1054 Commits

Author SHA1 Message Date
CaIon
2189fd8f3e feat(gemini): implement video generation configuration and billing estimation
- Added Gemini video generation configuration structures and payloads.
- Introduced functions for parsing and resolving video duration and resolution from metadata.
- Enhanced the Vertex adaptor to support Gemini video generation requests and billing estimation based on duration and resolution.
- Updated model pricing settings for new Gemini video models.
2026-02-28 17:37:08 +08:00
CaIon
4a4cf0a0df fix: improve multipart form data handling by detecting content type. fix #3007 2026-02-25 12:51:46 +08:00
hekx
98de082804 fix: skip Accept-Encoding during header passthrough (#2214) 2026-02-24 09:58:50 +08:00
Calcium-Ion
d0b35ed60b Merge pull request #2959 from seefs001/fix/gemini-tool-use-token
fix: unify usage mapping and include toolUsePromptTokenCount
2026-02-22 23:35:09 +08:00
Calcium-Ion
4b058b4a1d Merge pull request #2960 from seefs001/feature/minimax-native-claude
feat: minimax native /v1/messages
2026-02-22 23:32:53 +08:00
CaIon
3b6af5dca3 refactor: clean up unused code and improve error logging in adaptor and mjp modules 2026-02-22 22:11:05 +08:00
CaIon
ec5c6b28ea feat(task): add model redirection, per-call billing, and multipart retry fix for async tasks
1. Async task model redirection (aligned with sync tasks):
   - Integrate ModelMappedHelper in RelayTaskSubmit after model name
     determination, populating OriginModelName / UpstreamModelName on RelayInfo.
   - All task adaptors now send UpstreamModelName to upstream providers:
     - Gemini & Vertex: BuildRequestURL uses UpstreamModelName.
     - Doubao & Ali: BuildRequestBody conditionally overwrites body.Model.
     - Vidu, Kling, Hailuo, Jimeng: convertToRequestPayload accepts RelayInfo
       and unconditionally uses info.UpstreamModelName.
     - Sora: BuildRequestBody parses JSON and multipart bodies to replace
       the "model" field with UpstreamModelName.
   - Frontend log visibility: LogTaskConsumption and taskBillingOther now
     emit is_model_mapped / upstream_model_name in the "other" JSON field.
   - Billing safety: RecalculateTaskQuotaByTokens reads model name from
     BillingContext.OriginModelName (via taskModelName) instead of
     task.Data["model"], preventing billing leaks from upstream model names.

2. Per-call billing (TaskPricePatches lifecycle):
   - Rename TaskBillingContext.ModelName → OriginModelName; add PerCallBilling
     bool field, populated from TaskPricePatches at submission time.
   - settleTaskBillingOnComplete short-circuits when PerCallBilling is true,
     skipping both adaptor adjustments and token-based recalculation.
   - Remove ModelName from TaskSubmitResult; use relayInfo.OriginModelName
     consistently in controller/relay.go for billing context and logging.

3. Multipart retry boundary mismatch fix:
   - Root cause: after Sora (or OpenAI audio) rebuilds a multipart body with a
     new boundary and overwrites c.Request.Header["Content-Type"], subsequent
     calls to ParseMultipartFormReusable on retry would parse the cached
     original body with the wrong boundary, causing "NextPart: EOF".
   - Fix: ParseMultipartFormReusable now caches the original Content-Type in
     gin context key "_original_multipart_ct" on first call and reuses it for
     all subsequent parses, making multipart parsing retry-safe globally.
   - Sora adaptor reverted to the standard pattern (direct header set/get),
     which is now safe thanks to the root fix.

4. Tests:
   - task_billing_test.go: update makeTask to use OriginModelName; add
     PerCallBilling settlement tests (skip adaptor adjust, skip token recalc);
     add non-per-call adaptor adjustment test with refund verification.
2026-02-22 16:33:00 +08:00
CaIon
a920d1f925 refactor(relay): rename RelayTask to RelayTaskFetch and update routing
- Renamed RelayTask function to RelayTaskFetch for clarity.
- Updated routing in relay-router.go and video-router.go to use RelayTaskFetch for fetch operations.
- Enhanced error handling in RelayTaskFetch function.
- Adjusted task data conversion in TaskAdaptor to include task ID.
2026-02-22 16:01:19 +08:00
CaIon
d6e11fd2e1 feat(task): add adaptor billing interface and async settlement framework
Add three billing lifecycle methods to the TaskAdaptor interface:
- EstimateBilling: compute OtherRatios from user request before pricing
- AdjustBillingOnSubmit: adjust ratios from upstream submit response
- AdjustBillingOnComplete: determine final quota at task terminal state

Introduce BaseBilling as embeddable no-op default for adaptors without
custom billing. Move Sora/Ali OtherRatios logic from shared validation
into per-adaptor EstimateBilling implementations.

Add TaskBillingContext to persist pricing params (model_price, group_ratio,
other_ratios) in task private data for async polling settlement.

Extract RecalculateTaskQuota as a general-purpose delta settlement
function and unify polling billing via settleTaskBillingOnComplete
(adaptor-first, then token-based fallback).
2026-02-22 16:00:27 +08:00
CaIon
9e3954428d refactor(task): extract billing and polling logic from controller to service layer
Restructure the task relay system for better separation of concerns:
- Extract task billing into service/task_billing.go with unified settlement flow
- Move task polling loop from controller to service/task_polling.go (supports Suno + video platforms)
- Split RelayTask into fetch/submit paths with dedicated retry logic (taskSubmitWithRetry)
- Add TaskDto, TaskResponse generics, and FetchReq to dto/task.go
- Add taskcommon/helpers.go for shared task adaptor utilities
- Remove controller/task_video.go (logic consolidated into service layer)
- Update all task adaptors (ali, doubao, gemini, hailuo, jimeng, kling, sora, suno, vertex, vidu)
- Simplify frontend task logs to use new TaskDto response format
2026-02-22 16:00:27 +08:00
wellsgz
452ac1cdb8 feat: add aws claude-sonnet-4-6 model mapping 2026-02-21 13:24:30 +08:00
Seefs
721d0a41fb feat: minimax native /v1/messages 2026-02-17 17:27:57 +08:00
Seefs
4360393dc1 fix: unify usage mapping and include toolUsePromptTokenCount in input tokens 2026-02-17 15:45:14 +08:00
Seefs
c78b37662b fix: ignore header passthrough during channel tests 2026-02-12 15:16:24 +08:00
CaIon
197b89ea58 feat: refactor request body handling to use BodyStorage for improved efficiency 2026-02-12 01:51:27 +08:00
funkpopo
75e533edb0 feat(xai): 为xAI渠道添加/v1/responses支持 (#2897)
* feat(xai): 为xAI渠道添加/v1/responses支持

* Add video generation model to constants

* fix: 修正先前更改中对于grok-3-mini的思考预算和"-search"设计
2026-02-12 00:42:39 +08:00
CaIon
f57f7646d3 feat: refactor extra_body handling for improved configuration parsing 2026-02-11 22:15:22 +08:00
Calcium-Ion
897955256e Merge pull request #2889 from seefs001/feature/messages2responses
feat: /v1/messages -> /v1/responses
2026-02-08 00:25:27 +08:00
Calcium-Ion
bc6810ca5a Merge pull request #2887 from seefs001/fix/claude
fix: 补全 streaming message_delta 事件缺失的 input_tokens 和 cache 相关字段
2026-02-08 00:18:04 +08:00
Calcium-Ion
742f4ad1e4 Merge pull request #2883 from seefs001/fix/claude-relay-info-input-token
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
2026-02-08 00:17:50 +08:00
Seefs
2faa873caf Merge branch 'feature/messages2responses' into upstream-main
# Conflicts:
#	service/openaicompat/chat_to_responses.go
2026-02-08 00:16:35 +08:00
Calcium-Ion
ce0113a6b5 Merge pull request #2864 from seefs001/fix/thining-summary
fix: add paragraph breaks between reasoning summary chunks
2026-02-08 00:15:32 +08:00
Calcium-Ion
78ddb85f22 Merge pull request #2852 from seefs001/fix/codex-tips
feat: add Codex channel disclaimer (i18n, OpenAI terms)
2026-02-08 00:07:41 +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
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
Seefs
aa8240e482 feat: /v1/messages -> /v1/responses 2026-02-06 15:22:32 +08:00
Seefs
a1695b7657 feat: gpt-5.3-codex 2026-02-06 14:47:23 +08:00
Seefs
b580b8bd1d fix: add paragraph breaks between reasoning summary chunks in chat2responses stream 2026-02-06 14:46:29 +08:00
Papersnake
c9f5de7048 feat: support adaptive thinking 2026-02-06 11:01:23 +08:00
Papersnake
ff71786d8d fix: aws claude 2026-02-06 09:51:15 +08:00
Papersnake
2504818b5a feat: add claude-opus-4-6 2026-02-06 09:12:45 +08:00
CaIon
b55e42eda7 feat(api): add 'cookie' to passthroughSkipHeaderNamesLower 2026-02-05 22:16:35 +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
ecebd619a4 fix: charge local input tokens when Gemini returns empty response 2026-02-05 15:57:17 +08:00
dahetaoa
05ed9d43af fix(relay/codex): optimize headers and ensure instructions presence 2026-02-04 21:43:33 +00:00
Calcium-Ion
a21ee5f9ed Merge pull request #2840 from seefs001/feature/header-regex-override
feat: 支持基于Go Regex规则和全量的请求体透传
2026-02-05 01:56:27 +08:00
Seefs
f3e6585441 feat: add header passthrough 2026-02-05 01:43:49 +08:00
Seefs
32fae53a3f fix reasoning_effort log 2026-02-05 00:31:52 +08:00
Seefs
7e13a01a96 fix: map Responses reasoning stream to chat completion deltas
fix: default summary = detailed

fix ReasoningContent

fix ReasoningContent

fix ReasoningContent

fix ReasoningContent

Revert "fix ReasoningContent"

This reverts commit 45a88f78b91ce2376bca68745d19374bb9e95e88.

fix ReasoningContent

fix ReasoningContent
2026-02-05 00:12:16 +08:00
CaIon
7cfed0df8e refactor(gemini): remove GeminiVisionMaxImageNum constant and related image count logic 2026-02-04 19:10:06 +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
thirking
8d67c571e4 fix: remove unnecessary unescapeMapOrSlice call in Gemini relay
The JSON serialization/deserialization already handles escape characters
correctly, so the unescapeMapOrSlice function is redundant.
2026-02-03 11:47:45 +08:00
Seefs
cbebd15692 fix: vertex maas api addr (#2810)
* fix: vertex maas api addr
2026-02-03 00:09:45 +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
Calcium-Ion
5d2e45a147 Merge pull request #2803 from seefs001/feature/qwen-responses
feat: /v1/responses qwen3 max && perplexity
2026-02-02 21:22:25 +08:00
Calcium-Ion
1788fb290e fix: claude panic (#2804) 2026-02-02 21:22:07 +08:00
Seefs
4978fead3a Merge pull request #2805 from lanfunoe/fix/make-channel-Host-override-take-effect
fix: make channel Host override take effect
2026-02-02 21:20:31 +08:00
Seefs
57b9905539 fix: claude panic 2026-02-02 15:03:30 +08:00
lanfunoe
0d5ae12ebc fix: make channel Host override take effect 2026-02-02 14:59:36 +08:00