Commit Graph

113 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
0b3a0b38d6 fix: patch message_delta usage via gjson/sjson and skip on passthrough 2026-02-07 19:13:58 +08:00
Thomas
bbad917101 fix: 补全 streaming message_delta 事件缺失的 input_tokens 和 cache 相关字段 (#2881)
当上游为 AWS Bedrock 时,message_delta 的 usage 可能缺少 input_tokens、
cache_creation_input_tokens、cache_read_input_tokens 等字段,导致与原生
Anthropic 格式不一致。从 message_start 积累的 claudeInfo 中补全这些字段后
重新序列化,确保客户端收到一致的 usage 格式。
2026-02-07 18:17:22 +08:00
Papersnake
c9f5de7048 feat: support adaptive thinking 2026-02-06 11:01:23 +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
CaIon
9ef7740fe7 feat(file): unify file handling with a new FileSource abstraction for URL and base64 data 2026-02-04 18:23:17 +08:00
Seefs
760fbeb6e6 Merge pull request #2811 from seefs001/fix/openrouter-claude-cache-usage
fix: openrouter claude cache usage
2026-02-03 00:03:19 +08:00
Seefs
57b9905539 fix: claude panic 2026-02-02 15:03:30 +08:00
Seefs
41b33e85db fix: disable_parallel_tool_use parameter should be removed for tool_choice=none: 2026-01-28 13:31:14 +08:00
Seefs
48efa1ddb9 fix: reason convert 2026-01-25 15:31:23 +08:00
Seefs
7afa476770 feat: claude refusal reason 2026-01-25 15:21:31 +08:00
feitianbubu
3652dfdbd5 fix: check claudeResponse delta StopReason nil point 2025-12-24 11:54:23 +08:00
CaIon
f5b409d74f feat: refactor token estimation logic
- Introduced new OpenAI text models in `common/model.go`.
- Added `IsOpenAITextModel` function to check for OpenAI text models.
- Refactored token estimation methods across various channels to use estimated prompt tokens instead of direct prompt token counts.
- Updated related functions and structures to accommodate the new token estimation approach, enhancing overall token management.
2025-12-02 21:34:39 +08:00
CaIon
84745d5ca4 feat: Add ContextKeyLocalCountTokens and update ResponseText2Usage to use context in multiple channels 2025-11-21 18:17:01 +08:00
Seefs
e082268533 feat: ShouldPreserveThinkingSuffix (#2189) 2025-11-07 17:43:33 +08:00
Seefs
df2ee649ab feat: claude 1h cache (#2155)
* feat: claude 1h cache

* feat: claude 1h cache

* fix price
2025-11-04 00:20:50 +08:00
yanggh
8b9188c584 fix(convert): 修复 OpenAI 转 Claude 流时 thinking 块的格式问题
将 `ClaudeMediaMessage.Thinking` 的类型从 `string` 修改为 `*string`,以解决 `omitempty` 导致 `"thinking": ""` 字段在 JSON 序列化时被忽略的问题。

同时更新了 `service/convert.go` 和 `relay/channel/claude/relay-claude.go` 中的相关逻辑,以兼容新的指针类型,确保生成的 Claude 事件流符合官方规范。
2025-10-13 19:32:17 +08:00
Seefs
e1c7a4f41f format: package name -> github.com/QuantumNous/new-api (#2017) 2025-10-11 15:30:09 +08:00
creamlike1024
c40a4f5444 fix: claude header was not set correctly 2025-09-09 23:18:07 +08:00
Calcium-Ion
a616aa3c89 Merge pull request #1692 from yunayj/alpha
修改claude system参数为数组,增加通用性
2025-09-08 14:55:48 +08:00
creamlike1024
b29efbde52 feat(relay-claude): mapping stop reason and send text delta on block start type
- convert claude stop reason "max_tokens" to openai "length"
- send content_block_start content text delta
2025-09-07 23:03:19 +08:00
yunayj
af94e11c7d 修改claude system参数为数组格式,提升API兼容性 2025-08-29 19:06:01 +08:00
Nekohy
652d71d799 feats:Standardize ClaudeHandler, add zhipu_4v Anthropic native support 2025-08-18 13:14:48 +08:00
CaIon
0bb43aa464 refactor: update function signatures to include context and improve file handling #1599 2025-08-15 18:40:54 +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
0ea0a432bf feat: support qwen claude format 2025-08-07 18:32:31 +08:00
CaIon
d9c1fb5244 feat: update MaxTokens handling 2025-08-07 16:15:59 +08:00
CaIon
ce031f7d15 refactor: update error handling to support dynamic error types 2025-07-31 21:16:01 +08:00
Calcium-Ion
6b3f1ab0e4 Merge pull request #1384 from QuantumNous/RequestOpenAI2ClaudeMessage
feat: 改进 RequestOpenAI2ClaudeMessage 和添加 claude web search 计费
2025-07-17 19:15:54 +08:00
creamlike1024
961bc874d2 feat: claude web search tool 计费 2025-07-15 18:57:22 +08:00
creamlike1024
77da33de4f feat: RequestOpenAI2ClaudeMessage add more parms map 2025-07-15 12:38:05 +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
df862732df fix: update JSON decoding and budget token handling in RequestOpenAI2ClaudeMessage 2025-06-22 01:15:01 +08:00
Calcium-Ion
ea79d59aa0 Merge pull request #1235 from prnake/thinking-fix-0616
feat: openrouter format for claude request
2025-06-22 01:08:01 +08:00
CaIon
7afd3f97ee fix: remove unnecessary error handling in token counting functions 2025-06-21 01:16:54 +08:00
CaIon
a9e5d99ea3 refactor: token counter logic 2025-06-21 00:54:40 +08:00
CaIon
b7c3328d43 feat(channel): enhance Claude response handling with new Done flag and improved usage tracking 2025-06-17 20:08:25 +08:00
CaIon
b77574dad5 🔧 refactor(dto): update BudgetTokens handling in Thinking struct 2025-06-16 18:29:49 +08:00
Papersnake
296da5dbcc feat: openrouter format for claude request 2025-06-16 17:43:39 +08:00
Xyfacai
b778cd2b23 refactor: message content 改成 any
refactor: message content 改成 any
2025-06-07 23:47:22 +08:00
CaIon
25ae077ac9 refactor: update claude media source handling 2025-04-24 15:59:43 +08:00
CaIon
aaa41a8074 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
214ca4db56 fix: claude parallel function calling 2025-04-15 04:52:33 +08:00
CaIon
99efc1fbb6 fix: try to fix claude to openai format mcp #966 2025-04-15 01:16:06 +08:00
Seefs
20c043f584 fix: claude function calling type 2025-03-19 22:48:49 +08:00
1808837298@qq.com
8c7c39550c refactor: Update ClaudeResponse error handling to use pointer for ClaudeError and improve nil checks in response processing 2025-03-16 23:14:45 +08:00
1808837298@qq.com
53b3599827 refactor: Enhance Claude response handling 2025-03-16 19:11:58 +08:00
1808837298@qq.com
b3b1c803fc feat: Introduce JSON decoding utility functions and update error handling in Claude and OpenAI response structures 2025-03-16 18:34:39 +08:00