Commit Graph

185 Commits

Author SHA1 Message Date
yangjianbo
fd43be8d0b merge: 合并 main 分支到 test,解决 config 和 modelWhitelist 冲突
- config.go: 保留 Sora 配置,合入 SubscriptionCache 配置
- useModelWhitelist.ts: 同时保留 soraModels 和 antigravityModels

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-07 20:18:07 +08:00
yangjianbo
a14dfb769a Merge branch 'dev-release' 2026-02-07 19:58:00 +08:00
yangjianbo
8226a4ce4d perf(service): 优化 model 替换函数,用 gjson/sjson 替代全量 JSON 序列化
SSE 热路径中 replaceModelInSSELine 和 replaceModelInResponseBody 原来
使用 json.Unmarshal/Marshal 对每个事件做全量反序列化再序列化,现改为
gjson.Get/sjson.Set 精确字段操作,消除 O(n) 中间 map 分配,保持 JSON
字段顺序不变。涉及 OpenAIGatewayService 和 GatewayService 两个服务。

新增 23 个单元测试覆盖:顶层/嵌套 model 替换、不匹配跳过、空行/[DONE]/
非法 JSON 等边界情况。

Fixes: P1-08

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-07 17:09:55 +08:00
erio
b4f6c4f9d5 style: fix gofmt formatting in gateway_service.go
Remove extra blank line that caused golangci-lint gofmt check to fail.
2026-02-07 14:51:20 +08:00
erio
14c6c9321a refactor: remove unused IsAntigravityModelSupported function and its tests 2026-02-07 14:42:28 +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
edb0937024 fix: restore non-failover error passthrough from 7b156489 2026-02-07 14:24:55 +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
shaw
7b1564898b fix: make error passthrough effective for non-failover upstream errors 2026-02-07 10:25:56 +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
d182ef0391 fix(gateway): 移除 PR #316 引入的工具名转换逻辑
移除响应阶段的工具名/schema/description 转换逻辑,修复第三方工具调用时
工具名被错误转换的问题(如 Task → task)。

移除内容:
- 工具名相关正则变量(toolPrefixRe, toolNameBoundaryRe 等)
- openCodeToolOverrides 和 claudeToolNameOverrides 映射表
- 工具名转换函数(normalizeToolNameForClaude, normalizeToolNameForOpenCode 等)
- 响应体工具名替换函数(replaceToolNamesInText, replaceToolNamesInResponseBody 等)
- 参数名转换函数(normalizeParamNameForOpenCode, rewriteParamKeysInValue)
- 工具描述清理函数(sanitizeToolDescription)
- 输入 schema 转换函数(normalizeToolInputSchema)
- 模型 ID 正则替换函数(replaceModelIDInText)

保留内容:
- 系统提示词清理(sanitizeSystemText)
- Claude Code 指纹 headers 处理
- 模型 ID 映射(通过 JSON 对象操作)
2026-02-06 16:09:58 +08:00
yangjianbo
f33a950103 fix(兼容): 将 Kimi cached_tokens 映射到 Claude 标准 cache_read_input_tokens
Kimi 等 Claude 兼容 API 返回缓存信息使用 OpenAI 风格的 cached_tokens 字段,
而非 Claude 标准的 cache_read_input_tokens,导致客户端收不到缓存命中信息且
内部计费缓存折扣为 0。

新增 reconcileCachedTokens 辅助函数,在 cache_read_input_tokens == 0 且
cached_tokens > 0 时自动填充,覆盖流式(message_start/message_delta)和
非流式两种响应路径。对 Claude 原生上游无影响。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-06 09:27:42 +08:00
yangjianbo
000a943cce Merge branch 'main' into test 2026-02-06 08:43:42 +08:00
yangjianbo
c6a456c7c7 fix(兼容): 将 Kimi cached_tokens 映射到 Claude 标准 cache_read_input_tokens
Kimi 等 Claude 兼容 API 返回缓存信息使用 OpenAI 风格的 cached_tokens 字段,
而非 Claude 标准的 cache_read_input_tokens,导致客户端收不到缓存命中信息且
内部计费缓存折扣为 0。

新增 reconcileCachedTokens 辅助函数,在 cache_read_input_tokens == 0 且
cached_tokens > 0 时自动填充,覆盖流式(message_start/message_delta)和
非流式两种响应路径。对 Claude 原生上游无影响。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-06 08:42:55 +08:00
yangjianbo
d8e405511e Merge branch 'main' of https://github.com/mt21625457/aicodex2api 2026-02-06 06:56:23 +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
shaw
2b192f7dca feat: 支持用户专属分组倍率配置 2026-02-05 16:05:42 +08:00
shaw
05af95dade fix(gateway): 修复工具名转换破坏 Anthropic 特殊工具的问题
未知工具名不再进行 PascalCase/snake_case 转换,保持原样透传。
修复 text_editor_20250728 等 Anthropic 特殊工具被错误转换的问题。
2026-02-05 09:53:20 +08:00
yangjianbo
de7ff902de Merge branch 'main' into test 2026-02-04 20:35:09 +08:00
shaw
8f39754812 fix(gateway): 修复模型前缀映射逻辑错误
问题:normalizeClaudeModelForAnthropic 函数错误地将长模型ID截断为短ID,
导致 APIKey 账号的模型名被错误修改。

修复:
- 删除错误的 normalizeClaudeModelForAnthropic 函数和 anthropicPrefixMappings 变量
- 直接使用 claude.NormalizeModelID(正确的短ID->长ID扩展)
- APIKey 账号无显式映射时透传原始模型名
2026-02-04 17:50:05 +08:00
yangjianbo
377bffe281 Merge branch 'main' into test 2026-02-03 22:48:04 +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
Wesley Liddick
4cce21b125 Merge branch 'main' into main 2026-02-03 21:43:41 +08:00
bayma888
3fed478e4d fix(lint): format gateway_service.go with gofmt 2026-02-03 20:55:17 +08:00
bayma888
6146be1474 feat(api-key): add independent quota and expiration support
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
2026-02-03 19:49:31 +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
a09478f374 Merge pull request #316 from cyhhao/fix/claude-oauth-compat
fix(网关): 完善 Claude OAuth/Claude Code 兼容
2026-02-03 14:26:19 +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
liuxiongfeng
45e1429ae8 feat(billing): 添加 Gemini 200K 长上下文双倍计费功能
- 新增 CalculateCostWithLongContext 方法支持阈值双倍计费
- 新增 RecordUsageWithLongContext 方法专用于 Gemini 计费
- Gemini 超过 200K token 的部分按 2 倍费率计算
- 其他平台(Claude/OpenAI)完全不受影响
2026-02-02 21:47:02 +08:00
liuxiongfeng
bbc7b4aeed feat(gateway): Gemini API Key 账户跳过模型映射检查,直接透传
Gemini API Key 账户通常代理上游服务,模型支持由上游判断,
本地不需要预先配置模型映射。
2026-02-02 13:40:29 +08:00
yangjianbo
78d0ca3775 fix(sora): 修复流式重写与计费问题 2026-01-31 21:46:28 +08:00
yangjianbo
618a614cbf feat(Sora): 完成Sora网关接入与媒体能力
新增 Sora 网关路由、账号调度与同步服务\n补充媒体代理与签名 URL、模型列表动态拉取\n完善计费配置、前端支持与相关测试
2026-01-31 20:22:22 +08:00
cyhhao
adb77af1d9 fix: satisfy golangci-lint (nil checks, remove unused helpers) 2026-01-31 02:07:57 +08:00
cyhhao
3a34746668 refactor: stop rewriting tool descriptions; keep only system sentence rewrite 2026-01-31 02:01:51 +08:00
cyhhao
fe17058700 refactor: limit OpenCode keyword replacement to tool descriptions 2026-01-31 01:40:38 +08:00
cyhhao
fa454b1b99 fix: align Claude Code system banner with opencode latest 2026-01-29 15:37:07 +08:00
cyhhao
8375094c69 fix(oauth): match Claude CLI accept header and beta set 2026-01-29 15:31:29 +08:00
cyhhao
91079d3f15 chore(debug): emit Claude mimic fingerprint on credential-scope error 2026-01-29 15:17:46 +08:00
cyhhao
63412a9fcc chore(debug): log Claude mimic fingerprint 2026-01-29 03:13:14 +08:00
cyhhao
d98648f03b fix: rewrite OpenCode identity sentence to Claude Code 2026-01-29 03:03:40 +08:00
cyhhao
4d40fb6b60 fix(oauth): merge anthropic-beta and force Claude Code headers in mimic mode 2026-01-29 02:36:28 +08:00
cyhhao
be3b788b8f fix: also prefix next system block with Claude Code banner 2026-01-29 02:03:54 +08:00
cyhhao
723e54013a fix(oauth): mimic Claude Code metadata and beta headers 2026-01-29 01:49:51 +08:00
cyhhao
4d566f68b6 chore: gofmt 2026-01-29 01:34:58 +08:00
cyhhao
31f817d189 fix: add newline separation for Claude Code system prompt 2026-01-29 01:28:43 +08:00
cyhhao
59231668c5 Merge branch 'main' of github.com:Wei-Shaw/sub2api 2026-01-29 01:16:36 +08:00
shaw
cadca752c4 修复SSE流式响应中usage数据被覆盖的问题 2026-01-28 18:36:21 +08:00
cyhhao
ffe43f6098 Merge branch 'main' of github.com:Wei-Shaw/sub2api 2026-01-27 11:09:11 +08:00