Commit Graph

138 Commits

Author SHA1 Message Date
yangjianbo
3b0910f664 Merge branch 'main' into test-sora 2026-02-10 18:01:17 +08:00
程序猿MT
1dd3158c7e Merge branch 'Wei-Shaw:main' into main 2026-02-10 13:55:51 +08:00
shaw
5dd83d3cf2 fix: 移除特定system以适配新版cc客户端缓存失效的bug 2026-02-10 10:28:34 +08:00
Wesley Liddick
14e1aac9b5 Merge pull request #533 from GuangYiDing/feat/antigravity-single-account-503-retry
feat: Antigravity 单账号分组 503 退避重试机制
2026-02-10 09:59:48 +08:00
yangjianbo
58912d4ac5 perf(backend): 使用 gjson/sjson 优化热路径 JSON 处理
将 API 网关热路径中的 json.Unmarshal+json.Marshal 替换为 gjson 零拷贝查询和 sjson 精准写入:
- unwrapV1InternalResponse 性能提升 22x(4009ns→182ns),内存分配减少 28.5x
- unwrapGeminiResponse、extractGeminiUsage、estimateGeminiCountTokens、ParseGeminiRateLimitResetTime 改为接收 []byte 使用 gjson 提取
- ParseGatewayRequest 的 model/stream/metadata/thinking/max_tokens 改用 gjson 类型安全提取
- Handler 层(sora/openai)改用 gjson 提取字段、sjson 注入/修改字段,移除 map[string]any 中间变量
- Sora Client 响应解析改用 gjson ForEach 遍历,减少内存分配
- 新增约 100 个单元测试用例,所有改动函数覆盖率 >85%

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-10 08:59:30 +08:00
yangjianbo
16131c3d3f Merge branch 'main' of https://github.com/mt21625457/aicodex2api 2026-02-09 20:26:03 +08:00
erio
6892e84ad2 fix: skip rate limiting when custom error codes don't match upstream status
Add ShouldHandleErrorCode guard at the entry of handleGeminiUpstreamError
and AntigravityGatewayService.handleUpstreamError so that accounts with
custom error codes (e.g. [599]) are not rate-limited when the upstream
returns a non-matching status (e.g. 429).
2026-02-09 19:55:05 +08:00
erio
73f455745c feat: ErrorPolicySkipped returns 500 instead of upstream status code
When custom error codes are enabled and the upstream error code is NOT
in the configured list, return HTTP 500 to the client instead of
transparently forwarding the original status code.

Also adds integration test TestCustomErrorCode599 verifying that 429,
500, 503, 401, 403 all return 500 without triggering SetRateLimited
or SetError.
2026-02-09 19:54:54 +08:00
Rose Ding
f6cfab9901 feat: 添加 Antigravity 单账号 503 退避重试机制
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
2026-02-09 14:26:01 +08:00
erio
fc095bf054 refactor: replace scope-level rate limiting with model-level rate limiting
Merge functional changes from develop branch:
- Remove AntigravityQuotaScope system (claude/gemini_text/gemini_image)
- Replace with per-model rate limiting using resolveAntigravityModelKey
- Remove model load statistics (IncrModelCallCount/GetModelLoadBatch)
- Simplify account selection to unified priority→load→LRU algorithm
- Remove SetAntigravityQuotaScopeLimit from AccountRepository
- Clean up scope-related UI indicators and API fields
2026-02-09 08:19:01 +08:00
erio
9236936a55 feat: route AccountTypeUpstream to ForwardUpstream in Forward() entry
Without this routing guard, ForwardUpstream is never called because
Forward() always proceeds with the standard OAuth/cookie flow.
2026-02-09 07:27:10 +08:00
erio
125152460f fix: use upstream retryDelay for rate limit duration instead of fixed default
- In handleSmartRetry, use the actual upstream retryDelay to set model
  rate limit duration instead of always using the 30s default
- Return info.RetryDelay from shouldTriggerAntigravitySmartRetry when
  shouldRateLimitModel=true, so callers know the actual delay
- Extract getDefaultRateLimitDuration() and resolveResetTime() helpers
  to reduce duplication in handleUpstreamError 429 handling
- Improve debug logging with upstream_retry_delay and response body
2026-02-09 07:11:29 +08:00
erio
6d90fb0bc3 feat: detect client disconnect during streaming and continue draining upstream for billing 2026-02-09 07:06:26 +08:00
erio
2f1182e8a9 feat: unified error policy for Antigravity + enable custom error codes for Gemini accounts 2026-02-09 06:54:42 +08:00
Wesley Liddick
2185a3b674 Merge pull request #517 from touwaeriol/fix/upstream-baseurl
refactor(upstream): replace upstream account type with apikey + auto-append base_url
2026-02-08 14:03:12 +08:00
Wesley Liddick
9e3c306a5b Merge pull request #513 from touwaeriol/pr/antigravity-full-v2
feat(antigravity): comprehensive enhancements — rate limiting, scheduling & smart retry
2026-02-08 14:01:17 +08:00
erio
69816f8691 fix: remove unused upstreamHopByHopHeaders variable to pass golangci-lint 2026-02-08 13:30:39 +08:00
erio
fb58560d15 refactor(upstream): replace upstream account type with apikey, auto-append /antigravity
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
2026-02-08 13:06:25 +08:00
erio
6ab77f5eb5 fix(upstream): passthrough response body directly instead of parsing SSE
ForwardUpstream/ForwardUpstreamGemini should pipe the upstream response
directly to the client (headers + body), not parse it as SSE stream.
2026-02-08 08:49:43 +08:00
erio
4f57d7f761 fix: add nil guard for gin.Context in header passthrough to satisfy staticcheck SA5011 2026-02-08 08:36:35 +08:00
erio
1563bd3dda feat(upstream): passthrough all client headers instead of manual header setting
Replace manual header setting (Content-Type, anthropic-version, anthropic-beta)
with full client header passthrough in ForwardUpstream/ForwardUpstreamGemini.
Only authentication headers (Authorization, x-api-key) are overridden with
upstream account credentials. Hop-by-hop headers are excluded.

Add unit tests covering header passthrough, auth override, and hop-by-hop filtering.
2026-02-08 08:33:09 +08:00
erio
77b66653ed fix(gateway): restore upstream account forwarding with dedicated methods
v0.1.74 merged upstream accounts into the OAuth path, causing requests
to hit the wrong protocol and endpoint. Add three upstream-specific
methods (testUpstreamConnection, ForwardUpstream, ForwardUpstreamGemini)
that use base_url + apiKey auth and passthrough the original body, while
reusing the existing response handling and error/retry logic.
2026-02-08 01:21:02 +08:00
yangjianbo
836ba14b70 fix: 修复函数签名变更后的调用参数不匹配
- handleUpstreamError 补齐新增的三个参数 (0, "", false)
- handleStreamingResponse 移除已删除的 nil 参数

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-07 20:05:29 +08:00
yangjianbo
a14dfb769a Merge branch 'dev-release' 2026-02-07 19:58:00 +08:00
yangjianbo
2588fa6a8f fix(audit): 第二批审计修复 — P0 生产 Bug、安全加固、性能优化、缓存一致性、代码质量
基于 backend-code-audit 审计报告,修复剩余 P0/P1/P2 共 34 项问题:

P0 生产 Bug:
- 修复 time.Since(time.Now()) 计时逻辑错误 (P0-03)
- generateRandomID 改用 crypto/rand 替代固定索引 (P0-04)
- IncrementQuotaUsed 重写为 Ent 原子操作消除 TOCTOU 竞态 (P0-05)

安全加固:
- gateway/openai handler 错误响应替换为泛化消息,防止内部信息泄露 (P1-14)
- usage_log_repo dateFormat 参数改用白名单映射,防止 SQL 注入 (P1-16)
- 默认配置安全加固:sslmode=prefer、response_headers=true、mode=release (P1-18/19, P2-15)

性能优化:
- gateway handler 循环内 defer 替换为显式 releaseWait 闭包 (P1-02)
- group_repo/promo_code_repo Count 前 Clone 查询避免状态污染 (P1-03)
- usage_log_repo 四个查询添加 LIMIT 10000 防止 OOM (P1-07)
- GetBatchUsageStats 添加时间范围参数,默认最近 30 天 (P1-10)
- ip.go CIDR 预编译为包级变量 (P1-11)
- BatchUpdateCredentials 重构为先验证后更新 (P1-13)

缓存一致性:
- billing_cache 添加 jitteredTTL 防止缓存雪崩 (P2-10)
- DeductUserBalance/UpdateSubscriptionUsage 错误传播修复 (P2-12)
- UserService.UpdateBalance 成功后异步失效 billingCache (P2-13)

代码质量:
- search 截断改为按 rune 处理,支持多字节字符 (P2-01)
- TLS Handshake 改为 HandshakeContext 支持 context 取消 (P2-07)
- CORS 预检添加 Access-Control-Max-Age: 86400 (P2-16)

测试覆盖:
- 新增 user_service_test.go(UpdateBalance 缓存失效 6 个用例)
- 新增 batch_update_credentials_test.go(fail-fast + 类型验证 7 个用例)
- 新增 response_transformer_test.go、ip_test.go、usage_log_repo_unit_test.go、search_truncate_test.go
- 集成测试:IncrementQuotaUsed 并发测试、billing_cache 错误传播测试
- config_test.go 补充 server.mode/sslmode 默认值断言

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-07 19:46:42 +08:00
erio
3077fd279d feat: smart retry max 1 attempt + clear sticky session on failure
- Change antigravitySmartRetryMaxAttempts from 3 to 1 to prevent
  repeated rate limiting and long waits
- Clear sticky session binding (DeleteSessionAccountID) after smart
  retry exhaustion, so subsequent requests don't hit the same
  rate-limited account
- Add flow diagrams to Forward/ForwardGemini doc comments
- Add comprehensive unit tests covering:
  - Sticky session cleared on retry failure (429, 503, network error)
  - Sticky session NOT cleared on retry success
  - Sticky session NOT cleared for non-sticky requests (empty hash)
  - Sticky session NOT cleared on long delay path (handled by handler)
  - Nil cache safety (no panic)
  - MaxAttempts constant verification
  - End-to-end retryLoop → switchError propagation with session clear
2026-02-07 19:30:58 +08:00
shaw
1439eb39a9 fix(gateway): harden digest logging and align antigravity ops
- avoid panic by using safe UUID prefix truncation in Gemini digest fallback logs\n- remove unconditional Antigravity 429 full-body debug logs and honor log truncation config\n- align Antigravity quick preset mappings to opus 4.6-thinking targets only\n- restore scope rate-limit aggregation/output in ops availability stats
2026-02-07 17:12:15 +08:00
erio
e1a68497d6 refactor: simplify sticky session rate limit handling — switch immediately on any rate limit
Remove threshold-based waiting in both sticky session and antigravity
pre-check paths. When a model is rate-limited, immediately clear the
sticky session and switch accounts instead of waiting for short durations.
2026-02-07 17:06:49 +08:00
erio
2656320d04 fix(antigravity): fetch default mapping from API and sync Redis on rate limit
1. Frontend: replace hardcoded antigravityDefaultMappings with async
   fetch from GET /admin/accounts/antigravity/default-model-mapping,
   eliminating the duplicate data source that caused frontend/backend
   mapping inconsistency.

2. Backend: convert handleSmartRetry and antigravityRetryLoop from
   standalone functions to AntigravityGatewayService methods, enabling
   Redis cache sync (updateAccountModelRateLimitInCache) after both
   rate-limit write paths — long-delay branch and retry-exhausted branch.
2026-02-07 15:59:27 +08:00
erio
de0927289e fix(antigravity): support upstream accounts and custom model_mapping in scheduling
- GetAccessToken: add upstream branch to read api_key from credentials
- shouldTriggerAntigravitySmartRetry: relax check from IsOAuth to Platform-based
- isModelSupportedByAccount/WithContext: replace IsAntigravityModelSupported
  whitelist with mapAntigravityModel for unified scheduling/forwarding logic
- mapAntigravityModel: fix edge case where wildcard target equals request model
- Update tests for new behavior and add custom model_mapping test cases
2026-02-07 14:32:08 +08:00
erio
5e98445b22 feat(antigravity): comprehensive enhancements - model mapping, rate limiting, scheduling & ops
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
2026-02-07 12:31:10 +08:00
erio
8917afab2a fix(antigravity): reduce 429 fallback cooldown from 5min to 30s
The default fallback cooldown when rate limit reset time cannot be
parsed was 5 minutes, which is too aggressive and causes accounts
to be unnecessarily locked out. Reduce to 30 seconds for faster
recovery. Config override still works (unit remains minutes).
2026-02-07 11:54:00 +08:00
shaw
5299f3dcf6 fix: ix: antigravity 添加 aude-opus-4-6-thinking 模型支持 2026-02-07 10:38:10 +08:00
yangjianbo
d71537d431 perf(service): SSE Scanner buffer 改用 sync.Pool 复用,减少高并发 GC 压力
将流式响应中 bufio.Scanner 的 64KB buffer 从每次 make 分配改为
sync.Pool 复用,统一切片表达式为 [:0]、变量命名为 scanBuf,
并补充对应的单元测试。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-06 22:55:12 +08:00
shaw
39e05a2dad feat: 新增全局错误透传规则功能
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
2026-02-05 21:52:54 +08:00
Wesley Liddick
804b6f2282 Merge pull request #468 from s-Joshua-s/fix/thinking-block-modification-error
fix(api): 修复 thinking 块被意外修改导致的 400 错误
2026-02-03 22:21:06 +08:00
song
7cb5444dbb fix: update tests for group fallback 2026-02-03 16:48:52 +08:00
song
3bede6e65f merge upstream main 2026-02-03 16:21:58 +08:00
JIA-ss
ad90bb4645 fix(api): 修复 thinking 块被意外修改导致的 400 错误
问题描述:
使用扩展思考功能时,偶现以下错误:
"thinking or redacted_thinking blocks in the latest assistant message cannot be modified"

根因分析:
当代理服务修改请求体中的某些字段时(如 metadata.user_id、model),
使用 map[string]any 解析整个 JSON 后重新序列化,导致:
1. 字段顺序改变(Go map 序列化按字母排序)
2. 数字格式变化(如 1.0 → 1)
3. Unicode 转义变化

Claude API 对 thinking 块进行字节级验证,任何变化都会触发错误。

修复内容:
1. identity_service.go - RewriteUserID/RewriteUserIDWithMasking
   使用 json.RawMessage 保留其他字段的原始字节

2. gateway_service.go - replaceModelInBody
   使用 json.RawMessage 保留其他字段的原始字节

3. gateway_service.go - normalizeClaudeOAuthRequestBody
   保留 messages 的原始字节,跳过包含 thinking 块的消息修改

4. gateway_service.go - isThinkingBlockSignatureError
   添加 "cannot be modified" 错误检测,触发自动重试

5. antigravity_gateway_service.go - isSignatureRelatedError
   添加 "cannot be modified" 错误检测

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-03 16:15:37 +08:00
song
2220fd18ca merge upstream main 2026-02-03 15:36:17 +08:00
Wesley Liddick
6e54eda41f Merge pull request #464 from touwaeriol/pr/antigravity-scope-ratelimit
feat(antigravity): 支持按配额域(scope)级别限流
2026-02-03 15:02:15 +08:00
liuxiongfeng
56949a58bc feat(antigravity): 默认开启按配额域限流,避免整个账号被锁定
将 GATEWAY_ANTIGRAVITY_429_SCOPE_LIMIT 的默认值从关闭改为开启。
当 Gemini 模型触发 429 限流时,只会限制对应的配额域(gemini_text),
而 Claude 和 gemini_image 仍可继续使用,提高账号利用率。
2026-02-03 14:25:30 +08:00
liuxiongfeng
7d256879c5 feat(antigravity): map all gemini-2.5 to gemini-3 series
Antigravity 上游不再支持 gemini-2.5 系列,统一映射到 gemini-3:
- gemini-2.5-flash → gemini-3-flash
- gemini-2.5-flash-lite → gemini-3-flash
- gemini-2.5-flash-thinking → gemini-3-flash
- gemini-2.5-flash-image → gemini-3-pro-image
- gemini-2.5-pro → gemini-3-pro-high
- gemini-2.5-pro-preview → gemini-3-pro-high
- gemini-2.5-pro-exp → gemini-3-pro-high
2026-02-03 14:23:47 +08:00
liuxiongfeng
beb63cb152 feat(antigravity): map gemini-2.5-pro to gemini-3-pro-high
Add prefix mapping rules for gemini-2.5-pro variants:
- gemini-2.5-pro -> gemini-3-pro-high
- gemini-2.5-pro-preview -> gemini-3-pro-high
- gemini-2.5-pro-exp -> gemini-3-pro-high
2026-02-03 14:23:47 +08:00
song
3ecadf4aad chore: apply stashed changes 2026-02-02 22:20:08 +08:00
song
0170d19fa7 merge upstream main 2026-02-02 22:13:50 +08:00
song
7ade9baa15 fix(gateway): 过滤 Gemini 请求中 parts 为空的消息
Gemini API 不接受 contents 数组中 parts 为空的消息,会返回 400 INVALID_ARGUMENT 错误。
添加 filterEmptyPartsFromGeminiRequest 函数在转发前过滤这类消息。

影响范围:ForwardGemini (antigravity) 和 ForwardNative (gemini)
2026-01-29 21:09:33 +08:00
song
5b787334c8 antigravity: 转发优先 daily 2026-01-28 11:17:39 +08:00
song
f761afb1ef antigravity: 区分切换后重试次数 2026-01-28 00:01:03 +08:00
song
877c17251d feat(group): 添加 MCP XML 注入开关
- Group 新增 mcp_xml_inject 字段,控制 Antigravity 平台的 MCP XML 协议注入
- 默认启用,可在分组设置中关闭
- 修复 GetByKeyForAuth 遗漏查询 mcp_xml_inject 字段导致认证缓存值始终为 false 的问题
2026-01-27 13:09:56 +08:00