zfc/sub2api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3,395 Commits 3 Branches 0 Tags
Commit Graph

234 Commits

Author SHA1 Message Date
Wesley Liddick
ae4c738887
Merge pull request #2457 from wucm667/fix/openai-fast-policy-default-pass 
fix: 默认透传 OpenAI service_tier
 2026-05-19 14:34:37 +08:00
Wesley Liddick
a340002c6d
Merge pull request #2401 from 2ue/fix/normalize-image-billing-size 
修复图片计费尺寸归一化与使用记录展示
 2026-05-19 14:00:24 +08:00
Wesley Liddick
14f54be03f
Merge pull request #2481 from weak-fox/lyp/fix-issue-2223-capacity-retry 
fix: 修复 OpenAI 模型容量错误未进入自动重试
 2026-05-19 10:24:18 +08:00
Wesley Liddick
f9fec78b70
Merge pull request #2505 from is7Qin/fix/openai-compat-usage-parsing 
修复 Claude 映射 GPT 后被记为 0 token 的计费漏洞
 2026-05-19 09:53:50 +08:00
lyen1688
cc5328c491 修复 OpenAI Responses SSE 终止事件识别 2026-05-17 15:33:34 +08:00
name
0393bd7c82 Fix OpenAI compat usage parsing 2026-05-16 03:03:43 +08:00
weak-fox
9f07741c13 fix: retry model capacity transient errors 2026-05-15 10:43:29 +08:00
wucm667
e9637148dd fix(openai): pass service_tier by default 2026-05-14 16:45:31 +08:00
2ue
bb4c1abe28 Fix image billing size normalization 2026-05-12 15:21:31 +08:00
wucm667
6d69ae87c3 fix(openai): record zero-cost usage for unpriced models 2026-05-09 17:33:35 +08:00
Jlypx
26043a8f29 fix(openai): gate Codex image bridge injection 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-05-07 00:10:20 +08:00
lyen1688
0584305e5a feat: improve OpenAI messages compatibility for Claude Code 2026-05-05 19:36:33 +08:00
2ue
6faa344916 feat: add OpenAI image generation controls 2026-05-05 03:26:54 +08:00
shaw
47fb38bca1 fix: record zero OpenAI usage logs 2026-05-03 17:43:56 +08:00
shaw
72d5ee4cd1 fix: drain OpenAI compat streams for usage 2026-05-03 17:11:27 +08:00
Wesley Liddick
55a7fa1e07
Merge pull request #2005 from gaoren002/pr/openai-strip-passthrough-fields 
fix(openai): strip unsupported passthrough fields
 2026-04-29 21:46:19 +08:00
Wesley Liddick
46f06b2498
Merge pull request #2050 from zvensmoluya/fix/openai-compact-payload-fields 
fix(openai): preserve current Codex compact payload fields
 2026-04-29 21:03:48 +08:00
DaydreamCoding
30f55a1f72 feat(openai): OpenAI Fast/Flex Policy 完整实现（HTTP + WebSocket + Admin） 
对称参照 Claude BetaPolicy 的 fast-mode 过滤实现，新增针对 OpenAI 上游
service_tier 字段（priority / flex，含客户端 "fast" → "priority" 归一化）的
pass / filter / block 三态策略，覆盖全部 OpenAI 入口 + admin 配置入口。

后端核心
- 新增 SettingKeyOpenAIFastPolicySettings、OpenAIFastPolicyRule、
  OpenAIFastPolicySettings 配置模型，含规则的 service_tier × action × scope
  × 模型白名单 × fallback action 维度。
- SettingService.Get/SetOpenAIFastPolicySettings；缺失时返回内置默认策略
  （所有模型的 priority 走 filter，whitelist 为空，fallback=pass）。设计
  依据：service_tier=fast 是用户级开关，与 model 字段正交，默认锁定特定
  model slug 会留下"用 gpt-4 + fast 透传 priority 上游"的绕过路径。JSON
  解析失败不再静默 fallback，slog.Warn 记录脏数据，便于运维定位。
- service_tier 归一化（trim + ToLower + fast→priority + 白名单 priority/flex）
  与策略评估（evaluateOpenAIFastPolicy）作为唯一真实来源，HTTP / WS 共用。
  抽出纯函数 evaluateOpenAIFastPolicyWithSettings，配合 ctx-bound settings
  快照（withOpenAIFastPolicyContext / openAIFastPolicySettingsFromContext），
  WS 长会话入口预取一次后所有帧复用，避免每帧打到 settingService。

HTTP 入口（4 个）
- Chat Completions、Anthropic 兼容（Messages，含 BetaFastMode→priority 二次
  命中）、原生 Responses、Passthrough Responses 全部接入
  applyOpenAIFastPolicyToBody，filter 走 sjson 顶层删除 service_tier，block
  返回 403 forbidden_error JSON。
- 4 入口统一使用 upstream 视角的 model（GetMappedModel +
  normalizeOpenAIModelForUpstream + Codex OAuth normalize 后的 slug），
  避免 chat/messages/native /responses/passthrough 因为 model 维度不同
  造成 whitelist 命中差异。
- 在 pass 路径也把客户端 "fast" 别名归一化为 "priority" 写回 body，
  否则 native /responses 与 passthrough 入口会把 "fast" 原样透传给上游
  导致 400/拒绝（chat-completions 入口的 normalizeResponsesBodyServiceTier
  此前已具备同等行为）。

WebSocket 入口
- 新增 applyOpenAIFastPolicyToWSResponseCreate：严格匹配
  type="response.create"，仅处理顶层 service_tier；filter 用 sjson 删字段，
  block 返回 typed *OpenAIFastBlockedError。
- ingress 路径在 parseClientPayload 内调用，block 命中先 Write Realtime
  风格 error event 再返回 OpenAIWSClientCloseError(StatusPolicyViolation
  =1008)，依赖底层 WebSocket Conn.Write 的同步 flush 保证 error 先于
  close。
- passthrough 路径在 RunEntry 前对 firstClientMessage 应用策略，并通过
  openAIWSPolicyEnforcingFrameConn 包装 ReadFrame 对每个 client→upstream
  帧执行策略；后续帧无 model 字段时回退到 capturedSessionModel。
  filter 闭包内同时侦测 session.update / session.created 帧的 session.model
  字段刷新 capturedSessionModel，封堵"首帧 model=gpt-4o（pass）→
  session.update 改为 gpt-5.5 → 不带 model 的 response.create fallback
  到 gpt-4o"的 mid-session 绕过路径。
- passthrough billing：requestServiceTier 在策略 filter 之后再从
  firstClientMessage 提取，filter 命中时 OpenAIForwardResult.ServiceTier
  上报 nil（default tier），与 HTTP 入口（reqBody 来自 post-filter map）
  / WS ingress（payload 来自 post-filter bytes）的语义一致。
- 错误事件 schema：{event_id: "evt_<32hex>", type: "error",
  error: {type: "forbidden_error", code: "policy_violation", message}}，
  与 OpenAI codex 客户端 error event 解析兼容。

Admin / Frontend
- dto.SystemSettings / UpdateSettingsRequest 新增
  openai_fast_policy_settings 字段（omitempty），bulk GET/PUT 接入。
- Settings 页 Gateway 页签新增 Fast/Flex Policy 表单卡片：
  service_tier × action × scope × 模型白名单 × fallback action 全字段配置。
- 前端守门：openaiFastPolicyLoaded 标志仅在 GET 真带回字段时才允许回写，
  避免 rollout/错误把默认规则覆盖成空；saveSettings 回写循环 skip 该字段，
  由专用刷新逻辑处理；仅 action=block 时发送 error_message，匹配后端
  omitempty 行为。

测试
- HTTP 路径：openai_fast_policy_test.go 覆盖默认配置（whitelist=[]，所有
  模型 priority filter）/ block 自定义错误 / scope 区分 / filter 删字段 /
  block 不改 body / block 短路上游 / Anthropic BetaFastMode 触发 OpenAI
  fast policy 等场景。
- WebSocket 路径：openai_fast_policy_ws_test.go 覆盖
    helper 单元（filter / fast→priority 归一化 / flex 透传 / block typed
    error / 无 service_tier 字节不变 / 非 response.create 帧不动 / 空 type
    帧不动 / event_id+code 字段断言 / 非字符串 service_tier 容错）+
    pass 路径 fast 别名归一化回归 +
    ingress 端到端（filter 后上游不含 service_tier / block 后客户端先收
    error event 再收 close 1008 且上游 0 写）+
    passthrough capturedSessionModel fallback 用例（whitelist 策略下首帧
    建立、缺 model 命中 fallback、缺少 fallback 时的 leak 文档化）+
    passthrough session.update / session.created 旋转 capturedSessionModel
    的 mid-session 绕过回归 +
    passthrough billing post-filter ServiceTier 与 idempotent filter 回归。

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-28 11:15:09 +08:00
Zven
3d4ca5e8d1 fix(openai): preserve current Codex compact payload fields 2026-04-28 10:55:29 +08:00
gaoren002
9fe02bba7e fix(openai): strip unsupported passthrough fields 2026-04-27 00:39:06 +00:00
gaoren002
615557ec20 fix(openai): avoid implicit image sticky sessions 2026-04-26 17:09:41 +00:00
Wesley Liddick
22b1277572
Merge pull request #1948 from hungryboy1025/fix/openai-account-test-responses-stream 
fix(openai): tighten responses stream account tests
 2026-04-25 20:31:07 +08:00
gaoren002
dac6e52091 fix(openai): keep responses stream alive during pre-output failover 2026-04-25 12:11:27 +00:00
hungryboy1025
8987e0ba67 fix(openai): tighten responses stream account tests 2026-04-25 16:56:50 +08:00
AyeSt0
5b63a9b02d fix(openai): fail over before responses stream output 2026-04-25 15:09:40 +08:00
Wesley Liddick
641e61073f
Merge pull request #1940 from 4fuu/fix/bump-codex-cli-version-to-0.125.0 
fix(openai): bump codex CLI version from 0.104.0 to 0.125.0
 2026-04-25 14:57:51 +08:00
shaw
095f457c57 feat(openai): port /responses/compact account support flow (PR #1555) 
将 vansour/sub2api#1555 的 OpenAI compact 能力建模手工移植到当前 main：账号
级 compact 状态/auto-force_on-force_off 模式、compact-only 模型映射、调度器
tier 分层（已支持 > 未知 > 已知不支持）、管理后台 compact 主动探测，以及对应
i18n/状态徽章。普通 /responses 流量行为不变，无数据库迁移。
 2026-04-25 14:52:58 +08:00
4fuu
1e57e88e43 fix(openai): bump codex CLI version from 0.104.0 to 0.125.0 
The hardcoded codex CLI version (0.104.0) causes upstream rejection
when using gpt-5.5 with compact, as the server treats the request
as an outdated client and returns 400/502.

Update codexCLIVersion, codexCLIUserAgent, and openAICodexProbeVersion
to 0.125.0 to match the current Codex CLI release.

Fixes #1933, #1887, #1865
Related: #1609, #1298, #849
 2026-04-25 05:26:33 +00:00
gaoren002
c4d496da18 fix(openai): handle codex spark model limitations 2026-04-24 07:42:31 +00:00
shaw
ca204ddd2f fix(openai): preserve image outputs when text content serialization fails 
In reconstructResponseOutputFromSSE, text content Marshal/Unmarshal
failure previously caused an early return that silently discarded
already-extracted image_generation_call outputs. Now serialization
errors are tolerated so image results still reach the client.
 2026-04-24 08:58:51 +08:00
gaoren002
5f41899705 fix: bridge codex image generation over responses 2026-04-23 15:13:57 +00:00
shaw
ef967d8f8a fix: 修复 golangci-lint 报告的 36 个问题 2026-04-23 16:30:43 +08:00
wx-11
9e5a6351fc 修复计费问题以及模型回显 2026-04-23 15:09:47 +08:00
wx-11
11cf23da7d 修改403逻辑: 先临时冷却，再根据连续次数决定是否判坏号 2026-04-23 12:58:13 +08:00
meteor041
00778dca31 fix openai image request handling 2026-04-23 09:53:57 +08:00
lucas morgan
c548021921 feat(openai): 同步生图 API 支持并接入图片计费调度 
- 同步 OpenAI 图片生成与编辑接口
- 接入图片请求解析、账号调度、转发与用量记录
- 接入图片计费与图片用量落库
- 限制 OAuth 生图仅支持无显式模型和尺寸的基础请求
 2026-04-22 12:30:08 +08:00
erio
10699eeb34 refactor: extract ReadUpstreamResponseBody to deduplicate upstream response read + too-large error handling 
Consolidates 9 call sites of resolveUpstreamResponseReadLimit + readUpstreamResponseBodyLimited + ErrUpstreamResponseBodyTooLarge error handling into a single ReadUpstreamResponseBody function with TooLargeWriter callback for API-format-specific error responses (Anthropic, OpenAI, countTokens).
 2026-04-16 01:53:22 +08:00
Wesley Liddick
7451b6f9ae 修复 OpenAI 账号限流回流误判：7d 窗口可用时不因 5h 窗口为 0 回写 429 2026-04-15 15:29:52 +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
98c9d51791 fix: correct account stats pricing priority order 
Priority was wrong:
- Before: custom rules → LiteLLM (when ApplyPricingToAccountStats) → nil
- After:  custom rules → totalCost (when ApplyPricingToAccountStats) → LiteLLM → nil

When ApplyPricingToAccountStats is enabled, use the request's actual
client billing cost (before multiplier) as account_stats_cost, instead
of recalculating from LiteLLM per-token prices which produced incorrect
values for per-request billing mode.

LiteLLM model pricing is now the final fallback (priority 3), used only
when neither custom rules nor ApplyPricingToAccountStats apply.
 2026-04-14 09:28:11 +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
11c4606874 fix(channel): use upstream model for account stats pricing and remove channel pricing fallback 
- resolveAccountStatsCost now uses the final upstream model (after
  account-level mapping) to match custom pricing rules, fixing the
  issue where requested model (e.g. claude-sonnet-4-5) didn't match
  rules configured for upstream model (e.g. claude-opus-4-6)
- Remove tryChannelPricing fallback — only custom rules are applied,
  unmatched requests use default formula (total_cost × rate)
- Remove unused billingService and serviceTier parameters
- Update description: "启用后将支持自定义账号统计的模型价格"
 2026-04-14 09:26:08 +08:00
erio
b32d1a2c9f feat(notify): add balance low & account quota notification system 
- User balance low notification: email alert when balance drops below
  configurable threshold (user email + verified extra emails)
- Account quota notification: broadcast email to admin-configured
  recipients when daily/weekly/total quota usage exceeds alert threshold
- Admin settings: global enable/disable, default threshold, quota
  notification email list (Email Settings tab)
- User profile: enable/disable, custom threshold, add/remove extra
  notification emails with verification code flow
- Account quota: per-dimension alert toggle and threshold in quota
  control card
- Trigger logic: first-crossing only (old >= threshold && new < threshold
  for balance; old < threshold && new >= threshold for quota), naturally
  prevents duplicate notifications without Redis dedup
 2026-04-14 09:23:02 +08:00
erio
7535e312e0 feat(channels): add custom account stats pricing rules 
Allow channels to configure independent model pricing for account
statistics cost calculation, decoupled from user billing.

Backend:
- Migration 101: channels.apply_pricing_to_account_stats toggle,
  channel_account_stats_pricing_rules/model_pricing tables,
  usage_logs.account_stats_cost column
- resolveAccountStatsCost: match rules by group/account, then channel
  pricing, fallback to original formula when unconfigured
- Integrate into both GatewayService.recordUsageCore and
  OpenAIGatewayService.RecordUsage
- Update 8 account stats SQL queries to use
  COALESCE(account_stats_cost, total_cost) * account_rate_multiplier
- 23 unit tests for matching, pricing lookup, and cost calculation

Frontend:
- Channel edit dialog: toggle + custom rules UI with group/account
  multi-select and pricing entry cards
- API types and i18n (zh/en)
 2026-04-14 09:22:12 +08:00
ius
265687b56d fix: 优化调度快照缓存以避免 Redis 大 MGET 2026-04-08 10:39:15 -07:00
Wesley Liddick
5088e91566
Merge pull request #1417 from YanzheL/fix/openai-empty-base64-image-payloads 
fix: sanitize empty base64 image payloads for OpenAI requests
 2026-04-08 14:20:38 +08:00
Wesley Liddick
5c203ce6c6
Merge pull request #1428 from YanzheL/fix/openai-gateway-content-session-hash-fallback 
fix(gateway): add content-based session hash fallback for non-Codex clients
 2026-04-08 14:17:49 +08:00
Elysia
9e515ea7c4 fix: 非流式响应路径扩展SSE检测至所有账号类型 (#1493) 
当上游返回SSE格式响应(如sub2api链路)时，API Key账号的非流式路径
未检测SSE，导致终态事件中空output直接透传给客户端。

- 将Content-Type SSE检测从仅OAuth扩展至所有账号类型
- 重命名handleOAuthSSEToJSON为handleSSEToJSON（无OAuth专属逻辑）
- 为透传路径新增handlePassthroughSSEToJSON，支持SSE转JSON及空output重建

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-07 22:49:14 +08:00
Wesley Liddick
81b96ae123
Merge pull request #1498 from aiexz/main 
do not normalize model for openai API token based accounts
 2026-04-07 20:37:10 +08:00
shaw
b2e379cf7a fix: 非流式路径在上游终态事件output为空时从delta事件重建响应内容 
上游API近期更新后，response.completed终态SSE事件的output字段可能为空，
实际内容仅通过response.output_text.delta等增量事件下发。流式路径不受影响，
但chat_completions非流式路径和responses OAuth非流式路径只依赖终态事件的
output，导致返回空响应。

新增BufferedResponseAccumulator累积器，在SSE扫描过程中收集delta事件内容
（文本、function_call、reasoning），当终态output为空时补充重建。

同时修复handleChatBufferedStreamingResponse遗漏response.done事件类型的问题。
 2026-04-07 19:35:56 +08:00