github/sub2api
4
0
Fork 0
mirror of https://github.com/Wei-Shaw/sub2api.git synced 2026-10-20 00:18:55 +00:00
Code Issues Packages Projects Releases Wiki Activity
7,318 Commits 49 Branches 63 Tags
v0.2.9
Commit Graph
7318 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Zhaofeng Li e35123b8ac fix(codex): include OpenCode Go in model capability resolution 2026-09-22 14:50:29 +08:00
Erik 7f1f85cb76 fix(gemini): stop cooling Vertex 429s until PST midnight, honor RetryInfo 
Vertex AI reports 429s with a standard google.rpc.RetryInfo detail
(retryDelay like "39s"), but ParseGeminiRateLimitResetTime only knew the
AI Studio quotaResetDelay metadata, so parsing always failed for Vertex
bodies. The fallback then lumped service_account accounts in with
API-key/AI-Studio ones and rate limited them until the next PST
midnight, so a transient per-minute throttle could take a pay-as-you-go
account (and with it the whole group) offline for up to a day.

- Parse google.rpc.RetryInfo retryDelay from 429 bodies, capped at 15
  minutes to guard against absurd upstream values.
- When no reset time can be parsed, cool service_account (Vertex)
  accounts down for 60s instead of until PST midnight: pay-as-you-go
  quotas are short-window RPM/TPM with no daily reset.

Fallback behavior for Code Assist, Google One and API-key accounts is
unchanged, covered by new regression tests.
 2026-09-22 11:31:31 +08:00
nagi330 935db68517 feat(grok):add grok 4.7 support 2026-09-22 10:30:01 +08:00
Wesley Liddick 1c0a69c0ce Merge pull request #7412 from StarryKira/codex/custom-reasoning-effort-billing 
feat: 支持自定义思考等级倍率计费
 2026-09-21 22:55:17 +08:00
lcy 27f4398b50 fix(antigravity): 裸 Gemini 模型名在所有转发入口解析到思考变体 
#7258 引入的 resolveGeminiThinkingVariant 只接到了 ForwardGemini，
因此仅覆盖 /v1beta 原生 Gemini 路径。经 /v1/chat/completions 与
/v1/messages 进来的请求直接调用 getMappedModel，裸名被原样透传；
Antigravity 目录只登记 -low/-medium/-high/-tiered 变体，这些请求
仍然以 404 "Requested entity was not found." 失败。

把解析下沉到 getMappedModel（新增 getMappedModelForThinkingLevel），
一次覆盖四个调用点：/v1beta 原生、/v1/chat/completions、/v1/messages
以及后台账号连接测试。各转发入口按自身协议推导档位——原生读
generationConfig.thinkingConfig，Claude 侧读 thinking.budget_tokens，
两者阈值一致；默认入口按 high 兜底。

mapAntigravityModel 保持不变，调度侧的模型支持判定语义不受影响。
 2026-09-21 20:13:44 +08:00
haruka e47255715d fix(billing): preserve final reasoning effort across forwarding paths 2026-09-21 19:58:02 +08:00
feeeei d0ed0eacac fix(gemini): 传输层错误转 failover,不再同账号退避重试 
上游 Do 返回非 HTTP 错误(代理/DNS/TCP/TLS/响应头超时)时,Gemini 三条转发路径
(ForwardNative / Forward / ForwardAsChatCompletions)原先在同一账号上重试 5 次,
退避 1+2+4+8≈15s(time.Sleep 不感知 ctx),耗尽后直接向客户端写 502 且不换号:
单账号链路故障期间 TTFT 被整段拖高,同组健康账号闲置。

对齐 Anthropic/Bedrock 侧 handleUpstreamTransportError 的既有语义:
- 传输层错误单次尝试后即返回 *UpstreamFailoverError(502),由 handler failover
  循环换号,耗尽后才按端点格式渲染错误;service 不再写响应
- 持久性故障(connection refused/no route/DNS not found/代理认证失败)额外临时
  摘除账号 10 分钟;瞬时故障(EOF/reset/超时)只换号不摘号
- context.Canceled 保持原样返回:不换号也不摘账号
- countTokens 传输失败时立即本地估算兜底,不换号
- 摘号实现抽为 tempUnscheduleAccountForTransportError 供两侧共用,日志事件名不变

HTTP 状态码(429/5xx)的服务内重试环未改动。
 2026-09-21 14:13:57 +08:00
wucm667 386f321d3c fix(usage): export missing reasoning effort cleanly 2026-09-21 12:41:01 +08:00
wucm667 60a64568bf ci: run simple mode compose environment test 2026-09-21 11:06:25 +08:00
wucm667 de98bdff1e fix(images): preserve insufficient balance failures 2026-09-21 10:23:10 +08:00
wucm667 992c4f4b89 test(frontend): run platform quota modal spec in CI 2026-09-21 08:16:18 +08:00
shaw 7c700729c2 chore: update gitignore 2026-09-20 20:05:09 +08:00
Wesley Liddick 87957a608b Merge pull request #7413 from ranxi2001/ci/release-build-matrix 
ci: parallelize release builds across platform runners
 2026-09-20 20:02:48 +08:00
xlplbo 0d02000592 fix(openai): 非高级调度按 previous_response 路由到持有响应的账号 2026-09-20 19:28:13 +08:00
xlplbo 8d88b66668 fix(openai): 补齐非高级调度选号决策标签 2026-09-20 19:27:53 +08:00
xlplbo 763443abf2 fix(openai): 改写 Codex turn metadata 时保留非 ASCII 转义 2026-09-20 19:27:47 +08:00
chihao.ou 7f18f3e9af fix(users): keep API key results scoped to the selected user 2026-09-20 18:09:50 +08:00
chihao.ou b86849e442 fix(usage): ignore superseded error detail requests 2026-09-20 18:07:52 +08:00
chihao.ou 319299519b fix(monitor): preserve the saved auto-refresh preference 2026-09-20 18:07:39 +08:00
chihao.ou 23a1d38187 fix(pricing): parse scientific notation in token bounds 2026-09-20 18:05:23 +08:00
chihao.ou 1582347204 fix(payment): trim callback base URL trailing slashes 2026-09-20 18:05:09 +08:00
ranxi2001 d1556a7a96 ci: point release helper tests at their final directory 2026-09-20 17:01:27 +08:00
ranxi2001 d2416a9b68 ci: keep release tooling and cache keys stable across jobs 2026-09-20 16:54:06 +08:00
HuntercodeT fb58dfbd93 test(antigravity): cover the identity rewrite end-to-end through the transformer 
Adds a case with the real block layout (attribution block, identity sentence,
task instructions) and asserts that user content mentioning Claude Code and
claude-sonnet-4-6 is forwarded unchanged.
 2026-09-20 16:48:04 +08:00
haruka b8d52fad34 feat(billing): support configurable reasoning effort multipliers 2026-09-20 16:41:49 +08:00
shaw d2e319b2a1 test: 修复 WebSocket 同线程抢占测试的关闭时序竞态 2026-09-20 16:37:07 +08:00
ranxi2001 0892ef3a9a ci: build release targets on independent matrix runners 2026-09-20 16:36:24 +08:00
HuntercodeT dd292e3b00 fix(antigravity): neutralize Claude Agent SDK identity in system prompts 
Stripping the x-anthropic-billing-header line is not enough. Claude Code's
Agent SDK prompts (session title generation, and other SDK-driven calls) open
a separate system block with

    You are a Claude agent, built on Anthropic's Claude Agent SDK.

and the Google upstream still rejects those requests with 429 RESOURCE_EXHAUSTED.

Measured on Sub2API 0.2.7, which already contains the attribution fix, using an isolated single-account group, waiting for the per-model cooldown
to expire before every request so that a previous failure could not turn later
results into 503:

  original request replayed                      429 (8/8)
  same request, generic system prompt            200 (8/8)
  attribution also removed client-side           429 (3/3)
  attribution removed + identity neutralized     200 (3/3)
  only 'Claude' replaced in system               200 (2/2)
  only 'Anthropic' removed from system           200 (2/2)
  output_config / max_tokens / non-stream        no effect

The rewrite is anchored at the start of a system block, so user instructions that
merely mention Claude or Anthropic, and model ids such as claude-sonnet-4-6, are
left untouched. Scoped to the Antigravity transformer, as with the existing
attribution handling.
 2026-09-20 16:34:26 +08:00
shaw 95134201b2 docs: 删除误合入的 Codex 积分文档和截图 2026-09-20 16:12:11 +08:00
Wesley Liddick acdf3c54da Merge pull request #7401 from StarryKira/codex/codex-credits-referrals-upstream 
feat(openai): display Codex credits and support referral invitations
 2026-09-20 16:00:28 +08:00
haruka fc96132e72 fix(openai): harden referral outcomes and isolate HTTP transport 2026-09-20 15:47:53 +08:00
haruka 8f6bbb59c7 test: stabilize Gemini keepalive test 2026-09-20 15:04:15 +08:00
Wesley Liddick fbb9006ade Merge pull request #7402 from Wei-Shaw/fix/7268-openai-http2-keepalive 
fix(upstream): 恢复 OpenAI HTTP/2 保活容错期限
 2026-09-20 14:57:35 +08:00
shaw e009ea3036 fix(upstream): 恢复 OpenAI HTTP/2 保活容错期限 2026-09-20 14:46:25 +08:00
a408665321 63c079d873 fix(account): preserve settings on OAuth reauth 2026-09-20 14:39:36 +08:00
haruka e509937382 docs: add Codex referral UI validation screenshots 2026-09-20 14:38:30 +08:00
haruka 5090ffe05e feat(openai): show Codex credits and manage referral invitations 2026-09-20 14:38:29 +08:00
Wesley Liddick bbdcfbac0a Merge pull request #7304 from wucm667/fix/issue-7298-response-model-alias 
fix(gateway): restore public response model aliases
 2026-09-20 14:07:16 +08:00
Wesley Liddick 7403a01177 Merge pull request #7314 from wucm667/fix/issue-7306-keyword-reminder-bypass 
fix(moderation): prevent reminder tags from bypassing keyword checks
 2026-09-20 14:07:04 +08:00
Wesley Liddick 53b4bbe736 Merge pull request #7349 from wucm667/fix/issue-7348-preserve-client-version 
fix(settings): preserve client version on invalid user agent
 2026-09-20 14:06:48 +08:00
Wesley Liddick 8bb48622a3 Merge pull request #7362 from wucm667/fix/issue-7358-preserve-account-errors 
fix(accounts): preserve refresh errors during usage queries
 2026-09-20 14:06:36 +08:00
Wesley Liddick f28adb6ddb Merge pull request #7387 from Brisbanehuang/codex/upstream-content-audit-typesafe 
feat: 内容审计接入 TypeSafe AI，支持双引擎切换与独立配置
 2026-09-20 13:47:14 +08:00
Wesley Liddick 19794bc46a Merge pull request #7397 from Wei-Shaw/feat/hostservice-account-metadata 
feat(pluginapi): HostService 账号目录返回结构化只读元数据
 2026-09-20 11:39:15 +08:00
shaw 29eead917f feat(pluginapi): HostService 账号目录返回结构化只读元数据 
纯宿主侧改动，向后兼容。

- 契约(pkg/pluginapi/v1/plugin.proto，已重新生成)：ListAccounts 增补
  repeated AccountInfo accounts（保留 account_ids 向后兼容），新增 metadata_json
  只读快照字段。HostServiceAPIVersion 1→2（InitHostServices 运行时协商，加法式，
  旧调用方忽略新字段即可）。
- 权限边界：可见范围由清单能力经 pluginCapabilityAccountScopeGrants 推导，
  ListAccounts 与 ResolveOutboundIdentity 均以该范围为权威边界。
- metadata_json 采用 denylist：剥离 Credentials 与含反向引用的关联对象
  Groups/AccountGroups（避免 encoding/json 循环引用），其余字段自动透传，
  数据模型新增非机密字段无需改宿主。

测试：范围/元数据/无凭据泄漏用例、denylist 反射护栏 + 循环引用安全断言、纵深过滤用例；
build/vet/gofmt、-tags unit 与 -race 全绿。
 2026-09-20 11:26:19 +08:00
zhuzhihaocool-bit fabdfb8a5b fix(frontend): ensure Codex base URLs include /v1 2026-09-20 11:07:29 +08:00
Achord Chan 1411b7eb7e fix(gateway): recognize Baseten reasoning budget errors 2026-09-20 11:02:06 +08:00
Achord Chan ef51690b5a fix(antigravity): preserve string const constraints in tool schemas 2026-09-20 10:46:09 +08:00
Brisbanehuang 1bfe0d3728 fix: sync draft audit key status and threshold defaults 2026-09-19 20:52:31 -04:00
Brisbanehuang 783a0a9830 feat(content-audit): add independent TypeSafe engine profiles 2026-09-19 20:52:31 -04:00
chihao.ou cd2a4357c2 fix(groups): reject negative custom rates before adding 2026-09-19 19:43:39 +08:00