oadmin/xinghuoapi
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,952 Commits 1 Branch 0 Tags
921599948b627323d25f2c08877019ab91ce7878
Commit Graph

252 Commits

Author SHA1 Message Date
Wesley Liddick
afbe8bf001 Merge pull request #809 from alfadb/feature/openai-messages 
feat(openai): 添加 /v1/messages 端点和 API 兼容层
 2026-03-06 20:16:06 +08:00
Wesley Liddick
005d0c5f53 Merge pull request #815 from mt21625457/pr/openai-user-group-rate-upstream 
fix(openai): 统一专属倍率计费链路并补齐回归测试
 2026-03-06 17:33:09 +08:00
yangjianbo
a18bbb5f2f fix(openai): 统一专属倍率计费链路并补齐回归测试 
抽取共享的用户分组专属倍率解析器，统一缓存、singleflight 与回退逻辑。\n\n让 OpenAI 独立计费链路复用专属倍率解析，修复 usage 记录与实际扣费未命中用户专属倍率的问题。\n\n补齐 OpenAI 计费与解析器单元测试，并修复全量回归中暴露的 lint 阻塞项。\n\nCo-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-06 16:47:51 +08:00
alfadb
ff1f114989 feat(openai): add /v1/messages endpoint and API compatibility layer 
Add Anthropic Messages API support for OpenAI platform groups, enabling
clients using Claude-style /v1/messages format to access OpenAI accounts
through automatic protocol conversion.

- Add apicompat package with type definitions and bidirectional converters
  (Anthropic ↔ Chat, Chat ↔ Responses, Anthropic ↔ Responses)
- Implement /v1/messages endpoint for OpenAI gateway with streaming support
- Add model mapping UI for OpenAI OAuth accounts (whitelist + mapping modes)
- Support prompt caching fields and codex OAuth transforms
- Fix tool call ID conversion for Responses API (fc_ prefix)
- Ensure function_call_output has non-empty output field

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-06 14:29:22 +08:00
erio
79ae15d5e8 fix: OpenAI passthrough accounts bypass model mapping check 
透传模式账号仅替换认证，应允许所有模型通过。之前调度阶段的
isModelSupportedByAccount 不感知透传模式，导致 model_mapping
中未配置的新模型（如 gpt-5.4）被拒绝返回 503。
 2026-03-06 14:01:47 +08:00
Wesley Liddick
63a8c76946 Merge pull request #798 from touwaeriol/feature/account-load-factor 
feat: add account load_factor for scheduling load calculation
 2026-03-06 09:42:10 +08:00
erio
0d6c1c7790 feat: add independent load_factor field for scheduling load calculation 2026-03-06 05:07:10 +08:00
erio
02dea7b09b refactor: unify post-usage billing logic and fix account quota calculation 
- Extract postUsageBilling() to consolidate billing logic across
  GatewayService.RecordUsage, RecordUsageWithLongContext, and
  OpenAIGatewayService.RecordUsage, eliminating ~120 lines of
  duplicated code
- Fix account quota to use TotalCost × accountRateMultiplier
  (was using raw TotalCost, inconsistent with account cost stats)
- Fix RecordUsageWithLongContext API Key quota only updating in
  balance mode (now updates regardless of billing type)
- Fix WebSocket client disconnect detection on Windows by adding
  "an established connection was aborted" to known disconnect errors
 2026-03-06 00:54:17 +08:00
erio
05527b13db feat: add quota limit for API key accounts 
- Add configurable spending limit (quota_limit) for apikey-type accounts
- Atomic quota accumulation via PostgreSQL JSONB operations on TotalCost
- Scheduler filters out over-quota accounts with outbox-triggered snapshot refresh
- Display quota usage ($used / $limit) in account capacity column
- Add "Reset Quota" action in account menu to reset usage to zero
- Editing account settings preserves quota_used (no accidental reset)
- Covers all 3 billing paths: Anthropic, Gemini, OpenAI RecordUsage

chore: bump version to 0.1.90.4
 2026-03-06 00:35:09 +08:00
shaw
9d70c38504 fix: 修复claude apikey账号请求时未携带beta=true 查询参数的bug 2026-03-05 15:01:04 +08:00
shaw
aeb464f3ca feat: 模型映射应用 /v1/messages/count_tokens端点 2026-03-05 14:49:28 +08:00
Wesley Liddick
43c203333e Merge pull request #733 from DaydreamCoding/fix/group-isolation 
fix(gateway): 分组隔离 — 禁止未分组账号被跨组调度
 2026-03-03 15:10:30 +08:00
shaw
a80ec5d8bb feat: apikey支持5h/1d/7d速率控制 2026-03-03 15:01:10 +08:00
QTom
530a16291c fix(gateway): 分组隔离 — 禁止未分组账号被跨组调度 
当 API Key 无分组时，调度仅从未分组账号池中选取。
修复 isAccountInGroup 在 groupID==nil 时的逻辑，
同时补全 scheduler_snapshot_service 和 gemini_compat_service
中的 SimpleMode 保护，确保分组隔离在所有调度路径生效。

新增 ListSchedulableUngroupedByPlatform/s 方法，
使用 Ent 的 Not(HasAccountGroups()) 谓词实现未分组账号隔离。
新增 17 个单元和端到端隔离测试，覆盖所有分支和边界条件。
 2026-03-03 13:20:58 +08:00
QTom
a9285b8a94 feat(gateway): 双模式用户消息队列 — 串行队列 + 软性限速 
新增 UMQ (User Message Queue) 双模式支持:
- serialize: 账号级分布式串行锁 + RPM 自适应延迟（严格限流）
- throttle: 仅 RPM 自适应前置延迟，不阻塞并发（软性限速）

后端:
- config: 新增 Mode 字段，保留 Enabled 向后兼容
- service: 新增 UserMessageQueueService（Lua 锁/延迟算法/清理 worker）
- repository: 新增 UserMsgQueueCache（Redis Lua acquire/release/force-release）
- handler: 新增 UserMsgQueueHelper（SSE ping + 等待循环 + throttle）
- gateway: 按 mode 分支集成 serialize/throttle 逻辑
- lint: 修复 gofmt rewrite rules、errcheck 类型断言、staticcheck QF1012

前端:
- 三态选择器 UI（关闭/软性限速/串行队列）替代 toggle 开关
- BulkEdit 支持 null 语义（不修改）
- i18n 中英文文案

通过 6 轮专家评审（42 次 review）、golangci-lint、单元测试、集成测试。
 2026-03-03 01:05:11 +08:00
QTom
2491e9b5ad fix: round-3 review fixes for RPM limiting 
- Add sanitizeExtraBaseRPM to BulkUpdate handler (was missing)
- Add WindowCost scheduling checks to legacy non-sticky selection
  paths (4 sites), matching existing sticky + load-aware coverage
- Export ParseExtraInt from service package, remove duplicate
  parseExtraIntForValidation from admin handler
 2026-02-28 20:38:06 +08:00
QTom
e63c83955a fix: address deep code review issues for RPM limiting 
- Move IncrementRPM after Forward success to prevent phantom RPM
  consumption during account switch retries
- Add base_rpm input sanitization (clamp to 0-10000) in Create/Update
- Add WindowCost scheduling checks to legacy path sticky sessions
  (4 check sites + 4 prefetch sites), fixing pre-existing gap
- Clean up rpm_strategy/rpm_sticky_buffer when disabling RPM in
  BulkEditModal (JSONB merge cannot delete keys, use empty values)
- Add json.Number test cases to TestGetBaseRPM/TestGetRPMStickyBuffer
- Document TOCTOU race as accepted soft-limit design trade-off
 2026-02-28 20:38:06 +08:00
QTom
ff9683b0fc fix: move RPM prefetch before routing segment in legacy/mixed paths 
Ensures isAccountSchedulableForRPM calls within the routing segment
hit the prefetch cache instead of querying Redis individually.
 2026-02-28 20:37:37 +08:00
QTom
607237571f fix: address code review issues for RPM limiting feature 
- Use TxPipeline (MULTI/EXEC) instead of Pipeline for atomic INCR+EXPIRE
- Filter negative values in GetBaseRPM(), update test expectation
- Add RPM batch query (GetRPMBatch) to account List API
- Add warn logs for RPM increment failures in gateway handler
- Reset enableRpmLimit on BulkEditAccountModal close
- Use union type 'tiered' | 'sticky_exempt' for rpmStrategy refs
- Add design decision comments for rdb.Time() RTT trade-off
 2026-02-28 20:37:37 +08:00
QTom
f648b8e026 feat: increment RPM counter before request forwarding 2026-02-28 20:37:10 +08:00
QTom
678c3ae132 feat: integrate RPM scheduling checks into account selection flow 2026-02-28 20:37:10 +08:00
QTom
c1c31ed9b2 feat: wire RPMCache into GatewayService and AccountHandler 2026-02-28 20:35:38 +08:00
yangjianbo
bb664d9bbf feat(sync): full code sync from release 2026-02-28 15:01:20 +08:00
erio
a6f9f9f968 feat: replace gemini-3-pro-image with gemini-3.1-flash-image 
- Add migration 060 to update model_mapping for all antigravity accounts
- Remove gemini-3-pro-image and gemini-3-pro-image-preview mappings
- Add gemini-3.1-flash-image and gemini-3.1-flash-image-preview mappings
- Update frontend usage window to show GImage for new model
- Update isImageGenerationModel to support new model
 2026-02-27 09:52:50 +08:00
alfadb
e6969acb50 fix: address review - fix log wording and add response body assertion in test 2026-02-26 23:49:30 +08:00
alfadb
9489531431 fix(gateway): return 404 instead of fake 200 for unsupported count_tokens endpoint 
PR #635 returned HTTP 200 with {"input_tokens": 0} when upstream doesn't
support count_tokens (404). This caused Claude Code CLI to trust the zero
value, believing context uses 0 tokens, so auto-compression never triggers.

Fix: return 404 with proper error body so CLI falls back to its local
tokenizer for accurate estimation. Return nil (not error) to avoid
polluting ops error metrics with expected 404s.

Affected paths:
- Passthrough APIKey accounts: upstream 404 now passed through as 404
- Antigravity accounts: same fix (was also returning fake 200)
 2026-02-26 23:34:53 +08:00
shaw
4ac57b4edf fix: 临时移除fast-mode-2026-02-01避免429问题 2026-02-26 15:44:28 +08:00
alfadb
03bcd94ae5 fix: count_tokens 端点不支持时降级返回空值 (404 only) 
第三方 Anthropic 中转站通常不支持 /v1/messages/count_tokens 端点，
上游返回 404 时降级返回 {input_tokens: 0}，客户端 fallback 到本地估算。

- 仅匹配 404 状态码，语义明确：端点不存在
- 其他错误 (400/429/500) 保留原始处理链和 ops 遥测
- 无需解析错误消息内容，不依赖字符串匹配
- 新增 table-driven 测试覆盖 fallback 和 non-fallback 路径
 2026-02-26 09:28:45 +08:00
erio
644058174e fix(gemini): enable model_mapping filtering for Gemini API Key accounts 
Remove the special case that bypassed model-supported checks for Gemini
API Key accounts, allowing model_mapping to filter requests properly.
Add tests for multiplatform model filtering behavior.
 2026-02-24 18:54:59 +08:00
yangjianbo
2ee6c26676 fix(gateway): 修复粘性会话预取分组错配并优化并发等待热路径 2026-02-22 16:43:33 +08:00
yangjianbo
a89477ddf5 perf(gateway): 优化热点路径并补齐高覆盖测试 2026-02-22 13:31:30 +08:00
yangjianbo
1985be26b2 fix(gateway): 恢复 Anthropic 透传流数据间隔超时保护并补充回归测试 2026-02-21 16:54:44 +08:00
yangjianbo
bde9dbc57a feat(anthropic): 支持 API Key 自动透传并优化透传链路性能 
- 新增 Anthropic API Key 自动透传开关与后端透传分支（仅替换认证）

- 账号编辑页新增自动透传开关，默认关闭

- 优化透传性能：SSE usage 解析 gjson 快路径、减少请求体重复拷贝、优化流式写回与非流式 usage 解析

- 补充单元测试与 benchmark，确保 Claude OAuth 路径不受影响
 2026-02-21 14:16:18 +08:00
yangjianbo
46d9aee6dd feat(proxy,sora): 增强代理质量检测与Sora稳定性并修复审查问题 2026-02-19 21:18:35 +08:00
yangjianbo
440b87094a fix(sora): 增强 Cloudflare 挑战识别并收敛 Sora 请求链路 
- 在 failover 场景透传上游响应头并识别 Cloudflare challenge/cf-ray

- 统一 Sora 任务请求的 UA 与代理使用，sentinel 与业务请求保持一致

- 修复流式错误事件 JSON 转义问题并补充相关单元测试
 2026-02-19 15:09:58 +08:00
yangjianbo
5d9667d27a Merge branch 'main' into test 
# Conflicts:
#	backend/cmd/server/VERSION
#	backend/ent/migrate/schema.go
#	backend/ent/mutation.go
#	backend/ent/runtime/runtime.go
#	backend/ent/usagelog.go
#	backend/ent/usagelog/usagelog.go
#	backend/ent/usagelog/where.go
#	backend/ent/usagelog_create.go
#	backend/ent/usagelog_update.go
#	backend/internal/repository/usage_log_repo.go
#	backend/internal/server/api_contract_test.go
#	backend/internal/server/middleware/cors.go
#	backend/internal/service/gateway_service.go
 2026-02-18 20:16:31 +08:00
yangjianbo
fad04ca995 Merge branch 'main' of https://github.com/mt21625457/aicodex2api 2026-02-18 20:10:32 +08:00
shaw
074bd0dfda fix: 临时移除context-1m-2025-08-07以确保避免sonnet1m触发429 2026-02-18 18:41:30 +08:00
John Doe
3d1f03c286 feat: add Cache TTL Override per account + bump VERSION to 0.1.83 
- Account-level cache TTL override: rewrite Anthropic cache_creation
  token classification (5m↔1h) in streaming/non-streaming responses
- New DB field cache_ttl_overridden in usage_log for billing tracking
- Migration 055_add_cache_ttl_overridden
- Frontend: CacheTTL override toggle in account create/edit modals
- Ent schema regenerated for new usage_log fields

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-17 14:19:24 +03:00
yangjianbo
6577f2ef03 fix(gateway): 避免SSE delta将缓存创建明细重置为0 
- 仅在 delta 中 5m/1h 值大于0时覆盖 usage 明细
- 新增回归测试覆盖 delta 默认 0 不应覆盖 message_start 非零值
- 迁移 054 在删除 legacy 字段前追加一次回填，避免升级实例丢失历史写入

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-16 13:23:12 +08:00
yangjianbo
41d0383fb7 merge(test): 合并 main 并解决前端筛选器冲突 2026-02-15 22:04:06 +08:00
程序猿MT
1cf51b14f7 Merge branch 'Wei-Shaw:main' into main 2026-02-15 20:49:14 +08:00
shaw
a817cafe3d feat: 区分 Anthropic 5m/1h 缓存创建 token 的差异化计费 
Anthropic API 的 cache_creation 对象区分了 ephemeral_5m 和 ephemeral_1h
两种缓存创建 token，1h 单价远高于 5m（如 claude-3-5-haiku: 5m=$1/MTok,
1h=$6/MTok）。此前系统统一按 5m 单价计费，导致计费偏低。

后端：
- pricing_service: 加载 LiteLLM 的 cache_creation_input_token_cost_above_1hr
- billing_service: GetModelPricing 启用分类计费（安全守卫 1h>5m），
  CalculateCost 按 5m/1h 分别计费，无明细时回退到 5m 单价
- gateway_service: parseSSEUsage/handleNonStreamingResponse 用 gjson
  提取嵌套 cache_creation 对象的 ephemeral_5m/1h_input_tokens
- antigravity_gateway_service: extractSSEUsage/extractClaudeUsage 同步提取
- usage_log: 修复 GORM column tag 确保写入正确的数据库列
- 新增迁移 054: 删除 GORM 自动生成的重复列

前端：
- 使用记录 tooltip 展示 5m/1h 缓存创建明细（带彩色 badge 区分）
- 表格单元格缓存写入数值旁显示 1h 标识
 2026-02-14 18:15:35 +08:00
yangjianbo
d04b47b3ca feat(backend): 提交后端审计修复与配套测试改动 2026-02-14 11:23:10 +08:00
yangjianbo
abf5de69fb Merge branch 'main' into test 2026-02-12 23:43:47 +08:00
程序猿MT
174d7c774d Merge branch 'Wei-Shaw:main' into main 2026-02-12 23:12:41 +08:00
yangjianbo
584cfc3db2 chore(logging): 完成后端日志审计与结构化迁移 
- 将高密度服务与处理器日志迁移到新日志系统（LegacyPrintf/结构化日志）
- 增加 stdlog bridge 与兼容测试，保留旧日志捕获能力
- 将 OpenAI 断流告警改为结构化 Warn 并改造对应测试为 sink 捕获
- 补齐后端相关文件 logger 引用并通过全量 go test
 2026-02-12 19:01:09 +08:00
程序猿MT
8da5fac69e Merge branch 'Wei-Shaw:main' into main 2026-02-11 18:39:52 +08:00
SilentFlower
19cca11e00 [UPDATE] 增强 Claude Thinking 模式支持与 Opus 4.6 动态预算适配 
✨ feat(antigravity): 支持 thinking adaptive 类型并适配 Opus 4.6 动态预算
🧪 test(gateway): 增加 thinking 模式解析与签名块过滤的边界用例测试
 2026-02-11 10:31:16 +08:00
Edric Li
378e476e48 fix: 修复 CI 检查失败 
- gofmt: 修复 error_passthrough_service.go 格式问题
- errcheck: 修复 error_passthrough_runtime_test.go 类型断言未检查
- staticcheck: if-else 改为 switch (gateway_service.go)
- test: 修复两个测试用例错误使用 MODEL_CAPACITY_EXHAUSTED 导致走错路径
 2026-02-10 22:08:49 +08:00