Commit Graph

198 Commits

Author SHA1 Message Date
Seefs
da24a165d0 fix(gemini): handle minimal reasoning effort budget
- Add minimal case to clampThinkingBudgetByEffort to avoid defaulting to full thinking budget
2025-12-18 08:10:46 +08:00
t0ng7u
8e3f9b1faa 🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled
Clamp request body size (including post-decompression) to avoid memory exhaustion caused by huge payloads/zip bombs, especially with large-context Claude requests. Add a configurable `MAX_REQUEST_BODY_MB` (default `32`) and document it.

- Enforce max request body size after gzip/br decompression via `http.MaxBytesReader`
- Add a secondary size guard in `common.GetRequestBody` and cache-safe handling
- Return **413 Request Entity Too Large** on oversized bodies in relay entry
- Avoid building large `TokenCountMeta.CombineText` when both token counting and sensitive check are disabled (use lightweight meta for pricing)
- Update READMEs (CN/EN/FR/JA) with `MAX_REQUEST_BODY_MB`
- Fix a handful of vet/formatting issues encountered during the change
- `go test ./...` passes
2025-12-16 17:00:19 +08:00
CaIon
689c43143b feat(model_ratio): add default ratios for gpt-4o-mini-tts 2025-12-13 19:14:27 +08:00
CaIon
e36e2e1b69 feat(audio): enhance audio request handling with token type detection and streaming support 2025-12-13 17:24:23 +08:00
FlowerRealm
c3c119a9b4 feat: add claude-haiku-4-5-20251001 model support
- Add model to Claude ModelList
- Add model ratio (0.5, $1/1M input tokens)
- Add completion ratio support (5x, $5/1M output tokens)
- Add cache read ratio (0.1, $0.10/1M tokens)
- Add cache write ratio (1.25, $1.25/1M tokens)

Model specs:
- Context window: 200K tokens
- Max output: 64K tokens
- Release date: October 1, 2025
2025-12-05 18:54:20 +08:00
Seefs
b6a02d8303 feat: gemini 3 thinking level gemini-3-pro-preview-high 2025-12-01 16:40:46 +08:00
Seefs
3257723a55 Revert "OAI生图接口支持gemini 3 pro image preview" 2025-11-30 18:49:18 +08:00
feitianbubu
bff04514a8 feat: support gemini-3-pro-image-preview via images/generations 2025-11-26 12:03:24 +08:00
Papersnake
79682dc542 feat: add claude-opus-4-5-20251101 2025-11-25 10:53:01 +08:00
Papersnake
5931d333cb feat: add claude-opus-4-5-20251101 ratio 2025-11-25 10:49:34 +08:00
CaIon
c939686509 refactor: Deprecate HARM_CATEGORY_CIVIC_INTEGRITY in safety settings 2025-11-23 23:45:48 +08:00
Seefs
07aff1fe02 Merge pull request #1706 from StageDog/feat/discord_oauth
feat: 关联 discord 账号
2025-11-23 18:54:55 +08:00
StageDog
2bc991685f feat: 针对 discord 登录配置使用新版设置方案 2025-11-22 19:06:53 +08:00
CaIon
84745d5ca4 feat: Add ContextKeyLocalCountTokens and update ResponseText2Usage to use context in multiple channels 2025-11-21 18:17:01 +08:00
Seefs
50c04a62f9 feat: Fill thoughtSignature only for Gemini/Vertex channels using the OpenAI format 2025-11-20 15:54:33 +08:00
Xyfacai
06cd774c10 fix: 未设置价格模型不会被拉取,除非设置自用模式 2025-11-13 18:44:18 +08:00
CaIon
4419be9c09 fix(claude): Prevent duplicate header values in WriteHeaders method 2025-11-13 16:49:40 +08:00
Calcium-Ion
af0f542db8 Merge pull request #2190 from Sh1n3zZ/support-replicate-channel
feat: replicate channel flux model
2025-11-10 17:22:31 +08:00
Sh1n3zZ
d0c45a01fa feat: replicate channel flux model 2025-11-08 01:24:45 +08:00
Seefs
e082268533 feat: ShouldPreserveThinkingSuffix (#2189) 2025-11-07 17:43:33 +08:00
Seefs
1f419a3c71 Merge pull request #2121 from QuantumNous/feat/special_group
feat: add special user usable group setting
2025-10-29 18:54:51 +09:00
CaIon
1ded19795a feat: add special user usable group setting 2025-10-28 23:25:43 +08:00
Seefs
158b46eb4b fix: test channel frequency (#2119) 2025-10-28 23:23:24 +08:00
Little Write
ac3baacec7 Merge branch 'main' into feat_subscribe_sp1 2025-10-20 22:36:33 +08:00
CaIon
ede47ef014 feat: support free model setting 2025-10-12 13:31:03 +08:00
Seefs
e1c7a4f41f format: package name -> github.com/QuantumNous/new-api (#2017) 2025-10-11 15:30:09 +08:00
Xyfacai
a54baf4998 feat: sora 增加参数校验与计费 2025-10-10 23:56:36 +08:00
Seefs
fe9b305232 fix: legal setting 2025-10-10 13:18:26 +08:00
Seefs
3199e2e8cd Merge branch 'main-upstream' into pr/custom-currency-1923
# Conflicts:
#	web/src/components/settings/personal/cards/AccountManagement.jsx
#	web/src/components/table/channels/modals/EditChannelModal.jsx
#	web/src/hooks/channels/useChannelsData.jsx
#	web/src/hooks/common/useSidebar.js
#	web/src/i18n/locales/fr.json
#	web/src/pages/Setting/Operation/SettingsGeneral.jsx
2025-10-02 20:30:48 +08:00
creamlike1024
70263e96ab feat: 支持 gemini-robotics-er-1.5-preview 2025-10-01 17:33:54 +08:00
Seefs
0a6f39e60b fix: passkey 文案 2025-09-30 16:15:33 +08:00
Seefs
fcc6172b43 fix: passkey rpid detect 2025-09-30 15:53:19 +08:00
Seefs
4c13666f26 Merge branch 'main-upstream' into feature/passkey
# Conflicts:
#	web/src/components/settings/PersonalSetting.jsx
#	web/src/i18n/locales/en.json
#	web/src/i18n/locales/zh.json
2025-09-30 12:15:20 +08:00
Seefs
31544405f4 Merge pull request #1924 from prnake/claude-4-5
feat: support claude-sonnet-4-5-20250929
2025-09-30 09:26:34 +08:00
papersnake
d7db30a23e feat: support claude-sonnet-4-5-20250929 2025-09-30 09:14:12 +08:00
t0ng7u
39a868faea 💱 feat(settings): introduce site-wide quota display type (USD/CNY/TOKENS/CUSTOM)
Replace the legacy boolean “DisplayInCurrencyEnabled” with an injected, type-safe
configuration `general_setting.quota_display_type`, and wire it through the
backend and frontend.

Backend
- Add `QuotaDisplayType` to `operation_setting.GeneralSetting` with injected
  registration via `config.GlobalConfig.Register("general_setting", ...)`.
  Helpers: `IsCurrencyDisplay()`, `IsCNYDisplay()`, `GetQuotaDisplayType()`.
- Expose `quota_display_type` in `/api/status` and keep legacy
  `display_in_currency` for backward compatibility.
- Logger: update `LogQuota` and `FormatQuota` to support USD/CNY/TOKENS. When
  CNY is selected, convert using `operation_setting.USDExchangeRate`.
- Controllers:
  - `billing`: compute subscription/usage amounts based on the selected type
    (USD: divide by `QuotaPerUnit`; CNY: USD→CNY; TOKENS: keep raw tokens).
  - `topup` / `topup_stripe`: treat inputs as “amount” for USD/CNY and as
    token-count for TOKENS; adjust min topup and pay money accordingly.
  - `misc`: include `quota_display_type` in status payload.
- Compatibility: in `model/option.UpdateOption`, map updates to
  `DisplayInCurrencyEnabled` → `general_setting.quota_display_type`
  (true→USD, false→TOKENS). Keep exporting the legacy key in `OptionMap`.

Frontend
- Settings: replace the “display in currency” switch with a Select
  (`general_setting.quota_display_type`) offering USD / CNY / Tokens.
  Provide fallback mapping from legacy `DisplayInCurrencyEnabled`.
- Persist `quota_display_type` to localStorage (keep `display_in_currency`
  for legacy components).
- Rendering helpers: base all quota/price rendering on `quota_display_type`;
  use `usd_exchange_rate` for CNY symbol/values.
- Pricing page: default view currency follows site display type (USD/CNY),
  while TOKENS mode still allows per-view currency toggling when needed.

Notes
- No database migrations required.
- Legacy clients remain functional via compatibility fields.
2025-09-29 23:23:31 +08:00
dd
8c5b6654cb Merge branch 'QuantumNous:main' into main 2025-09-29 19:15:43 +08:00
RedwindA
ca0eaa7697 解锁deepseek补全倍率;允许deepseek渠道获取模型 2025-09-29 18:32:44 +08:00
Seefs
dcf4336c75 feat: passkey 2025-09-29 17:45:09 +08:00
dd
4c2979bb67 Merge branch 'QuantumNous:main' into main 2025-09-29 14:13:50 +08:00
Little Write
fade73d970 Merge branch 'main' into feat_subscribe_sp1 2025-09-27 22:54:52 +08:00
Seefs
ad72500941 feat: allow stripe promotion code 2025-09-27 15:43:12 +08:00
CaIon
b5d3e87ea2 Merge branch 'alpha' 2025-09-19 14:20:15 +08:00
creamlike1024
9f1ab16aa5 feat: 支持 gemini-embedding-001 2025-09-19 00:24:01 +08:00
CaIon
50a432180d feat: add experimental IP filtering for domains and update related settings 2025-09-18 13:40:52 +08:00
CaIon
2ea7634549 Merge branch 'main' into ssrf
# Conflicts:
#	service/cf_worker.go
2025-09-18 13:29:11 +08:00
creamlike1024
467e584359 feat: 添加域名启用ip过滤开关 2025-09-17 23:46:04 +08:00
creamlike1024
b7bc609a7a feat: 添加域名和ip过滤模式设置 2025-09-16 22:40:40 +08:00
Little Write
a7d6a8b0d0 完善 订单处理,以及 优化 ui 2025-09-16 22:35:46 +08:00
creamlike1024
11cf70e60d fix: openai responses api 未统计图像生成调用计费 2025-09-16 12:47:59 +08:00