 CaIon
|
0f35d2368f
✨ feat: enhance group ratio handling in pricing calculations
|
il y a 8 mois |
 Calcium-Ion
|
358af20ad1
Merge pull request #1207 from QuantumNous/user_group_ratio
|
il y a 8 mois |
 creamlike1024
|
a28ab3628a
feat: 分组特殊倍率
|
il y a 8 mois |
|
CaIon
|
66d3206d7d
🔧 fix(channel-test): ensure proper state reset to prevent deadlocks
|
il y a 9 mois |
 Xyfacai
|
b778cd2b23
refactor: message content 改成 any
|
il y a 9 mois |
|
creamlike1024
|
f968d77365
fix: remove apikey from test channel log, close #1000
|
il y a 10 mois |
|
CaIon
|
ee4f27d01b
refactor: simplify model prefix checks and update message role for o-series models
|
il y a 10 mois |
|
CaIon
|
79b35e385f
Update MaxTokens for gemini model to 300 in test request
|
il y a 11 mois |
|
Calcium-Ion
|
30f32c6a6d
Set MaxTokens to 50 for gemini
|
il y a 11 mois |
 zkp
|
f24de65626
fix: gemini test MaxTokens
|
il y a 11 mois |
|
CaIon
|
c418d9ed9a
✨ feat: Enhance user settings and notification options
|
il y a 11 mois |
|
1808837298@qq.com
|
73263e02d6
fix: Adjust MaxTokens logic for non-Claude models in test request
|
il y a 11 mois |
|
1808837298@qq.com
|
7e46d4217d
feat: 初步兼容流模式下openai渠道类型转为claude格式访问 #862
|
il y a 11 mois |
|
1808837298@qq.com
|
1819c4d5f5
feat(error): Enhance error handling with optional detailed error messages
|
il y a 1 an |
|
1808837298@qq.com
|
00c2d6c102
feat: Introduce configurable docs link and remove hardcoded chat links
|
il y a 1 an |
|
1808837298@qq.com
|
4a8bb625b8
fix: Refine embedding model detection in channel test
|
il y a 1 an |
|
1808837298@qq.com
|
7fcb14e25f
feat: Add column visibility settings for Channels and Logs tables
|
il y a 1 an |
|
1808837298@qq.com
|
4f194f4e6a
feat: Implement cache token ratio for more precise token pricing
|
il y a 1 an |
|
1808837298@qq.com
|
17e9f1a07d
fix: #810
|
il y a 1 an |
|
1808837298@qq.com
|
792754cee3
fix: #810
|
il y a 1 an |
|
1808837298@qq.com
|
760514c3e1
fix: channel test model mapped
|
il y a 1 an |
|
1808837298@qq.com
|
2ca0d7246d
fix: Use channel group in model testing log record
|
il y a 1 an |
|
1808837298@qq.com
|
d042a1bd55
refactor: Improve channel testing and model price handling
|
il y a 1 an |
|
1808837298@qq.com
|
7dbb6b017c
feat: Add self-use mode for model ratio and price configuration
|
il y a 1 an |
|
1808837298@qq.com
|
2f9faba40d
fix: Improve error handling for model ratio and price validation #800
|
il y a 1 an |
|
1808837298@qq.com
|
d6fd50e382
feat: add new GPT-4.5 preview model ratios
|
il y a 1 an |
|
1808837298@qq.com
|
1bcf7a3c39
chore: Update Azure OpenAI API version and embedding model detection
|
il y a 1 an |
|
1808837298@qq.com
|
0907a078b4
refactor: Simplify root user notification and remove global email variable
|
il y a 1 an |
|
1808837298@qq.com
|
9edb9f7a71
feat: Add automatic channel disabling based on configurable keywords
|
il y a 1 an |
|
Calcium-Ion
|
88bdedd2c9
Merge pull request #723 from kuwork/main
|
il y a 1 an |
