fix: 三端联调测试 2 P0 + 6 P1 + 2 P2 修复

P0-1: SaaS relay 模型别名解析 — "glm-4-flash" → "glm-4-flash-250414" (resolve_model)
P0-2: config.rs interpolate_env_vars UTF-8 修复 (chars 迭代器替代 bytes as char)
      + DB 启动编码检查 + docker-compose UTF-8 编码参数

P1-3: UI 模型选择器覆盖 Agent 默认模型 (model_override 全链路: TS→Tauri→Rust kernel)
P1-6: 知识搜索管道修复 — seed_knowledge 创建 chunks + 默认分类 (seed/uploaded/distillation)
P1-7: 用量限额从当前 Plan 读取 (非 stale usage 表)
P1-8: relay 双维度配额检查 (relay_requests + input_tokens)

P2-9: SSE 路径 token 计数修复 — 流结束检测替代固定 500ms sleep + billing increment

crates/zclaw-saas/src/middleware.rs

@@ -145,6 +145,26 @@ pub async fn quota_check_middleware(
         _ => {}
     }
 
+    // P1-8 修复: 同时检查 input_tokens 配额
+    match crate::billing::service::check_quota(&state.db, &account_id, "input_tokens").await {
+        Ok(check) if !check.allowed => {
+            tracing::warn!(
+                "Token quota exceeded for account {}: {} ({}/{})",
+                account_id,
+                check.reason.as_deref().unwrap_or("Token配额已用尽"),
+                check.current,
+                check.limit.map(|l| l.to_string()).unwrap_or_else(|| "∞".into()),
+            );
+            return SaasError::RateLimited(
+                check.reason.unwrap_or_else(|| "月度 Token 配额已用尽".into()),
+            ).into_response();
+        }
+        Err(e) => {
+            tracing::warn!("Token quota check failed for account {}: {}", account_id, e);
+        }
+        _ => {}
+    }
+
     next.run(req).await
 }