GitLab

单账号 antigravity 分组收到 503 (MODEL_CAPACITY_EXHAUSTED) 时，
原逻辑会设置 ~29s 模型限流标记。由于只有一个账号无法切换，
后续所有新请求在预检查时命中限流 → 几毫秒内直接返回 503，
导致约 30 秒的雪崩窗口。

修复：在 Handler 入口处检查分组是否只有单个 antigravity 账号，
如果是则提前设置 SingleAccountRetry context 标记，让 Service 层
首次 503 就走原地重试逻辑（不设限流标记），避免污染后续请求。

当分组内只有一个可用账号且上游返回 503 (MODEL_CAPACITY_EXHAUSTED) 时，
不再设置模型限流+切换账号（因为切换回来还是同一个账号），而是在 Service 层
原地等待+重试，避免双重等待问题。

主要变更：
- Handler 层：检测单账号 503 场景，清除排除列表并设置 SingleAccountRetry 标记
- Service 层：新增 handleSingleAccountRetryInPlace 原地重试逻辑
- Service 层：预检查跳过单账号模式下的限流检查
- 新增 ctxkey.SingleAccountRetry 上下文标记

ParseGatewayRequest only parsed Anthropic format (system/messages),
ignoring Gemini native format (systemInstruction/contents). This caused
GenerateSessionHash to produce identical hashes for all Gemini sessions.

Add protocol parameter to ParseGatewayRequest to branch between
Anthropic and Gemini parsing. Update GenerateSessionHash message
traversal to extract text from both formats.

Mix SessionContext (ClientIP, UserAgent, APIKeyID) into
GenerateSessionHash 3rd-level fallback to differentiate requests
from different users sending identical content.

Also switch hashContent from SHA256-truncated to XXHash64 for
better performance, and optimize Trie Lua script to match from
longest prefix first.

Upstream accounts now use the standard APIKey type instead of a dedicated
upstream type. GetBaseURL() and new GetGeminiBaseURL() automatically append
/antigravity for Antigravity platform APIKey accounts, eliminating the need
for separate upstream forwarding methods.

- Remove ForwardUpstream, ForwardUpstreamGemini, testUpstreamConnection
- Remove upstream branch guards in Forward/ForwardGemini/TestConnection
- Add migration 052 to convert existing upstream accounts to apikey
- Update frontend CreateAccountModal to create apikey type
- Add unit tests for GetBaseURL and GetGeminiBaseURL

The digest chain fallback is only needed for Gemini endpoints, not
for the Anthropic Messages API path. Remove the handler integration
while keeping the reusable service/repository layer for future use.

The previous fallback (step 3) in GenerateSessionHash hashed system +
all messages together, producing a different hash each round as the
conversation grew ([a] -> [a,b] -> [a,b,c]). This made fallback sticky
sessions ineffective for multi-turn conversations.

Implement per-message Trie digest chain matching (reusing Gemini's Trie
infrastructure) so that the previous round's chain is always a prefix
of the current round's chain, enabling reliable session affinity.

Key changes:
- Upgrade model mapping: Opus 4.5 → Opus 4.6-thinking with precise matching
- Unified rate limiting: scope-level → model-level with Redis snapshot sync
- Load-balanced scheduling by call count with smart retry mechanism
- Force cache billing support
- Model identity injection in prompts with leak prevention
- Thinking mode auto-handling (max_tokens/budget_tokens fix)
- Frontend: whitelist mode toggle, model mapping validation, status indicators
- Gemini session fallback with Redis Trie O(L) matching
- Ops: enhanced concurrency monitoring, account availability, retry logic
- Migration scripts: 049-051 for model mapping unification

支持管理员配置上游错误如何返回给客户端：
- 新增 ErrorPassthroughRule 数据模型和 Ent Schema
- 实现规则的 CRUD API（/admin/error-passthrough-rules）
- 支持按错误码、关键词匹配，支持 any/all 匹配模式
- 支持按平台过滤（anthropic/openai/gemini/antigravity）
- 支持透传或自定义响应状态码和错误消息
- 实现两级缓存（Redis + 本地内存）和多实例同步
- 集成到 gateway_handler 的错误处理流程
- 新增前端管理界面组件
- 新增单元测试覆盖核心匹配逻辑

优化：
- 移除 refreshLocalCache 中的冗余排序（数据库已排序）
- 后端 Validate() 增加匹配条件非空校验

Previously the /v1/usage endpoint aggregated usage stats (today/total
tokens, cost, RPM/TPM) across all API Keys belonging to the user.
This made it impossible to distinguish usage from different API Keys
(e.g. balance vs subscription keys).

Now the usage stats are filtered by the current request's API Key ID,
so each key only sees its own usage data. The balance/remaining fields
are unaffected and still reflect the user-level wallet balance.

Changes:
- Add GetAPIKeyDashboardStats to repository interface and implementation
- Add getPerformanceStatsByAPIKey helper (also fixes TPM to include
  cache_creation_tokens and cache_read_tokens)
- Add GetAPIKeyDashboardStats to UsageService
- Update Usage handler to call GetAPIKeyDashboardStats(apiKey.ID)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

This feature allows API Keys to have their own quota limits and expiration
times, independent of the user's balance.

Backend:
- Add quota, quota_used, expires_at fields to api_key schema
- Implement IsExpired() and IsQuotaExhausted() checks in middleware
- Add ResetQuota and ClearExpiration API endpoints
- Integrate quota billing in gateway handlers (OpenAI, Anthropic, Gemini)
- Include quota/expiration fields in auth cache for performance
- Expiration check returns 403, quota exhausted returns 429

Frontend:
- Add quota and expiration inputs to key create/edit dialog
- Add quick-select buttons for expiration (+7, +30, +90 days)
- Add reset quota confirmation dialog
- Add expires_at column to keys list
- Add i18n translations for new features (en/zh)

Migration:
- Add 045_add_api_key_quota.sql for new columns

为 CC Switch 集成增强 /v1/usage 网关端点，在保持原有 4 字段
(isValid, planName, remaining, unit) 向后兼容的基础上，新增：

- usage 对象：今日/累计的请求数、token 用量、费用，以及 RPM/TPM
- subscription 对象（订阅模式）：日/周/月用量和限额、过期时间
- balance 字段（余额模式）：当前钱包余额

用量数据获取采用 best-effort 策略，失败不影响基础响应。
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

扩展现有的预热请求拦截功能，新增对 SUGGESTION MODE 请求的拦截：
- 检测 messages 最后一条 user 消息是否以 [SUGGESTION MODE: 开头
- 拦截后返回空内容响应，节省 token 消耗
- 重构检测逻辑，合并为单一函数，只解析一次 JSON

- 支持Anthropic OAuth/SetupToken账号的5h窗口费用阈值控制
- 支持账号级别的并发会话数量限制
- 使用Redis缓存窗口费用(30秒TTL)减少数据库压力
- 费用计算基于标准费用(不含账号倍率)

- gateway.max_account_switches: 账户切换最大次数，默认 10
- gateway.max_account_switches_gemini: Gemini 账户切换次数，默认 3
- gateway.antigravity_fallback_cooldown_minutes: Antigravity 429 fallback 限流时间，默认 5 分钟
- Antigravity 429 不再重试，直接标记账户限流

此提交解决了思考块 (thinking blocks) 在转发过程中的兼容性问题。

主要变更：

1. **思考块优化 (Thinking Blocks)**：
   - 在 AntigravityGatewayService 中增加了 sanitizeThinkingBlocks 处理，强制移除思考块中不支持的 cache_control 字段（避免 Anthropic/Vertex AI 报错）
   - 实现历史思考块展平 (Flattening)：将非最后一条消息中的思考块转换为普通文本块，以绕过上游对历史思考块签名的严格校验
   - 增加 cleanCacheControlFromGeminiJSON 作为最后一道防线，确保转换后的 Gemini 请求中不残留非法的 cache_control

2. **GatewayService 缓存控制优化**：
   - 更新缓存控制逻辑，跳过 thinking 块（thinking 块不支持 cache_control 字段）
   - 增加 removeCacheControlFromThinkingBlocks 函数强制清理

关联 Issue: #225

在 nginx 反向代理场景下，使用 ip.GetClientIP() 替代 c.ClientIP()
以正确获取客户端真实 IP 地址

- 在 Messages 方法中调用 SetClaudeCodeClientContext 启用客户端检测
- 修复 RecordUsageInput 未传递 UserAgent 和 IPAddress 的问题

- 添加 LinuxDo 和 Update 配置（从 main 分支缺失）
- 添加 LinuxDoConnectSyntheticEmailDomain 常量
- 添加 IsClaudeCodeClient context key
- 添加 GetLinuxDoConnectOAuthConfig 方法
- 修复 BindStickySession 调用签名
- 修复前端 i18n 重复属性
- 重新生成 wire 依赖注入代码

这个提交准备被合并替换，先保存以防丢失。

* feat(api-key): add IP whitelist/blacklist restriction and usage log IP tracking

- Add IP restriction feature for API keys (whitelist/blacklist with CIDR support)
- Add IP address logging to usage logs (admin-only visibility)
- Remove billing_type column from usage logs UI (redundant)
- Use generic "Access denied" error message for security

Backend:
- New ip package with IP/CIDR validation and matching utilities
- Database migrations for ip_whitelist, ip_blacklist (api_keys) and ip_address (usage_logs)
- Middleware IP restriction check after API key validation
- Input validation for IP/CIDR patterns on create/update

Frontend:
- API key form with enable toggle for IP restriction
- Shield icon indicator in table for keys with IP restriction
- Removed billing_type filter and column from usage views

* fix: update API contract tests for ip_whitelist/ip_blacklist fields

Add ip_whitelist and ip_blacklist fields to expected JSON responses
in API contract tests to match the new API key schema.

- Add IP restriction feature for API keys (whitelist/blacklist with CIDR support)
- Add IP address logging to usage logs (admin-only visibility)
- Remove billing_type column from usage logs UI (redundant)
- Use generic "Access denied" error message for security

Backend:
- New ip package with IP/CIDR validation and matching utilities
- Database migrations for ip_whitelist, ip_blacklist (api_keys) and ip_address (usage_logs)
- Middleware IP restriction check after API key validation
- Input validation for IP/CIDR patterns on create/update

Frontend:
- API key form with enable toggle for IP restriction
- Shield icon indicator in table for keys with IP restriction
- Removed billing_type filter and column from usage views

- 在 gateway_handler 中添加请求监控和错误追踪
- 在 openai_gateway_handler 中集成 ops 指标采集
- 在 gemini_v1beta_handler 中集成 ops 指标采集
- 更新 handler 基类支持 ops 错误日志记录

- Add claude_code_only field to restrict groups to Claude Code clients only
- Add fallback_group_id for non-Claude Code requests to use alternate group
- Implement ClaudeCodeValidator for User-Agent detection
- Add group-level session binding isolation (groupID in Redis key)
- Prevent cross-group sticky session pollution
- Update frontend with Claude Code restriction controls

在使用记录中添加 user_agent 字段，用于记录 API 请求的 User-Agent 头信息，
便于分析客户端类型和调试。

变更内容：
- 新增数据库迁移 028_add_usage_logs_user_agent.sql
- 更新 UsageLog 模型和 Ent Schema 添加 user_agent 字段
- 更新 Repository 层的 Create 和 scanUsageLog 方法
- 更新 RecordUsageInput 结构体支持传入 UserAgent
- 更新 Claude/OpenAI/Gemini 三个网关 Handler 传递 UserAgent

🤖 Generated with [Claude Code](https://claude.com/claude-code

)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

修正测试中的 APIKey 名称引用
移除不可达返回与未使用函数
统一 gofmt 格式并处理 Close 错误

P0 严重问题修复：
- 优化重试机制：降至 5 次 + 指数退避 + 10s 上限，防止请求堆积
- 修复 SSE 错误格式：符合 Anthropic API 规范，添加错误类型标准化

P1 重要问题修复：
- 防止 DOS 攻击：使用 io.LimitReader 限制请求体 10MB，流式解析
- 修复计费数据丢失：改为同步计费，使用独立 context 防止中断

技术细节：
- 新增 retryBackoffDelay() 和 sleepWithContext() 支持 context 取消
- 新增 normalizeAnthropicErrorType() 和 sanitizePublicErrorMessage()
- 新增 parseGatewayRequestStream() 实现流式解析
- 新增 recordUsageSync() 确保计费数据持久化

影响：
- 极端场景重试时间从 30s 降至 ≤10s
- 防止高并发 OOM 攻击
- 消除计费数据丢失风险
- 提升客户端兼容性

- 扩展SSE行长与间隔超时处理，补充keepalive

- 写入失败与超长行时发送错误事件，修复并发释放

- 同步默认配置与示例配置，更新Caddy超时/压缩规则

- 新增OpenAI流式超时与超长行测试

测试: go test ./...