CaIon
64bf6d1e95
fix(token_counter): correct model name reference in image token estimation
2025-12-03 00:25:05 +08:00
Calcium-Ion
cb40004d86
Merge pull request #2355 from QuantumNous/feat/optimize-token-counter
...
feat: refactor token estimation logic
2025-12-02 21:51:09 +08:00
CaIon
2e4d27e001
feat(token_estimator): add concurrency support for multipliers retrieval
2025-12-02 21:38:58 +08:00
CaIon
1fededceb3
feat: refactor token estimation logic
...
- Introduced new OpenAI text models in `common/model.go`.
- Added `IsOpenAITextModel` function to check for OpenAI text models.
- Refactored token estimation methods across various channels to use estimated prompt tokens instead of direct prompt token counts.
- Updated related functions and structures to accommodate the new token estimation approach, enhancing overall token management.
2025-12-02 21:34:39 +08:00
Papersnake
bf1a31df80
fix: add ForceAttemptHTTP2
2025-12-02 10:08:58 +08:00
Papersnake
14622aede6
fix: set MaxIdleConnsPerHost to 100
2025-12-02 09:55:03 +08:00
CaIon
5a037f2acd
feat: Add CountToken configuration and update token counting logic
2025-11-22 17:15:34 +08:00
CaIon
c8bbf7bed8
feat: Add ContextKeyLocalCountTokens and update ResponseText2Usage to use context in multiple channels
2025-11-21 18:17:01 +08:00
Seefs
e1b9317531
feat: claude 1h cache ( #2155 )
...
* feat: claude 1h cache
* feat: claude 1h cache
* fix price
2025-11-04 00:20:50 +08:00
Seefs
19c40c5ae4
Merge pull request #2124 from feitianbubu/pr/fix-topup-link
...
fix: correct topUp link
2025-10-31 13:43:23 +08:00
CaIon
758cd2c15f
refactor(group): update user group handling to utilize userUsableGroups directly and add GetUserGroupRatio function
2025-10-30 21:16:42 +08:00
Seefs
b26333b2cd
Merge pull request #2121 from QuantumNous/feat/special_group
...
feat: add special user usable group setting
2025-10-29 18:54:51 +09:00
feitianbubu
ee75f0919a
fix: correct topUp link
2025-10-29 16:55:29 +08:00
CaIon
6aec088693
feat: add special user usable group setting
2025-10-28 23:25:43 +08:00
CaIon
a00c6393c5
feat: implement audio duration retrieval without ffmpeg dependencies
2025-10-28 15:50:45 +08:00
Seefs
b3fc7255ee
feat: endpoint type log
2025-10-13 22:44:54 +08:00
Seefs
9718568179
feat: endpoint type log
2025-10-13 22:25:39 +08:00
yanggh
b6f352735e
fix(convert): 修复 OpenAI 转 Claude 流时 thinking 块的格式问题
...
将 `ClaudeMediaMessage.Thinking` 的类型从 `string` 修改为 `*string`，以解决 `omitempty` 导致 `"thinking": ""` 字段在 JSON 序列化时被忽略的问题。
同时更新了 `service/convert.go` 和 `relay/channel/claude/relay-claude.go` 中的相关逻辑，以兼容新的指针类型，确保生成的 Claude 事件流符合官方规范。
2025-10-13 19:32:17 +08:00
CaIon
250f10fa67
fix: mask sensitive information in error messages and refine task retrieval query
2025-10-12 12:25:11 +08:00
Seefs
5010f2d004
format: package name -> github.com/QuantumNous/new-api ( #2017 )
2025-10-11 15:30:09 +08:00
Seefs
452a7b0e95
Merge pull request #1401 from feitianbubu/pr/add-qwen-channel-auto-disabled
...
feat: add qwen channel auto disabled
2025-10-10 16:41:43 +08:00
CaIon
bdb522021a
feat: enhance HTTP client with custom redirect handling and SSRF protection
2025-10-10 15:13:41 +08:00
CaIon
35105b3da5
feat: update Gemini API response handling to include block reason and improve error reporting
2025-10-05 19:33:47 +08:00
RedwindA
98050ee6e9
feat: add Gotify notification option for quota alerts
2025-10-01 19:15:00 +08:00
Seefs
75ee632182
fix: passkey rpid detect
2025-09-30 15:53:19 +08:00
Seefs
e26c794742
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
1599a8403f
feat: passkey
2025-09-29 17:45:09 +08:00
CaIon
f03f4187e0
fix(http_client): improve error message for unsupported proxy schemes
2025-09-29 14:02:15 +08:00
RedwindA
4f3ec81b3f
fix: add missing timeout
2025-09-27 22:29:27 +08:00
RedwindA
fcc5c73bc0
feat: 添加代理客户端缓存和重置功能，优化 HTTP 客户端管理
2025-09-27 22:18:39 +08:00
CaIon
552d795742
Merge branch 'alpha'
2025-09-19 14:20:15 +08:00
creamlike1024
82163b4be7
feat: 添加域名启用ip过滤开关
2025-09-17 23:46:04 +08:00
creamlike1024
b46bffde03
feat: ssrf支持域名和ip黑白名单过滤模式
2025-09-17 15:41:21 +08:00
creamlike1024
cc9a559b75
feat: 添加域名和ip过滤模式设置
2025-09-16 22:40:40 +08:00
Xyfacai
b0bb2fe5a9
fix: gemini support webp file
2025-09-15 01:01:48 +08:00
CaIon
c3f5478593
feat: implement SSRF protection settings and update related references
2025-09-13 18:15:03 +08:00
CaIon
9e17df3f74
fix: update references from setting to system_setting for ServerAddress
2025-09-13 15:27:41 +08:00
CaIon
1a8d781721
Revert "feat: gemini-2.5-flash-image-preview 文本和图片输出计费"
...
This reverts commit a45513a7a6
2025-09-13 12:53:28 +08:00
CaIon
c47d9fb5b5
feat(payment): add payment settings configuration and update payment methods handling
2025-09-12 19:29:34 +08:00
Xyfacai
9fb64f337c
fix: 预扣额度使用 relay info 传递
2025-09-11 16:04:32 +08:00
Xyfacai
3f9adc9992
fix: openai 格式请求 claude 没计费 create cache token
2025-09-10 15:30:23 +08:00
Seefs
80cfa0d0df
Merge pull request #1677 from QuantumNous/gemini-2.5-flash-image-preview-billing
...
feat: gemini-2.5-flash-image-preview 文本和图片输出计费
2025-09-07 14:15:24 +08:00
CaIon
1bbabda081
feat(monitor_setting): implement automatic channel testing configuration
2025-09-03 14:00:52 +08:00
Seefs
4f44bbed31
feat: bark notification #1699
2025-09-01 15:57:23 +08:00
CaIon
742871db57
feat(token_counter): add mime type extraction for base64 encoded data
2025-08-28 17:30:53 +08:00
CaIon
7e698f658a
fix(pre_consume_quota): improve error messages for insufficient user quota
2025-08-28 13:57:16 +08:00
creamlike1024
a45513a7a6
feat: gemini-2.5-flash-image-preview 文本和图片输出计费
2025-08-27 21:30:52 +08:00
CaIon
d1f3f2c395
fix(token_counter): update token counting logic to handle media token conditions
2025-08-27 17:11:33 +08:00
CaIon
d92c9db61c
fix(image): add error handling for empty base64 string in image decoding
2025-08-27 16:38:32 +08:00
Calcium-Ion
59a5cb8d32
Merge pull request #1579 from wzxjohn/hotfix/openai_claude_convert
...
fix(adaptor): missing first text delta while convert OpenAI to Claude
2025-08-26 20:37:54 +08:00
