fix: 修复缓存 token usage 转换语义

统一 OpenAI、Gemini、Claude 之间缓存 token 的 usage 语义，避免 Claude 侧重复统计缓存输入 token。

同时补充 stream 合并逻辑、字段注释和覆盖转换链路的测试。

crates/aether-ai-formats/src/protocol/stream.rs

@@ -4,6 +4,10 @@ use serde_json::Value;
 #[derive(Clone, Debug, Default, PartialEq, Eq, Serialize, Deserialize)]
 pub struct CanonicalUsage {
     pub input_tokens: u64,
+    /// True when `input_tokens` already includes cache read and cache creation
+    /// input tokens. Claude-style usage leaves cached input tokens separate.
+    #[serde(default, skip_serializing_if = "is_false")]
+    pub input_tokens_include_cache: bool,
     pub output_tokens: u64,
     pub total_tokens: u64,
     pub cache_creation_tokens: u64,
@@ -13,6 +17,10 @@ pub struct CanonicalUsage {
     pub reasoning_tokens: u64,
 }
 
+fn is_false(value: &bool) -> bool {
+    !*value
+}
+
 #[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
 #[serde(tag = "type", rename_all = "snake_case")]
 pub enum CanonicalContentPart {