github/sub2api
4
0
Fork 0
mirror of https://github.com/Wei-Shaw/sub2api.git synced 2026-10-28 00:07:33 +00:00
Code Issues Packages Projects Releases Wiki Activity
6,121 Commits 49 Branches 64 Tags
83d4eb6a43d57d02269899d2cf7a2af257da088b
Commit Graph
3345 Commits
Author SHA1 Message Date
feeeei 83d4eb6a43 模型广场：增加渠道分时段计价展示 
- 阶梯表查询附带分时倍率时段：时段取自计费解析到的渠道定价，
  每个时段的倍率由计费的 resolvedChannelTimeMultiplier 在时段内取值，
  分组价卡覆盖或配置非法时自然不出现；倍率为 1 的时段不列
- 广场模型条目新增 time_pricing（时区 + 时段 + 倍率）
- 前端把分时时段展开为独立行：模型名旁标注时段，价格按时段倍率折算，
  倍率列显示生效倍率；时区与计算口径放在提示中
 2026-08-24 10:50:52 +08:00
feeeei ecce0769c0 模型广场：上下文档位统一标签形态并保证升序 
- 阶梯表标签由计费层统一生成：有上限的档为「≤上限」、末档为「>下限」
  （达到阈值即进高档时用 < / ≥），不再沿用渠道区间的自定义 tier_label；
  合并同价段只看单价
- 前端档位按下限升序兜底展示，无标签时按同一形态生成
 2026-08-24 10:50:52 +08:00
feeeei 377d1230fc 模型广场：按计费阶梯单价表展示长上下文档位 
- 新建 ModelPlazaService（持计费服务与定价解析器）承接广场聚合，
  token 模型的单价与档位全部取自 ResolveContextPricingSchedule，
  渠道选择与计费同源；图片/按次模型沿用原档位合成
- 官方参考价改走计费目录（LiteLLM → 内置兜底 → 模型策略），带官方阶梯
- DTO 增加 long_context_pricing_enabled / long_context_basis /
  official_pricing.intervals
- 前端实付与官方三列按档分行（标签只在首列，其余列按行对齐），
  缓存列按档展示写/读价，边际计价以徽章与 tooltip 标注，
  分组关闭阶梯时在头部说明
 2026-08-24 10:50:52 +08:00
feeeei 6466978d2f 计费：统一 token 计费路径选择并提供上下文阶梯单价表查询 
- BillingService.CalculateTokenCostForRequest 承接网关的路径选择
  （分组/渠道定价 → 平台旧长上下文规则 → 内置目录），网关改为调用该入口
- Gemini /v1beta 的 200K 边际翻倍常量从 handler 移入
  BillingService.LegacyLongContextRule，入口只声明适用
- 新增 ResolveContextPricingSchedule：沿用 Resolve 解析链收集断点
  （渠道区间边界、目录阶梯阈值、旧规则阈值），每档单价由真实计费函数
  探针差商得出，倍率/策略变更无需同步；附阶梯表 vs 计费函数的对账测试
 2026-08-24 10:50:52 +08:00
Wesley Liddick 3b8a148bcf Merge pull request #6111 from feeeei/fix/request_billing 
fix(billing): bill fast mode by the tier upstream actually served
 2026-08-24 10:43:17 +08:00
Wesley Liddick 3e45d4e030 Merge pull request #6089 from lyen1688/feat/channel-time-pricing-weekdays 
新增渠道时间段定价工作日生效规则
 2026-08-24 10:21:47 +08:00
shaw 40aaf7b3ae fix: handle plugin route health update errors 2026-08-24 10:02:06 +08:00
shaw 684d9efb1f fix: harden plugin runtime and UI bridge 2026-08-24 09:50:46 +08:00
shaw 40ea3aebad feat: add OAuth outbound transport plugin system 2026-08-24 09:03:37 +08:00
feeeei 75faedda95 计费：fast/priority 按上游响应实际档位只降不升计费 
此前 OpenAI service_tier 与 Anthropic speed 的计费档位只看请求侧，上游
因容量把 priority/fast 静默降为 default/standard 时仍按 2x 收费。现在：

- upstreamResponseModelObserver 同时观察响应侧档位：OpenAI 只信终止事件
  与无类型 body 里的 service_tier（response.created 为请求回显，忽略），
  Anthropic 读 usage.speed；查找仅在带 model 的帧上触发
- ResolveBillingServiceTier 只降不升：响应档位比请求便宜才采纳，更贵、
  未知或缺失一律沿用请求侧，与图片尺寸归并、response_model 计费的
  "不得更贵"不变式一致
- usage_logs.service_tier 记录实际计费档位，降级写
  billing.service_tier_downgraded 审计日志；HTTP、WS 及 ws_v2 relay 全覆盖
 2026-08-23 16:53:28 +08:00
lyen1688 77e0409f7c 新增渠道时间段定价工作日规则 2026-08-23 00:30:27 +08:00
Wesley Liddick d45135d87d Merge pull request #6068 from okbexx/fix/codex-guardian-parent-affinity 
fix(openai): keep auto-review on parent account
 2026-08-22 13:41:42 +08:00
Wesley Liddick d29d7f8cbc Merge pull request #6065 from chinnsenn/fix/image-generation-flows 
fix(openai): stabilize oauth image generation
 2026-08-22 13:35:26 +08:00
Wesley Liddick fd6cd474d6 Merge pull request #5846 from lbyxiaolizi/fix/responses-chat-malformed-tool-arguments 
fix(apicompat): reject malformed tool-call arguments
 2026-08-22 13:35:02 +08:00
Wesley Liddick 73f6a590bf Merge pull request #5912 from xuhaihan/fix/deepseek-responses-client-tools 
fix(deepseek): adapt Codex client tools for Responses
 2026-08-22 13:34:49 +08:00
Wesley Liddick ffc01f9c66 Merge pull request #5864 from wucm667/fix/issue-5850-http-bridge-replay 
fix(openai): avoid duplicate HTTP bridge replay
 2026-08-22 13:34:32 +08:00
Wesley Liddick 844b118785 Merge pull request #5938 from Hakunm/fix/google-one-model-catalog 
fix(gemini): 限制 Google One OAuth 模型目录 / constrain Google One model catalog
 2026-08-22 13:34:05 +08:00
alfadb 86470628df feat(ollama): 对 Ollama Cloud 账号 clamp max_tokens 上限 2026-08-22 12:38:05 +08:00
Jarl fa4587041c fix(openai): keep auto-review on parent account 2026-08-22 12:14:19 +08:00
chinnsenn cb8dabc12f fix(openai): stabilize oauth image generation 2026-08-22 11:21:39 +09:00
alfadb b30651a0ad fix(ollama): 对齐 Cloud Chat Completions 思维字段为 reasoning_content 
Ollama Cloud 的 raw /v1/chat/completions 把思维放在 reasoning/thinking，
DeepSeek 客户端只认 reasoning_content。仅对 openai+apikey+force_chat_completions
且具备 Ollama Cloud 信号的账号，在 raw CC 直转路径做 wire JSON 双向补齐。
 2026-08-22 09:26:23 +08:00
xuhaihan cef18b4ad3 fix(deepseek): route client tools through native responses 2026-08-22 01:04:11 +08:00
xuhaihan 30ae15268f Merge remote-tracking branch 'origin2/main' into fix/deepseek-responses-client-tools 2026-08-22 00:52:33 +08:00
Wesley Liddick 67380eafd5 Merge pull request #5549 from zcxads666/fix/openai-capabilities-empty-set 
fix(openai): 允许空 openai_capabilities 的 OAuth 账号加入文本调度
 2026-08-21 21:53:27 +08:00
Wesley Liddick 2ddda67354 Merge pull request #6049 from MokoYee/fix/openai-sticky-prefix-system 
修复 OpenAI Chat 动态系统消息导致账号亲和漂移
 2026-08-21 21:34:57 +08:00
zcxads666 40c26f343a fix(openai): 空 openai_capabilities 不再排除 OAuth 账号的文本调度（#5530） 2026-08-21 21:30:40 +08:00
Wesley Liddick fb56bcbd07 Merge pull request #5913 from xuhaihan/fix/deepseek-responses-account-test 
fix(deepseek): route Responses account tests through OpenAI probe
 2026-08-21 21:27:01 +08:00
Wesley Liddick ccfced36ae Merge pull request #6011 from HypoxanthineOvO/fix/cn-anthropic-protocol-account-test 
fix(accounts): route CN provider anthropic-protocol tests to the native endpoint
 2026-08-21 21:24:38 +08:00
Wesley Liddick 77d8516e87 Merge pull request #5911 from xuhaihan/fix/deepseek-relay-balance-validation 
fix(deepseek): reject invalid relay balance payloads
 2026-08-21 21:24:21 +08:00
Wesley Liddick afa21336a5 Merge pull request #6048 from wucm667/fix/issue-5886-composite-messages-dispatch 
fix: allow messages dispatch for composite groups
 2026-08-21 21:24:06 +08:00
MokoYee e45490a360 fix(openai): stabilize chat sticky hash across dynamic system messages 2026-08-21 18:11:18 +08:00
wucm667 68653fb2cc fix: allow messages dispatch for composite groups 2026-08-21 18:01:16 +08:00
Wesley Liddick fd24923f61 Merge pull request #5685 from Monster-DP/main 
fix(gateway): 修复池模式同账号错误重试
 2026-08-21 17:49:07 +08:00
Wesley Liddick f96035462f Merge pull request #5612 from wucm667/fix/issue-5611-antigravity-paid-tier-endpoint 
fix(antigravity): route paid accounts to daily endpoint
 2026-08-21 17:40:39 +08:00
Wesley Liddick 6816c63883 Merge pull request #5906 from feeeei/main 
fix(test): CN 供应商额度探测 fake 加锁消除并发 append 竞态
 2026-08-21 17:39:03 +08:00
Wesley Liddick 9f74eb57f4 Merge pull request #5919 from clearmann/fix/cn-native-anthropic-reasoning-effort 
fix(gateway): 记录国产厂商原生 Anthropic 直通路径的 reasoning_effort
 2026-08-21 17:38:52 +08:00
Wesley Liddick 98d60931c1 Merge pull request #5954 from StarryKira/codex/fix-5945-upstream 
fix: preserve native max reasoning effort
 2026-08-21 17:38:39 +08:00
HypoxanthineOvO a749673de3 fix(accounts): route CN provider anthropic-protocol tests to the native endpoint 
CN-provider accounts explicitly configured with api_protocol=anthropic
(the frontend offers per-provider presets such as GLM Anthropic) fell
through the account-test router to the generic Claude tester, which:

- appended ?beta=true, which the native passthrough deliberately avoids
  for third-party Anthropic endpoints, and
- defaulted a missing base_url to https://api.anthropic.com — sending
  the provider's API key to Anthropic instead of the provider's own
  Anthropic-compatible endpoint (guaranteed 401 plus cross-provider
  credential exposure).

Route them to a dedicated probe that mirrors the adaptive Anthropic
check: resolve the endpoint via GetAnthropicProtocolBaseURL (same
resolution as real /v1/messages forwarding, including per-platform
defaults), use the shared API-key auth header, and mark 401/403 as the
account error state.

Also fail fast with an actionable hint when the anthropic-protocol
base_url still points at an OpenAI-compatible endpoint (paas path,
version segment, or chat/completions suffix): the naive {base}/v1/messages
join would 404 (e.g. /api/paas/v4/v1/messages) without any pointer to
the actual misconfiguration.
 2026-08-21 16:37:25 +08:00
haruka d5824f6a5b fix: preserve native max reasoning effort 2026-08-21 14:24:32 +08:00
IanShaw 1429e8f714 修复 PR 5888 剩余审计问题 2026-08-20 22:01:20 -07:00
IanShaw b2b2adcf8d 修复 PR 5888 审查发现的兼容性与竞态问题 2026-08-20 21:06:48 -07:00
IanShaw027 7e9af4c100 将 compact fallback 的流式重试改为循环，避免递归重置单次重试标志 2026-08-21 08:55:04 +08:00
IanShaw027 7c53a842e4 合并上游 main，保留 5925 的 Grok 重试上限与 5888 的协议兼容修复 
同账号重试采用次数上限加 deadline；畸形 tools 在出站前删除；compaction 422 与结构化错误扫描一并保留。
 2026-08-21 08:49:44 +08:00
Hakunm f98a056f75 fix(gemini): constrain Google One model catalog 2026-08-21 02:33:00 +08:00
IanShaw 1bff06ea50 修复 Grok Realtime 关闭检查与 rollup 时区断言 
golangci 要求检查 Realtime 上游 Close 返回值，并删除已无调用的 heavy-model 冷却函数。分组日汇总集成测试在 UTC 晚上跨上海零点时会把水位写成 UTC 日期，将会话时区钉到 Asia/Shanghai。
 2026-08-20 09:50:23 -07:00
IanShaw 2e68b10aad 完善 Grok 内容拒绝计费与媒体兼容 2026-08-20 09:12:52 -07:00
IanShaw 39aaf2fea3 收紧 Grok 容量重试与兼容性分类 2026-08-20 08:07:04 -07:00
IanShaw d78e366db5 补齐 Grok Realtime 握手失败账号冷却 2026-08-20 07:31:19 -07:00
IanShaw cca235365b 修正 Grok 默认模型测试断言 2026-08-20 07:19:51 -07:00
IanShaw c628b3eea7 让 Grok stream idle 重试上限作用于主路径 2026-08-20 07:07:55 -07:00