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

- 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

View File

@@ -28,6 +28,8 @@ pub struct StoredRequestUsageAudit {
pub output_tokens: u64,
pub total_tokens: u64,
pub cache_creation_input_tokens: u64,
pub cache_creation_ephemeral_5m_input_tokens: u64,
pub cache_creation_ephemeral_1h_input_tokens: u64,
pub cache_read_input_tokens: u64,
pub cache_creation_cost_usd: f64,
pub cache_read_cost_usd: f64,
@@ -166,6 +168,8 @@ impl StoredRequestUsageAudit {
output_tokens: parse_u64(output_tokens, "usage.output_tokens")?,
total_tokens: parse_u64(total_tokens, "usage.total_tokens")?,
cache_creation_input_tokens: 0,
cache_creation_ephemeral_5m_input_tokens: 0,
cache_creation_ephemeral_1h_input_tokens: 0,
cache_read_input_tokens: 0,
cache_creation_cost_usd: 0.0,
cache_read_cost_usd: 0.0,
@@ -346,6 +350,8 @@ pub struct UpsertUsageRecord {
pub output_tokens: Option<u64>,
pub total_tokens: Option<u64>,
pub cache_creation_input_tokens: Option<u64>,
pub cache_creation_ephemeral_5m_input_tokens: Option<u64>,
pub cache_creation_ephemeral_1h_input_tokens: Option<u64>,
pub cache_read_input_tokens: Option<u64>,
pub cache_creation_cost_usd: Option<f64>,
pub cache_read_cost_usd: Option<f64>,
@@ -604,6 +610,8 @@ mod tests {
output_tokens: Some(20),
total_tokens: Some(30),
cache_creation_input_tokens: None,
cache_creation_ephemeral_5m_input_tokens: None,
cache_creation_ephemeral_1h_input_tokens: None,
cache_read_input_tokens: None,
cache_creation_cost_usd: None,
cache_read_cost_usd: None,