zfc/sub2api
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
3,565 Commits 3 Branches 0 Tags
Commit Graph

161 Commits

Author SHA1 Message Date
win
158785bfc9 chore: merge upstream v0.1.127 — keep omniroute customizations 
Upstream highlights:
- v0.1.127 release (150 commits): channel-monitor 协议管理、OpenAI
  Responses 路由配置、模型定价 LiteLLM 默认、payment 强制扫码、
  钉钉 OAuth、用户用量按平台拆分、Ops 错误分类 SLA 调整、
  Anthropic passthrough keepalive、Gemini chat completions 路由 ...
- 91da8159 feat(risk-control): 内容审计新增关键词拦截
- 3d22dd34 feat: gemini-3.5-flash 模型支持

Conflicts resolved:
- Dockerfile: keep pnpm pin to 9.15.9 (upstream pinned generic v9 floating).
- wire_gen.go: combine upstream NewSettingHandler(+userAttributeService)
  with local NewOpsHandler(opsService, requestEventBus, opsLogBroadcaster).
  Verified by re-running wire generate.
- scheduler_cache.go: keep both upstream openai_responses_{mode,supported}
  keys and local model_rate_limits key in filterSchedulerExtra().
- gateway_service.go: keep local context-compression block; drop now-dead
  setOpsUpstreamRequestBody call (upstream removed ops retry replay).
- docker-compose.yml: keep local windsurf-ls service profile and named
  volumes; keep local healthcheck start_period values.

Test mock signatures bumped to match current constructors:
- gateway_models_test.go: add nil for RPMTokenBucketService.
- account_handler_available_models_test.go: add nil for windsurfChatService.
 2026-05-20 12:39:40 +08:00
name
2eb622f2f6 Remove ops retry replay storage 2026-05-19 19:37:41 +08:00
wucm667
6381f9e37d fix(openai): 识别上游静默拒绝并触发 failover 2026-05-19 15:48:36 +08:00
Wesley Liddick
8a4ee578cb
Merge pull request #2451 from wucm667/codex/issue-2237-gemini-chat-completions 
fix(gateway): 修复 Gemini 组 Chat Completions 路由
 2026-05-19 14:47:52 +08:00
benjamin
6acb46c113 fix: 标记通用网关本地调度容量错误 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-05-18 16:52:32 +08:00
wucm667
2ec1d331e0 fix(gateway): return Gemini models for Gemini groups 2026-05-15 11:33:26 +08:00
win
7347dfffc1 chore: merge upstream v0.1.124-125, keep Windsurf/Antigravity customizations 
Upstream changes:
- feat: 邮箱 + GitHub + Google OAuth 快捷登录
- feat: Codex image bridge 开关
- feat: 内容审核 (content moderation) — 新增 contentModerationService/Handler
- feat: redeem code 返利、批量并发 API、markdown 页面渲染
- feat: 登录注册条款确认
- fix(security): pages API 加 JWT + 可见性校验
- fix: 修复 markdown 页面图片路径
- fix(gateway): 不再默认注入 redact thinking beta
- fix: 稳定 anthropic passthrough 超时错误
- chore: VERSION 升到 0.1.125 + golang:1.26.3-alpine

Conflict resolutions:
- Dockerfile/backend/Dockerfile: 取 upstream golang:1.26.3-alpine
- backend/go.mod: 取 upstream term v0.42.0，保留定制 protobuf v1.36.10
- frontend/src/api/admin/index.ts: 并集 (windsurf + riskControl)
- backend/cmd/server/wire_gen.go: 接 upstream contentModeration*，保留 windsurfHandler/windsurfGatewayService/billingCacheService/requestEventBus；并通过 wire 重生成
- frontend/src/views/admin/AccountsView.vue: 采用 upstream 双层布局 + OpenAI Meta，保留 is_enterprise prop 和 Windsurf tier badge

Note:
- WIP commit (de048fad) preserved Windsurf tier access service / NLU
  extractor / ops log stream / Google OAuth login modal et al before merge.
- 3 pre-existing go vet issues in test files (NewOpsHandler, RegisterGatewayRoutes,
  DefaultCLIProductVersion) are unrelated to this merge — leftover from local
  customization refactors; production code (go build ./...) passes.
 2026-05-09 01:42:39 +08:00
shaw
fff4a300c6 feat(risk-control): add content moderation audit 2026-05-07 09:14:47 +08:00
win
c5eb305f7f chore: merge upstream v0.1.119-121, keep Windsurf/Antigravity customizations 
Upstream changes merged:
- fix(scheduler): resolve SetSnapshot race conditions with Lua CAS script
- fix: improve sticky session scheduling (debug logs + layer 1.5 checks)
- feat: Anthropic cache TTL injection toggle
- fix(gateway): stream EOF failover + sanitize stream errors
- feat(httputil): zstd/gzip/deflate request decompression + bomb guard
- feat(openai): OpenAI Fast/Flex Policy (HTTP + WebSocket + Admin)
- feat(vertex): Vertex Service Account support
- feat: account bulk edit scope and compact settings
- feat(affiliate): rebate freeze migration
- fix(openai): various fixes (passthrough fields, compact payload, etc.)

Conflict resolutions:
- domain/constants.go: keep both AccountTypeWindsurfSession + AccountTypeServiceAccount
- scheduler_cache_unit_test.go: keep both test functions
- gateway_service.go: remove dead code (claudeCodeUserAgentRe, isClaudeCodeRequest)
- wire_gen.go: keep Windsurf service chain + add upstream claudeTokenProvider param
- frontend/src/types/index.ts: keep windsurf + service_account types
- frontend CreateAccountModal.vue: keep Windsurf login + Vertex service_account blocks
- frontend PlatformTypeBadge.vue: keep both Session + Vertex cases
- account_test_service.go: fix createTestPayload call to pass empty prompt arg
 2026-05-02 16:52:21 +08:00
shaw
733627cf9d fix: improve sticky session scheduling 2026-04-30 11:38:11 +08:00
win
fdd2d08a4d feat: merge feat/omniroute-ideas — P2C scheduler, quota scoring, tier fallback 2026-04-29 15:42:37 +08:00
win
0a3666ef24 x
Some checks failed
Security Scan / backend-security (push) Failing after 1m31s
Details
Security Scan / frontend-security (push) Failing after 7s
Details
CI / test (push) Failing after 6s
Details
CI / frontend (push) Failing after 4s
Details
CI / golangci-lint (push) Failing after 4s
Details
CI / windsurf-platform (macos-latest) (push) Has been cancelled
Details
CI / windsurf-platform (windows-latest) (push) Has been cancelled
Details
2026-04-29 10:32:36 +08:00
win
d1e2d39c26 feat(viewer): add real-time request stream WebSocket endpoint 
Adds GET /api/v1/admin/ops/ws/requests — a fan-out WebSocket that pushes
per-request metadata (method, path, model, account_id, status, latency_ms)
to all connected admin clients the moment each gateway dispatch completes.

- service/request_event_bus.go: lock-free pub/sub with non-blocking drop
  when per-subscriber buffer (64 slots) is full; nil-safe Publish
- service/request_event_bus_test.go: 6 tests (basic, fanout, drop, nil, close)
- GatewayHandler: records reqStartTime at entry; defer emits RequestEvent on
  every return; sets status success/error/rate_limited in both Gemini and
  Anthropic dispatch paths
- OpsHandler: accepts *RequestEventBus; wires it to RequestStreamWSHandler
- ops_ws_requests_handler.go: subscribes to bus, pushes JSON per event,
  reuses existing upgrader/conn-limit/ping-pong infrastructure
- Route: ws.GET("/requests", ...) alongside existing /ws/qps
- wire_gen.go: requestEventBus shared between OpsHandler and GatewayHandler
 2026-04-29 01:48:15 +08:00
win
95814974de feat(rpm): add token bucket smoothing for RPM rate limiting 
- New RPMTokenBucketService: per-account continuous-refill token buckets
  (rate = rpm/60 tokens/sec, capacity = rpm). No new dependencies.
- GatewayService.AcquireRPMToken() delegates to the bucket service.
- Gateway handler inserts RPM token wait BEFORE wrapReleaseOnDone in both
  Gemini and Anthropic dispatch paths; timeout returns 429 and releases slot.
- Config: gateway.rpm_smoothing.enabled (default false) + max_wait_ms (default 5000).
- 7 unit tests covering: immediate acquire, zero RPM, timeout, wait+refill,
  context cancel, account isolation, bucket reset on RPM change.
 2026-04-29 01:22:54 +08:00
win
2a9c5da91a fix(antigravity): mixed tools (web_search + functions) now use agent route
Some checks failed
CI / test (push) Failing after 3s
Details
CI / frontend (push) Failing after 3s
Details
CI / golangci-lint (push) Failing after 6s
Details
Security Scan / backend-security (push) Failing after 3s
Details
Security Scan / frontend-security (push) Failing after 3s
Details
CI / windsurf-platform (macos-latest) (push) Has been cancelled
Details
CI / windsurf-platform (windows-latest) (push) Has been cancelled
Details 
- When tools contain both web_search and function declarations, use
  requestType=agent instead of web_search (Google web_search route
  rejects functionDeclarations)
- Set toolConfig.mode=AUTO when mixed tools detected (VALIDATED is
  incompatible with googleSearch + functionDeclarations)
- Add hasOnlyWebSearchTools helper
- Fix buildParts test calls missing 4th arg (stripSignatures)
 2026-04-28 02:05:25 +08:00
win
9da079a5ee x
Some checks failed
Security Scan / backend-security (push) Failing after 3s
Details
Security Scan / frontend-security (push) Failing after 5s
Details
CI / test (push) Failing after 3s
Details
CI / frontend (push) Failing after 3s
Details
CI / golangci-lint (push) Failing after 3s
Details
CI / windsurf-platform (macos-latest) (push) Has been cancelled
Details
CI / windsurf-platform (windows-latest) (push) Has been cancelled
Details
2026-04-27 19:01:41 +08:00
win
2d2f677a64 chore: merge upstream Wei-Shaw/sub2api 至 v0.1.117 
主要合并内容：
- feat(channel-monitor): admin 渠道监控 MVP + 日聚合/模板/用户端卡片
- feat(available-channels): 新增"可用渠道"聚合视图与平台聚合
- feat(settings): 功能开关联动到配置页
- refactor(channel-monitor): 事件驱动调度器 / runner 生命周期 + 单测
- fix(openai/codex): 图像生成桥接修复、支付 webhook 未知单号处理
- misc: i18n/UI polish, typing tightening

冲突已手动解决，保留本地订制：
- handler.Handlers / AdminHandlers 联合 windsurf + channel_monitor/available_channel 字段
- wire/wire_gen 清理步骤同时注册 WindsurfRefreshService 与 ChannelMonitorRunner
- routes/admin 同时注册 windsurf 与 channel-monitor 路由
- service/wire 合并 Windsurf* 与 ChannelMonitor* 的 provider
- frontend admin API barrel 取两侧并集
- 采纳上游对 migrationChecksumCompatibilityRule 字段的重命名（非订制代码）
 2026-04-24 11:52:21 +08:00
win
002066e700 chore(wip): 保存订制改动以便合并上游 
- windsurf: client/pool/local_ls/tool_emulation/tool_names/models 调整
- handler: admin account_data / failover_loop / gateway_handler
- repository: scheduler_cache 及测试
- service: windsurf_chat_service / windsurf_gateway_service
- deploy: compose 合并为单文件（含 windsurf-ls profile），Dockerfile.ls
- cmd: 新增 dump_ls_models / dump_preamble / test_windsurf_tools 辅助工具
 2026-04-24 11:14:36 +08:00
win
2a4103298e Merge remote-tracking branch 'origin/main' 
# Conflicts:
#	backend/cmd/server/wire_gen.go
 2026-04-24 01:21:36 +08:00
erio
5e060b2222 Merge remote-tracking branch 'upstream/main' into feat/channel-insights 
# Conflicts:
#	backend/cmd/server/wire_gen.go
 2026-04-23 22:30:45 +08:00
erio
748a84d871 sync: bring over remaining release/custom-0.1.115 changes 
- Extract PublicSettingsInjectionPayload named struct with drift test
- Add channel_monitor_default_interval_seconds to SSR injection
- Add image_output_price to SupportedModelChip
- Simplify AppSidebar buildSelfNavItems (admins see available channels)
- Add gateway WARN logs for 503 no-available-accounts branches
- Wire ChannelMonitorRunner into provideCleanup for graceful shutdown
- Add migrations 130/131 (CC template userid fix + mimicry field cleanup)
- Clean up fork-only features (sora, claude max simulation, client affinity)
- Remove ~320 obsolete i18n keys
- Add codexUsage utility, WechatServiceButton, BulkEditAccountModal
- Tidy go.sum
 2026-04-23 20:55:18 +08:00
win
21325afb33 feat(windsurf): 补全ops日志记录与endpoint派生，对齐其他平台
Some checks failed
CI / test (push) Failing after 10s
Details
CI / frontend (push) Failing after 8s
Details
CI / golangci-lint (push) Failing after 5s
Details
Security Scan / backend-security (push) Failing after 5s
Details
Security Scan / frontend-security (push) Failing after 4s
Details 
- windsurf_gateway_service: 添加上游延迟/TTFT/错误上下文记录
- endpoint: DeriveUpstreamEndpoint 添加 PlatformWindsurf 分支
- ops_error_logger: guessPlatformFromPath 添加 /windsurf/ 识别
 2026-04-23 20:46:27 +08:00
james-6-23
dc5d42addc feat(rpm): RPM 限流模块优化 
P0:
- rpm_override 嵌入 Auth Cache Snapshot，消除每请求 DB 查询 (snapshot v6→v7)
- 429 RPM 响应返回 Retry-After 头（当前分钟剩余秒数）

P1:
- ClearAll 按钮直连 DELETE API，带 loading 防重复
- 新增 GET /admin/users/:id/rpm-status 管理员 RPM 用量查询端点

优化:
- checkRPM 从级联互斥改为并行取最严，user.rpm_limit 作为全局硬上限始终生效
- Override/Group 变更后自动失效 auth cache
- fail-open 语义不变，Redis 故障不阻塞业务
 2026-04-23 16:34:37 +08:00
erio
63f539b382 fix: merge general improvements from release branch 
Backend:
- gateway_handler: pass subject.UserID instead of int64(0) for user-level routing
- setting_handler: add missing BalanceLowNotifyRechargeURL to UpdateSettings response
- openai_gateway_service: use applyAccountStatsCost for account stats pricing integration
- embed_on: add local file override (data/public/) for embedded frontend assets

Frontend:
- useTableSelection: add batchUpdate method for batch operations
- AccountsView: virtual scrolling params, Set-based isSelected, swipe virtualization
- ProxiesView: add batchUpdate to selection and swipe-select
- BulkEditAccountModal: fix submit handler to prevent event object as argument
- SettingsView: move payload construction outside try block
- i18n: add general translation keys (saved, deleted, view, validation, allowUserRefund)
- api/client: reorder error fields for consistency
- stores/payment: clarify pollOrderStatus JSDoc
 2026-04-14 19:29:37 +08:00
erio
58677dd53f fix: merge 5 PR-related improvements 
- gateway_handler: pass ParsedRequest to RecordUsage + set in gin.Context
- channel_handler: add FeaturesConfig to CRUD (WebSearch channel toggle)
- channel_repo: features_config JSONB persistence (Create/Get/Update/List)
- security_headers: add Stripe CSP domains (script-src + frame-src)
 2026-04-14 18:34:57 +08:00
erio
1262654d97 feat: WebSearch tri-state, account stats pricing fix, quota cache fix, usage tooltip 
WebSearch tri-state switch:
- Account-level web_search_emulation changed from bool to tri-state
  string: "default" (follow channel) / "enabled" / "disabled"
- shouldEmulateWebSearch checks channel config when account is "default"
- SQL migration converts old bool values
- Frontend select replaces toggle in Edit/CreateAccountModal

Account stats pricing:
- resolveAccountStatsCost uses upstream model (post-mapping) for matching
- Priority: custom rules → model pricing file (when toggle on) → default
- Custom rules always configurable, independent of toggle
- Account ID field changed to searchable selector filtered by platform
- Description updated to reflect new behavior

Quota notification cache fix:
- CheckAccountQuotaAfterIncrement fetches real-time account from DB
- Reconstructs pre-increment usage for accurate threshold crossing detection
- New AccountQuotaReader interface (minimal: GetByID only)

Usage tooltip:
- Per-request/image billing shows per-request price instead of $0 token price
- Token billing continues to show input/output price per million tokens
 2026-04-14 09:26:08 +08:00
erio
62e80c602d revert: completely remove all Sora functionality 2026-04-05 17:11:01 +08:00
erio
e59fa8637a fix: resolve cherry-pick compilation and test issues 
- Add int64(0) param to SelectAccountWithLoadAwareness callers (signature change from channel scheduling refactor)
- Add UsageMapHook type and struct field to StreamingProcessor
- Revert Claude Max cache billing code to upstream/main (not part of channel feature)
- Revert credits overages logic to upstream/main (non-channel change)
- Remove Instructions field reference (non-channel OpenAI feature)
- Restore sora_client_handler_test.go from upstream + add channel service nil params
 2026-04-04 12:38:50 +08:00
erio
ce41afb756 refactor: move channel model restriction from handler to scheduling phase 
Move the model pricing restriction check from 8 handler entry points
to the account scheduling phase (SelectAccountForModelWithExclusions /
SelectAccountWithLoadAwareness), aligning restriction with billing:

- requested: check original request model against pricing list
- channel_mapped: check channel-mapped model against pricing list
- upstream: per-account check using account-mapped model

Handler layer now only resolves channel mapping (no restriction).
Scheduling layer performs pre-check for requested/channel_mapped,
and per-account filtering for upstream billing source.
 2026-04-04 11:24:48 +08:00
erio
2555951be4 feat(channel): 渠道管理全链路集成 — 模型映射、定价、限制、用量统计 
- 渠道模型映射：支持精确匹配和通配符映射，按平台隔离
- 渠道模型定价：支持 token/按次/图片三种计费模式，区间分层定价
- 模型限制：渠道可限制仅允许定价列表中的模型
- 计费模型来源：支持 requested/upstream 两种计费模型选择
- 用量统计：usage_logs 新增 channel_id/model_mapping_chain/billing_tier/billing_mode 字段
- Dashboard 支持 model_source 维度（requested/upstream/mapping）查看模型统计
- 全部 gateway handler 统一接入 ResolveChannelMappingAndRestrict
- 修复测试：同步 SoraGenerationRepository 接口、SQL INSERT 参数、scan 字段
 2026-04-04 11:13:58 +08:00
erio
eb385457b2 fix(channel): 全平台渠道映射覆盖 + 公共函数抽取 + 死代码清理 
- 4个缺失handler入口添加渠道映射+限制检查(ChatCompletions/Responses/Gemini)
- 模型限制错误信息优化，区分"模型不可用"和"无账号"
- OpenAI RecordUsage RequestedModel 改用 OriginalModel
- ResolveChannelMappingAndRestrict/ReplaceModelInBody 抽取到 ChannelService 消除跨service重复
- validateNoDuplicateModels 按 platform:model 去重
- 删除 Channel.ResolveMappedModel 死代码和 CalculateCostWithChannel Deprecated方法
- 移除冗余nil检查，抽取 validatePricingBillingMode 公共校验
 2026-04-04 11:13:56 +08:00
erio
4ea8b4cb4f refactor(channel): 抽取渠道映射公共函数 + OpenAI映射到body + 空响应修复 + 清理日志 
- 抽取 ResolveChannelMappingAndRestrict 统一入口（5处→1个方法）
- 抽取 BuildModelMappingChain 到 ChannelMappingResult 方法（5处→1行调用）
- OpenAI 三入口 Forward 前应用渠道映射到请求体
- OpenAI Responses/Messages 限制检查添加错误响应
- 清理前端 3 处 console.log 调试日志
 2026-04-04 11:13:56 +08:00
erio
91bdcf8994 fix(channel): 模型限制用映射后模型检查 + 平台开关保留配置不删除 
- OpenAI 网关三处 IsModelRestricted 改用 channelMapping.MappedModel
- 前端平台勾选改为 enabled 开关，取消勾选不清空配置数据
- formToAPI/校验只处理 enabled 的平台
 2026-04-04 11:13:56 +08:00
erio
632035aabd feat(billing): 网关计费迁移到 CalculateCostUnified + 模型限制错误统一 
- GatewayService/OpenAIGatewayService 注入 ModelPricingResolver
- RecordUsage 从旧路径迁移到 CalculateCostUnified（支持 per_request/image 模式）
- 无渠道时自动回退旧路径，保持原有行为
- 长上下文双倍计费仅在无渠道定价时生效
- CostBreakdown 新增 BillingMode 字段，使用日志记录实际计费模式
- 模型限制错误改为与"无可用账号"相同的 503 响应
 2026-04-04 11:12:21 +08:00
erio
ebac0dc628 feat(channel): 缓存扁平化 + 网关映射集成 + 计费模式统一 + 模型限制 
- 缓存重构为 O(1) 哈希结构 (pricingByGroupModel, mappingByGroupModel)
- 渠道模型映射接入网关流程 (Forward 前应用, a→b→c 映射链)
- 新增 billing_model_source 配置 (请求模型/最终模型计费)
- usage_logs 新增 channel_id, model_mapping_chain, billing_tier 字段
- 每种计费模式统一支持默认价格 + 区间定价
- 渠道模型限制开关 (restrict_models)
- 分组按平台分类展示 + 彩色图标
- 必填字段红色星号 + 模型映射 UI
- 去除模型通配符支持
 2026-04-04 11:09:01 +08:00
Dave King
7c6dc9dda8 fix: add account and proxy details to gateway.forward_failed log 
The forward_failed error log only included account_id, making it
difficult to identify which account and proxy caused the failure
without querying the database. Add account_name, account_platform,
and proxy details (id, name, host, port) to the log fields.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-25 12:19:17 +00:00
Ethan0x0000
db9021f9c1 feat(ops): propagate endpoint/request-type context in handlers; add UpstreamURL to upstream error events 2026-03-21 23:47:39 +08:00
shaw
01d8286bd9 feat: add max_claude_code_version setting and disable auto-upgrade env var 
Add maximum Claude Code version limit to complement the existing minimum
version check. Refactor the version cache from single-value to unified
bounds struct (min+max) with a single atomic.Value and singleflight group.

- Backend: new constant, struct field, cache refactor, validation (semver
  format + cross-validation max >= min), gateway enforcement, audit diff
- Frontend: settings UI input, TypeScript types, zh/en i18n
- Add CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 to all Claude Code
  tutorials on /keys page (unix/cmd/powershell/vscode settings.json)
 2026-03-20 09:10:01 +08:00
haruka
1fd1a58a7a fix: record original upstream status code when failover exhausted (#1128) 
When all failover accounts are exhausted, handleFailoverExhausted maps
the upstream status code (e.g. 403) to a client-facing code (e.g. 502)
but did not write the original code to the gin context. This caused ops
error logs to show the mapped code instead of the real upstream code.

Call SetOpsUpstreamError before mapUpstreamError in all failover-
exhausted paths so that ops_error_logger captures the true upstream
status code and message.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-19 11:15:02 +08:00
Ethan0x0000
7bd1972f94 refactor: migrate all handlers to shared endpoint normalization middleware 
- Apply InboundEndpointMiddleware to all gateway route groups
- Replace normalizedOpenAIInboundEndpoint/normalizedOpenAIUpstreamEndpoint and normalizedGatewayInboundEndpoint/normalizedGatewayUpstreamEndpoint with GetInboundEndpoint/GetUpstreamEndpoint
- Remove 4 old constants and 4 old normalization functions (-70 lines)
- Migrate existing endpoint normalization test to new API

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-03-15 22:13:42 +08:00
Wesley Liddick
8321e4a647
Merge pull request #1023 from YanzheL/fix/claude-output-effort-logging 
fix: extract and log Claude output_config.effort in usage records
 2026-03-15 16:45:37 +08:00
Elysia
359e56751b 增加测试 2026-03-15 16:21:49 +08:00
YanzheL
1bff2292a6
fix: extract and log Claude output_config.effort in usage records 
Claude's output_config.effort parameter (low/medium/high/max) was not
being extracted from requests or logged in the reasoning_effort column
of usage logs. Only the OpenAI path populated this field.

Changes:
- Extract output_config.effort in ParseGatewayRequest
- Add ReasoningEffort field to ForwardResult
- Populate reasoning_effort in both RecordUsage and RecordUsageWithLongContext
- Guard against overwriting service-set effort values in handler
- Update stale comments that described reasoning_effort as OpenAI-only
- Add unit tests for extraction, normalization, and persistence
 2026-03-15 12:55:37 +08:00
Elysia
0e23732631 fix(gateway): 防止流式 failover 拼接腐化导致客户端收到双 message_start 
当上游在 SSE 流中途返回 event:error 时，handleStreamingResponse 已将
部分 SSE 事件写入客户端，但原先的 failover 逻辑仍会切换到下一个账号
并写入完整流，导致客户端收到两个 message_start 进而产生 400 错误。

修复方案：在每次 Forward 调用前记录 c.Writer.Size()，若 Forward 返回
UpstreamFailoverError 后 writer 字节数增加，说明 SSE 内容已不可撤销地
发送给客户端，此时直接调用 handleFailoverExhausted 发送 SSE error 事件
终止流，而非继续 failover。

Ping-only 场景不受影响：slot 等待期的 ping 字节在 Forward 前后相等，
正常 failover 流程照常进行。

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-14 22:49:23 +08:00
ius
611fd884bd feat: decouple billing correctness from usage log batching 2026-03-12 16:53:18 +08:00
shaw
00a0a12138 feat: Anthropic平台可配置 anthropic-beta 策略 2026-03-10 11:20:10 +08:00
shaw
c7fcb7a84b feat: apikey限额支持查询重置时间 2026-03-09 10:22:24 +08:00
shaw
7a353028e7 fix: 修复keys速率限制未自动重置额度的bug 2026-03-07 10:13:51 +08:00
shaw
838dad8759 feat: 重构 /v1/usage 端点，支持 quota_limited 和 unrestricted 双模式 
- quota_limited 模式：返回 Key 级别的总额度、速率限制窗口用量和过期时间
- unrestricted 模式：返回订阅限额或钱包余额信息（向后兼容）
- 新增 model_stats 字段，支持 start_date/end_date 参数查询按模型用量统计
- 提取 buildUsageData/parseUsageDateRange 等辅助方法，减少主函数复杂度
- 新增 APIKeyService.GetRateLimitData 和 UsageService.GetAPIKeyModelStats
 2026-03-03 20:59:12 +08:00
shaw
a80ec5d8bb feat: apikey支持5h/1d/7d速率控制 2026-03-03 15:01:10 +08:00