github/sub2api
4
0
Fork 0
mirror of https://github.com/Wei-Shaw/sub2api.git synced 2026-10-26 08:02:08 +00:00
Code Issues Packages Projects Releases Wiki Activity
4,593 Commits 49 Branches 64 Tags
0f2ec134b5eb8bcaa67a06aa920b014d18a4e309
Commit Graph
2431 Commits
Author SHA1 Message Date
bestonyandmultica-agent 0f2ec134b5 fix(ops): bound indexed log host length 
Co-authored-by: multica-agent <github@multica.ai>
 2026-07-14 01:29:47 +08:00
bestonyandmultica-agent 2c2e50ba58 feat(ops): add host filtering to system logs 
Co-authored-by: multica-agent <github@multica.ai>
 2026-07-14 01:29:46 +08:00
Wesley Liddick 7d239d62e8 Merge pull request #4173 from heathermhuang/codex/fix-grok-oauth-media-routing 
fix(grok): keep OAuth media on the official API
 2026-07-13 17:37:00 +08:00
Heatherm Huang bb73416733 fix(grok): route OAuth media through official API 2026-07-13 17:08:55 +08:00
Bestony 5aeb03018c fix(scheduler): cool down Codex plan-gated models per account 
OpenAI OAuth (ChatGPT) accounts deterministically reject plan-gated
models with 400 "The 'X' model is not supported when using Codex with
a ChatGPT account". Account selection had no capability filtering for
this, so the scheduler kept picking the same account for the same model
forever; every attempt burned an upstream call and surfaced to clients
as a retryable 502, sustaining client retry storms.

Treat this 400 like upstream model-not-found: mark the (account, model)
pair via SetModelRateLimit (30min cooldown) so
IsSchedulableForModelWithContext skips the account for that model
during selection, and return true so the in-flight request fails over
to another account through the existing UpstreamFailoverError path.
 2026-07-13 16:29:18 +08:00
Wesley Liddick a2bc133747 Merge pull request #4163 from bestony/fix/openai-ws-ingress-lifecycle 
fix(openai-ws): bound ingress session lifecycle
 2026-07-13 16:07:53 +08:00
Wesley Liddick 540e90ca8b Merge pull request #4162 from heathermhuang/codex/fix-grok-third-party-api 
fix(grok): allow third-party API base URLs
 2026-07-13 16:07:36 +08:00
Bestony@Homelab c8cfc93632 fix(openai-ws): bound ingress session lifecycle 2026-07-13 15:32:42 +08:00
Wesley Liddick b0d0de0547 Merge pull request #4045 from xiaopixiu2019/codex/upstream-gpt56-oauth-test 
fix: normalize GPT-5.6 alias in OpenAI OAuth account tests
 2026-07-13 15:31:44 +08:00
Heatherm Huang bc5d6ecb46 fix(grok): allow third-party API base URLs 2026-07-13 15:27:57 +08:00
shaw 8315defe8e Merge branch 'main' into feat/grok-video-edit-extension 2026-07-13 14:50:18 +08:00
Wesley Liddick d774948e09 Merge pull request #4082 from zuelu/agent/fix-codex-additional-tools-chat-bridge 
fix(apicompat): 支持 Codex additional_tools 到 Chat Completions 桥接
 2026-07-13 14:42:16 +08:00
Heatherm Huang b0441ca5aa fix(grok): support upstream model sync for API keys 2026-07-13 11:46:52 +08:00
chenjian 909b96edd2 feat: support Grok video edits and extensions 2026-07-13 10:50:42 +08:00
Wesley Liddick b73d8c3efe Merge pull request #4009 from heathermhuang/codex/fix-recent-grok-issues 
fix: expand Grok API, CLI, billing, and setup support
 2026-07-13 10:36:11 +08:00
Heatherm Huang f73031f436 test(grok): align scheduling reasons with upstream 2026-07-13 10:21:34 +08:00
shaw 64a2a31729 fix(billing): 修复复审发现的三处按次计费问题 
- HIGH: GetByKeyForAuth 的 WithGroup 显式 Select 补 web_search_price_per_call 列，
  否则 auth 快照里分组覆盖价恒为 nil，覆盖价/免费配置在实际计费中静默失效
- MEDIUM: 按次搜索倍率改用不含高峰因子的基础倍率（与 image/video 按次不变式
  及分组表单价格预览承诺一致），calculateOpenAIRecordUsageCost 新增独立倍率参数
- LOW: 计费门槛从 <400 收紧为严格 2xx，1xx/3xx 透传不计费
 2026-07-13 10:14:53 +08:00
Heatherm Huang aeb34d2003 fix(grok): sanitize composer reasoning parameters 2026-07-13 10:11:33 +08:00
Heatherm Huang f187f08ae3 fix(grok): harden OAuth routing and CLI version guard 2026-07-13 10:11:33 +08:00
Heatherm Huang 3375b4ed2b fix(grok): route OAuth subscriptions through CLI proxy 2026-07-13 10:11:33 +08:00
Heatherm Huang d9e466ad3a feat(grok): support xAI API key accounts 
Allow Grok API-key accounts in Responses forwarding and connection tests, expose creation and edit defaults in the dashboard, and document the supported setup.
 2026-07-13 10:11:33 +08:00
Heatherm Huang 038b25c0b1 fix(grok): resolve recent integration issues 2026-07-13 10:09:53 +08:00
shaw 7cbb36f278 feat(billing): Codex alpha/search 网页搜索按次计费 
- alpha/search 成功请求（上游 2xx）按次计费落 usage_logs（billing_mode=per_request），
  上游错误透传/failover 不计费；使用 mandatory 池提交，池满同步兜底不丢扣费
- 单价默认 0.01 USD/次（官方 $10/1000 次），分组新增 web_search_price_per_call
  覆盖价（0=免费，负数/留空=默认价），实际扣费叠加分组费率倍数（与 token 口径一致）
- 分组字段全链路：ent schema + 迁移 174 + 端口快照 v15 + admin 创建/更新 + DTO
- 前端分组表单（openai 平台）新增单次价格配置，实时预览应用当前倍率后的单次价格
- 该端点鉴权维持仅 OpenAI 分组（非 OpenAI 分组 404）
 2026-07-13 09:54:51 +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
Wesley Liddick 33b1d772f7 Merge pull request #4063 from yardbirds0/fix/codex-alpha-search 
fix: 转发 Codex alpha/search 独立搜索端点
 2026-07-13 08:58:01 +08:00
Wesley Liddick 1c214eaca4 Merge pull request #4059 from visa2/fix/openai-messages-codex-identity 
fix(openai): restore Codex identity headers for OAuth Messages
 2026-07-13 08:56:21 +08:00
Wesley Liddick 841481e051 Merge pull request #3971 from yardbirds0/codex/fix-remote-compaction-v2 
fix: 保留 remote_compaction_v2 原生 Responses 请求链路
 2026-07-13 08:54:53 +08:00
Wesley Liddick 2f4478fd32 Merge pull request #4019 from wucm667/fix/compact-keepalive-writer-nil-guard 
fix(service): 补齐 compact keepalive writer nil 守卫
 2026-07-13 08:54:31 +08:00
Wesley Liddick 877bee84a1 Merge pull request #4072 from jianjianai/codex/fix-upstream-review 
修复 tool_search 参数解析与 compact writer 生命周期
 2026-07-13 08:54:15 +08:00
superman2003 7050070aa3 fix(grok): route cacheable chat requests via responses 2026-07-12 11:50:56 +08:00
zuelu ff5c216189 fix(apicompat): bridge Codex additional tools 2026-07-12 11:33:09 +08:00
jjaw 06af8115f7 修复 compact 心跳 writer 生命周期 2026-07-12 04:53:41 +08:00
visa2 d5b47c2142 fix(openai): restore Codex identity for OAuth Messages 2026-07-11 20:47:52 +08:00
superman2003 1dedb2097d fix(grok): persist quota exhaustion as rate limit 2026-07-11 20:41:32 +08:00
Tian Lee 52071d391b fix(openai): 转发 Codex alpha/search 独立搜索端点 2026-07-11 20:31:33 +08:00
superman2003 0478fd3668 feat(grok): enable free OAuth prompt caching 2026-07-11 19:34:01 +08:00
xiaopixiu2019 51de58b37f fix: normalize GPT-5.6 alias in OpenAI OAuth account tests 2026-07-11 15:39:32 +08:00
Tian Lee 84bb7d0709 fix: 保留 remote_compaction_v2 原生 Responses 链路 2026-07-11 12:51:53 +08:00
wucm667 6e2bb31281 fix(service): guard compact keepalive writer delegates 2026-07-11 08:52:46 +08:00
wucm667andClaude Opus 4.8 4d4ba64bf7 fix(codex): 剥离续链 message item 的非法 item_* id 
OpenAI OAuth 转发续链请求时，type=message 的 item 的 id 被客户端以
item_* 形式回放，但上游要求以 msg 开头，返回 400
"Expected an ID that begins with 'msg'"，sub2api 随后向客户端返回 502。
客户端自动重试会不断重放同一份坏上下文，导致连续失败。

filterCodexInputWithOptions 在 PreserveReferences=true 路径下为
type=message 增加与 #3785 (fd64d07e6) 平行的 id 前缀检查：非 msg 开头
即删除。合法的 msg* id 原样保留，不改写 item_* 为 msg_*，因为改写出的
id 未必对应真实上游对象。

原 TestFilterCodexInput_NonToolCallItemKeepsID 以 message + item_msg_001
断言"保留 id"，该行为已被上游拒绝，改用 web_search_call 覆盖同一意图。

Fixes #3981

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
 2026-07-10 23:32:34 +08:00
xlplbo eb4d005031 Merge remote-tracking branch 'upstream/main' 2026-07-10 20:46:38 +08:00
shaw 8a51119e39 fix(openai): pair originator with final User-Agent for codex upstream 
上游 /backend-api/codex 的 404 gating 是配套校验：originator 必须与
User-Agent 首段（首个 '/' 前的 client 名）配套且为官方 codex 身份，
错配（如 originator=codex_cli_rs + UA=codex-tui/...）一律 404；version
头若携带须 >= 0.144.0。

修复：
- pkg/openai 新增 PairCodexClientIdentity：由最终出站 UA 推导配套
  originator（含 CODEX_INTERNAL_ORIGINATOR_OVERRIDE 尾部括号组身份恢复、
  精确集合大小写归一、长度/字符集校验）
- service 新增 enforceCodexIdentityHeaders 终态收口：originator 按最终
  UA 重配，推导不出官方身份整体回退默认 Codex CLI 身份；version 低于
  0.144.0 提升为内置版本；originator 缺失时 no-op（保护 messages bridge）
- 接入非透传/透传/WS 三条转发路径（透传与 WS 删除会把 codex-tui 等官方
  UA 强改为 codex_cli_rs 造成错配的旧兜底）、用量探针（指纹缓存 UA 与硬
  编码 originator 错配）、账号 responses/图像测试（opencode 错配）
- messages 兼容桥构建前显式打 bridge 标记，防止映射到非 gpt-5/codex
  模型时收口误改其刻意最小化的请求形态

Fixes #3901
 2026-07-10 19:11:26 +08:00
xlplboandClaude Fable 5 7942338328 fix(apicompat): 回程还原 namespace 子工具调用，修复 Codex MCP 工具 unsupported call 
Codex 0.14x 将 MCP 工具声明为 namespace 工具，chat 桥去程摊平为
"<namespace>__<name>" function 工具后，回程仅原样回传平铺名的
function_call 项；codex 按 namespace+name 路由查不到该名字，所有
MCP 工具调用被判为 unsupported call。

- NamespaceToolNames 构建摊平名 →（namespace, 子工具名）反查表
  （摊平名超长带截断哈希，无法按字符串切分还原）
- 非流式/流式回程命中映射时还原为裸子工具名 + namespace 字段，
  ResponsesOutput 新增 Namespace 字段并同步 wire 层白名单
- 回退桥入口将映射与 CustomTools/ToolSearchDeclared 一并穿入

已在测试机经 codex exec + MCP server 端到端验证。

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NWQyEgFKKbdve67G6qCoAU
 2026-07-10 17:38:17 +08:00
Wesley Liddick 5260a42a0b Merge pull request #3953 from lyon-le/feat/openai-fast-policy-user-scope 
feat(openai): 支持用户级 Fast/Flex 策略
 2026-07-10 17:31:55 +08:00
Wesley Liddick 815516d8d3 Merge pull request #3969 from jinfeijie/fix/grok-responses-reasoning-effort 
fix(grok): preserve compatible reasoning effort
 2026-07-10 17:31:41 +08:00
jinfeijie bot 5a0dd510e5 fix(grok): remove obsolete helper 2026-07-10 17:11:04 +08:00
jinfeijie bot 0fa1eb85ec fix(grok): preserve compatible reasoning effort 2026-07-10 16:58:17 +08:00
Wesley Liddick 6dd3274aaf Merge pull request #3948 from superman2003/fix/gpt56-billing-usage-integrity 
fix(openai): correct GPT-5.6 billing and usage gaps
 2026-07-10 15:45:18 +08:00
Wesley Liddick d0f6f27d5f Merge pull request #3941 from Tassoi/codex/fix-image-gen-namespace-strip 
fix(image): strip Codex image_gen namespace declarations
 2026-07-10 15:45:05 +08:00
Wesley Liddick 6a2063b374 Merge pull request #3883 from ShuminFu/fix/setup-token-auto-refresh 
fix: 后台自动刷新纳入 setup-token 账号（修复 8h 后 401）
 2026-07-10 15:44:54 +08:00