fix(relay,store): 审计修复 — 自动恢复可达化 + 类型化错误 + 全路径重连

C1: mark_key_429 设 is_active=FALSE，使 select_best_key 自动恢复
路径真正可达。之前 429 只设 cooldown_until，恢复代码为死代码。

H1+H2: 重试查询补全 debug 日志（RPM/TPM 跳过、解密失败）+ 修复
fallthrough 错误信息（RateLimited 而非 NotFound）。

H3+H4+M3+M4+M5: agentStore.ts 提取 classifyAgentError() 类型化错误
分类，覆盖 502/503/401/403/429/500，统一 createClone/
createFromTemplate/updateClone/deleteClone 错误处理，不再泄露原始
错误详情。所有 catch 块添加 log.error。

H5+H6: auth.ts 提取 triggerReconnect() 共享函数，login/loginWithTotp/
restoreSession 三处统一调用。状态检查改为仅 'disconnected' 时触发，
避免 connecting/reconnecting 状态下并发 connect。

M1: toggle_key_active(true) 同步清除 cooldown_until，防止管理员
激活后 key 仍被 cooldown 过滤不可见。

crates/zclaw-saas/src/relay/key_pool.rs

@@ -201,14 +201,23 @@ pub async fn select_best_key(db: &PgPool, provider_id: &str, enc_key: &[u8; 32])
 
             for (id, key_value, _priority, max_rpm, max_tpm, req_count, token_count) in &retry_rows {
                 if let Some(rpm_limit) = max_rpm {
-                    if *rpm_limit > 0 && req_count.unwrap_or(0) >= *rpm_limit { continue; }
+                    if *rpm_limit > 0 && req_count.unwrap_or(0) >= *rpm_limit {
+                        tracing::debug!("[retry] Reactivated key {} hit RPM limit ({}/{})", id, req_count.unwrap_or(0), rpm_limit);
+                        continue;
+                    }
                 }
                 if let Some(tpm_limit) = max_tpm {
-                    if *tpm_limit > 0 && token_count.unwrap_or(0) >= *tpm_limit { continue; }
+                    if *tpm_limit > 0 && token_count.unwrap_or(0) >= *tpm_limit {
+                        tracing::debug!("[retry] Reactivated key {} hit TPM limit ({}/{})", id, token_count.unwrap_or(0), tpm_limit);
+                        continue;
+                    }
                 }
                 let decrypted_kv = match decrypt_key_value(key_value, enc_key) {
                     Ok(v) => v,
-                    Err(_) => continue,
+                    Err(e) => {
+                        tracing::warn!("[retry] Reactivated key {} decryption failed: {}", id, e);
+                        continue;
+                    }
                 };
                 let selection = KeySelection {
                     key: PoolKey { id: id.clone(), key_value: decrypted_kv, priority: *_priority, max_rpm: *max_rpm, max_tpm: *max_tpm },
@@ -220,6 +229,12 @@ pub async fn select_best_key(db: &PgPool, provider_id: &str, enc_key: &[u8; 32])
                 });
                 return Ok(selection);
             }
+
+            // 所有恢复的 Key 仍被 RPM/TPM 限制或解密失败
+            tracing::warn!("Provider {} 恢复的 Key 全部不可用（RPM/TPM 超限或解密失败）", provider_id);
+            return Err(SaasError::RateLimited(
+                format!("Provider {} 恢复的 Key 仍在限流中，请稍后重试", provider_id)
+            ));
         }
     }
 
@@ -286,14 +301,14 @@ pub async fn mark_key_429(
     let now = chrono::Utc::now();
 
     sqlx::query(
-        "UPDATE provider_keys SET last_429_at = $1, cooldown_until = $2, updated_at = $3
+        "UPDATE provider_keys SET last_429_at = $1, cooldown_until = $2, is_active = FALSE, updated_at = $3
          WHERE id = $4"
     )
     .bind(&now).bind(&cooldown).bind(&now).bind(key_id)
     .execute(db).await?;
 
     tracing::warn!(
-        "Key {} 收到 429，冷却至 {}",
+        "Key {} 收到 429，标记 is_active=FALSE，冷却至 {}",
         key_id,
         cooldown
     );
@@ -372,9 +387,16 @@ pub async fn toggle_key_active(
     active: bool,
 ) -> SaasResult<()> {
     let now = chrono::Utc::now();
-    sqlx::query(
-        "UPDATE provider_keys SET is_active = $1, updated_at = $2 WHERE id = $3"
-    ).bind(active).bind(&now).bind(key_id).execute(db).await?;
+    // When activating, clear cooldown so the key is immediately selectable
+    if active {
+        sqlx::query(
+            "UPDATE provider_keys SET is_active = $1, cooldown_until = NULL, updated_at = $2 WHERE id = $3"
+        ).bind(active).bind(&now).bind(key_id).execute(db).await?;
+    } else {
+        sqlx::query(
+            "UPDATE provider_keys SET is_active = $1, updated_at = $2 WHERE id = $3"
+        ).bind(active).bind(&now).bind(key_id).execute(db).await?;
+    }
     Ok(())
 }
 

desktop/src/store/agentStore.ts

@@ -16,6 +16,29 @@ import { createLogger } from '../lib/logger';
 
 const log = createLogger('AgentStore');
 
+// === Error Classification ===
+
+/**
+ * Extract HTTP status code from typed errors or Tauri invoke errors.
+ * Falls back to substring matching only for untyped error strings.
+ */
+function classifyAgentError(err: unknown, prefix = '操作失败'): string {
+  // Typed error paths — no false positives
+  if (err && typeof err === 'object') {
+    const status = (err as { status?: number }).status;
+    if (typeof status === 'number') {
+      if (status === 502) return `${prefix}：后端服务暂时不可用，请稍后重试。如果问题持续，请检查 Provider Key 是否已激活。`;
+      if (status === 503) return `${prefix}：服务暂不可用，请稍后重试。`;
+      if (status === 401) return `${prefix}：登录已过期，请重新登录后重试。`;
+      if (status === 403) return `${prefix}：权限不足，请检查账户权限。`;
+      if (status === 429) return `${prefix}：请求过于频繁，请稍后重试。`;
+      if (status === 500) return `${prefix}：服务器内部错误，请稍后重试。`;
+    }
+  }
+  // Fallback: generic message, no internal details leaked
+  return `${prefix}：发生未知错误，请稍后重试。`;
+}
+
 // === Types ===
 
 export interface Clone {
@@ -188,15 +211,8 @@ export const useAgentStore = create<AgentStore>((set, get) => ({
       await get().loadClones(); // Refresh the list
       return result?.clone;
     } catch (err: unknown) {
-      const rawMsg = err instanceof Error ? err.message : String(err);
-      let userMsg: string;
-      if (rawMsg.includes('502') || rawMsg.includes('Bad Gateway')) {
-        userMsg = '创建失败：后端服务暂时不可用，请稍后重试。';
-      } else if (rawMsg.includes('401') || rawMsg.includes('Unauthorized')) {
-        userMsg = '创建失败：登录已过期，请重新登录后重试。';
-      } else {
-        userMsg = rawMsg.length > 100 ? rawMsg.substring(0, 100) + '…' : rawMsg;
-      }
+      log.error('[AgentStore] createClone error:', err);
+      const userMsg = classifyAgentError(err, '创建失败');
       set({ error: userMsg, isLoading: false });
       return undefined;
     }
@@ -326,19 +342,8 @@ export const useAgentStore = create<AgentStore>((set, get) => ({
       }
       return undefined;
     } catch (error) {
-      const rawMsg = String(error);
-      // 提供更友好的错误信息，而非暴露原始 HTTP 错误
-      let userMsg: string;
-      if (rawMsg.includes('502') || rawMsg.includes('Bad Gateway')) {
-        userMsg = '创建失败：后端服务暂时不可用，请稍后重试。如果问题持续，请检查 Provider Key 是否已激活。';
-      } else if (rawMsg.includes('503') || rawMsg.includes('Service Unavailable')) {
-        userMsg = '创建失败：服务暂不可用，请稍后重试。';
-      } else if (rawMsg.includes('401') || rawMsg.includes('Unauthorized')) {
-        userMsg = '创建失败：登录已过期，请重新登录后重试。';
-      } else {
-        userMsg = `创建失败：${rawMsg.length > 100 ? rawMsg.substring(0, 100) + '…' : rawMsg}`;
-      }
       log.error('[AgentStore] createFromTemplate error:', error);
+      const userMsg = classifyAgentError(error, '创建失败');
       set({ error: userMsg });
       return undefined;
     } finally {
@@ -359,8 +364,8 @@ export const useAgentStore = create<AgentStore>((set, get) => ({
       await get().loadClones(); // Refresh the list
       return result?.clone;
     } catch (err: unknown) {
-      const errorMessage = err instanceof Error ? err.message : String(err);
-      set({ error: errorMessage, isLoading: false });
+      log.error('[AgentStore] updateClone error:', err);
+      set({ error: classifyAgentError(err, '更新失败'), isLoading: false });
       return undefined;
     }
   },
@@ -377,8 +382,8 @@ export const useAgentStore = create<AgentStore>((set, get) => ({
       await client.deleteClone(id);
       await get().loadClones(); // Refresh the list
     } catch (err: unknown) {
-      const errorMessage = err instanceof Error ? err.message : String(err);
-      set({ error: errorMessage, isLoading: false });
+      log.error('[AgentStore] deleteClone error:', err);
+      set({ error: classifyAgentError(err, '删除失败'), isLoading: false });
     }
   },
 

desktop/src/store/saas/auth.ts

@@ -24,6 +24,23 @@ const log = createLogger('SaaSStore:Auth');
 type SetFn = (partial: Partial<SaaSStore> | ((state: SaaSStore) => Partial<SaaSStore>)) => void;
 type GetFn = () => SaaSStore;
 
+/**
+ * Trigger reconnection after authentication changes (login, TOTP, restore).
+ * Only reconnects when actually disconnected to avoid double-connect race.
+ */
+async function triggerReconnect(context: string) {
+  try {
+    const { useConnectionStore } = await import('../connectionStore');
+    const connState = useConnectionStore.getState();
+    if (connState.connectionState === 'disconnected') {
+      log.info(`[${context}] Reconnecting after auth change`);
+      connState.connect().catch((err: unknown) => log.warn(`[${context}] Reconnect failed:`, err));
+    }
+  } catch (e) {
+    log.warn(`[${context}] Failed to trigger reconnect:`, e);
+  }
+}
+
 export function createAuthSlice(set: SetFn, get: GetFn) {
   // Restore session metadata synchronously (URL + account only).
   const sessionMeta = loadSaaSSessionSync();
@@ -87,17 +104,7 @@ export function createAuthSlice(set: SetFn, get: GetFn) {
           get().pushConfigToSaaS().catch((err: unknown) => log.warn('Failed to push config to SaaS:', err));
         }).catch((err: unknown) => log.warn('Failed to sync config after login:', err));
 
-        // 登录成功后重新建立连接（用新 token 配置 kernel）
-        try {
-          const { useConnectionStore } = await import('../connectionStore');
-          const connState = useConnectionStore.getState();
-          if (connState.connectionState !== 'connected') {
-            log.info('[SaaS Auth] Reconnecting with fresh token after login');
-            connState.connect().catch((err: unknown) => log.warn('[SaaS Auth] Post-login reconnect failed:', err));
-          }
-        } catch (e) {
-          log.warn('[SaaS Auth] Failed to trigger post-login reconnect:', e);
-        }
+        triggerReconnect('SaaS Auth');
 
         initTelemetryCollector(DEVICE_ID);
         startPromptOTASync(DEVICE_ID);
@@ -156,6 +163,7 @@ export function createAuthSlice(set: SetFn, get: GetFn) {
 
         get().registerCurrentDevice().catch((err: unknown) => log.warn('Failed to register device:', err));
         get().fetchAvailableModels().catch((err: unknown) => log.warn('Failed to fetch models:', err));
+        triggerReconnect('SaaS Auth TOTP');
         initTelemetryCollector(DEVICE_ID);
         startPromptOTASync(DEVICE_ID);
       } catch (err: unknown) {
@@ -313,6 +321,7 @@ export function createAuthSlice(set: SetFn, get: GetFn) {
       get().syncConfigFromSaaS().then(() => {
         get().pushConfigToSaaS().catch(() => {});
       }).catch(() => {});
+      triggerReconnect('SaaS Restore');
       initTelemetryCollector(DEVICE_ID);
       startPromptOTASync(DEVICE_ID);
     },