Commit Graph

85 Commits

Author SHA1 Message Date
wellsgz
86def71df0 feat: add aws claude-sonnet-4-6 model mapping 2026-02-21 13:24:30 +08:00
CaIon
29d48e262e feat: refactor request body handling to use BodyStorage for improved efficiency 2026-02-12 01:51:27 +08:00
Papersnake
e194b747c3 feat: support adaptive thinking 2026-02-06 11:01:23 +08:00
Papersnake
27825ec377 fix: aws claude 2026-02-06 09:51:15 +08:00
Papersnake
7ca072b1b0 feat: add claude-opus-4-6 2026-02-06 09:12:45 +08:00
CaIon
330e1e6395 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
9ef9e78821 feat(file): unify file handling with a new FileSource abstraction for URL and base64 data 2026-02-04 18:23:17 +08:00
Seefs
0ef2804757 fix: fix the proxyURL is empty, not using the default HTTP client configuration && the AWS calling side did not apply the relay timeout. 2026-01-05 17:56:24 +08:00
t0ng7u
c2ed76ddfd 🛡️ 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
zdwy5
85ecad90a7 fix: 支持aws 通过全局参数透传或者渠道参数透传来 调用 (#2423)
* fix: 支持aws 通过全局参数透传或者渠道参数透传来 调用

* fix(aws): replace json.Unmarshal with common.Unmarshal for request body processing

---------

Co-authored-by: r0 <liangchunlei@01.ai>
Co-authored-by: CaIon <i@caion.me>
2025-12-12 17:09:27 +08:00
jason.mei
f928e9d5da fix(aws): simplify HTTP status code extraction from AWS errors 2025-11-28 18:03:53 +08:00
jason.mei
a925b8ecb9 fix(aws): extract HTTP status code from AWS SDK errors 2025-11-28 17:43:37 +08:00
Papersnake
766b6bc795 feat: add claude-opus-4-5-20251101 2025-11-25 10:53:01 +08:00
CaIon
0d16a06c3a fix: aws 2025-11-18 16:56:46 +08:00
creamlike1024
11426aa83a fix(relay/channel/aws): 修复AnthropicBeta字段的omitempty处理 2025-11-14 15:54:12 +08:00
CaIon
d2c268dd51 feat(aws): Add support for anthropic-beta header in AwsClaudeRequest 2025-11-14 12:01:20 +08:00
Seefs
576775cbe1 Merge pull request #2098 from HynoR/chore/c1
chore: Update AWS claude 4.5 haiku model's information
2025-10-28 18:32:23 +09:00
iwu
ea6dc0c338 feat: aws client supports proxy settings
Signed-off-by: iwu <iwu@tencent.com>
2025-10-27 15:00:20 +08:00
HynoR
87d72a50c9 chore: update aws claude 4.5 haiku model's information 2025-10-24 14:21:17 +08:00
CaIon
6df44134ab refactor: rename AWS model ID and region prefix functions for clarity 2025-10-16 12:10:55 +08:00
CaIon
48cadc95f3 feat: 修复aws渠道-thinking后缀不生效的问题 2025-10-15 18:49:27 +08:00
CaIon
1fdb54651b feat: 临时兼容aws使用链接媒体 2025-10-15 18:21:19 +08:00
CaIon
59caea8f34 feat: support aws bedrock api-keys-use 2025-10-15 17:29:10 +08:00
CaIon
31e09b960f refactor: aws 2025-10-15 16:44:33 +08:00
Seefs
5010f2d004 format: package name -> github.com/QuantumNous/new-api (#2017) 2025-10-11 15:30:09 +08:00
CaIon
9d418d0df8 refactor(adaptor): extract common header operations into a separate function 2025-10-02 15:28:09 +08:00
Seefs
853814045a Merge pull request #1925 from seefs001/feature/claude-context-editing
feat: claude context editing
2025-09-30 09:48:32 +08:00
Seefs
a7f6065f42 feat: claude context editing 2025-09-30 09:22:40 +08:00
papersnake
112ab0b17c feat: support claude-sonnet-4-5-20250929 2025-09-30 09:14:12 +08:00
huanghejian
a069d03ef7 feat: amazon nova model 2025-09-26 15:55:00 +08:00
huanghejian
5545e70a42 feat: amazon nova model 2025-09-26 15:32:59 +08:00
huanghejian
837f5556d9 feat: improve nova config 2025-09-11 12:31:43 +08:00
huanghejian
b10ed4b424 pref: support amazon nova 2025-09-11 12:17:16 +08:00
huanghejian
2d4ecaaf28 feat: amazon.nova-premier-v1:0 2025-09-11 10:01:54 +08:00
huanghejian
f795148c58 feat: support amazon nova 2025-09-10 20:30:00 +08:00
creamlike1024
bbfbce9c67 fix: claude header was not set correctly 2025-09-09 23:18:07 +08:00
CaIon
77b100ba2b refactor: update function signatures to include context and improve file handling #1599 2025-08-15 18:40:54 +08:00
CaIon
4c0c9ffd0a feat: add AWS invoke error handling and new error code 2025-08-09 19:26:41 +08:00
Calcium-Ion
f1faa08c1e Merge pull request #1508 from wzxjohn/feature/aws_new_apikey_support
feat: support aws bedrock apikey
2025-08-06 12:04:28 +08:00
Calcium-Ion
e7c657ef87 Merge pull request #1511 from neotf/feat-05
feat: add support for claude-opus-4-1 model and update ratios
2025-08-06 12:03:33 +08:00
neotf
c9bcdc89f0 feat: add support for claude-opus-4-1 model and update ratios 2025-08-06 00:58:46 +08:00
wzxjohn
d31027d5c7 feat: support aws bedrock apikey 2025-08-05 23:01:30 +08:00
creamlike1024
689dbfe71a feat: convert gemini format to openai chat completions 2025-08-01 22:23:35 +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
daggeryu
0a7842e897 fix aws claude-sonnet-4-20250514 2025-05-24 01:21:14 +08:00
CaIon
eea5967e2c feat: add support for new regions in Claude Sonnet 4 and Claude Opus 4 models in AWS constants 2025-05-23 21:11:00 +08:00
CaIon
3cc1a79449 feat: add new model entries for Claude Sonnet 4 and Claude Opus 4 across multiple components, including constants and cache settings 2025-05-23 15:20:16 +08:00
creamlike1024
8ea4c76f2b feat: support /v1/responses API 2025-05-02 13:59:46 +08:00
1808837298@qq.com
6e17d31e92 feat: Add support for cross-region AWS model handling in awsStreamHandler 2025-03-17 23:41:00 +08:00
1808837298@qq.com
9b2cc6add7 feat: Enhance ConvertClaudeRequest method to set request model and handle vertex-specific request conversion 2025-03-17 17:13:33 +08:00