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

apps/aether-gateway/src/tests/ai_execute/sync/claude/local_chat.rs

@@ -18,6 +18,8 @@ async fn gateway_executes_claude_chat_sync_via_local_decision_gate_with_local_sy
         url: String,
         model: String,
         auth_header_value: String,
+        anthropic_version: String,
+        anthropic_beta: String,
         endpoint_tag: String,
         metadata_mode: String,
         metadata_source: String,
@@ -261,6 +263,18 @@ async fn gateway_executes_claude_chat_sync_via_local_decision_gate_with_local_sy
                         .and_then(|value| value.as_str())
                         .unwrap_or_default()
                         .to_string(),
+                    anthropic_version: payload
+                        .get("headers")
+                        .and_then(|value| value.get("anthropic-version"))
+                        .and_then(|value| value.as_str())
+                        .unwrap_or_default()
+                        .to_string(),
+                    anthropic_beta: payload
+                        .get("headers")
+                        .and_then(|value| value.get("anthropic-beta"))
+                        .and_then(|value| value.as_str())
+                        .unwrap_or_default()
+                        .to_string(),
                     endpoint_tag: payload
                         .get("headers")
                         .and_then(|value| value.get("x-endpoint-tag"))
@@ -357,6 +371,8 @@ async fn gateway_executes_claude_chat_sync_via_local_decision_gate_with_local_sy
         .post(format!("{gateway_url}/v1/messages"))
         .header(http::header::CONTENT_TYPE, "application/json")
         .header("x-api-key", "sk-client-claude-chat-local")
+        .header("anthropic-version", "2023-06-01")
+        .header("anthropic-beta", "prompt-caching-2024-07-31,context-1m-2025-08-07")
         .header(TRACE_ID_HEADER, "trace-claude-chat-local-123")
         .body(
             "{\"model\":\"claude-sonnet-4-5\",\"messages\":[],\"metadata\":{\"client\":\"desktop-claude\"}}",
@@ -390,6 +406,14 @@ async fn gateway_executes_claude_chat_sync_via_local_decision_gate_with_local_sy
         seen_execution_runtime_request.auth_header_value,
         "sk-upstream-claude-chat"
     );
+    assert_eq!(
+        seen_execution_runtime_request.anthropic_version,
+        "2023-06-01"
+    );
+    assert_eq!(
+        seen_execution_runtime_request.anthropic_beta,
+        "prompt-caching-2024-07-31,context-1m-2025-08-07"
+    );
     assert_eq!(
         seen_execution_runtime_request.endpoint_tag,
         "claude-chat-local"

apps/aether-gateway/src/tests/ai_execute/sync/claude/local_cli.rs

@@ -18,6 +18,8 @@ async fn gateway_executes_claude_cli_sync_via_local_decision_gate_with_local_syn
         url: String,
         model: String,
         authorization: String,
+        anthropic_version: String,
+        anthropic_beta: String,
         endpoint_tag: String,
         metadata_mode: String,
         metadata_source: String,
@@ -261,6 +263,18 @@ async fn gateway_executes_claude_cli_sync_via_local_decision_gate_with_local_syn
                         .and_then(|value| value.as_str())
                         .unwrap_or_default()
                         .to_string(),
+                    anthropic_version: payload
+                        .get("headers")
+                        .and_then(|value| value.get("anthropic-version"))
+                        .and_then(|value| value.as_str())
+                        .unwrap_or_default()
+                        .to_string(),
+                    anthropic_beta: payload
+                        .get("headers")
+                        .and_then(|value| value.get("anthropic-beta"))
+                        .and_then(|value| value.as_str())
+                        .unwrap_or_default()
+                        .to_string(),
                     endpoint_tag: payload
                         .get("headers")
                         .and_then(|value| value.get("x-endpoint-tag"))
@@ -359,6 +373,8 @@ async fn gateway_executes_claude_cli_sync_via_local_decision_gate_with_local_syn
             http::header::AUTHORIZATION,
             "Bearer sk-client-claude-cli-local",
         )
+        .header("anthropic-version", "2023-06-01")
+        .header("anthropic-beta", "prompt-caching-2024-07-31")
         .header(TRACE_ID_HEADER, "trace-claude-cli-local-sync-123")
         .body(
             "{\"model\":\"claude-code\",\"messages\":[],\"metadata\":{\"client\":\"desktop-claude-cli\"}}",
@@ -398,6 +414,14 @@ async fn gateway_executes_claude_cli_sync_via_local_decision_gate_with_local_syn
         seen_execution_runtime_request.authorization,
         "Bearer sk-upstream-claude-cli"
     );
+    assert_eq!(
+        seen_execution_runtime_request.anthropic_version,
+        "2023-06-01"
+    );
+    assert_eq!(
+        seen_execution_runtime_request.anthropic_beta,
+        "prompt-caching-2024-07-31"
+    );
     assert_eq!(
         seen_execution_runtime_request.endpoint_tag,
         "claude-cli-local"