fix(proxy): improve usage logging and cache token parsing

- Log requests even when usage parsing fails (with default values)
- Add detailed debug logging for usage metrics
- Support cache_read_input_tokens field in Codex responses
- Fallback to input_tokens_details.cached_tokens if needed
- Add test case for cached_tokens in input_tokens_details
- Ensure all requests are tracked in database for analytics

This fixes missing request logs when API responses lack usage data
and improves cache token detection across different response formats.

src-tauri/src/proxy/response_processor.rs

@@ -112,6 +112,19 @@ pub async fn handle_non_streaming(
 
             spawn_log_usage(state, ctx, usage, &model, status.as_u16(), false);
         } else {
+            let model = json_value
+                .get("model")
+                .and_then(|m| m.as_str())
+                .unwrap_or(&ctx.request_model)
+                .to_string();
+            spawn_log_usage(
+                state,
+                ctx,
+                TokenUsage::default(),
+                &model,
+                status.as_u16(),
+                false,
+            );
             log::debug!(
                 "[{}] 未能解析 usage 信息，跳过记录",
                 parser_config.app_type_str
@@ -123,6 +136,14 @@ pub async fn handle_non_streaming(
             ctx.tag,
             body_bytes.len()
         );
+        spawn_log_usage(
+            state,
+            ctx,
+            TokenUsage::default(),
+            &ctx.request_model,
+            status.as_u16(),
+            false,
+        );
     }
 
     log::info!("[{}] ====== 请求结束 ======", ctx.tag);
@@ -267,6 +288,25 @@ fn create_usage_collector(
                 .await;
             });
         } else {
+            let model = model_extractor(&events, &request_model);
+            let latency_ms = start_time.elapsed().as_millis() as u64;
+            let state = state.clone();
+            let provider_id = provider_id.clone();
+
+            tokio::spawn(async move {
+                log_usage_internal(
+                    &state,
+                    &provider_id,
+                    app_type_str,
+                    &model,
+                    TokenUsage::default(),
+                    latency_ms,
+                    first_token_ms,
+                    true, // is_streaming
+                    status_code,
+                )
+                .await;
+            });
             log::debug!("[{tag}] 流式响应缺少 usage 统计，跳过消费记录");
         }
     })
@@ -338,6 +378,14 @@ async fn log_usage_internal(
 
     let request_id = uuid::Uuid::new_v4().to_string();
 
+    log::debug!(
+        "[{app_type}] 记录请求日志: id={request_id}, provider={provider_id}, model={model}, streaming={is_streaming}, status={status_code}, latency_ms={latency_ms}, first_token_ms={first_token_ms:?}, input={}, output={}, cache_read={}, cache_creation={}",
+        usage.input_tokens,
+        usage.output_tokens,
+        usage.cache_read_tokens,
+        usage.cache_creation_tokens
+    );
+
     if let Err(e) = logger.log_with_calculation(
         request_id,
         provider_id.to_string(),

src-tauri/src/proxy/usage/parser.rs

@@ -163,13 +163,21 @@ impl TokenUsage {
             .and_then(|v| v.as_str())
             .map(|s| s.to_string());
 
+        let cached_tokens = usage
+            .get("cache_read_input_tokens")
+            .and_then(|v| v.as_u64())
+            .or_else(|| {
+                usage
+                    .get("input_tokens_details")
+                    .and_then(|d| d.get("cached_tokens"))
+                    .and_then(|v| v.as_u64())
+            })
+            .unwrap_or(0) as u32;
+
         Some(Self {
             input_tokens: input_tokens? as u32,
             output_tokens: output_tokens? as u32,
-            cache_read_tokens: usage
-                .get("cache_read_input_tokens")
-                .and_then(|v| v.as_u64())
-                .unwrap_or(0) as u32,
+            cache_read_tokens: cached_tokens,
             cache_creation_tokens: usage
                 .get("cache_creation_input_tokens")
                 .and_then(|v| v.as_u64())
@@ -188,11 +196,16 @@ impl TokenUsage {
         let input_tokens = usage.get("input_tokens")?.as_u64()? as u32;
         let output_tokens = usage.get("output_tokens")?.as_u64()? as u32;
 
-        // 获取 cached_tokens (可能在 input_tokens_details 中)
+        // 获取 cached_tokens (可能在 cache_read_input_tokens 或 input_tokens_details 中)
         let cached_tokens = usage
-            .get("input_tokens_details")
-            .and_then(|d| d.get("cached_tokens"))
+            .get("cache_read_input_tokens")
             .and_then(|v| v.as_u64())
+            .or_else(|| {
+                usage
+                    .get("input_tokens_details")
+                    .and_then(|d| d.get("cached_tokens"))
+                    .and_then(|v| v.as_u64())
+            })
             .unwrap_or(0) as u32;
 
         // 调整 input_tokens: 减去 cached_tokens
@@ -499,6 +512,25 @@ mod tests {
         assert_eq!(usage.model, None);
     }
 
+    #[test]
+    fn test_codex_response_parsing_cached_tokens_in_details() {
+        let response = json!({
+            "usage": {
+                "input_tokens": 1000,
+                "output_tokens": 500,
+                "input_tokens_details": {
+                    "cached_tokens": 300
+                }
+            }
+        });
+
+        let usage = TokenUsage::from_codex_response(&response).unwrap();
+        // 非调整模式：input_tokens 保持原值，但应记录缓存命中
+        assert_eq!(usage.input_tokens, 1000);
+        assert_eq!(usage.output_tokens, 500);
+        assert_eq!(usage.cache_read_tokens, 300);
+    }
+
     #[test]
     fn test_codex_response_adjusted() {
         let response = json!({
@@ -534,6 +566,22 @@ mod tests {
         assert_eq!(usage.cache_read_tokens, 0);
     }
 
+    #[test]
+    fn test_codex_response_adjusted_cache_read_input_tokens() {
+        let response = json!({
+            "usage": {
+                "input_tokens": 1000,
+                "output_tokens": 500,
+                "cache_read_input_tokens": 200
+            }
+        });
+
+        let usage = TokenUsage::from_codex_response_adjusted(&response).unwrap();
+        assert_eq!(usage.input_tokens, 800);
+        assert_eq!(usage.output_tokens, 500);
+        assert_eq!(usage.cache_read_tokens, 200);
+    }
+
     #[test]
     fn test_codex_response_adjusted_saturating_sub() {
         // 测试 cached_tokens > input_tokens 的边界情况