Commit Graph

176 Commits

Author SHA1 Message Date
RedwindA
f242220132 feat: update dto for embeddings 2025-08-09 18:31:56 +08:00
RedwindA
03b670971b Merge branch 'alpha' into 'feat/support-native-gemini-embedding' 2025-08-09 18:05:11 +08:00
Calcium-Ion
3b61617cb1 Merge pull request #1500 from antecanis8/gemini_batchembedcontents
fix: Gemini embedding model only embeds the first text in a batch
2025-08-09 11:42:08 +08:00
RedwindA
7a31e481a6 fix typo; add ParamOverride for Gemini Embedding 2025-08-09 01:07:48 +08:00
RedwindA
b70d2655ed feat: support native Gemini Embedding 2025-08-09 00:27:33 +08:00
CaIon
daa7a13505 feat: 完善格式抓换,修复gemini渠道和openai渠道在claude code中使用的问题 2025-08-08 16:45:37 +08:00
Calcium-Ion
177b891905 Merge pull request #1518 from RedwindA/fix/disable-gemini-sse
Fix/disable-gemini-ping
2025-08-07 20:44:24 +08:00
CaIon
d9c1fb5244 feat: update MaxTokens handling 2025-08-07 16:15:59 +08:00
RedwindA
1cea7a0314 fix: 调整Disable Ping标志的设置位置 2025-08-07 06:18:22 +08:00
CaIon
f46cefbd39 fix: update budget calculation logic in relay-gemini to use clamping function 2025-08-06 16:25:48 +08:00
CaIon
feef022303 feat: enhance ThinkingAdaptor with effort-based budget clamping and extra body handling 2025-08-06 16:20:38 +08:00
antecanis8
49abd6aaf3 feat: add support for configuring output dimensionality for multiple Gemini new models 2025-08-04 14:19:19 +00:00
antecanis8
43263a3bc8 fix : Gemini embedding model only embeds the first text in a batch 2025-08-04 13:02:57 +00:00
Xyfacai
10b04416c1 fix: 修复gemini2openai 没有返回 usage 2025-08-04 09:06:57 +08:00
CaIon
97d6f10f15 feat: enhance ConvertGeminiRequest to set default role and handle YouTube video MIME type 2025-08-02 12:53:58 +08:00
creamlike1024
e01986fdd4 Merge remote-tracking branch 'origin/alpha' into ConvertGeminiRequest 2025-08-01 22:42:48 +08:00
creamlike1024
d2183af23f feat: convert gemini format to openai chat completions 2025-08-01 22:23:35 +08:00
CaIon
f0945da4fb refactor: simplify streamResponseGeminiChat2OpenAI by removing hasImage return value and optimizing response text handling 2025-08-01 17:58:21 +08:00
CaIon
8df3de9ae5 fix: update JSONEditor to default to manual mode for invalid JSON and add error message for invalid data 2025-08-01 17:21:25 +08:00
CaIon
07a92293e4 fix: handle case where no response is received from Gemini API 2025-08-01 17:04:16 +08:00
CaIon
ce031f7d15 refactor: update error handling to support dynamic error types 2025-07-31 21:16:01 +08:00
creamlike1024
6a85206e32 Merge branch 'fix/gemini-native-sse' of github.com:RedwindA/new-api into RedwindA-fix/gemini-native-sse 2025-07-30 20:34:12 +08:00
CaIon
0cd93d67ff fix: auto ban 2025-07-30 18:39:19 +08:00
CaIon
010f27678d fix: auto ban 2025-07-29 15:20:08 +08:00
CaIon
8e3cf2eaab feat: support claude convert to gemini 2025-07-26 13:31:33 +08:00
CaIon
2469c439b1 fix: improve error messaging and JSON schema handling in distributor and relay components 2025-07-26 12:11:20 +08:00
RedwindA
7af3fb5ae4 禁用原生Gemini模式中的ping保活 2025-07-18 23:39:01 +08:00
CaIon
98952198bb refactor: Introduce standardized API error
This commit refactors the application's error handling mechanism by introducing a new standardized error type, `types.NewAPIError`. It also renames common JSON utility functions for better clarity.

Previously, internal error handling was tightly coupled to the `dto.OpenAIError` format. This change decouples the internal logic from the external API representation.

Key changes:
- A new `types.NewAPIError` struct is introduced to serve as a canonical internal representation for all API errors.
- All relay adapters (OpenAI, Claude, Gemini, etc.) are updated to return `*types.NewAPIError`.
- Controllers now convert the internal `NewAPIError` to the client-facing `OpenAIError` format at the API boundary, ensuring backward compatibility.
- Channel auto-disable/enable logic is updated to use the new standardized error type.
- JSON utility functions are renamed to align with Go's standard library conventions (e.g., `UnmarshalJson` -> `Unmarshal`, `EncodeJson` -> `Marshal`).
2025-07-10 15:02:40 +08:00
CaIon
6b9237f868 🐛 fix: refactor JSON unmarshalling across multiple handlers to use UnmarshalJson and UnmarshalJsonStr for consistency
This update replaces instances of DecodeJson and DecodeJsonStr with UnmarshalJson and UnmarshalJsonStr in various relay handlers, enhancing code consistency and clarity in JSON processing. The changes improve maintainability and align with recent refactoring efforts in the codebase.
2025-06-28 00:02:07 +08:00
CaIon
3002659f47 feat: add CloseResponseBodyGracefully function to handle HTTP response body closure 2025-06-27 21:37:13 +08:00
CaIon
384fadf227 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
CaIon
6bb552128c feat(relay-gemini): conditionally set ThinkingBudget based on MaxOutputTokens 2025-06-21 17:51:13 +08:00
Calcium-Ion
4ebf9e35e1 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
0708452939 fix: improve usage calculation in GeminiTextGenerationStreamHandler 2025-06-21 01:08:15 +08:00
CaIon
a9e5d99ea3 refactor: token counter logic 2025-06-21 00:54:40 +08:00
creamlike1024
a56d9ea98b 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
f5e80af0b3 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
CaIon
d3286893c4 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
5d8a0952b4 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
098880b796 Merge remote-tracking branch 'upstream/alpha' into update-gemini-ratio 2025-06-19 20:02:27 +08:00
CaIon
58752d2dcf Merge branch 'alpha' 2025-06-19 16:17:56 +08:00
creamlike1024
8201daa4b4 update relay-gemini-native.go 2025-06-19 14:50:50 +08:00
Calcium-Ion
ab78efc815 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
tbphp
a87d4271d3 fix: Gemini & Vertex empty content error 2025-06-19 11:25:59 +08:00
CaIon
7572e791f6 feat(relay): add debug logging for Gemini request body and introduce flexible speech configuration 2025-06-18 20:50:13 +08:00
xqx121
edcdb378fd Update relay-gemini-native.go 2025-06-18 14:26:23 +08:00
RedwindA
f35784aa97 feat(gemini): update audio input pricing and adjust model handling logic 2025-06-18 03:25:59 +08:00
RedwindA
21f43b0dd8 feat(Gemini): enhance budget clamping logic for Gemini models 2025-06-18 00:49:35 +08:00
CaIon
2e4fa32d63 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
0199896d9a fix(relay): improve error handling for unsupported MIME types by sanitizing URLs 2025-06-17 22:40:41 +08:00