t0ng7u
8e3f9b1faa
🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt meta when token count is disabled
...
Clamp request body size (including post-decompression) to avoid memory exhaustion caused by huge payloads/zip bombs, especially with large-context Claude requests. Add a configurable `MAX_REQUEST_BODY_MB` (default `32`) and document it.
- Enforce max request body size after gzip/br decompression via `http.MaxBytesReader`
- Add a secondary size guard in `common.GetRequestBody` and cache-safe handling
- Return **413 Request Entity Too Large** on oversized bodies in relay entry
- Avoid building large `TokenCountMeta.CombineText` when both token counting and sensitive check are disabled (use lightweight meta for pricing)
- Update READMEs (CN/EN/FR/JA) with `MAX_REQUEST_BODY_MB`
- Fix a handful of vet/formatting issues encountered during the change
- `go test ./...` passes
2025-12-16 17:00:19 +08:00
Seefs
4e69c98b42
Merge pull request #2412 from seefs001/pr-2372
...
feat: add openai video remix endpoint
2025-12-11 23:35:23 +08:00
Seefs
5889571108
fix: Use channel proxy settings for task query scenarios
2025-12-09 11:15:27 +08:00
CaIon
3f7ea1fd83
fix(vertex): ensure sampleCount is a positive integer and update OtherRatios
2025-11-30 19:05:33 +08:00
Seefs
ded463ee57
Revert "Gemini Veo3.1[AI Studio]增加图生视频支持"
2025-11-30 18:45:37 +08:00
feitianbubu
f7d6c36032
feat: gemini video veo3.1 add task fail check
2025-11-26 21:56:14 +08:00
feitianbubu
4a367edfde
feat: gemini video veo3.1 add i2v
2025-11-26 21:56:13 +08:00
feitianbubu
d8dc8029c0
feat: add hailuo i2v fl2v r2v
2025-11-14 11:55:43 +08:00
feitianbubu
87bc4ba419
feat: get hailuo video url
2025-11-14 11:55:43 +08:00
feitianbubu
850a553958
feat: add MiniMax Hailuo video
2025-11-14 11:55:43 +08:00
feitianbubu
1a8d89c410
feat: vidu reference2video only viduq2
2025-11-10 16:37:27 +08:00
feitianbubu
a62d96c1f1
feat: vidu specify reference2video via metadata action
2025-11-10 16:37:26 +08:00
Seefs
2fd33ea294
Merge pull request #2168 from feitianbubu/pr/fix-jimeng-1080p-image
...
fix: trim suffix p for jimeng image model
2025-11-06 19:54:02 +08:00
CaIon
424325162e
feat: enhance Ali video request processing with resolution mapping and size validation
2025-11-05 16:02:39 +08:00
feitianbubu
14295f0035
fix: trim suffix p for jimeng image model
2025-11-04 20:21:33 +08:00
feitianbubu
8599b348c0
feat: jimeng_v30_pro only jimeng_ti2v_v30_pro model
2025-11-04 18:29:53 +08:00
CaIon
70f8a59a65
fix: improve error handling and validation in Ali video request conversion
2025-10-31 22:39:35 +08:00
CaIon
a4cf9bb6fe
feat: enhance Ali video request handling and validation
2025-10-31 22:26:56 +08:00
Seefs
ab30f584cc
feat: add ali wan video ( #2141 )
...
* feat: add ali wan video
* refactor: use same UnmarshalBodyReusable
* feat: enhance request body metadata
* feat: opt wan convertToOpenAIVideo
* feat: add wan support other param via json metadata
* refactor: remove unused code
* fix ali
---------
Co-authored-by: feitianbubu <feitianbubu@qq.com >
2025-10-31 16:51:05 +08:00
Seefs
9629c8a771
fix veo3 ( #2140 )
2025-10-31 15:29:17 +08:00
Seefs
fc56f45628
Merge pull request #2075 from feitianbubu/pr/add-gemini-veo-video
...
Gemini渠道支持veo视频生成
2025-10-31 13:57:59 +08:00
Sh1n3zZ
810641a264
feat: vertex veo sora-compatible video output
2025-10-25 02:00:35 +08:00
IcedTangerine
5c792263ba
Add type assertion for task_request in adaptor.go
2025-10-18 23:07:50 +08:00
feitianbubu
fa81fe9396
feat: gemini veo req to struct
2025-10-18 21:55:25 +08:00
feitianbubu
f0a727ccb8
feat: veo video url use proxy download
2025-10-18 21:55:25 +08:00
feitianbubu
b77bf11b02
feat: add gemini veo3.1
2025-10-18 21:55:25 +08:00
CaIon
aa35d8db69
refactor: update ConvertToOpenAIVideo method to return byte array and improve error handling
2025-10-14 23:03:17 +08:00
skynono
826ef2e5a6
feat: jimeng images base64 limit ( #2032 )
2025-10-13 15:17:23 +08:00
Seefs
4a4238d830
Merge pull request #2029 from feitianbubu/pr/jimeng-support-oai-files
...
feat: jimeng use openai sdk input_reference i2v
2025-10-13 14:14:43 +08:00
feitianbubu
dfca9681c8
feat: jimeng use openai sdk input_reference i2v
2025-10-13 13:06:03 +08:00
Xyfacai
a6e6897f63
refactor: Openai video model 移动到 dto
2025-10-13 11:45:45 +08:00
feitianbubu
e08f799994
feat: add vidu use openai sdk
2025-10-11 17:11:44 +08:00
feitianbubu
cc41ac63bf
fix: kling create video via openai sdk
2025-10-11 17:11:44 +08:00
feitianbubu
4e0f4b207d
refactor: add openaiVideo and method
2025-10-11 17:05:36 +08:00
feitianbubu
8a7033e5a3
feat: add jimeng use openai sdk
2025-10-11 17:05:33 +08:00
Seefs
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api ( #2017 )
2025-10-11 15:30:09 +08:00
feitianbubu
11e8e4e7a6
feat: add openai sdk for kling
2025-10-11 02:43:56 +08:00
feitianbubu
35422b316d
refactor: openAI video use OpenAIVideoConverter
2025-10-11 02:43:43 +08:00
feitianbubu
2479da4986
feat: add sora video fetch task
2025-10-10 15:25:29 +08:00
feitianbubu
b880094296
feat: add sora video proxy video content
2025-10-09 15:00:02 +08:00
feitianbubu
9c37b63f2e
feat: add sora video retrieve task
2025-10-09 15:00:02 +08:00
feitianbubu
9f4a2d64a3
feat: add sora video submit task
2025-10-09 15:00:02 +08:00
CaIon
60dc910a27
fix: update jwt package import to v5 across multiple files
2025-10-09 14:17:49 +08:00
feitianbubu
b244a06ca1
feat: add doubao video use quota by total token
2025-10-02 04:00:46 +08:00
feitianbubu
c320410c84
feat: add doubao video generate
2025-10-02 04:00:43 +08:00
feitianbubu
8f9960bcc7
feat: vidu video add starEnd and reference gen video
2025-09-19 18:54:45 +08:00
feitianbubu
3c70617060
feat: vidu video support multi images
2025-09-19 18:54:40 +08:00
CaIon
b5d3e87ea2
Merge branch 'alpha'
2025-09-19 14:20:15 +08:00
Xyfacai
91e57a4c69
feat: jimeng kling 支持new api 嵌套中转
2025-09-16 16:28:27 +08:00
feitianbubu
f3e220b196
feat: jimeng video 3.0 req_key convert
2025-09-15 15:54:13 +08:00
