github/new-api
1
0
Fork 0
mirror of https://github.com/QuantumNous/new-api.git synced 2026-04-19 11:08:37 +00:00
Code Issues Packages Projects Releases Wiki Activity
4,955 Commits 34 Branches 616 Tags
v0.10.6-alpha.1
Commit Graph

4955 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
comeback01
f04ed7584a Merge branch 'main' into french-translation 2025-12-20 11:08:07 +01:00
长安
0a2f12c04e fix: 修复 Anthropic 渠道缓存计费错误 
## 问题描述

当使用 Anthropic 渠道通过 `/v1/chat/completions` 端点调用且启用缓存功能时，
计费逻辑错误地减去了缓存 tokens，导致严重的收入损失（94.5%）。

## 根本原因

不同 API 的 `prompt_tokens` 定义不同：

- **Anthropic API**: `input_tokens` 字段已经是纯输入 tokens（不包含缓存）
- **OpenAI API**: `prompt_tokens` 字段包含所有 tokens（包含缓存）
- **OpenRouter API**: `prompt_tokens` 字段包含所有 tokens（包含缓存）

当前 `postConsumeQuota` 函数对所有渠道都减去缓存 tokens，这对 Anthropic
渠道是错误的，因为其 `input_tokens` 已经不包含缓存。

## 修复方案

在 `relay/compatible_handler.go` 的 `postConsumeQuota` 函数中，添加渠道类型判断：

```go
if relayInfo.ChannelType != constant.ChannelTypeAnthropic {
    baseTokens = baseTokens.Sub(dCacheTokens)
}
```

只对非 Anthropic 渠道减去缓存 tokens。

## 影响分析

### ✅ 不受影响的场景

1. **无缓存调用**（所有渠道）
   - cache_tokens = 0
   - 减去 0 = 不减去
   - 结果：完全一致

2. **OpenAI/OpenRouter 渠道 + 缓存**
   - 继续减去缓存（因为 ChannelType != Anthropic）
   - 结果：完全一致

3. **Anthropic 渠道 + /v1/messages 端点**
   - 使用 PostClaudeConsumeQuota（不修改）
   - 结果：完全不受影响

### ✅ 修复的场景

4. **Anthropic 渠道 + /v1/chat/completions + 缓存**
   - 修复前：错误地减去缓存，导致 94.5% 收入损失
   - 修复后：不减去缓存，计费正确

## 验证数据

以实际记录 143509 为例：

| 项目 | 修复前 | 修复后 | 差异 |
|------|--------|--------|------|
| Quota | 10,489 | 191,330 | +180,841 |
| 费用 | ¥0.020978 | ¥0.382660 | +¥0.361682 |
| 收入恢复 | - | - | **+1724.1%** |

## 测试建议

1. 测试 Anthropic 渠道 + 缓存场景
2. 测试 OpenAI 渠道 + 缓存场景（确保不受影响）
3. 测试无缓存场景（确保不受影响）

## 相关 Issue

修复 Anthropic 渠道使用 prompt caching 时的计费错误。
 2025-12-20 14:17:12 +08:00
CaIon
cc3ba39e72 feat(gin): improve request body handling and error reporting v0.10.1 2025-12-20 13:34:10 +08:00
CaIon
4ee595c448 feat(init): increase MaxRequestBodyMB to enhance request handling 2025-12-20 13:27:55 +08:00
CaIon
d9634ad2d3 feat(channel): add error handling for SaveWithoutKey when channel ID is 0 2025-12-20 13:26:40 +08:00
Seefs
a343ce84ee Merge pull request #2476 from TinsFox/chore/code-inspector-plugin 2025-12-20 11:04:40 +08:00
Seefs
531dfb2555 docs: document pyroscope env var 2025-12-19 23:16:56 +08:00
TinsFox
e6ec551fbf chore: add code-inspector-plugin integration 2025-12-19 23:04:53 +08:00
Seefs
5ef7247eac docs: document pyroscope env var 2025-12-19 23:03:04 +08:00
Seefs
1168ddf9f9 fix: systemname 2025-12-19 22:27:35 +08:00
Seefs
a98aad2501 Merge pull request #2474 from TinsFox/main 2025-12-19 21:39:56 +08:00
TinsFox
97132de2ca style: add card spacing 2025-12-19 21:00:31 +08:00
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
comeback01
f88fc26150 Refine French translations for UI conciseness 
Updated web/src/i18n/locales/fr.json to improve French translations for the user interface.

Removed verbose prefixes like 'Gestion des...' and 'Paramètres de...' to prevent truncation in sidebars and menus.

Harmonized terms for consistency (e.g., 'Tâches', 'Journaux', 'Dessins').

Renamed 'Place du marché' to 'Marché des modèles'.
 2025-12-17 12:10:36 +01:00
Seefs
b35ae9f693 Merge pull request #2452 from QuantumNous/fix/oom-request-body-limit 2025-12-16 18:21:59 +08:00
t0ng7u
8cb56fc319 🧹 fix: harden request-body size handling and error unwrapping 
Tighten oversized request handling across relay paths and make error matching reliable.

- Align `MAX_REQUEST_BODY_MB` fallback to `32` in request body reader and decompression middleware
- Stop ignoring `GetRequestBody` errors in relay retry paths; return consistent **413** on oversized bodies (400 for other read errors)
- Add `Unwrap()` to `types.NewAPIError` so `errors.Is/As` can match wrapped underlying errors
- `go test ./...` passes
 2025-12-16 18:10:00 +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
Seefs
2a511c6ee4 fix: 支持传入system_instruction和systemInstruction两种风格系统提示词参数名 2025-12-16 13:08:58 +08:00
Calcium-Ion
11593bd3da Merge pull request #2445 from QuantumNous/feat/token-ip-whitelist-cidr 
feat(auth): enhance IP restriction handling with CIDR support
 2025-12-15 20:14:09 +08:00
CaIon
e16e7d6fb9 feat(auth): refactor IP restriction handling to use clearer variable naming 2025-12-15 20:13:09 +08:00
旃蒙
0217ed2f98 fix(task): 修复渠道配置多个key时无法获取任务的问题 2025-12-15 18:15:35 +08:00
CaIon
39593052b6 feat(auth): enhance IP restriction handling with CIDR support 2025-12-15 17:24:09 +08:00
CaIon
4ea8cbd207 Revert "feat(audio): replace SysLog with logger for improved logging in GetAudioDuration" 
This reverts commit e293be0138.
v0.10.1-alpha.8 		2025-12-14 00:04:40 +08:00
CaIon
e293be0138 feat(audio): replace SysLog with logger for improved logging in GetAudioDuration 2025-12-13 23:59:58 +08:00
CaIon
9c2483ef48 fix(audio): improve WAV duration calculation with enhanced PCM size handling 2025-12-13 23:57:32 +08:00
CaIon
689c43143b feat(model_ratio): add default ratios for gpt-4o-mini-tts 2025-12-13 19:14:27 +08:00
CaIon
a2da6a9e90 refactor(channel_select): improve retry logic with reset functionality 2025-12-13 18:09:10 +08:00
Calcium-Ion
7a307e2e99 Merge pull request #2434 from QuantumNous/feat/gpt-4o-mini-tts 
feat: support gpt tts series model quota calculate
v0.10.1-alpha.6 		2025-12-13 17:55:16 +08:00
CaIon
7cae4a640b fix(audio): correct TotalTokens calculation for accurate usage reporting 2025-12-13 17:49:57 +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
CaIon
b602843ce1 feat(token): add CrossGroupRetry field to token insertion 2025-12-13 16:45:42 +08:00
CaIon
21fca238bf refactor(error): replace dto.OpenAIError with types.OpenAIError for consistency 2025-12-13 16:43:57 +08:00
CaIon
c51936e068 refactor(channel_select): enhance retry logic and context key usage for channel selection 2025-12-13 16:43:38 +08:00
Seefs
fcafadc6bb feat: pyroscope integrate 2025-12-13 13:49:38 +08:00
CaIon
b58fa3debc fix(helper): improve error handling in FlushWriter and related functions v0.10.1-alpha.5 2025-12-13 13:29:21 +08:00
CaIon
1c167c1068 refactor(auth): replace direct token group setting with context key retrieval v0.10.1-alpha.4 2025-12-13 01:38:12 +08:00
Calcium-Ion
f9b6e4c243 Merge pull request #2430 from QuantumNous/fix/cross-group-retry 
fix(channel_select): adjust priority retry logic for cross-group
v0.10.1-alpha.3 		2025-12-13 01:05:40 +08:00
CaIon
b523f6a0ba fix(channel_select): adjust priority retry logic for cross-group channel selection 2025-12-13 01:04:10 +08:00
Calcium-Ion
30cb224793 Merge pull request #2429 from QuantumNous/feat/xhigh 
feat(adaptor): add '-xhigh' suffix to reasoning effort options
 2025-12-12 22:06:19 +08:00
CaIon
ce6fb95f96 refactor(relay): update channel retrieval to use RelayInfo structure v0.10.1-alpha.2 2025-12-12 22:04:38 +08:00
Calcium-Ion
2ac6a5b02f Merge pull request #2424 from ion1ze/main 
fix: correct sender format issues fix #1347
 2025-12-12 20:55:22 +08:00
CaIon
50854c17bb feat(adaptor): add '-xhigh' suffix to reasoning effort options for model parsing 2025-12-12 20:53:48 +08:00
Calcium-Ion
147659fb6e Merge pull request #2426 from QuantumNous/feat/auto-cross-group-retry 
feat(token): add cross-group retry option for token processing
v0.10.1-alpha.1 		2025-12-12 20:45:54 +08:00
Calcium-Ion
e9fb2ccdd1 Merge pull request #2428 from seefs001/fix/health-check 
fix: health check
 2025-12-12 20:45:34 +08:00
Seefs
48a17efade fix: health check 2025-12-12 20:37:32 +08:00
CaIon
7e1d1350c7 feat: implement cross-group retry functionality and update translations 2025-12-12 18:28:33 +08:00
CaIon
01b4039e96 feat(token): add cross-group retry option for token processing 2025-12-12 17:59:21 +08:00
hackerxiao
8e629a2a11 feat: 支持仅使用x-api-key获取anthropic格式的模型列表 注释增加 2025-12-12 17:27:24 +08:00
zdwy5
e1bee48152 fix: 支持aws 通过全局参数透传或者渠道参数透传来 调用 (#2423) 
* fix: 支持aws 通过全局参数透传或者渠道参数透传来 调用

* fix(aws): replace json.Unmarshal with common.Unmarshal for request body processing

---------

Co-authored-by: r0 <liangchunlei@01.ai>
Co-authored-by: CaIon <i@caion.me>
 2025-12-12 17:09:27 +08:00
hackerxiao
2a16c37aab feat: 支持仅使用x-api-key获取anthropic格式的模型列表 2025-12-12 16:53:10 +08:00