This website requires JavaScript.
fbbbe77657
feat: 分组速率前端优化
2025-05-05 22:06:16 +08:00
103cca019d
feat: Modellimitgroup check
2025-05-05 20:00:06 +08:00
cd40bdbdc6
refactor: 调整代码，符合项目现有规范
2025-05-05 19:32:22 +08:00
e24a3f7587
fix: rm debug file
2025-05-05 17:57:02 +08:00
2a0e1ab914
fix: Redis limit ignoring max eq 0
2025-05-05 12:55:48 +08:00
c9ce1210be
feat: 优化代码，去除多余注释和修改
2025-05-05 11:34:57 +08:00
b32ed55624
feat: 增加分组速率功能
2025-05-05 07:31:54 +08:00
e9812b0fd5
feat: implement OpenAI responses handling and streaming support with built-in tool tracking
2025-05-05 00:40:16 +08:00
52d5d495c0
Merge pull request #1024 from tbphp/fix-edituser-text
2025-05-04 18:30:32 +08:00
fb81fe05dd
fix: EditUser text error
2025-05-04 18:26:18 +08:00
24200df47e
refactor: remove unnecessary call to helper.Done and adjust data rendering in ClaudeChunkData
2025-05-04 17:35:45 +08:00
4cc1f2b4e3
Merge pull request #1020 from QuantumNous/v1responses
2025-05-04 17:13:39 +08:00
fa89410e41
Merge pull request #1012 from tbphp/vertex_thinking_support
2025-05-04 17:11:27 +08:00
209265e68c
feat: enhance OaiResponsesStreamHandler to handle output text and improve response streaming
2025-05-04 17:09:37 +08:00
3753e5720a
add OaiResponsesStreamHandler
2025-05-03 19:19:19 +08:00
4bf0d094c4
feat: add video URL support in MediaContent and update token counting logic
2025-05-03 21:12:07 +08:00
8ea4c76f2b
feat: support /v1/responses API
2025-05-02 13:59:46 +08:00
3654169939
refactor: optimize Dockerfile apk usage
2025-04-29 22:54:43 +08:00
9dc153eda1
feat: /api/token/usage
2025-04-29 17:13:28 +08:00
f5c2fda22a
feat: enable error logging configuration in docker-compose and application
2025-04-29 16:26:55 +08:00
d309727e99
fix: gemini thinking tokens count #1014
2025-04-29 16:21:20 +08:00
7e3e9b1a96
refactor: Reducing the lock duration to the minimum necessary time in CacheGetRandomSatisfiedChannel function
2025-04-29 15:57:21 +08:00
5b81e88e41
feat: support thinking suffix for vertex gemini channel
2025-04-29 13:30:03 +08:00
8b9ba91184
fix: update audio ratio logic for model names in GetAudioRatio function
2025-04-28 20:55:40 +08:00
d402f5a5d9
Merge pull request #1008 from JoeyLearnsToCode/feat-search-channel-by-url
2025-04-28 13:15:49 +08:00
8bea13976f
Merge branch 'wzxjohn-feature/wellknown'
2025-04-28 12:55:06 +08:00
c56ec3b3ea
feat: support searching channels by base url
2025-04-28 11:38:53 +08:00
9f165b8924
fix: remove custom header in oidc well known request
2025-04-25 09:51:01 +08:00
93f634d228
feat: support empty well known url
2025-04-24 21:03:55 +08:00
45073b3b2b
feat: improve log delete api
2025-04-10 22:52:17 +08:00
4f123cf9f4
Merge branch 'error-logs' of github.com:zenghongtu/new-api into zenghongtu-error-logs
2025-04-28 11:06:32 +08:00
4759bbdb95
feat: add image preview functionality and update model name instructions in EditChannel
2025-04-27 17:20:49 +08:00
5bf1f2f275
refactor: rename InitModelSettings to InitRatioSettings
2025-04-26 17:15:34 +08:00
e24d9bd8db
fix: update cacheRatioMap initialization in InitModelSettings function
2025-04-26 17:09:23 +08:00
f4dcf8d6b6
feat: initialize cacheRatioMap in InitModelSettings function
2025-04-26 17:06:03 +08:00
9246dd2070
fix: handle optional user_group_ratio in LogsTable and render helper
2025-04-26 15:59:49 +08:00
1ab9892090
Merge remote-tracking branch 'new-api/main' into gpt-image
2025-04-26 15:54:08 +08:00
0647872c15
feat: support image edit model mapping
2025-04-24 21:41:38 +08:00
873ebcf0c7
feat: support /images/edit
2025-04-24 19:25:08 +08:00
1727d5664a
Merge pull request #950 from datehoer/main
2025-04-26 15:34:15 +08:00
8160fb642c
Merge pull request #843 from IllTamer/pr
2025-04-25 18:27:45 +08:00
b26b34ec2f
Merge branch 'main' into pr
2025-04-25 18:27:11 +08:00
a0017f2235
feat: 增加sendcloud邮件服务器的支持 (#947 )
2025-04-25 18:17:46 +08:00
b16c05ead4
fix: remove apikey from test channel log, close #1000
2025-04-25 17:08:26 +08:00
283d021fa2
refactor: update deepseek beta api
2025-04-25 16:26:16 +08:00
fea6f17e80
fix: GetMaxUserId use Unscope, close #987
2025-04-25 16:13:11 +08:00
f77a153e6c
Merge pull request #975 from asjfoajs/qn-main
2025-04-25 11:59:05 +08:00
c1a0ca0bc7
refactor: update claude media source handling
2025-04-24 15:59:43 +08:00
3169bfe362
refactor: update ClaudeMessageSource struct to include optional Url field and adjust media source handling in relay-claude #993
2025-04-24 00:39:09 +08:00
2b1470d5f7
f*** gemini
2025-04-19 18:07:51 +08:00
91902ce1f4
refactor: enhance SystemSetting submission logic and handle empty WorkerUrl
2025-04-19 00:20:25 +08:00
fdd349c909
refactor: update GeminiThinkingConfig initialization
2025-04-18 23:13:28 +08:00
ace677b3e7
refactor: remove unsupported 'exclusiveMinimum' field from cleanFunctionParameters
2025-04-18 22:40:05 +08:00
6e2e10adf1
refactor: remove unsupported root-level fields from cleanFunctionParameters
2025-04-18 21:38:12 +08:00
1989ae95c1
refactor: streamline value assignment in SettingGeminiModel
2025-04-18 20:08:26 +08:00
d378543819
feat: add gemini thinking suffix support #981
2025-04-18 19:36:18 +08:00
8ead0864b5
refactor: remove reasoning field from GeneralOpenAIRequest struct
2025-04-17 17:11:42 +08:00
80e6b9e04e
feat: add reasoning field to GeneralOpenAIReques
2025-04-17 17:09:46 +08:00
b364e9e3b1
refactor: simplify model prefix checks and update message role for o-series models
2025-04-17 16:50:52 +08:00
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
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
c20fbec17b
Merge pull request #927 from QuentinHsu/refactor-system-setting
2025-04-16 16:27:11 +08:00
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
50bf4a6615
refactor: remove unused mutex from RelayInfo struct
2025-04-15 23:06:32 +08:00
115c85390f
fix: claude parallel function calling
2025-04-15 04:52:33 +08:00
effa523a54
feat: support gemini output text and inline images. (close #866 )
2025-04-15 02:32:51 +08:00
44a14ced01
fix: try to fix claude to openai format mcp #966
2025-04-15 01:16:06 +08:00
12ca7c4789
Merge pull request #967 from neotf/fix-01
2025-04-15 00:05:41 +08:00
e3b262da1d
feat: 添加流模式下的SSE保活机制 #945
2025-04-14 19:40:23 +08:00
935cc1c605
fix: wrong systemStr for Claude (OpenAI Upstream)
2025-04-14 01:09:02 +08:00
da86db0d46
fix: update model name handling in UI and localization
2025-04-12 17:44:29 +08:00
75f0cb8eb0
feat: add error logging functionality to relay and update logs table for error type display
2025-04-12 00:43:34 +08:00
f970a03986
fix: xAI usage
2025-04-11 23:31:32 +08:00
74d9bb1a12
feat: enhance Claude to OpenAI request conversion with additional relay info support
2025-04-11 19:13:38 +08:00
9e4506ebaf
feat: 完善openai转claude支持
2025-04-11 18:28:50 +08:00
c94f662829
chore: update .gitignore and docker-compose.yml to include tiktoken_cache directory
2025-04-11 16:24:27 +08:00
577b18a1a1
feat: enhance file handling and logging in the application
2025-04-11 16:23:54 +08:00
7e0d4cd055
refactor: move maxFileSize variable inside GetFileBase64FromUrl function
2025-04-11 15:53:23 +08:00
95f0ed1821
feat: implement parameter cleaning for Gemini functions
2025-04-10 22:35:03 +08:00
984f91d111
feat: support zhipu_4v embeddings path
2025-04-10 20:53:51 +08:00
cc219801f8
Merge pull request #959 from Praying/main
2025-04-10 17:21:55 +08:00
60a9bd45c6
feat: add xAI handling and response processing
2025-04-10 17:20:59 +08:00
5bcfb8507d
fix(relay): 优化数据流处理
2025-04-10 16:56:16 +08:00
b40bf7c812
Merge pull request #953 from wkxu/main
2025-04-10 16:14:11 +08:00
55ec0e5424
Merge pull request #956 from HynoR/feat/xai
2025-04-10 16:13:48 +08:00
cdd58282c2
feat: update adaptor methods and add new image model
2025-04-10 15:08:12 +08:00
5c1386af2c
feat: add xai grok-3-mini reasoning effort
2025-04-10 13:31:43 +08:00
4622c17c83
feat: add xai channel
2025-04-10 12:26:48 +08:00
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
3f58fcb4f3
Merge pull request #944 from lamcodes/main
2025-04-10 00:09:54 +08:00
32db85607e
fix: Update model ratios for gemini-2.5-pro
2025-04-10 00:09:11 +08:00
ed855e78f7
refactor: Remove duplicate model settings initialization in main function
2025-04-10 00:07:34 +08:00
b4889878d0
refactor: Update localization keys for API address in English translations and adjust related UI labels
2025-04-09 22:22:19 +08:00
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
20c47c12b4
Update: Gemini channel fetch_models
2025-04-08 22:43:13 +08:00
ac06e9a46f
feat: Add CheckSetup function call in main to ensure proper initialization #942
2025-04-08 18:14:36 +08:00
97be874cf5
Merge pull request #930 from Yiffyi/main
2025-04-08 17:39:42 +08:00
c40404a8c1
Update MaxTokens for gemini model to 300 in test request
2025-04-08 17:37:25 +08:00
ba9cd9314b
Merge pull request #936 from lamcodes/main
2025-04-08 17:33:31 +08:00
950572b02e
Set MaxTokens to 50 for gemini
2025-04-08 17:33:10 +08:00
tbphp