chore: sync VERSION file with release v1.1.239 [skip ci]

针对 OAuth 和 Setup Token 类型的 Claude 账户，遇到 403 错误时：
- 休息 2 秒后进行重试
- 最多重试 2 次（总共最多 3 次请求）
- 重试后仍是 403 才标记账户为 blocked

同时支持流式和非流式请求，并修复了流式请求中的竞态条件问题。

README.md

@@ -408,6 +408,8 @@ export ANTHROPIC_AUTH_TOKEN="后台创建的API密钥"
 
 如果该文件不存在，请手动创建。Windows 用户路径为 `C:\Users\你的用户名\.claude\config.json`。
 
+> 💡 **IntelliJ IDEA 用户推荐**：[Claude Code Plus](https://github.com/touwaeriol/claude-code-plus) - 将 Claude Code 直接集成到 IDE，支持代码理解、文件读写、命令执行。插件市场搜索 `Claude Code Plus` 即可安装。
+
 **Gemini CLI 设置环境变量：**
 
 **方式一（推荐）：通过 Gemini Assist API 方式访问**

VERSION

@@ -1 +1 @@
-1.1.237
+1.1.239

src/app.js

@@ -581,10 +581,11 @@ class Application {
 
         const now = Date.now()
         let totalCleaned = 0
+        let legacyCleaned = 0
 
         // 使用 Lua 脚本批量清理所有过期项
         for (const key of keys) {
-          // 跳过非 Sorted Set 类型的键（这些键有各自的清理逻辑）
+          // 跳过已知非 Sorted Set 类型的键（这些键有各自的清理逻辑）
           // - concurrency:queue:stats:* 是 Hash 类型
           // - concurrency:queue:wait_times:* 是 List 类型
           // - concurrency:queue:* (不含stats/wait_times) 是 String 类型
@@ -599,11 +600,21 @@ class Application {
           }
 
           try {
-            const cleaned = await redis.client.eval(
+            // 使用原子 Lua 脚本：先检查类型，再执行清理
+            // 返回值：0 = 正常清理无删除，1 = 清理后删除空键，-1 = 遗留键已删除
+            const result = await redis.client.eval(
               `
               local key = KEYS[1]
               local now = tonumber(ARGV[1])
 
+              -- 先检查键类型，只对 Sorted Set 执行清理
+              local keyType = redis.call('TYPE', key)
+              if keyType.ok ~= 'zset' then
+                -- 非 ZSET 类型的遗留键，直接删除
+                redis.call('DEL', key)
+                return -1
+              end
+
               -- 清理过期项
               redis.call('ZREMRANGEBYSCORE', key, '-inf', now)
 
@@ -622,8 +633,10 @@ class Application {
               key,
               now
             )
-            if (cleaned === 1) {
+            if (result === 1) {
               totalCleaned++
+            } else if (result === -1) {
+              legacyCleaned++
             }
           } catch (error) {
             logger.error(`❌ Failed to clean concurrency key ${key}:`, error)
@@ -633,6 +646,9 @@ class Application {
         if (totalCleaned > 0) {
           logger.info(`🔢 Concurrency cleanup: cleaned ${totalCleaned} expired keys`)
         }
+        if (legacyCleaned > 0) {
+          logger.warn(`🧹 Concurrency cleanup: removed ${legacyCleaned} legacy keys (wrong type)`)
+        }
       } catch (error) {
         logger.error('❌ Concurrency cleanup task failed:', error)
       }

src/middleware/auth.js

@@ -1744,10 +1744,14 @@ const requestLogger = (req, res, next) => {
   const referer = req.get('Referer') || 'none'
 
   // 记录请求开始
+  const isDebugRoute = req.originalUrl.includes('event_logging')
   if (req.originalUrl !== '/health') {
-    // 避免健康检查日志过多
+    if (isDebugRoute) {
+      logger.debug(`▶️ [${requestId}] ${req.method} ${req.originalUrl} | IP: ${clientIP}`)
+    } else {
       logger.info(`▶️ [${requestId}] ${req.method} ${req.originalUrl} | IP: ${clientIP}`)
     }
+  }
 
   res.on('finish', () => {
     const duration = Date.now() - start
@@ -1778,8 +1782,15 @@ const requestLogger = (req, res, next) => {
         logMetadata
       )
     } else if (req.originalUrl !== '/health') {
+      if (isDebugRoute) {
+        logger.debug(
+          `🟢 ${req.method} ${req.originalUrl} - ${res.statusCode} (${duration}ms)`,
+          logMetadata
+        )
+      } else {
         logger.request(req.method, req.originalUrl, res.statusCode, duration, logMetadata)
       }
+    }
 
     // API Key相关日志
     if (req.apiKey) {

src/models/redis.js

@@ -2140,6 +2140,27 @@ class RedisClient {
       const results = []
 
       for (const key of keys) {
+        // 跳过已知非 Sorted Set 类型的键
+        // - concurrency:queue:stats:* 是 Hash 类型
+        // - concurrency:queue:wait_times:* 是 List 类型
+        // - concurrency:queue:* (不含stats/wait_times) 是 String 类型
+        if (
+          key.startsWith('concurrency:queue:stats:') ||
+          key.startsWith('concurrency:queue:wait_times:') ||
+          (key.startsWith('concurrency:queue:') &&
+            !key.includes(':stats:') &&
+            !key.includes(':wait_times:'))
+        ) {
+          continue
+        }
+
+        // 检查键类型，只处理 Sorted Set
+        const keyType = await client.type(key)
+        if (keyType !== 'zset') {
+          logger.debug(`🔢 getAllConcurrencyStatus skipped non-zset key: ${key} (type: ${keyType})`)
+          continue
+        }
+
         // 提取 apiKeyId（去掉 concurrency: 前缀）
         const apiKeyId = key.replace('concurrency:', '')
 
@@ -2202,6 +2223,23 @@ class RedisClient {
         }
       }
 
+      // 检查键类型，只处理 Sorted Set
+      const keyType = await client.type(key)
+      if (keyType !== 'zset') {
+        logger.warn(
+          `⚠️ getConcurrencyStatus: key ${key} has unexpected type: ${keyType}, expected zset`
+        )
+        return {
+          apiKeyId,
+          key,
+          activeCount: 0,
+          expiredCount: 0,
+          activeRequests: [],
+          exists: true,
+          invalidType: keyType
+        }
+      }
+
       // 获取所有成员和分数
       const allMembers = await client.zrange(key, 0, -1, 'WITHSCORES')
 
@@ -2251,20 +2289,36 @@ class RedisClient {
       const client = this.getClientSafe()
       const key = `concurrency:${apiKeyId}`
 
-      // 获取清理前的状态
+      // 检查键类型
-      const beforeCount = await client.zcard(key)
+      const keyType = await client.type(key)
 
-      // 删除整个 key
+      let beforeCount = 0
+      let isLegacy = false
+
+      if (keyType === 'zset') {
+        // 正常的 zset 键，获取条目数
+        beforeCount = await client.zcard(key)
+      } else if (keyType !== 'none') {
+        // 非 zset 且非空的遗留键
+        isLegacy = true
+        logger.warn(
+          `⚠️ forceClearConcurrency: key ${key} has unexpected type: ${keyType}, will be deleted`
+        )
+      }
+
+      // 删除键（无论什么类型）
       await client.del(key)
 
       logger.warn(
-        `🧹 Force cleared concurrency for key ${apiKeyId}, removed ${beforeCount} entries`
+        `🧹 Force cleared concurrency for key ${apiKeyId}, removed ${beforeCount} entries${isLegacy ? ' (legacy key)' : ''}`
       )
 
       return {
         apiKeyId,
         key,
         clearedCount: beforeCount,
+        type: keyType,
+        legacy: isLegacy,
         success: true
       }
     } catch (error) {
@@ -2283,25 +2337,47 @@ class RedisClient {
       const keys = await client.keys('concurrency:*')
 
       let totalCleared = 0
+      let legacyCleared = 0
       const clearedKeys = []
 
       for (const key of keys) {
+        // 跳过 queue 相关的键（它们有各自的清理逻辑）
+        if (key.startsWith('concurrency:queue:')) {
+          continue
+        }
+
+        // 检查键类型
+        const keyType = await client.type(key)
+        if (keyType === 'zset') {
           const count = await client.zcard(key)
           await client.del(key)
           totalCleared += count
           clearedKeys.push({
             key,
-          clearedCount: count
+            clearedCount: count,
+            type: 'zset'
           })
+        } else {
+          // 非 zset 类型的遗留键，直接删除
+          await client.del(key)
+          legacyCleared++
+          clearedKeys.push({
+            key,
+            clearedCount: 0,
+            type: keyType,
+            legacy: true
+          })
+        }
       }
 
       logger.warn(
-        `🧹 Force cleared all concurrency: ${keys.length} keys, ${totalCleared} total entries`
+        `🧹 Force cleared all concurrency: ${clearedKeys.length} keys, ${totalCleared} entries, ${legacyCleared} legacy keys`
       )
 
       return {
-        keysCleared: keys.length,
+        keysCleared: clearedKeys.length,
         totalEntriesCleared: totalCleared,
+        legacyKeysCleared: legacyCleared,
         clearedKeys,
         success: true
       }
@@ -2329,9 +2405,30 @@ class RedisClient {
       }
 
       let totalCleaned = 0
+      let legacyCleaned = 0
       const cleanedKeys = []
 
       for (const key of keys) {
+        // 跳过 queue 相关的键（它们有各自的清理逻辑）
+        if (key.startsWith('concurrency:queue:')) {
+          continue
+        }
+
+        // 检查键类型
+        const keyType = await client.type(key)
+        if (keyType !== 'zset') {
+          // 非 zset 类型的遗留键，直接删除
+          await client.del(key)
+          legacyCleaned++
+          cleanedKeys.push({
+            key,
+            cleanedCount: 0,
+            type: keyType,
+            legacy: true
+          })
+          continue
+        }
+
         // 只清理过期的条目
         const cleaned = await client.zremrangebyscore(key, '-inf', now)
         if (cleaned > 0) {
@@ -2350,13 +2447,14 @@ class RedisClient {
       }
 
       logger.info(
-        `🧹 Cleaned up expired concurrency: ${totalCleaned} entries from ${cleanedKeys.length} keys`
+        `🧹 Cleaned up expired concurrency: ${totalCleaned} entries from ${cleanedKeys.length} keys, ${legacyCleaned} legacy keys removed`
       )
 
       return {
         keysProcessed: keys.length,
         keysCleaned: cleanedKeys.length,
         totalEntriesCleaned: totalCleaned,
+        legacyKeysRemoved: legacyCleaned,
         cleanedKeys,
         success: true
       }

src/routes/admin/claudeAccounts.js

@@ -585,7 +585,8 @@ router.post('/claude-accounts', authenticateAdmin, async (req, res) => {
       unifiedClientId,
       expiresAt,
       extInfo,
-      maxConcurrency
+      maxConcurrency,
+      interceptWarmup
     } = req.body
 
     if (!name) {
@@ -631,7 +632,8 @@ router.post('/claude-accounts', authenticateAdmin, async (req, res) => {
       unifiedClientId: unifiedClientId || '', // 统一的客户端标识
       expiresAt: expiresAt || null, // 账户订阅到期时间
       extInfo: extInfo || null,
-      maxConcurrency: maxConcurrency || 0 // 账户级串行队列：0=使用全局配置，>0=强制启用
+      maxConcurrency: maxConcurrency || 0, // 账户级串行队列：0=使用全局配置，>0=强制启用
+      interceptWarmup: interceptWarmup === true // 拦截预热请求：默认为false
     })
 
     // 如果是分组类型，将账户添加到分组

src/routes/admin/claudeConsoleAccounts.js

@@ -132,7 +132,8 @@ router.post('/claude-console-accounts', authenticateAdmin, async (req, res) => {
       dailyQuota,
       quotaResetTime,
       maxConcurrentTasks,
-      disableAutoProtection
+      disableAutoProtection,
+      interceptWarmup
     } = req.body
 
     if (!name || !apiUrl || !apiKey) {
@@ -186,7 +187,8 @@ router.post('/claude-console-accounts', authenticateAdmin, async (req, res) => {
         maxConcurrentTasks !== undefined && maxConcurrentTasks !== null
           ? Number(maxConcurrentTasks)
           : 0,
-      disableAutoProtection: normalizedDisableAutoProtection
+      disableAutoProtection: normalizedDisableAutoProtection,
+      interceptWarmup: interceptWarmup === true || interceptWarmup === 'true'
     })
 
     // 如果是分组类型，将账户添加到分组（CCR 归属 Claude 平台分组）

src/routes/api.js

@@ -12,6 +12,13 @@ const { getEffectiveModel, parseVendorPrefixedModel } = require('../utils/modelH
 const sessionHelper = require('../utils/sessionHelper')
 const { updateRateLimitCounters } = require('../utils/rateLimitHelper')
 const claudeRelayConfigService = require('../services/claudeRelayConfigService')
+const claudeAccountService = require('../services/claudeAccountService')
+const claudeConsoleAccountService = require('../services/claudeConsoleAccountService')
+const {
+  isWarmupRequest,
+  buildMockWarmupResponse,
+  sendMockWarmupStream
+} = require('../utils/warmupInterceptor')
 const { sanitizeUpstreamError } = require('../utils/errorSanitizer')
 const router = express.Router()
 
@@ -363,6 +370,23 @@ async function handleMessagesRequest(req, res) {
         }
       }
 
+      // 🔥 预热请求拦截检查（在转发之前）
+      if (accountType === 'claude-official' || accountType === 'claude-console') {
+        const account =
+          accountType === 'claude-official'
+            ? await claudeAccountService.getAccount(accountId)
+            : await claudeConsoleAccountService.getAccount(accountId)
+
+        if (account?.interceptWarmup === 'true' && isWarmupRequest(req.body)) {
+          logger.api(`🔥 Warmup request intercepted for account: ${account.name} (${accountId})`)
+          if (isStream) {
+            return sendMockWarmupStream(res, req.body.model)
+          } else {
+            return res.json(buildMockWarmupResponse(req.body.model))
+          }
+        }
+      }
+
       // 根据账号类型选择对应的转发服务并调用
       if (accountType === 'claude-official') {
         // 官方Claude账号使用原有的转发服务（会自己选择账号）
@@ -862,6 +886,21 @@ async function handleMessagesRequest(req, res) {
         }
       }
 
+      // 🔥 预热请求拦截检查（非流式，在转发之前）
+      if (accountType === 'claude-official' || accountType === 'claude-console') {
+        const account =
+          accountType === 'claude-official'
+            ? await claudeAccountService.getAccount(accountId)
+            : await claudeConsoleAccountService.getAccount(accountId)
+
+        if (account?.interceptWarmup === 'true' && isWarmupRequest(req.body)) {
+          logger.api(
+            `🔥 Warmup request intercepted (non-stream) for account: ${account.name} (${accountId})`
+          )
+          return res.json(buildMockWarmupResponse(req.body.model))
+        }
+      }
+
       // 根据账号类型选择对应的转发服务
       let response
       logger.debug(`[DEBUG] Request query params: ${JSON.stringify(req.query)}`)
@@ -1354,9 +1393,6 @@ router.post('/v1/messages/count_tokens', authenticateApiKey, async (req, res) =>
   const maxAttempts = 2
   let attempt = 0
 
-  // 引入 claudeConsoleAccountService 用于检查 count_tokens 可用性
-  const claudeConsoleAccountService = require('../services/claudeConsoleAccountService')
-
   const processRequest = async () => {
     const { accountId, accountType } = await unifiedClaudeScheduler.selectAccountForApiKey(
       req.apiKey,
@@ -1552,5 +1588,10 @@ router.post('/v1/messages/count_tokens', authenticateApiKey, async (req, res) =>
   }
 })
 
+// Claude Code 客户端遥测端点 - 返回成功响应避免 404 日志
+router.post('/api/event_logging/batch', (req, res) => {
+  res.status(200).json({ success: true })
+})
+
 module.exports = router
 module.exports.handleMessagesRequest = handleMessagesRequest

src/services/claudeAccountService.js

@@ -92,7 +92,8 @@ class ClaudeAccountService {
       unifiedClientId = '', // 统一的客户端标识
       expiresAt = null, // 账户订阅到期时间
       extInfo = null, // 额外扩展信息
-      maxConcurrency = 0 // 账户级用户消息串行队列：0=使用全局配置，>0=强制启用串行
+      maxConcurrency = 0, // 账户级用户消息串行队列：0=使用全局配置，>0=强制启用串行
+      interceptWarmup = false // 拦截预热请求（标题生成、Warmup等）
     } = options
 
     const accountId = uuidv4()
@@ -139,7 +140,9 @@ class ClaudeAccountService {
         // 扩展信息
         extInfo: normalizedExtInfo ? JSON.stringify(normalizedExtInfo) : '',
         // 账户级用户消息串行队列限制
-        maxConcurrency: maxConcurrency.toString()
+        maxConcurrency: maxConcurrency.toString(),
+        // 拦截预热请求
+        interceptWarmup: interceptWarmup.toString()
       }
     } else {
       // 兼容旧格式
@@ -173,7 +176,9 @@ class ClaudeAccountService {
         // 扩展信息
         extInfo: normalizedExtInfo ? JSON.stringify(normalizedExtInfo) : '',
         // 账户级用户消息串行队列限制
-        maxConcurrency: maxConcurrency.toString()
+        maxConcurrency: maxConcurrency.toString(),
+        // 拦截预热请求
+        interceptWarmup: interceptWarmup.toString()
       }
     }
 
@@ -221,7 +226,8 @@ class ClaudeAccountService {
       useUnifiedUserAgent,
       useUnifiedClientId,
       unifiedClientId,
-      extInfo: normalizedExtInfo
+      extInfo: normalizedExtInfo,
+      interceptWarmup
     }
   }
 
@@ -581,7 +587,9 @@ class ClaudeAccountService {
             // 扩展信息
             extInfo: parsedExtInfo,
             // 账户级用户消息串行队列限制
-            maxConcurrency: parseInt(account.maxConcurrency || '0', 10)
+            maxConcurrency: parseInt(account.maxConcurrency || '0', 10),
+            // 拦截预热请求
+            interceptWarmup: account.interceptWarmup === 'true'
           }
         })
       )
@@ -674,7 +682,8 @@ class ClaudeAccountService {
         'unifiedClientId',
         'subscriptionExpiresAt',
         'extInfo',
-        'maxConcurrency'
+        'maxConcurrency',
+        'interceptWarmup'
       ]
       const updatedData = { ...accountData }
       let shouldClearAutoStopFields = false

src/services/claudeConsoleAccountService.js

@@ -68,7 +68,8 @@ class ClaudeConsoleAccountService {
       dailyQuota = 0, // 每日额度限制（美元），0表示不限制
       quotaResetTime = '00:00', // 额度重置时间（HH:mm格式）
       maxConcurrentTasks = 0, // 最大并发任务数，0表示无限制
-      disableAutoProtection = false // 是否关闭自动防护（429/401/400/529 不自动禁用）
+      disableAutoProtection = false, // 是否关闭自动防护（429/401/400/529 不自动禁用）
+      interceptWarmup = false // 拦截预热请求（标题生成、Warmup等）
     } = options
 
     // 验证必填字段
@@ -117,7 +118,8 @@ class ClaudeConsoleAccountService {
       quotaResetTime, // 额度重置时间
       quotaStoppedAt: '', // 因额度停用的时间
       maxConcurrentTasks: maxConcurrentTasks.toString(), // 最大并发任务数，0表示无限制
-      disableAutoProtection: disableAutoProtection.toString() // 关闭自动防护
+      disableAutoProtection: disableAutoProtection.toString(), // 关闭自动防护
+      interceptWarmup: interceptWarmup.toString() // 拦截预热请求
     }
 
     const client = redis.getClientSafe()
@@ -156,6 +158,7 @@ class ClaudeConsoleAccountService {
       quotaStoppedAt: null,
       maxConcurrentTasks, // 新增：返回并发限制配置
       disableAutoProtection, // 新增：返回自动防护开关
+      interceptWarmup, // 新增：返回预热请求拦截开关
       activeTaskCount: 0 // 新增：新建账户当前并发数为0
     }
   }
@@ -217,7 +220,9 @@ class ClaudeConsoleAccountService {
             // 并发控制相关
             maxConcurrentTasks: parseInt(accountData.maxConcurrentTasks) || 0,
             activeTaskCount,
-            disableAutoProtection: accountData.disableAutoProtection === 'true'
+            disableAutoProtection: accountData.disableAutoProtection === 'true',
+            // 拦截预热请求
+            interceptWarmup: accountData.interceptWarmup === 'true'
           })
         }
       }
@@ -375,6 +380,9 @@ class ClaudeConsoleAccountService {
       if (updates.disableAutoProtection !== undefined) {
         updatedData.disableAutoProtection = updates.disableAutoProtection.toString()
       }
+      if (updates.interceptWarmup !== undefined) {
+        updatedData.interceptWarmup = updates.interceptWarmup.toString()
+      }
 
       // ✅ 直接保存 subscriptionExpiresAt（如果提供）
       // Claude Console 没有 token 刷新逻辑，不会覆盖此字段

src/services/claudeRelayService.js

@@ -333,7 +333,14 @@ class ClaudeRelayService {
       }
 
       // 发送请求到Claude API（传入回调以获取请求对象）
-      const response = await this._makeClaudeRequest(
+      // 🔄 403 重试机制：仅对 claude-official 类型账户（OAuth 或 Setup Token）
+      const maxRetries = this._shouldRetryOn403(accountType) ? 2 : 0
+      let retryCount = 0
+      let response
+      let shouldRetry = false
+
+      do {
+        response = await this._makeClaudeRequest(
           processedBody,
           accessToken,
           proxyAgent,
@@ -345,6 +352,28 @@ class ClaudeRelayService {
           options
         )
 
+        // 检查是否需要重试 403
+        shouldRetry = response.statusCode === 403 && retryCount < maxRetries
+        if (shouldRetry) {
+          retryCount++
+          logger.warn(
+            `🔄 403 error for account ${accountId}, retry ${retryCount}/${maxRetries} after 2s`
+          )
+          await this._sleep(2000)
+        }
+      } while (shouldRetry)
+
+      // 如果进行了重试，记录最终结果
+      if (retryCount > 0) {
+        if (response.statusCode === 403) {
+          logger.error(`🚫 403 error persists for account ${accountId} after ${retryCount} retries`)
+        } else {
+          logger.info(
+            `✅ 403 retry successful for account ${accountId} on attempt ${retryCount}, got status ${response.statusCode}`
+          )
+        }
+      }
+
       // 📬 请求已发送成功，立即释放队列锁（无需等待响应处理完成）
       // 因为 Claude API 限流基于请求发送时刻计算（RPM），不是请求完成时刻
       if (queueLockAcquired && queueRequestId && selectedAccountId) {
@@ -408,9 +437,10 @@ class ClaudeRelayService {
           }
         }
         // 检查是否为403状态码（禁止访问）
+        // 注意：如果进行了重试，retryCount > 0；这里的 403 是重试后最终的结果
         else if (response.statusCode === 403) {
           logger.error(
-            `🚫 Forbidden error (403) detected for account ${accountId}, marking as blocked`
+            `🚫 Forbidden error (403) detected for account ${accountId}${retryCount > 0 ? ` after ${retryCount} retries` : ''}, marking as blocked`
           )
           await unifiedClaudeScheduler.markAccountBlocked(accountId, accountType, sessionHash)
         }
@@ -1517,8 +1547,10 @@ class ClaudeRelayService {
     streamTransformer = null,
     requestOptions = {},
     isDedicatedOfficialAccount = false,
-    onResponseStart = null // 📬 新增：收到响应头时的回调，用于提前释放队列锁
+    onResponseStart = null, // 📬 新增：收到响应头时的回调，用于提前释放队列锁
+    retryCount = 0 // 🔄 403 重试计数器
   ) {
+    const maxRetries = 2 // 最大重试次数
     // 获取账户信息用于统一 User-Agent
     const account = await claudeAccountService.getAccount(accountId)
 
@@ -1631,6 +1663,51 @@ class ClaudeRelayService {
             }
           }
 
+          // 🔄 403 重试机制（必须在设置 res.on('data')/res.on('end') 之前处理）
+          // 否则重试时旧响应的 on('end') 会与新请求产生竞态条件
+          if (res.statusCode === 403) {
+            const canRetry =
+              this._shouldRetryOn403(accountType) &&
+              retryCount < maxRetries &&
+              !responseStream.headersSent
+
+            if (canRetry) {
+              logger.warn(
+                `🔄 [Stream] 403 error for account ${accountId}, retry ${retryCount + 1}/${maxRetries} after 2s`
+              )
+              // 消费当前响应并销毁请求
+              res.resume()
+              req.destroy()
+
+              // 等待 2 秒后递归重试
+              await this._sleep(2000)
+
+              try {
+                // 递归调用自身进行重试
+                const retryResult = await this._makeClaudeStreamRequestWithUsageCapture(
+                  body,
+                  accessToken,
+                  proxyAgent,
+                  clientHeaders,
+                  responseStream,
+                  usageCallback,
+                  accountId,
+                  accountType,
+                  sessionHash,
+                  streamTransformer,
+                  requestOptions,
+                  isDedicatedOfficialAccount,
+                  onResponseStart,
+                  retryCount + 1
+                )
+                resolve(retryResult)
+              } catch (retryError) {
+                reject(retryError)
+              }
+              return // 重要：提前返回，不设置后续的错误处理器
+            }
+          }
+
           // 将错误处理逻辑封装在一个异步函数中
           const handleErrorResponse = async () => {
             if (res.statusCode === 401) {
@@ -1654,8 +1731,10 @@ class ClaudeRelayService {
                 )
               }
             } else if (res.statusCode === 403) {
+              // 403 处理：走到这里说明重试已用尽或不适用重试，直接标记 blocked
+              // 注意：重试逻辑已在 handleErrorResponse 外部提前处理
               logger.error(
-                `🚫 [Stream] Forbidden error (403) detected for account ${accountId}, marking as blocked`
+                `🚫 [Stream] Forbidden error (403) detected for account ${accountId}${retryCount > 0 ? ` after ${retryCount} retries` : ''}, marking as blocked`
               )
               await unifiedClaudeScheduler.markAccountBlocked(accountId, accountType, sessionHash)
             } else if (res.statusCode === 529) {
@@ -2693,6 +2772,17 @@ class ClaudeRelayService {
       }
     }
   }
+
+  // 🔄 判断账户是否应该在 403 错误时进行重试
+  // 仅 claude-official 类型账户（OAuth 或 Setup Token 授权）需要重试
+  _shouldRetryOn403(accountType) {
+    return accountType === 'claude-official'
+  }
+
+  // ⏱️ 等待指定毫秒数
+  _sleep(ms) {
+    return new Promise((resolve) => setTimeout(resolve, ms))
+  }
 }
 
 module.exports = new ClaudeRelayService()

src/utils/warmupInterceptor.js

@@ -0,0 +1,202 @@
+'use strict'
+
+const { v4: uuidv4 } = require('uuid')
+
+/**
+ * 预热请求拦截器
+ * 检测并拦截低价值请求（标题生成、Warmup等），直接返回模拟响应
+ */
+
+/**
+ * 检测是否为预热请求
+ * @param {Object} body - 请求体
+ * @returns {boolean}
+ */
+function isWarmupRequest(body) {
+  if (!body) {
+    return false
+  }
+
+  // 检查 messages
+  if (body.messages && Array.isArray(body.messages)) {
+    for (const msg of body.messages) {
+      // 处理 content 为数组的情况
+      if (Array.isArray(msg.content)) {
+        for (const content of msg.content) {
+          if (content.type === 'text' && typeof content.text === 'string') {
+            if (isTitleOrWarmupText(content.text)) {
+              return true
+            }
+          }
+        }
+      }
+      // 处理 content 为字符串的情况
+      if (typeof msg.content === 'string') {
+        if (isTitleOrWarmupText(msg.content)) {
+          return true
+        }
+      }
+    }
+  }
+
+  // 检查 system prompt
+  if (body.system) {
+    const systemText = extractSystemText(body.system)
+    if (isTitleExtractionSystemPrompt(systemText)) {
+      return true
+    }
+  }
+
+  return false
+}
+
+/**
+ * 检查文本是否为标题生成或Warmup请求
+ */
+function isTitleOrWarmupText(text) {
+  if (!text) {
+    return false
+  }
+  return (
+    text.includes('Please write a 5-10 word title for the following conversation:') ||
+    text === 'Warmup'
+  )
+}
+
+/**
+ * 检查system prompt是否为标题提取类型
+ */
+function isTitleExtractionSystemPrompt(systemText) {
+  if (!systemText) {
+    return false
+  }
+  return systemText.includes(
+    'nalyze if this message indicates a new conversation topic. If it does, extract a 2-3 word title'
+  )
+}
+
+/**
+ * 从system字段提取文本
+ */
+function extractSystemText(system) {
+  if (typeof system === 'string') {
+    return system
+  }
+  if (Array.isArray(system)) {
+    return system.map((s) => (typeof s === 'object' ? s.text || '' : String(s))).join('')
+  }
+  return ''
+}
+
+/**
+ * 生成模拟的非流式响应
+ * @param {string} model - 模型名称
+ * @returns {Object}
+ */
+function buildMockWarmupResponse(model) {
+  return {
+    id: `msg_warmup_${uuidv4().replace(/-/g, '').slice(0, 20)}`,
+    type: 'message',
+    role: 'assistant',
+    content: [{ type: 'text', text: 'New Conversation' }],
+    model: model || 'claude-3-5-sonnet-20241022',
+    stop_reason: 'end_turn',
+    stop_sequence: null,
+    usage: {
+      input_tokens: 10,
+      output_tokens: 2
+    }
+  }
+}
+
+/**
+ * 发送模拟的流式响应
+ * @param {Object} res - Express response对象
+ * @param {string} model - 模型名称
+ */
+function sendMockWarmupStream(res, model) {
+  const effectiveModel = model || 'claude-3-5-sonnet-20241022'
+  const messageId = `msg_warmup_${uuidv4().replace(/-/g, '').slice(0, 20)}`
+
+  const events = [
+    {
+      event: 'message_start',
+      data: {
+        message: {
+          content: [],
+          id: messageId,
+          model: effectiveModel,
+          role: 'assistant',
+          stop_reason: null,
+          stop_sequence: null,
+          type: 'message',
+          usage: { input_tokens: 10, output_tokens: 0 }
+        },
+        type: 'message_start'
+      }
+    },
+    {
+      event: 'content_block_start',
+      data: {
+        content_block: { text: '', type: 'text' },
+        index: 0,
+        type: 'content_block_start'
+      }
+    },
+    {
+      event: 'content_block_delta',
+      data: {
+        delta: { text: 'New', type: 'text_delta' },
+        index: 0,
+        type: 'content_block_delta'
+      }
+    },
+    {
+      event: 'content_block_delta',
+      data: {
+        delta: { text: ' Conversation', type: 'text_delta' },
+        index: 0,
+        type: 'content_block_delta'
+      }
+    },
+    {
+      event: 'content_block_stop',
+      data: { index: 0, type: 'content_block_stop' }
+    },
+    {
+      event: 'message_delta',
+      data: {
+        delta: { stop_reason: 'end_turn', stop_sequence: null },
+        type: 'message_delta',
+        usage: { input_tokens: 10, output_tokens: 2 }
+      }
+    },
+    {
+      event: 'message_stop',
+      data: { type: 'message_stop' }
+    }
+  ]
+
+  let index = 0
+  const sendNext = () => {
+    if (index >= events.length) {
+      res.end()
+      return
+    }
+
+    const { event, data } = events[index]
+    res.write(`event: ${event}\ndata: ${JSON.stringify(data)}\n\n`)
+    index++
+
+    // 模拟网络延迟
+    setTimeout(sendNext, 20)
+  }
+
+  sendNext()
+}
+
+module.exports = {
+  isWarmupRequest,
+  buildMockWarmupResponse,
+  sendMockWarmupStream
+}

web/admin-spa/src/components/accounts/AccountForm.vue

@@ -1651,6 +1651,28 @@
               </label>
             </div>
 
+            <!-- 拦截预热请求开关（Claude 和 Claude Console） -->
+            <div
+              v-if="form.platform === 'claude' || form.platform === 'claude-console'"
+              class="mt-4"
+            >
+              <label class="flex items-start">
+                <input
+                  v-model="form.interceptWarmup"
+                  class="mt-1 text-blue-600 focus:ring-blue-500 dark:border-gray-600 dark:bg-gray-700"
+                  type="checkbox"
+                />
+                <div class="ml-3">
+                  <span class="text-sm font-medium text-gray-700 dark:text-gray-300">
+                    拦截预热请求
+                  </span>
+                  <p class="mt-1 text-xs text-gray-500 dark:text-gray-400">
+                    启用后，对标题生成、Warmup 等低价值请求直接返回模拟响应，不消耗上游 API 额度
+                  </p>
+                </div>
+              </label>
+            </div>
+
             <!-- Claude User-Agent 版本配置 -->
             <div v-if="form.platform === 'claude'" class="mt-4">
               <label class="flex items-start">
@@ -2653,6 +2675,25 @@
             </label>
           </div>
 
+          <!-- 拦截预热请求开关（Claude 和 Claude Console 编辑模式） -->
+          <div v-if="form.platform === 'claude' || form.platform === 'claude-console'" class="mt-4">
+            <label class="flex items-start">
+              <input
+                v-model="form.interceptWarmup"
+                class="mt-1 text-blue-600 focus:ring-blue-500 dark:border-gray-600 dark:bg-gray-700"
+                type="checkbox"
+              />
+              <div class="ml-3">
+                <span class="text-sm font-medium text-gray-700 dark:text-gray-300">
+                  拦截预热请求
+                </span>
+                <p class="mt-1 text-xs text-gray-500 dark:text-gray-400">
+                  启用后，对标题生成、Warmup 等低价值请求直接返回模拟响应，不消耗上游 API 额度
+                </p>
+              </div>
+            </label>
+          </div>
+
           <!-- Claude User-Agent 版本配置（编辑模式） -->
           <div v-if="form.platform === 'claude'" class="mt-4">
             <label class="flex items-start">
@@ -3988,6 +4029,8 @@ const form = ref({
   useUnifiedClientId: props.account?.useUnifiedClientId || false, // 使用统一的客户端标识
   unifiedClientId: props.account?.unifiedClientId || '', // 统一的客户端标识
   serialQueueEnabled: (props.account?.maxConcurrency || 0) > 0, // 账户级串行队列开关
+  interceptWarmup:
+    props.account?.interceptWarmup === true || props.account?.interceptWarmup === 'true', // 拦截预热请求
   groupId: '',
   groupIds: [],
   projectId: props.account?.projectId || '',
@@ -4574,6 +4617,7 @@ const buildClaudeAccountData = (tokenInfo, accountName, clientId) => {
     claudeAiOauth: claudeOauthPayload,
     priority: form.value.priority || 50,
     autoStopOnWarning: form.value.autoStopOnWarning || false,
+    interceptWarmup: form.value.interceptWarmup || false,
     useUnifiedUserAgent: form.value.useUnifiedUserAgent || false,
     useUnifiedClientId: form.value.useUnifiedClientId || false,
     unifiedClientId: clientId,
@@ -5131,6 +5175,7 @@ const createAccount = async () => {
       // 上游错误处理（仅 Claude Console）
       if (form.value.platform === 'claude-console') {
         data.disableAutoProtection = !!form.value.disableAutoProtection
+        data.interceptWarmup = !!form.value.interceptWarmup
       }
       // 额度管理字段
       data.dailyQuota = form.value.dailyQuota || 0
@@ -5427,6 +5472,7 @@ const updateAccount = async () => {
 
       data.priority = form.value.priority || 50
       data.autoStopOnWarning = form.value.autoStopOnWarning || false
+      data.interceptWarmup = form.value.interceptWarmup || false
       data.useUnifiedUserAgent = form.value.useUnifiedUserAgent || false
       data.useUnifiedClientId = form.value.useUnifiedClientId || false
       data.unifiedClientId = form.value.unifiedClientId || ''
@@ -5463,6 +5509,8 @@ const updateAccount = async () => {
       data.rateLimitDuration = form.value.enableRateLimit ? form.value.rateLimitDuration || 60 : 0
       // 上游错误处理
       data.disableAutoProtection = !!form.value.disableAutoProtection
+      // 拦截预热请求
+      data.interceptWarmup = !!form.value.interceptWarmup
       // 额度管理字段
       data.dailyQuota = form.value.dailyQuota || 0
       data.quotaResetTime = form.value.quotaResetTime || '00:00'
@@ -6031,6 +6079,8 @@ watch(
         accountType: newAccount.accountType || 'shared',
         subscriptionType: subscriptionType,
         autoStopOnWarning: newAccount.autoStopOnWarning || false,
+        interceptWarmup:
+          newAccount.interceptWarmup === true || newAccount.interceptWarmup === 'true',
         useUnifiedUserAgent: newAccount.useUnifiedUserAgent || false,
         useUnifiedClientId: newAccount.useUnifiedClientId || false,
         unifiedClientId: newAccount.unifiedClientId || '',