 Calcium-Ion
|
e8da9d7dd7
Merge pull request #1270 from QuantumNous/refactor_model_mapping
|
hai 10 meses |
 CaIon
|
13277cf838
feat: implement new handlers for audio, image, embedding, and responses processing
|
hai 10 meses |
 skynono
|
5d9cf11466
feat: add unsupported test case for kling channel
|
hai 10 meses |
|
CaIon
|
4ec7012974
✨ feat: enhance group ratio handling in pricing calculations
|
hai 10 meses |
|
Calcium-Ion
|
158d621fd7
Merge pull request #1207 from QuantumNous/user_group_ratio
|
hai 10 meses |
 creamlike1024
|
2a0bf7f991
feat: 分组特殊倍率
|
hai 11 meses |
|
CaIon
|
b23416bbb4
🔧 fix(channel-test): ensure proper state reset to prevent deadlocks
|
hai 11 meses |
 Xyfacai
|
8343fe0740
refactor: message content 改成 any
|
hai 11 meses |
|
creamlike1024
|
b16c05ead4
fix: remove apikey from test channel log, close #1000
|
hai 1 ano |
|
CaIon
|
b364e9e3b1
refactor: simplify model prefix checks and update message role for o-series models
|
hai 1 ano |
|
CaIon
|
c40404a8c1
Update MaxTokens for gemini model to 300 in test request
|
hai 1 ano |
|
Calcium-Ion
|
950572b02e
Set MaxTokens to 50 for gemini
|
hai 1 ano |
 zkp
|
93d9f141fe
fix: gemini test MaxTokens
|
hai 1 ano |
|
CaIon
|
f0925dc105
✨ feat: Enhance user settings and notification options
|
hai 1 ano |
|
1808837298@qq.com
|
18b5122a9b
fix: Adjust MaxTokens logic for non-Claude models in test request
|
hai 1 ano |
|
1808837298@qq.com
|
47c297794d
feat: 初步兼容流模式下openai渠道类型转为claude格式访问 #862
|
hai 1 ano |
|
1808837298@qq.com
|
0db072de86
feat(error): Enhance error handling with optional detailed error messages
|
hai 1 ano |
|
1808837298@qq.com
|
6f9412ead3
feat: Introduce configurable docs link and remove hardcoded chat links
|
hai 1 ano |
|
1808837298@qq.com
|
61da6c3664
fix: Refine embedding model detection in channel test
|
hai 1 ano |
|
1808837298@qq.com
|
f8a8dbec6e
feat: Add column visibility settings for Channels and Logs tables
|
hai 1 ano |
|
1808837298@qq.com
|
b640118d74
feat: Implement cache token ratio for more precise token pricing
|
hai 1 ano |
|
1808837298@qq.com
|
208824451a
fix: #810
|
hai 1 ano |
|
1808837298@qq.com
|
62542b0b84
fix: #810
|
hai 1 ano |
|
1808837298@qq.com
|
4208ecb92c
fix: channel test model mapped
|
hai 1 ano |
|
1808837298@qq.com
|
574e28bad8
fix: Use channel group in model testing log record
|
hai 1 ano |
|
1808837298@qq.com
|
1665fcee3c
refactor: Improve channel testing and model price handling
|
hai 1 ano |
|
1808837298@qq.com
|
485face2c0
feat: Add self-use mode for model ratio and price configuration
|
hai 1 ano |
|
1808837298@qq.com
|
3f7d9c4b0f
fix: Improve error handling for model ratio and price validation #800
|
hai 1 ano |
|
1808837298@qq.com
|
3447df85c4
feat: add new GPT-4.5 preview model ratios
|
hai 1 ano |
|
1808837298@qq.com
|
bf9f5e59b5
chore: Update Azure OpenAI API version and embedding model detection
|
hai 1 ano |
