Commit Graph

518 Commits

Author SHA1 Message Date
CaIon
94455e34e6 fix: update Init method to correctly set RequestMode based on upstream model name prefixes 2025-05-23 01:34:53 +08:00
CaIon
6436a165af feat: enhance Gemini response handling by adding reasoning content and updating JSON decoding method 2025-05-22 16:11:50 +08:00
CaIon
526b7e6048 feat: add Thought field to GeminiPart and update response handling in streamResponseGeminiChat2OpenAI 2025-05-22 15:52:23 +08:00
CaIon
0bf328939a refactor: update JSON field names in GeminiChatRequest for consistency 2025-05-19 20:26:30 +08:00
Calcium-Ion
bb18f64d1f Merge pull request #1067 from QuantumNous/coze
Coze 渠道
2025-05-16 16:11:02 +08:00
creamlike1024
63232607cf coze stream 2025-05-16 10:27:07 +08:00
creamlike1024
e9690c7ad7 add frontend display, more model 2025-05-15 20:00:59 +08:00
creamlike1024
5e8217db0f use channel bot id 2025-05-13 22:23:38 +08:00
creamlike1024
ee7cdae0a8 cozeChatHelper 2025-05-13 22:01:12 +08:00
creamlike1024
7e0b2521a7 DoRequest 2025-05-13 21:13:34 +08:00
王永振
6a92483b01 fix: ALI completions api path error 2025-05-13 13:39:44 +08:00
creamlike1024
cd8a2f85db add coze request 2025-05-13 12:52:22 +08:00
CaIon
c2f3749cfe feat: enhance OpenAI handler to support forced response formatting and add debug logging for request URLs 2025-05-09 18:57:06 +08:00
creamlike1024
92ddbc4dfd fix: GetRequestURL remove unnecessary case 2025-05-09 18:13:19 +08:00
creamlike1024
a074e994b0 feat: send SSE ping before get response 2025-05-09 13:57:00 +08:00
CaIon
66cda24386 feat: add AzureNoRemoveDotTime constant and update channel handling #1044
- Introduced a new constant `AzureNoRemoveDotTime` in `constant/azure.go` to manage model name formatting for channels created after May 10, 2025.
- Updated `distributor.go` to set `channel_create_time` in the context.
- Modified `adaptor.go` to conditionally remove dots from model names based on the channel creation time.
- Enhanced `relay_info.go` to include `ChannelCreateTime` in the `RelayInfo` struct.
- Updated English localization files to reflect changes in model name handling for new channels.
2025-05-08 23:19:40 +08:00
CaIon
abc9d60fdc fix: update OpenAI request handling to include 'o1-preview' model support #1029 2025-05-08 23:19:38 +08:00
liusanp
9265d41b84 fix: xAi response 2025-05-08 23:19:35 +08:00
liusanp
89d40bbbf3 fix: xAi requestUrl 2025-05-08 23:19:34 +08:00
liusanp
2e73714f49 fix: quality, size or style are not supported by xAI API 2025-05-08 23:19:32 +08:00
Alex Liu
7ecd9d053e fix: gemini response json schema 2025-05-07 18:08:56 +08:00
creamlike1024
a3fe88772f feat: 添加 built in tools 计费
- 增加非流的工具调用次数统计
- 添加 web search 和 file search 计费
2025-05-06 21:58:01 +08:00
CaIon
e9812b0fd5 feat: implement OpenAI responses handling and streaming support with built-in tool tracking 2025-05-05 00:40:16 +08:00
CaIon
24200df47e refactor: remove unnecessary call to helper.Done and adjust data rendering in ClaudeChunkData 2025-05-04 17:35:45 +08:00
Calcium-Ion
4cc1f2b4e3 Merge pull request #1020 from QuantumNous/v1responses
feat: support /v1/responses API
2025-05-04 17:13:39 +08:00
Calcium-Ion
fa89410e41 Merge pull request #1012 from tbphp/vertex_thinking_support
feat: support thinking suffix for vertex gemini channel
2025-05-04 17:11:27 +08:00
CaIon
209265e68c feat: enhance OaiResponsesStreamHandler to handle output text and improve response streaming 2025-05-04 17:09:37 +08:00
creamlike1024
3753e5720a add OaiResponsesStreamHandler 2025-05-03 22:36:27 +08:00
creamlike1024
8ea4c76f2b feat: support /v1/responses API 2025-05-02 13:59:46 +08:00
CaIon
d309727e99 fix: gemini thinking tokens count #1014 2025-04-29 16:21:54 +08:00
tbphp
5b81e88e41 feat: support thinking suffix for vertex gemini channel 2025-04-29 13:30:03 +08:00
CaIon
1ab9892090 Merge remote-tracking branch 'new-api/main' into gpt-image
# Conflicts:
#	relay/relay-image.go
2025-04-26 15:54:08 +08:00
CaIon
0647872c15 feat: support image edit model mapping
(cherry picked from commit 1a869d8ad77f262ee27675ec2deaf451b1743eb7)
2025-04-26 15:48:59 +08:00
xyfacai
873ebcf0c7 feat: support /images/edit
(cherry picked from commit 1c0a1238787d490f02dd9269b616580a16604180)
2025-04-26 15:44:56 +08:00
CaIon
283d021fa2 refactor: update deepseek beta api 2025-04-25 16:26:16 +08:00
CaIon
c1a0ca0bc7 refactor: update claude media source handling 2025-04-24 15:59:43 +08:00
CaIon
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
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
d378543819 feat: add gemini thinking suffix support #981 2025-04-18 19:36:18 +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
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
CaIon
e3b262da1d feat: 添加流模式下的SSE保活机制 #945 2025-04-14 19:40:23 +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
577b18a1a1 feat: enhance file handling and logging in the application 2025-04-11 16:23:54 +08:00