Commit Graph

672 Commits

Author SHA1 Message Date
CaIon
d084083e05 fix: update JSON decoding and budget token handling in RequestOpenAI2ClaudeMessage 2025-06-22 01:15:01 +08:00
Calcium-Ion
877529ef6b Merge pull request #1120 from neotf/feat-04
feat: enhance token usage details for upstream OpenRouter
2025-06-22 01:10:49 +08:00
Calcium-Ion
2dee2300eb Merge pull request #1235 from prnake/thinking-fix-0616
feat: openrouter format for claude request
2025-06-22 01:08:01 +08:00
Calcium-Ion
45543411cb Merge pull request #1279 from feitianbubu/add-kling-key-placeholder
feat: add placeholder for kling AccessKey and SecretKey
2025-06-22 00:46:09 +08:00
CaIon
7de52a0c0d feat(gemini): enhance ThinkingAdapter and model handling
- Introduced `isNoThinkingRequest` and `trimModelThinking` functions to manage model names and thinking configurations.
- Updated `GeminiHelper` to conditionally adjust the model name based on the thinking budget and request settings.
- Refactored `ThinkingAdaptor` to streamline the integration of thinking capabilities into Gemini requests.
- Cleaned up commented-out code in `FetchUpstreamModels` for clarity.

These changes improve the handling of model configurations and enhance the adaptability of the Gemini relay system.
2025-06-21 21:50:03 +08:00
skynono
1add4bf937 feat: kling apiKey format to use | delimiter 2025-06-21 21:38:36 +08:00
CaIon
d244915111 feat(relay-gemini): conditionally set ThinkingBudget based on MaxOutputTokens 2025-06-21 17:51:13 +08:00
CaIon
4307065c6c Merge branch 'main' into alpha 2025-06-21 17:04:29 +08:00
creamlike1024
5e501c22f1 Merge branch 'feat_images' of github.com:bddiudiu/new-api into bddiudiu-feat_images 2025-06-21 10:31:37 +08:00
Calcium-Ion
c60d87067d Merge pull request #1248 from RedwindA/update-gemini-ratio
feat(model-ratio): add default ratios for new Gemini models and refine flash model handling
2025-06-21 04:51:41 +08:00
CaIon
3164e86278 fix: remove unnecessary error handling in token counting functions 2025-06-21 01:16:54 +08:00
CaIon
2c0fd2915b fix: improve usage calculation in GeminiTextGenerationStreamHandler 2025-06-21 01:08:15 +08:00
CaIon
16997a695d refactor: token counter logic 2025-06-21 00:54:40 +08:00
creamlike1024
4f3024ad63 fix: gemini 原生格式流模式中断请求未计费 2025-06-20 23:01:10 +08:00
CaIon
8ceaaf7819 fix: update response handling in GeminiTextGenerationStreamHandler
- Changed response handling from ObjectData to StringData for improved data processing.
- Ensured proper error logging in case of response handling failure.
2025-06-20 21:55:28 +08:00
RedwindA
4f84fd6a71 fix: update model name logic for vertex 2025-06-20 16:40:51 +08:00
Calcium-Ion
e8da9d7dd7 Merge pull request #1270 from QuantumNous/refactor_model_mapping
feat: implement new handlers for relay processing
2025-06-20 16:12:41 +08:00
Calcium-Ion
2e242159a1 Merge pull request #1244 from feitianbubu/feat/video
feat: 支持可灵视频渠道(异步任务)
2025-06-20 16:11:59 +08:00
CaIon
13277cf838 feat: implement new handlers for audio, image, embedding, and responses processing
- Added new handlers: AudioHelper, ImageHelper, EmbeddingHelper, and ResponsesHelper to manage respective requests.
- Updated ModelMappedHelper to accept request parameters for better model mapping.
- Enhanced error handling and validation across new handlers to ensure robust request processing.
- Introduced support for new relay formats in relay_info and updated relevant functions accordingly.
2025-06-20 16:02:23 +08:00
CaIon
da067b7f90 refactor: update error handling in ClaudeHelper and GeminiHelper 2025-06-20 14:53:27 +08:00
CaIon
2b2e0a4777 feat: enhance error handling in GeminiHelper and streamline response processing
- Added status code mapping handling in GeminiHelper to reset status codes based on response.
- Removed redundant candidate check in GeminiTextGenerationHandler to simplify response processing.
2025-06-20 01:42:19 +08:00
RedwindA
50907a5758 Merge remote-tracking branch 'upstream/alpha' into update-gemini-ratio 2025-06-19 20:02:27 +08:00
CaIon
05aaf63337 Merge branch 'alpha' 2025-06-19 16:17:56 +08:00
CaIon
e685279207 fix: ratio render 2025-06-19 15:36:06 +08:00
creamlike1024
1271f8f648 update relay-gemini-native.go 2025-06-19 14:50:50 +08:00
creamlike1024
24dda1f6fa Merge branch 'main' of github.com:xqx121/new-api into xqx121-main 2025-06-19 14:45:41 +08:00
CaIon
fd943659c0 Merge remote-tracking branch 'origin/alpha' into alpha 2025-06-19 14:36:55 +08:00
CaIon
bf30adcde0 Merge branch 'main' into alpha 2025-06-19 14:36:17 +08:00
Calcium-Ion
0d51f07d8f Merge pull request #1260 from tbphp/fix-gemini-empty-content-error
fix: Gemini & Vertex empty content error
2025-06-19 14:34:27 +08:00
skynono
aaf7c88e0b feat: add video channel kling fix 2025-06-19 11:53:47 +08:00
skynono
d7ed0214ad feat: add video channel kling 2025-06-19 11:53:42 +08:00
tbphp
173594446e fix: Gemini & Vertex empty content error 2025-06-19 11:25:59 +08:00
CaIon
8d05e44f61 Merge remote-tracking branch 'origin/alpha' into alpha 2025-06-18 20:51:06 +08:00
CaIon
17f3832487 feat(relay): add debug logging for Gemini request body and introduce flexible speech configuration 2025-06-18 20:50:13 +08:00
neotf
685a65c722 format 2025-06-18 19:54:20 +08:00
Apple\Apple
175ea56fdd 🚚 Refactor(ratio_setting): refactor ratio management into standalone ratio_setting package
Summary
• Migrated all ratio-related sources into `setting/ratio_setting/`
  – `model_ratio.go` (renamed from model-ratio.go)
  – `cache_ratio.go`
  – `group_ratio.go`
• Changed package name to `ratio_setting` and relocated initialization (`ratio_setting.InitRatioSettings()` in main).
• Updated every import & call site:
  – Model / cache / completion / image ratio helpers
  – Group ratio helpers (`GetGroupRatio*`, `ContainsGroupRatio`, `CheckGroupRatio`, etc.)
  – JSON-serialization & update helpers (`*Ratio2JSONString`, `Update*RatioByJSONString`)
• Adjusted controllers, middleware, relay helpers, services and models to reference the new package.
• Removed obsolete `setting` / `operation_setting` imports; added missing `ratio_setting` imports.
• Adopted idiomatic map iteration (`for key := range m`) where value is unused.
• Ran static checks to ensure clean build.

This commit centralises all ratio configuration (model, cache and group) in one cohesive module, simplifying future maintenance and improving code clarity.
2025-06-18 18:00:49 +08:00
neotf
ecacff87ad Update relay/channel/openai/adaptor.go
use review's suggestion

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
2025-06-18 15:29:19 +08:00
neotf
c787f59822 Merge branch 'main' into feat-04 2025-06-18 15:20:24 +08:00
xqx121
2541defbf4 Update relay-gemini-native.go 2025-06-18 14:26:23 +08:00
sgyy
302ca0b847 fix: Vertex channel global region format 2025-06-18 11:21:56 +08:00
RedwindA
9bc9d40891 feat(gemini): update audio input pricing and adjust model handling logic 2025-06-18 03:25:59 +08:00
RedwindA
a004db93c9 feat(Gemini): enhance budget clamping logic for Gemini models 2025-06-18 00:49:35 +08:00
CaIon
36a0d4d7ae fix(relay): ensure consistent setting of web search context size in TextHelper function 2025-06-18 00:37:22 +08:00
CaIon
d4e20df7a6 fix(relay): refine error message for unsupported MIME types and enhance error handling in OpenAI wrapper 2025-06-17 22:44:57 +08:00
CaIon
8d0b54bf6e fix(relay): improve error handling for unsupported MIME types by sanitizing URLs 2025-06-17 22:40:41 +08:00
Calcium-Ion
129d1b081f Merge pull request #1239 from QuantumNous/auto_group
feat: auto分组
2025-06-17 21:14:09 +08:00
CaIon
4ec7012974 feat: enhance group ratio handling in pricing calculations 2025-06-17 21:05:35 +08:00
CaIon
4238068c65 feat(channel): enhance Claude response handling with new Done flag and improved usage tracking 2025-06-17 20:08:25 +08:00
CaIon
2a1ed60738 Merge branch 'alpha' 2025-06-17 14:49:13 +08:00
chenjm
ab5dfd8d97 fix(audio): :bugs: fix webm audio strconv.ParseFloat: parsing "N/A" 2025-06-17 10:04:36 +08:00