64 Commits

Author SHA1 Message Date
Seefs
0e9198e9b5 fix: preserve explicit zero values in native relay requests 2026-03-01 15:47:03 +08:00
Seefs
a0bb78edd0 fix: 使用openai兼容接口调用部分渠道在最终端点为claude原生端点下还是走了openai扣减input_token的逻辑 2026-02-07 14:21:19 +08:00
CaIon
1d611d89d2 remove: drop support for claude-2 and claude-1 series models
- Remove claude-instant-1.2, claude-2, claude-2.0, claude-2.1 from model lists
- Remove /v1/complete endpoint support (legacy completion API)
- Remove RequestModeCompletion and related code paths
- Simplify handler functions by removing requestMode parameter
- Update all channel adaptors that referenced claude handlers
2026-02-05 17:20:46 +08:00
Seefs
2c29993cfc feat: /v1/responses qwen3 max 2026-02-02 14:41:27 +08:00
Seefs
540cf6c991 fix: channel affinity (#2799)
* fix: channel affinity log styles

* fix: Issue with incorrect data storage when switching key sources

* feat: support not retrying after a single rule configuration fails

* fix: render channel affinity tooltip as multiline content

* feat: channel affinity cache hit

* fix: prevent ChannelAffinityUsageCacheModal infinite loading and hide data before fetch

* chore: format backend with gofmt and frontend with prettier/eslint autofix
2026-02-02 14:37:31 +08:00
Xyfacai
cf745623f8 feat(qwen): support qwen image sync image model config 2026-01-22 17:46:36 +08:00
Seefs
9037d992be fix: Only models with the "qwen" designation can use the Claude-compatible interface; others require conversion. 2026-01-20 22:56:02 +08:00
Seefs
63921912dd fix: replace Alibaba's Claude-compatible interface with the new interface 2026-01-20 22:36:36 +08:00
Seefs
67ba913b44 feat: add support for Doubao /v1/responses (#2567)
* feat: add support for Doubao /v1/responses
2026-01-03 12:35:35 +08:00
CaIon
2a5b2add9a refactor(image): remove unnecessary logging in oaiImage2Ali function 2025-12-31 00:23:19 +08:00
CaIon
48d358faec feat(adaptor): 新适配百炼多种图片生成模型
- wan2.6系列生图与编辑,适配多图生成计费
- wan2.5系列生图与编辑
- z-image-turbo生图,适配prompt_extend计费
2025-12-29 23:00:17 +08:00
feitianbubu
344a799fcf feat: add wan2.5-i2i-preview support 2025-11-14 20:30:18 +08:00
CaIon
de93fa5f5f refactor(adaptor): Comment out enable_thinking logic for clarity and future adjustments 2025-11-12 17:24:25 +08:00
CaIon
00782aae88 refactor: comment out image file validation for qwen edit in Ali image processing 2025-11-01 14:31:32 +08:00
creamlike1024
cdbc7a9510 refactor: remove unused functions and imports from ali text handler 2025-10-18 17:00:28 +08:00
Seefs
e1c7a4f41f format: package name -> github.com/QuantumNous/new-api (#2017) 2025-10-11 15:30:09 +08:00
CaIon
d374a22b70 feat: support qwen-image-edit 2025-08-25 14:33:12 +08:00
CaIon
de23ccd234 feat: update ali image response handling 2025-08-24 22:50:45 +08:00
CaIon
7fbf9c4851 feat: enhance image request handling and add async support 2025-08-24 21:52:56 +08:00
Nekohy
652d71d799 feats:Standardize ClaudeHandler, add zhipu_4v Anthropic native support 2025-08-18 13:14:48 +08:00
CaIon
6748b006b7 refactor: centralize logging and update resource initialization
This commit refactors the logging mechanism across the application by replacing direct logger calls with a centralized logging approach using the `common` package. Key changes include:

- Replaced instances of `logger.SysLog` and `logger.FatalLog` with `common.SysLog` and `common.FatalLog` for consistent logging practices.
- Updated resource initialization error handling to utilize the new logging structure, enhancing maintainability and readability.
- Minor adjustments to improve code clarity and organization throughout various modules.

This change aims to streamline logging and improve the overall architecture of the codebase.
2025-08-14 21:10:04 +08:00
CaIon
e2037ad756 refactor: Introduce pre-consume quota and unify relay handlers
This commit introduces a major architectural refactoring to improve quota management, centralize logging, and streamline the relay handling logic.

Key changes:
- **Pre-consume Quota:** Implements a new mechanism to check and reserve user quota *before* making the request to the upstream provider. This ensures more accurate quota deduction and prevents users from exceeding their limits due to concurrent requests.

- **Unified Relay Handlers:** Refactors the relay logic to use generic handlers (e.g., `ChatHandler`, `ImageHandler`) instead of provider-specific implementations. This significantly reduces code duplication and simplifies adding new channels.

- **Centralized Logger:** A new dedicated `logger` package is introduced, and all system logging calls are migrated to use it, moving this responsibility out of the `common` package.

- **Code Reorganization:** DTOs are generalized (e.g., `dalle.go` -> `openai_image.go`) and utility code is moved to more appropriate packages (e.g., `common/http.go` -> `service/http.go`) for better code structure.
2025-08-14 20:05:06 +08:00
CaIon
f6c7828160 feat: implement moonshot adaptor for request handling and response processing 2025-08-08 17:28:21 +08:00
CaIon
0ea0a432bf feat: support qwen claude format 2025-08-07 18:32:31 +08:00
feitianbubu
38067f1ddc feat: enable thinking mode on ali thinking model 2025-08-07 11:59:54 +08:00
creamlike1024
d2183af23f feat: convert gemini format to openai chat completions 2025-08-01 22:23:35 +08:00
CaIon
0cd93d67ff fix: auto ban 2025-07-30 18:39:19 +08:00
feitianbubu
5b869376ab fix: ali embedding support base64 2025-07-20 12:05:20 +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
skynono
6b1f94348a fix: ali embedding lose prompt_tokens 2025-07-02 15:12:02 +08:00
CaIon
281054ff4c 🐛 fix: replace direct response body closure with common.CloseResponseBodyGracefully for improved error handling
This update standardizes the closure of HTTP response bodies across multiple stream handlers, enhancing error management and resource cleanup. The new method ensures that any errors during closure are handled gracefully, preventing potential request termination issues.
2025-06-27 21:40:36 +08:00
CaIon
3002659f47 feat: add CloseResponseBodyGracefully function to handle HTTP response body closure 2025-06-27 21:37:13 +08:00
Calcium-Ion
bf296d92a5 Merge pull request #1174 from QuantumNous/refactor/message
refactor: message content 改成 any
2025-06-08 16:22:20 +08:00
Calcium-Ion
ed84f937e3 Merge pull request #1177 from QuantumNous/alpha
merge alpha to main
2025-06-08 02:26:06 +08:00
Xyfacai
b778cd2b23 refactor: message content 改成 any
refactor: message content 改成 any
2025-06-07 23:47:22 +08:00
RedwindA
f1f07cb31b 🐛 fix(ali): Remove hardcoding of embedding model names. 2025-06-07 22:28:32 +08:00
RedwindA
49e77fb3df feat: ali rerank 2025-06-07 21:29:46 +08:00
skynono
368fd75c86 fix: ali parameter.enable_thinking must be set to false for non-streaming calls 2025-05-26 17:41:02 +08:00
王永振
f17f38e569 fix: ALI completions api path error 2025-05-13 13:39:44 +08:00
creamlike1024
425feb88d8 feat: support /v1/responses API 2025-05-02 13:59:46 +08:00
CaIon
b64480b750 fix: gemini thinking tokens count #1014 2025-04-29 16:21:54 +08:00
CalciumIon
69e44a03b1 refactor: Simplify OpenAI handler function signature and remove unused TextResponseWithError struct; introduce common_handler for rerank functionality 2025-03-14 17:31:05 +08:00
Calcium-Ion
e5b6aa6e85 Merge pull request #857 from asjfoajs/main
Refactor: Optimize the ImageHandler under the Alibaba large model to …
2025-03-13 19:51:08 +08:00
1808837298@qq.com
7e46d4217d feat: 初步兼容流模式下openai渠道类型转为claude格式访问 #862 2025-03-13 19:32:08 +08:00
霍雨佳
23596d22c9 Refactor: Optimize the ImageHandler under the Alibaba large model to retrieve the key from the header.
Reason: The info parameter already includes the key, so there is no need to retrieve it again from the header.
Solution: Delete the code for obtaining the key and directly use info.ApiKey.
2025-03-13 08:54:45 +08:00
1808837298@qq.com
bd48f43410 feat: claude relay 2025-03-12 21:31:46 +08:00
霍雨佳
434e9d7695 Fix: Under Ali's large model, the task ID result for image retrieval is incorrect.
Reason: The URL is incomplete, missing baseurl.
Solution: Add baseurl. url := fmt.Sprintf("%s/api/v1/tasks/%s", info.BaseUrl, taskID).
2025-03-10 16:22:40 +08:00
1808837298@qq.com
37a83ecc33 refactor: Centralize stream handling and helper functions in relay package 2025-03-05 19:47:41 +08:00
1808837298@qq.com
f5e3063f33 feat: Improve embedding request handling and support across channels
- Update EmbeddingRequest DTO to support more flexible input types
- Add input parsing method to handle various input formats
- Implement ConvertEmbeddingRequest for multiple channel adaptors
- Remove relayMode parameter from EmbeddingHelper
- Add input validation for embedding requests
- Simplify embedding request conversion for different channels
2025-02-12 14:39:36 +08:00
Jerry
7588c42b42 Fix M3E not working 2025-01-23 05:54:39 +08:00