seewe/sub2api
1
0
Fork 0
mirror of https://github.com/Wei-Shaw/sub2api.git synced 2026-10-14 12:02:27 +08:00
Code Issues Packages Projects Releases Wiki Activity
5,242 Commits 43 Branches 62 Tags
f06c8c56985c2925732ff3d63a7ebbd2fa54302c
Commit Graph
193 Commits
Author SHA1 Message Date
Edison42 1c0cb24c7e feat(usage): persist client session identifiers 2026-07-24 01:22:34 +08:00
Heatherm Huang 1c7959d0de fix: allow composite grok chat completions 2026-07-23 09:20:52 +08:00
Heatherm Huang 1d2dfab86d fix: allow composite grok messages routing 2026-07-23 09:20:52 +08:00
Heatherm Huang 3a683fff55 Fix composite route alias attribution 2026-07-23 09:20:52 +08:00
Heatherm Huang c8d1e2e16f Harden composite group product surfaces 2026-07-23 09:19:25 +08:00
Heatherm Huang ebc1028771 Add composite group routing 2026-07-23 09:19:24 +08:00
Wesley Liddick ebfaf2496b Merge pull request #4674 from AdrianZhaoDev/main 
feat(groups): add OpenAI reasoning policy
 2026-07-22 09:37:06 +08:00
zhaozewu 6af622c340 feat(groups): add OpenAI reasoning policy 
Persist reasoning ceilings and exact mappings for OpenAI groups, enforce them across HTTP and WebSocket forwarding, and invalidate cached auth snapshots.
 2026-07-21 11:02:43 +08:00
abbzbb 2ae61f3da0 fix(grok): Codex compact 适配与链式视频 content 代理 
- #4223/#4554: Grok 模拟 /responses/compact，调度允许 Grok 账号
- #4494/#4626: 支持链式中继的受保护视频 /content 下载
 2026-07-20 16:12:56 +08:00
jjaw 8fd6f91b7e 优化 Responses 生图意图复用 2026-07-19 18:49:08 +08:00
Wesley Liddick 005bc5c8d4 Merge pull request #4497 from heathermhuang/agent/fix-grok-media-fallback-4471 
fix(grok): fail closed for ineligible OAuth media
 2026-07-18 20:41:24 +08:00
haruka bd0f2d6405 fix: report chat stream transport failures 2026-07-18 03:24:04 +08:00
Heatherm Huang e86063155f fix(grok): gate OAuth media on paid eligibility 2026-07-17 19:15:16 +08:00
Wesley Liddick 8bfbc5ca99 Merge pull request #4485 from Sub2API-Devs/dev 
feat(security-audit): 新增 OpenAI 兼容提示词审计能力与安全审计控制台
 2026-07-17 16:15:26 +08:00
li fc3c5a1e0c fix: 权限检查和并发槽也使用显式检查，修复被动 namespace 触发 403 
Fixes #4447
 2026-07-17 15:15:54 +08:00
li e375623abf fix(gateway): 被动 image_gen namespace 不再强制要求 Responses capability 
Fixes #4476
 2026-07-17 15:07:41 +08:00
mt21625457 d11bdb13f5 feat(security-audit): add OpenAI-compatible prompt auditing 2026-07-17 00:39:39 +08:00
harukaandClaude Opus 4.8 605b026cc4 fix(gateway): route image-intent /v1/responses only to Responses-capable accounts (#4417) 
For OpenAI-compatible API-key accounts, /v1/responses requests with
image-generation intent could be scheduled to accounts whose upstream
does not support the Responses API (extra.openai_responses_supported=false).
The flag was only consulted at forward time, where such accounts are
silently downgraded to a Chat-Completions path that cannot produce images,
causing upstream 4xx/5xx or canceled requests.

Fix:
- Add endpoint capability OpenAIEndpointCapabilityResponses. Its check in
  SupportsOpenAIEndpointCapability excludes only OpenAI API-key accounts
  probed as unsupported (mirroring the forward-time downgrade condition);
  OAuth/Grok/unprobed accounts keep existing behavior, and a responses-
  capable upstream must still pass the chat_completions gate. Reusing the
  existing requiredCapability plumbing makes every scheduler filter path
  enforce it with no scheduler signature changes.
- Request the responses capability at the HTTP Responses and
  ResponsesWebSocket call sites only when imageIntent && platform==openai,
  so non-image requests keep the downgrade path and Grok's own image path
  is untouched.
- Normalize max_tokens -> max_output_tokens on the native responses
  forward path (PlatformOpenAI), and strip prompt_cache_options alongside
  prompt_cache_retention/safety_identifier.

/v1/images/generations continues to use native image capability (unchanged).

Tests: capability truth table, scheduler exclusion of unsupported accounts,
and forward-path transform behavior.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KXpzKKvsb5jW2GvgBQqnnZ
 2026-07-16 00:23:40 -07:00
shaw 0408bdb34f Merge remote-tracking branch 'origin/main' into feat/upstream-rate-scheduling 
# Conflicts:
#	backend/internal/handler/openai_gateway_handler.go
 2026-07-16 10:31:21 +08:00
Wesley Liddick 531ae04a0b Merge pull request #4395 from wp-a/fix/openai-body-limit-failover 
[codex] fail over account-specific OpenAI body limits
 2026-07-16 09:33:48 +08:00
Wesley Liddick e4329a04e8 Merge pull request #4393 from superman2003/fix/grok-codex-compatibility 
fix(grok): improve Codex compatibility and key setup
 2026-07-16 09:33:20 +08:00
Wesley Liddick f3138ceb43 Merge pull request #4384 from wp-a/fix/openai-model-scoped-transient-cooldown 
[codex] scope OpenAI transient cooldowns by model
 2026-07-16 09:33:09 +08:00
Tian Lee 90ee85f3ef feat: 按上游计费倍率调度 OpenAI 账号 2026-07-16 00:40:46 +08:00
王鹏 3db00d3fee fix(openai): fail over account-specific body limits 2026-07-16 00:19:20 +08:00
superman2003 410ea8490c fix(grok): allow passive Codex image tool declarations 2026-07-16 00:16:21 +08:00
王鹏 40b8f04a6a fix(openai): scope transient cooldowns by model 2026-07-15 22:52:35 +08:00
王鹏 4f641208a0 fix(openai-ws): close ingress reads cleanly 2026-07-15 22:15:44 +08:00
Wesley Liddick bac925624f Merge pull request #4289 from Tiantianr/fix/openai-ws-first-message-timeout 
fix(openai-ws): make first-message timeout configurable
 2026-07-15 15:45:24 +08:00
王鹏 fc4089f292 fix(openai): bound native responses first output wait 
Add an opt-in first semantic output budget for native HTTP Responses, including response-header wait. Keep preamble and keepalive bytes non-semantic so a stalled account can fail over once without replaying its response IDs. Defaults remain disabled.

Related to #4201, #4185, and #4248. Complements the HTTP/2 dead-connection fix in #4207.
 2026-07-15 13:01:16 +08:00
Wesley Liddick 4344f6afb0 Merge pull request #4298 from wp-a/fix/openai-images-json-completion-boundary 
fix(images): preserve JSON completion boundaries
 2026-07-15 11:08:47 +08:00
Wesley Liddick 2ceaa4783c Merge pull request #4311 from jianjianai/codex/perf-openai-forwarding-final 
perf(openai): 优化 Responses 图片意图判定与透传流式刷新
 2026-07-15 10:12:05 +08:00
Wesley Liddick 125b03aee6 Merge pull request #4281 from bestony/feat/openai-ws-proxy-failed-host 
fix(openai): include proxy host in websocket_proxy_failed logs
 2026-07-15 09:37:04 +08:00
Wesley Liddick 65093591cd Merge pull request #4282 from bestony/feat/openai-failover-switching-proxy-host 
fix(openai): include proxy host in upstream_failover_switching logs
 2026-07-15 09:36:53 +08:00
shaw a0593b0bf8 fix(gateway): 客户端断开后 failover 静默终止，不再误报 502 账号耗尽 
上游请求经 detachUpstreamContext(WithoutCancel) 有意脱离客户端取消（保
计费），但 failover 循环仍用原始 c.Request.Context() 重新选号：客户端
断开后上游返回 520 等可 failover 错误时，重新选号必然得到 context
canceled，被误判为账号耗尽，记录并返回通用 502。

修复：客户端已断开 ⇒ failover 静默终止。

- 新增 failoverClientGone(c)：请求 ctx 已取消时先停 compact 心跳
  （建立 happens-before，对齐其它终结路径），响应未提交则标 499
  （statusClientClosedRequest，与并发槽取消路径同惯例）
- 7 个 OpenAI 内联 failover 循环（Responses/Messages/chat_completions/
  embeddings/images/grok_media/alpha_search）加双 guard：换号前 +
  选号失败分支入口；guard 位于 ReportOpenAIAccountScheduleResult(false)
  之后、RecordOpenAIAccountSwitch/池模式重试之前，账号健康副作用
  （service 层 detached ctx）不受影响
- FailoverState.HandleFailoverError/HandleSelectionExhausted 入口加
  ctx.Err() 检查返回 FailoverCanceled，取消不再改动 failover 状态；
  全部 10 个 FailoverCanceled 分支统一调用 failoverClientGone 归类 499
- 上游 detach 与计费设计不变；真实上游 520 事件仍完整落 ops
  （面板显示码 COALESCE(upstream_status_code,status_code)=520，
  错误率/告警口径不变）

测试：新增 openai_responses_failover_cancel_test.go 复现 issue 场景
（520+取消 ⇒ 不切号、499、无 502 终态）+ 在线客户端对照（正常切换、
耗尽 502）；failover_loop_test.go 补入口取消用例并修正取消语义断言。

Fixes #4257
 2026-07-15 09:29:05 +08:00
jjaw 4aedbfc4a8 补充 OpenAI 转发复用边界注释 2026-07-15 06:59:00 +08:00
jjaw 78e09a0f1a 复用请求级图片生成意图判断 2026-07-15 04:20:11 +08:00
王鹏 2c13ed32e7 fix(images): preserve JSON completion boundaries 2026-07-15 03:15:47 +08:00
Tiantianr 74e296703a fix(openai-ws): make first-message timeout configurable 
Add a dedicated client first-message timeout while preserving the legacy 30-second default.

Use the resolved value for both the WebSocket read deadline and structured timeout logs, and document tuning for large requests or slow links.

Add configuration, validation, handler, and resolver regression coverage.

Refs #4158
 2026-07-14 22:40:05 +08:00
bestony ba5b6970be fix(openai): include proxy host in upstream_failover_switching logs 
Enrich openai.upstream_failover_switching structured logs with proxy
identity fields (proxy_id, proxy_name, proxy_host, proxy_port) so
operators can see which outbound proxy failed when switching accounts.
Matches the existing gateway.forward_failed / websocket_proxy_failed
logging pattern.
 2026-07-14 19:33:56 +08:00
bestony b000aac474 fix(openai): include proxy host in websocket_proxy_failed logs 
Add proxy_id/proxy_name/proxy_host/proxy_port fields to openai.websocket_proxy_failed so operators can identify which proxy failed without extra lookups. Matches the existing gateway.forward_failed logging pattern.
 2026-07-14 19:32:49 +08:00
Heatherm Huang b32b815e46 fix(grok): harden OAuth pool recovery 2026-07-14 14:55:30 +08:00
Heatherm Huang 343390057d fix(grok): fail over OAuth credential errors safely 2026-07-14 14:55:30 +08:00
zh239ns 002c0b9fda fix(images): keep non-stream requests alive 2026-07-14 07:39:21 +08:00
Bestony@Homelab c8cfc93632 fix(openai-ws): bound ingress session lifecycle 2026-07-13 15:32:42 +08:00
Heatherm Huang 8a22dc7347 fix(grok): diagnose unavailable models by platform 2026-07-13 10:11:34 +08:00
shaw 8d51364c3d Merge remote-tracking branch 'origin/main' into feat/grok-prompt-cache-identity 
# Conflicts:
#	backend/internal/handler/endpoint.go
#	backend/internal/service/openai_gateway_grok_test.go
 2026-07-13 09:12:44 +08:00
superman2003 7050070aa3 fix(grok): route cacheable chat requests via responses 2026-07-12 11:50:56 +08:00
Tian Lee 84bb7d0709 fix: 保留 remote_compaction_v2 原生 Responses 链路 2026-07-11 12:51:53 +08:00
shaw ae9a01d852 fix(compact): 二轮审计加固——心跳字节不得污染 failover 判定与并发写安全 
对首轮修复的对抗式审计发现并修复以下问题：

1. failover 判定污染（真实回归风险）：handler 以 "Forward 前后
   c.Writer.Size() 是否变化" 判定响应是否已写出并据此放弃换号。心跳注释
   字节会使该判定恒真，compact 请求一旦在上游等待期间发过心跳，上游
   429/5xx 将不再 failover。新增
   OpenAICompactKeepaliveAdjustedWrittenSize（扣除心跳字节、互斥锁下
   一致读取、仅心跳字节归一化为未写哨兵 -1），快照、failover 比较与
   openAIForwardErrorAlreadyCommunicated 三处判定统一改用该口径；无心跳
   请求完全等价于原 c.Writer.Size()。

2. 并发写竞争：心跳 goroutine 与未被显式拦截的写回路径（Forward 内部
   本地拒绝等）存在 ResponseWriter 数据竞争。StartOpenAICompactSSE-
   Keepalive 现将 c.Writer 替换为 openAICompactKeepaliveWriter：写侧
   方法（Header/Write/WriteString/WriteHeader/WriteHeaderNow/Flush）
   先在互斥锁下停拍，读侧（Status/Size/Written）仅加锁不停拍——任何
   请求侧响应构造与心跳从构造上互斥，热路径状态读取不误杀心跳。

3. 语义拦截补齐：rejectIfCyberSessionBlocked（在用户槽位长等待之后
   执行的直接 c.JSON）与 writeOpenAIFastPolicyBlockedResponse 在心跳
   提交后降级为 response.failed 终止事件；未提交时先停拍再写 JSON，
   状态码语义不变。失败事件 errType 参数化（permission_error 等）。

4. reconstruct 混合形态：done 事件存在但 compaction 只在
   output_item.added 中时也要补入；done 已含 compaction 时跳过 added，
   避免无 id 可去重时收集两份（Codex 要求恰好一个）。

5. 观测性：logOpenAIRemoteCompactOutcome 对心跳提交后的失败（wire 200）
   以 GetOpsStreamError 纠正 outcome，不再误记 succeeded。

新增 5 个测试：failover 口径不变式、包装器停拍语义（-race）、fast
policy 提交前后两态、混合 done/added 形态（含去重）。

Refs #3887 #3777
 2026-07-10 10:18:16 +08:00
shaw 2cffe1cf5f fix(compact): SSE→JSON 保留 raw output_item.done 并为 unary 等待补下游心跳（修复 #3887） 
#3887 报告 v0.1.149（已含 #3880 桥接修复）remote compact 仍失败且持续
计费。核实为 #3880 明示的两个遗留：

1. 上游对 unary compact 返回 SSE 且 compaction item 只出现在 raw
   response.output_item.done、终态 completed.response.output 为空
   （#3777 实录形态）时，reconstructResponseOutputFromSSE 只累加
   text/function_call/reasoning 三类 delta，compaction item 被丢弃，
   桥接合成 0 个 output_item.done，Codex 报 "expected exactly one
   compaction output item, got 0" 后盲目重试，每次重试重新消耗上游
   compact 配额。
2. 桥接为全缓冲写回：上游 unary 完成前（大上下文可达数分钟，且上游
   处理期间不发送任何字节）下游连响应头都收不到，反向代理
   （Nginx/Cloudflare Tunnel）空闲超时掐断连接同样触发盲重连
   （同类问题见 #2243/#2976）。

修复：

- reconstructResponseOutputFromSSE 优先以 raw JSON 逐字节收集
  output_item.done item（协议上的最终完整形态），不经窄结构体，
  encrypted_content/summary/opaque 等 compact 专属字段全部保留；
  无 done 事件时退回收集 output_item.added 中的 compaction 类 item；
  两者皆无才回到原 delta 重建。path-based v1 JSON 写回同样受益。
- 新增 openAICompactSSEKeepalive：body-signal 客户端流式 compact 在
  上游等待期间按 gateway.stream_keepalive_interval 向下游写 SSE 注释
  行心跳（eventsource 解析层直接忽略）。首拍延迟一个间隔，快速失败
  仍走 JSON+状态码；首拍后状态码固化为 200，桥接/错误链路
  （writeOpenAICompactSSEBridge、errorResponse、
  handleStreamingAwareError、ensureForwardErrorResponse、
  writeOpenAINonStreamingProtocolError）统一降级为 response.failed
  终止事件并标记 ops 流内错误。
- API-key 账号的 compact 上游请求也强制 accept: application/json
  （#3777 期望行为 4；透传白名单原会放行客户端的 text/event-stream）。

测试：#3777 实录形态经 handleSSEToJSON / 透传 / path-based 三条链路
的修补断言；raw-done 优先不与 delta 重复；added 回退门控；心跳提交、
提交后 2xx 续写、提交后失败降级、未提交行为不变；-race 通过。

Fixes #3887
Refs #3777 #3875 #3880
 2026-07-10 09:56:56 +08:00