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

crates/aether-billing/src/default_rule.rs

@@ -50,6 +50,14 @@ impl DefaultBillingRuleGenerator {
             "cache_creation_price_per_1m".to_string(),
             json!(base_cache_creation_price),
         );
+        variables.insert(
+            "cache_creation_ephemeral_5m_price_per_1m".to_string(),
+            json!(base_cache_creation_price),
+        );
+        variables.insert(
+            "cache_creation_ephemeral_1h_price_per_1m".to_string(),
+            json!(base_cache_creation_price),
+        );
         variables.insert(
             "cache_read_price_per_1m".to_string(),
             json!(base_cache_read_price),
@@ -61,6 +69,21 @@ impl DefaultBillingRuleGenerator {
             ("input_tokens", "input_tokens", json!(0)),
             ("output_tokens", "output_tokens", json!(0)),
             ("cache_creation_tokens", "cache_creation_tokens", json!(0)),
+            (
+                "cache_creation_ephemeral_5m_tokens",
+                "cache_creation_ephemeral_5m_tokens",
+                json!(0),
+            ),
+            (
+                "cache_creation_ephemeral_1h_tokens",
+                "cache_creation_ephemeral_1h_tokens",
+                json!(0),
+            ),
+            (
+                "cache_creation_uncategorized_tokens",
+                "cache_creation_uncategorized_tokens",
+                json!(0),
+            ),
             ("cache_read_tokens", "cache_read_tokens", json!(0)),
             ("request_count", "request_count", json!(1)),
         ] {
@@ -83,8 +106,16 @@ impl DefaultBillingRuleGenerator {
                 "output_tokens * output_price_per_1m / 1000000",
             ),
             (
-                "cache_creation_cost",
-                "cache_creation_tokens * cache_creation_price_per_1m / 1000000",
+                "cache_creation_uncategorized_cost",
+                "cache_creation_uncategorized_tokens * cache_creation_price_per_1m / 1000000",
+            ),
+            (
+                "cache_creation_ephemeral_5m_cost",
+                "cache_creation_ephemeral_5m_tokens * cache_creation_ephemeral_5m_price_per_1m / 1000000",
+            ),
+            (
+                "cache_creation_ephemeral_1h_cost",
+                "cache_creation_ephemeral_1h_tokens * cache_creation_ephemeral_1h_price_per_1m / 1000000",
             ),
             (
                 "cache_read_cost",
@@ -136,6 +167,30 @@ impl DefaultBillingRuleGenerator {
                     "default": base_cache_creation_price,
                 }),
             );
+            dimension_mappings.insert(
+                "cache_creation_ephemeral_5m_price_per_1m".to_string(),
+                json!({
+                    "source": "tiered",
+                    "tier_key": "total_input_context",
+                    "allow_zero": true,
+                    "ttl_key": "cache_creation_ephemeral_5m_ttl_minutes",
+                    "ttl_value_key": "cache_creation_price_per_1m",
+                    "tiers": build_tier_entries(&tiers, "cache_creation_price_per_1m", Some(1.25), true),
+                    "default": base_cache_creation_price,
+                }),
+            );
+            dimension_mappings.insert(
+                "cache_creation_ephemeral_1h_price_per_1m".to_string(),
+                json!({
+                    "source": "tiered",
+                    "tier_key": "total_input_context",
+                    "allow_zero": true,
+                    "ttl_key": "cache_creation_ephemeral_1h_ttl_minutes",
+                    "ttl_value_key": "cache_creation_price_per_1m",
+                    "tiers": build_tier_entries(&tiers, "cache_creation_price_per_1m", Some(1.25), true),
+                    "default": base_cache_creation_price,
+                }),
+            );
             dimension_mappings.insert(
                 "cache_read_price_per_1m".to_string(),
                 json!({
@@ -154,9 +209,7 @@ impl DefaultBillingRuleGenerator {
             id: "__default__".to_string(),
             name: format!("Default rule for {}", pricing.global_model_name),
             task_type: normalize_task_type(task_type).to_string(),
-            expression:
-                "input_cost + output_cost + cache_creation_cost + cache_read_cost + request_cost"
-                    .to_string(),
+            expression: "input_cost + output_cost + cache_creation_uncategorized_cost + cache_creation_ephemeral_5m_cost + cache_creation_ephemeral_1h_cost + cache_read_cost + request_cost".to_string(),
             variables,
             dimension_mappings,
             scope: "default".to_string(),

crates/aether-billing/src/event_enrichment.rs

@@ -73,6 +73,14 @@ pub async fn enrich_usage_event_with_billing(
         input_tokens: event.data.input_tokens.unwrap_or_default() as i64,
         output_tokens: event.data.output_tokens.unwrap_or_default() as i64,
         cache_creation_tokens: event.data.cache_creation_input_tokens.unwrap_or_default() as i64,
+        cache_creation_ephemeral_5m_tokens: event
+            .data
+            .cache_creation_ephemeral_5m_input_tokens
+            .unwrap_or_default() as i64,
+        cache_creation_ephemeral_1h_tokens: event
+            .data
+            .cache_creation_ephemeral_1h_input_tokens
+            .unwrap_or_default() as i64,
         cache_read_tokens: event.data.cache_read_input_tokens.unwrap_or_default() as i64,
         cache_ttl_minutes: pricing.provider_api_key_cache_ttl_minutes,
     };

crates/aether-billing/src/pricing.rs

@@ -66,6 +66,8 @@ pub struct BillingUsageInput {
     pub input_tokens: i64,
     pub output_tokens: i64,
     pub cache_creation_tokens: i64,
+    pub cache_creation_ephemeral_5m_tokens: i64,
+    pub cache_creation_ephemeral_1h_tokens: i64,
     pub cache_read_tokens: i64,
     pub cache_ttl_minutes: Option<i64>,
 }
@@ -79,6 +81,8 @@ impl BillingUsageInput {
             input_tokens: 0,
             output_tokens: 0,
             cache_creation_tokens: 0,
+            cache_creation_ephemeral_5m_tokens: 0,
+            cache_creation_ephemeral_1h_tokens: 0,
             cache_read_tokens: 0,
             cache_ttl_minutes: None,
         }

crates/aether-billing/src/service.rs

@@ -129,6 +129,13 @@ fn build_dimensions(input: &BillingUsageInput) -> BTreeMap<String, Value> {
         input.input_tokens,
         input.cache_read_tokens,
     );
+    let classified_cache_creation_tokens = input
+        .cache_creation_ephemeral_5m_tokens
+        .saturating_add(input.cache_creation_ephemeral_1h_tokens);
+    let cache_creation_uncategorized_tokens = input
+        .cache_creation_tokens
+        .saturating_sub(classified_cache_creation_tokens)
+        .max(0);
     let total_input_context = input
         .input_tokens
         .saturating_add(input.cache_creation_tokens)
@@ -141,6 +148,18 @@ fn build_dimensions(input: &BillingUsageInput) -> BTreeMap<String, Value> {
             "cache_creation_tokens".to_string(),
             json!(input.cache_creation_tokens),
         ),
+        (
+            "cache_creation_ephemeral_5m_tokens".to_string(),
+            json!(input.cache_creation_ephemeral_5m_tokens),
+        ),
+        (
+            "cache_creation_ephemeral_1h_tokens".to_string(),
+            json!(input.cache_creation_ephemeral_1h_tokens),
+        ),
+        (
+            "cache_creation_uncategorized_tokens".to_string(),
+            json!(cache_creation_uncategorized_tokens),
+        ),
         (
             "cache_read_tokens".to_string(),
             json!(input.cache_read_tokens),
@@ -159,6 +178,15 @@ fn build_dimensions(input: &BillingUsageInput) -> BTreeMap<String, Value> {
         ),
     ]);
 
+    out.insert(
+        "cache_creation_ephemeral_5m_ttl_minutes".to_string(),
+        json!(5),
+    );
+    out.insert(
+        "cache_creation_ephemeral_1h_ttl_minutes".to_string(),
+        json!(60),
+    );
+
     if let Some(cache_ttl_minutes) = input.cache_ttl_minutes {
         out.insert(
             "cache_ttl_minutes".to_string(),
@@ -223,6 +251,8 @@ mod tests {
                     input_tokens: 1_000,
                     output_tokens: 500,
                     cache_creation_tokens: 0,
+                    cache_creation_ephemeral_5m_tokens: 0,
+                    cache_creation_ephemeral_1h_tokens: 0,
                     cache_read_tokens: 100,
                     cache_ttl_minutes: Some(60),
                 },