Commit Graph
3638 Commits
Author SHA1 Message Date
Long Li 22e1b8144a feat(gateway): expose routed Codex model catalogs
Codex model discovery expects a top-level models manifest, but Composite and other non-OpenAI groups either reached the OpenAI live-manifest handler or had no Codex-specific response at all. API key users also had no supported way to fetch that manifest and reference it from config.toml.

Generate minimal manifests from each group's effective model list while preserving the official OpenAI live path and the ordinary /models response. Add the Use Key flow for authenticated catalog download and model_catalog_json configuration without writing the API key into the downloaded file.
2026-08-22 14:43:40 +09:00
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
anguobao123 9f2f2738fd docs(openai): document force HTTP fallback 2026-08-21 23:43:09 +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
IanShaw f7bc1970ef 同步 Grok 默认模型回归断言 2026-08-20 07:00:42 -07:00
IanShaw 0b1f79c83c 同步 Grok 429 bridge 回归断言 2026-08-20 06:43:54 -07:00
IanShaw 2ab24a1e77 修正 Grok 429 边界与 stream idle 重试上限 2026-08-20 06:43:31 -07:00
IanShaw ab9cb69e7e Revert "修复 Grok WebSearch SSE action 兼容"
This reverts commit 726de30101.
2026-08-20 06:36:42 -07:00
IanShaw 5ae254f771 补齐 Grok CC bridge 同号重试 2026-08-20 06:25:57 -07:00
IanShaw 17c0ee3859 支持 Grok compaction 422 重试 2026-08-20 06:08:34 -07:00
IanShaw ad87ddee12 补齐 Grok CC 重试与 compaction 恢复 2026-08-20 06:08:09 -07:00
IanShaw 8db8791a73 为 Grok 普通 429 增加有限同号重试 2026-08-20 05:53:55 -07:00
IanShaw e62ec2c42f Revert "feat(429): add configurable cooldown and retry strategies"
This reverts commit 6c3edc0956.
2026-08-20 05:44:21 -07:00