Commit Graph

314 Commits

Author SHA1 Message Date
creamlike1024 689dbfe71a feat: convert gemini format to openai chat completions 2025-08-01 22:23:35 +08:00
CaIon 563d056ff7 refactor: update error handling to support dynamic error types 2025-07-31 21:16:01 +08:00
CaIon 2cb7b9ae62 fix: improve error messaging and JSON schema handling in distributor and relay components 2025-07-26 12:11:20 +08:00
CaIon f610773455 feat: enhance request handling with pass-through options and system prompt support 2025-07-26 11:39:09 +08:00
CaIon c5ec332ab3 fix: add Think field to OllamaRequest and support extra parameters in GeneralOpenAIRequest. (close #1125
)
2025-07-22 12:06:21 +08:00
feitianbubu 9c3a22964b fix: ali embedding support base64 2025-07-20 12:05:20 +08:00
Xyfacai dfc826a388 fix(response): tools 需要处理的参数很少 使用 map 2025-07-20 11:21:57 +08:00
Calcium-Ion fd3fe7fe0d Merge pull request #1383 from feitianbubu/pr/fix-gemini-and-claude-completions
fix: usage cost(any) to support claude and gemini
2025-07-17 19:16:55 +08:00
Calcium-Ion a1609f36c7 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
feitianbubu b1cf5d7705 fix: usage cost(any) to support claude and gemini 2025-07-16 16:58:34 +08:00
creamlike1024 e351642db9 feat: claude web search tool 计费 2025-07-15 18:57:22 +08:00
creamlike1024 aeca676d55 feat: RequestOpenAI2ClaudeMessage add more parms map 2025-07-15 12:38:05 +08:00
t0ng7u a66430c82c Merge remote-tracking branch 'origin/multi_keys_channel' into alpha
# Conflicts:
#	web/src/components/table/LogsTable.js
#	web/src/i18n/locales/en.json
#	web/src/pages/Channel/EditChannel.js
2025-07-12 23:47:24 +08:00
RedwindA 98696526d4 feat: 支持 xAI 网络搜索 2025-07-12 02:22:40 +08:00
CaIon 1437ceaa56 Merge branch 'alpha' into refactor_error
# Conflicts:
#	controller/channel.go
#	middleware/distributor.go
#	model/channel.go
#	model/user.go
#	model/user_cache.go
#	relay/common/relay_info.go
2025-07-10 15:11:55 +08:00
CaIon 4a9ca4209a 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
Xiangyuan-liu db98c0f4b1 refactor: log params and channel params
refactor: log params and channel params
2025-07-07 14:26:37 +08:00
Calcium-Ion aa0edd8dce Merge pull request #1321 from iszcz/main
支持Midjourney视频任务和图片编辑
2025-07-05 15:28:33 +08:00
CaIon 12977d9a52 feat: make TopN field in RerankRequest optional in JSON serialization 2025-07-03 15:45:32 +08:00
CaIon f14f4eaf1a feat: refactor environment variable initialization and introduce new constant types for API and context keys 2025-07-03 13:10:25 +08:00
iszcz d4f2f4dbbe 支持Midjourney视频任务和图片编辑 2025-06-30 22:31:12 +08:00
CaIon e2c34bdeb9 🐛 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 e234ad0740 feat: add Function and Container fields to ResponsesToolsCall struct #1305 2025-06-27 16:56:54 +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
CaIon 93fb5bab6b fix(dto): change Created field type in OpenAITextResponse to any. (close #1131) 2025-06-22 00:59:39 +08:00
t0ng7u cfef9a3b09 Merge remote-tracking branch 'origin/main' into alpha 2025-06-21 20:25:35 +08:00
t0ng7u 8248185e33 feat(ratio-sync): support /api/pricing parsing, confidence verification & UI enhancements
Backend
- controller/ratio_sync.go
  • Parse /api/pricing response and convert to ratio / price maps.
  • Introduce confidence heuristic (model_ratio = 37.5 && completion_ratio = 1) to flag unreliable data.
  • Include confidence map when building differences and filter “same”/empty entries.
- dto/ratio_sync.go
  • Add `ID` to UpstreamDTO, `upstreams` to UpstreamRequest, and `Confidence` to DifferenceItem.

Frontend
- ChannelSelectorModal.js
  • Re-implement with table layout, pagination, search, endpoint-type selector and mobile support.
- UpstreamRatioSync.js
  • Send full upstream objects, add ratio-type filter, confidence badges/tooltips, retain endpoints.
  • Leverage ChannelSelectorModal’s pagination reset.
- ChannelsTable.js – fix tag color for disabled status.
- en.json – add translations for new UI labels.

Motivation
These changes let users sync model ratios / prices from different upstream endpoints and visually identify potentially unreliable data, improving operational safety and flexibility.
2025-06-21 20:24:52 +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 c74a86d14d Merge pull request #1267 from t0ng7u/feature/upstream-ratio-sync
🔄 feat(ratio-sync): introduce upstream ratio synchronisation feature #1220
2025-06-20 16:22:00 +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
Apple\Apple cd4fc7a188 🚀 chore(controller, dto): elevate ratio-sync feature to production readiness
WHAT’S NEW
• controller/ratio_sync.go
  – Deleted unused local structs (TestResult, DifferenceItem, SyncableChannel).
  – Centralised config with constants: defaultTimeoutSeconds, defaultEndpoint, maxConcurrentFetches, ratioTypes.
  – Replaced magic numbers; added semaphore-based concurrency limit and shared http.Client (with TLS & Expect-Continue timeouts).
  – Added comprehensive error handling and context-aware logging via common.Log* helpers.
  – Checked DB errors from GetChannelsByIds; early-return on failures or empty upstream list.
  – Removed custom-channel support; logic now relies solely on ChannelIDs.
  – Minor clean-ups: import grouping, string trimming, endpoint normalisation.

• dto/ratio_sync.go
  – Simplified UpstreamRequest: dropped unused CustomChannels field.

WHY
These improvements harden the ratio-sync endpoint for production use by preventing silent failures, controlling resource usage, and making behaviour configurable and observable.

HOW
No business logic change—only structural refactor, logging, and safeguards—so existing API contracts (aside from removed custom_channels) remain intact.
2025-06-19 19:55:51 +08:00
KamiPasi 3247d7a341 透传thinking参数, 豆包模型用来控制是否思考 2025-06-19 12:06:42 +08:00
skynono d7ed0214ad feat: add video channel kling 2025-06-19 11:53:42 +08:00
Apple\Apple 8748425aa2 🚀 feat(ratio-sync): major refactor & UX overhaul for Upstream Ratio Sync 2025-06-19 08:57:34 +08:00
neotf c787f59822 Merge branch 'main' into feat-04 2025-06-18 15:20:24 +08:00
CaIon c4e652461e 🔧 refactor(dto): update BudgetTokens handling in Thinking struct 2025-06-16 18:29:49 +08:00
CaIon d26ae9aa77 feat(dto): add VlHighResolutionImages parameter to GeneralOpenAIRequest 2025-06-13 17:29:26 +08:00
neotf 342af15f73 format 2025-06-11 14:00:32 +08:00
neotf 0a3414bf26 format 2025-06-11 13:56:44 +08:00
neotf 1cff048cb7 Merge branch 'main' into feat-04 2025-06-11 13:55:47 +08:00
Xyfacai b30cf70c91 feat: dalle 格式支持自定义参数 2025-06-09 22:14:51 +08:00
Calcium-Ion a8b24bed00 Merge pull request #1184 from QuantumNous/refactor/message
fix: message 转 any 后,ImageUrl判断 panic
2025-06-09 15:51:53 +08:00
Xyfacai be38aaa80d fix: message 转 any 后,ImageUrl判断 panic 2025-06-09 11:27:24 +08:00
CaIon 2fb222b9a4 refactor(dto): change function and encoding fields to use json.RawMessage for improved flexibility 2025-06-08 16:28:47 +08:00
Xyfacai 8343fe0740 refactor: message content 改成 any
refactor: message content 改成 any
2025-06-07 23:47:22 +08:00
neotf 1ce5c34703 Merge branch 'main' into feat-04 2025-06-05 20:35:47 +08:00
neotf a813b24184 feat: support claude cache and thinking for upstream [OpenRouter] (#983)
* feat: support claude cache for upstream [OpenRouter]

* feat: support claude thinking for upstream [OpenRouter]

* feat: reasoning is common params for OpenRouter
2025-06-05 17:35:48 +08:00
CaIon 46f95fddcd feat: add ToMap method and enhance OpenAI request handling 2025-06-01 01:10:10 +08:00
neotf dde8c49a2e feat: enhance cache_create_tokens calculation for OpenRouter 2025-05-29 22:47:02 +08:00
neotf c0df38767c feat: enhance token usage details for upstream OpenRouter 2025-05-29 00:55:57 +08:00