CaIon
fdd349c909
refactor: update GeminiThinkingConfig initialization
2025-04-18 23:13:28 +08:00
CaIon
ace677b3e7
refactor: remove unsupported 'exclusiveMinimum' field from cleanFunctionParameters
2025-04-18 22:40:05 +08:00
CaIon
6e2e10adf1
refactor: remove unsupported root-level fields from cleanFunctionParameters
2025-04-18 21:38:12 +08:00
CaIon
1989ae95c1
refactor: streamline value assignment in SettingGeminiModel
2025-04-18 20:08:26 +08:00
CaIon
d378543819
feat: add gemini thinking suffix support #981
2025-04-18 19:36:18 +08:00
CaIon
8ead0864b5
refactor: remove reasoning field from GeneralOpenAIRequest struct
2025-04-17 17:11:42 +08:00
CaIon
80e6b9e04e
feat: add reasoning field to GeneralOpenAIReques
2025-04-17 17:09:46 +08:00
CaIon
b364e9e3b1
refactor: simplify model prefix checks and update message role for o-series models
2025-04-17 16:50:52 +08:00
Apple\Apple
45e8e04d56
🐛 fix: Fix the issue where new whitelist email domain names cannot be added in the system settings
2025-04-16 17:11:59 +08:00
霍雨佳
e121e77265
Refactor: Optimize the token bucket algorithm, specifically the New method in common/imiterlimiter.go.
...
Solution: Remove Redis ping. When printing exceptions, use SysLog to print and add additional logging information.
2025-04-16 16:36:07 +08:00
Apple\Apple
c20fbec17b
Merge pull request #927 from QuentinHsu/refactor-system-setting
...
# Conflicts:
# web/src/App.js
# web/src/components/ModelSetting.js
# web/src/components/PersonalSetting.js
# web/src/components/SystemSetting.js
# web/src/pages/Channel/EditChannel.js
2025-04-16 16:27:11 +08:00
霍雨佳
5aa2076e18
Refactor: Optimize the request rate limiting for ModelRequestRateLimitCount.
...
Reason: The original steps 1 and 3 in the redisRateLimitHandler method were not atomic, leading to poor precision under high concurrent requests. For example, with a rate limit set to 60, sending 200 concurrent requests would result in none being blocked, whereas theoretically around 140 should be intercepted.
Solution: I chose not to merge steps 1 and 3 into a single Lua script because a single atomic operation involving read, write, and delete operations could suffer from performance issues under high concurrency. Instead, I implemented a token bucket algorithm to optimize this, reducing the atomic operation to just read and write steps while significantly decreasing the memory footprint.
2025-04-16 10:33:43 +08:00
CaIon
50bf4a6615
refactor: remove unused mutex from RelayInfo struct
2025-04-15 23:06:32 +08:00
CaIon
115c85390f
fix: claude parallel function calling
2025-04-15 04:52:33 +08:00
CaIon
effa523a54
feat: support gemini output text and inline images. ( close #866 )
2025-04-15 02:32:51 +08:00
CaIon
44a14ced01
fix: try to fix claude to openai format mcp #966
2025-04-15 01:16:06 +08:00
Calcium-Ion
12ca7c4789
Merge pull request #967 from neotf/fix-01
...
fix: wrong field for Claude (OpenAI Upstream)
2025-04-15 00:05:41 +08:00
CaIon
e3b262da1d
feat: 添加流模式下的SSE保活机制 #945
2025-04-14 19:40:23 +08:00
neotf
935cc1c605
fix: wrong systemStr for Claude (OpenAI Upstream)
2025-04-14 01:09:02 +08:00
CaIon
da86db0d46
fix: update model name handling in UI and localization
2025-04-12 17:44:29 +08:00
jasonzeng
75f0cb8eb0
feat: add error logging functionality to relay and update logs table for error type display
2025-04-12 00:43:34 +08:00
CaIon
f970a03986
fix: xAI usage
2025-04-11 23:31:32 +08:00
CaIon
74d9bb1a12
feat: enhance Claude to OpenAI request conversion with additional relay info support
2025-04-11 19:13:38 +08:00
CaIon
9e4506ebaf
feat: 完善openai转claude支持
2025-04-11 18:28:50 +08:00
CaIon
c94f662829
chore: update .gitignore and docker-compose.yml to include tiktoken_cache directory
2025-04-11 16:24:27 +08:00
CaIon
577b18a1a1
feat: enhance file handling and logging in the application
2025-04-11 16:23:54 +08:00
CaIon
7e0d4cd055
refactor: move maxFileSize variable inside GetFileBase64FromUrl function
2025-04-11 15:53:23 +08:00
CaIon
95f0ed1821
feat: implement parameter cleaning for Gemini functions
2025-04-10 22:35:03 +08:00
CaIon
984f91d111
feat: support zhipu_4v embeddings path
2025-04-10 20:53:51 +08:00
Calcium-Ion
cc219801f8
Merge pull request #959 from Praying/main
...
fix(relay): 优化数据流处理
2025-04-10 17:21:55 +08:00
CaIon
60a9bd45c6
feat: add xAI handling and response processing
2025-04-10 17:20:59 +08:00
quran
5bcfb8507d
fix(relay): 优化数据流处理
...
- 移除了 bufio 的无效使用
- 在 StreamScannerHandler 中增加了初始和最大缓冲区大小的常量设置
- 调整 StreamScannerHandler 中缓冲区大小，避免出现token too long报错
2025-04-10 16:56:16 +08:00
Calcium-Ion
b40bf7c812
Merge pull request #953 from wkxu/main
...
fix: .env文件配置DEBUG=true等参数不起作用的fix
2025-04-10 16:14:11 +08:00
Calcium-Ion
55ec0e5424
Merge pull request #956 from HynoR/feat/xai
...
feat: add xAI channel
2025-04-10 16:13:48 +08:00
HynoR
cdd58282c2
feat: update adaptor methods and add new image model
2025-04-10 15:08:12 +08:00
HynoR
5c1386af2c
feat: add xai grok-3-mini reasoning effort
2025-04-10 13:31:43 +08:00
HynoR
4622c17c83
feat: add xai channel
...
feat: add xai channel
feat: add xai channel
2025-04-10 13:04:43 +08:00
wkxu
54c5c3118b
refactor: 把common/instants.go里的从Getenv获取的参数，放到init.go的LoadEnv函数里获取
...
把constant/env.go里的从Getenv获取的参数，放到env.go的InitEnv函数里获取。以避免.env文件配置参数不起作用的情况
2025-04-10 09:02:19 +08:00
Calcium-Ion
3f58fcb4f3
Merge pull request #944 from lamcodes/main
...
Update: Gemini channel fetch_models
2025-04-10 00:09:54 +08:00
CaIon
32db85607e
fix: Update model ratios for gemini-2.5-pro
2025-04-10 00:09:11 +08:00
CaIon
ed855e78f7
refactor: Remove duplicate model settings initialization in main function
2025-04-10 00:07:34 +08:00
CaIon
b4889878d0
refactor: Update localization keys for API address in English translations and adjust related UI labels
2025-04-09 22:22:19 +08:00
datehoer
7566ae9b3e
Add support for grok-2-image. Currently, grok-2-image doesn't support the size, quality, or style parameters. Set 'size'='empty' to use grok-2-image
2025-04-09 15:05:00 +08:00
zkp
20c47c12b4
Update: Gemini channel fetch_models
2025-04-08 22:43:13 +08:00
CaIon
ac06e9a46f
feat: Add CheckSetup function call in main to ensure proper initialization #942
2025-04-08 18:14:36 +08:00
Calcium-Ion
97be874cf5
Merge pull request #930 from Yiffyi/main
...
fix: save OIDC settings
2025-04-08 17:39:42 +08:00
CaIon
c40404a8c1
Update MaxTokens for gemini model to 300 in test request
2025-04-08 17:37:25 +08:00
Calcium-Ion
ba9cd9314b
Merge pull request #936 from lamcodes/main
...
fix: gemini test MaxTokens
2025-04-08 17:33:31 +08:00
Calcium-Ion
950572b02e
Set MaxTokens to 50 for gemini
2025-04-08 17:33:10 +08:00
CaIon
d85e25fc46
feat: Integrate SetupCheck component for improved setup validation in routing
2025-04-08 17:31:46 +08:00
