HEADER;
use crate::control::GatewayControlDecision;
use crate::executor::{maybe_execute_stream_request, maybe_execute_sync_request};
use crate::executor::{
maybe_execute_stream_request, maybe_execute_sync_request, LocalExecutionRequestOutcome,
};
use crate::{AppState, GatewayError};
use super::resolve_execution_runtime_auth_context;
@@ -19,9 +21,9 @@ pub(crate) async fn maybe_execute_via_control(
trace_id: &str,
decision: Option<&GatewayControlDecision>,
require_stream: bool,
) -> Result<Option<Response<Body>>, GatewayError> {
) -> Result<LocalExecutionRequestOutcome, GatewayError> {
let Some(decision) = decision else {
return Ok(None);
return Ok(LocalExecutionRequestOutcome::NoPath);
};
let mut local_decision = decision.clone();
@@ -46,7 +48,15 @@ pub(crate) async fn maybe_execute_via_control(
.await?
};
Ok(response.map(mark_control_executed))
Ok(match response {
LocalExecutionRequestOutcome::Responded(response) => {
LocalExecutionRequestOutcome::Responded(mark_control_executed(response))
}
LocalExecutionRequestOutcome::Exhausted(outcome) => {
LocalExecutionRequestOutcome::Exhausted(outcome)
}
LocalExecutionRequestOutcome::NoPath => LocalExecutionRequestOutcome::NoPath,
})
}
fn mark_control_executed(mut response: Response<Body>) -> Response<Body> {