fix(usage): 统一使用记录与仪表盘的缓存命中率计算口径

- 新增归一化总输入上下文计算逻辑，按 provider 区分 OpenAI/Gemini 与 Claude 的 cache token 语义
- 将管理端使用聚合、用户使用记录、仪表盘缓存统计、缓存亲和性分析统一为 token 级缓存命中率
- 修正 total_input_context 字段，避免 cache_read 在部分 provider 上被重复计入分母
- 同步更新相关 Rust 单元测试与网关集成测试断言
- 调整前端 dashboard mock 中 cache_hit_rate 的单位为百分比

crates/aether-billing/src/lib.rs

@@ -27,4 +27,6 @@ pub use schema::{
     BillingSnapshot, BillingSnapshotStatus, CostResult, BILLING_SNAPSHOT_SCHEMA_VERSION,
 };
 pub use service::BillingService;
-pub use token_normalization::normalize_input_tokens_for_billing;
+pub use token_normalization::{
+    normalize_input_tokens_for_billing, normalize_total_input_context_for_cache_hit_rate,
+};

crates/aether-billing/src/token_normalization.rs

@@ -43,9 +43,42 @@ pub fn normalize_input_tokens_for_billing(
     }
 }
 
+pub fn normalize_total_input_context_for_cache_hit_rate(
+    api_format: Option<&str>,
+    input_tokens: i64,
+    cache_creation_tokens: i64,
+    cache_read_tokens: i64,
+) -> i64 {
+    let normalized_input_tokens = input_tokens.max(0);
+    let normalized_cache_creation_tokens = cache_creation_tokens.max(0);
+    let normalized_cache_read_tokens = cache_read_tokens.max(0);
+
+    let fresh_input_tokens = match parse_api_family(api_format) {
+        ApiFamily::Claude => {
+            normalized_input_tokens.saturating_add(normalized_cache_creation_tokens)
+        }
+        ApiFamily::OpenAi | ApiFamily::Gemini => normalize_input_tokens_for_billing(
+            api_format,
+            normalized_input_tokens,
+            normalized_cache_read_tokens,
+        ),
+        ApiFamily::Unknown => {
+            if normalized_cache_creation_tokens > 0 {
+                normalized_input_tokens.saturating_add(normalized_cache_creation_tokens)
+            } else {
+                normalized_input_tokens
+            }
+        }
+    };
+
+    fresh_input_tokens.saturating_add(normalized_cache_read_tokens)
+}
+
 #[cfg(test)]
 mod tests {
-    use super::normalize_input_tokens_for_billing;
+    use super::{
+        normalize_input_tokens_for_billing, normalize_total_input_context_for_cache_hit_rate,
+    };
 
     #[test]
     fn subtracts_cache_tokens_for_openai_and_gemini() {
@@ -66,4 +99,36 @@ mod tests {
             100
         );
     }
+
+    #[test]
+    fn normalizes_cache_hit_context_for_openai_and_gemini() {
+        assert_eq!(
+            normalize_total_input_context_for_cache_hit_rate(Some("openai:chat"), 120, 10, 15),
+            120
+        );
+        assert_eq!(
+            normalize_total_input_context_for_cache_hit_rate(Some("gemini:chat"), 120, 10, 15),
+            120
+        );
+    }
+
+    #[test]
+    fn includes_cache_creation_for_claude_cache_hit_context() {
+        assert_eq!(
+            normalize_total_input_context_for_cache_hit_rate(Some("claude:chat"), 60, 15, 5),
+            80
+        );
+    }
+
+    #[test]
+    fn falls_back_to_creation_aware_context_for_unknown_formats() {
+        assert_eq!(
+            normalize_total_input_context_for_cache_hit_rate(None, 20, 10, 5),
+            35
+        );
+        assert_eq!(
+            normalize_total_input_context_for_cache_hit_rate(None, 20, 0, 5),
+            25
+        );
+    }
 }