Commit Graph

698 Commits

Author SHA1 Message Date
TianHao Zhang
24c69fb0b7 fix concurrent SSE connections returning wrong endpoint (#3341) 2026-01-19 11:56:57 +08:00
johnlanni
a38be77b9e Fix the issue of backend errors not being propagated in streamable proxy mode 2026-01-19 11:56:57 +08:00
johnlanni
27999dcc59 fix(mcp): remove accept-encoding header to prevent response compression 2026-01-19 11:56:56 +08:00
woody
5f43dd0224 feat/ai proxy vertex ai compatible (#3324) 2026-01-19 11:56:56 +08:00
rinfx
e23ab3ca7c Replace model-router and model-mapper with Go implementation (#3317) 2026-01-19 11:54:41 +08:00
woody
032a69556f feat(vertex): 为 ai-proxy 插件的 Vertex AI Provider 添加 Express Mode 支持 || feat(vertex): Add Express Mode support to Vertex AI Provider of ai-proxy plug-in (#3301) 2026-01-19 11:54:41 +08:00
qshuai
ee6bb11730 docs: unknown config entry <show_limit_quota_header> in ai-token-ratelimit plugin (#3241) 2026-01-19 11:54:41 +08:00
CZJCC
fc600f204a feat(ai-proxy): add Bearer Token authentication support for Bedrock p… (#3305) 2026-01-19 11:54:41 +08:00
nixidexiangjiao
d55b9a0837 feat(ai-load-balancer): enhance global least request load balancer (#3255) 2026-01-19 11:54:28 +08:00
Kent Dong
95ff52cde9 feat: Add traffic-editor plugin (#2825) 2026-01-19 11:54:27 +08:00
Jingze
f342f50ca4 feat: Add response-cache plugin (#3061)
Co-authored-by: mirror58229 <674958229@qq.com>
2026-01-19 11:54:27 +08:00
澄潭
541e5e206f fix(mcp-server): fix MCP server version negotiation to comply with spec (#3258) 2026-01-19 11:54:26 +08:00
rinfx
387c337654 support disable thinking and add reasoning token usage (#3261) 2026-01-19 11:54:14 +08:00
Bingkun Zhao
8024a96881 fix: ai-proxy dify provider extract hostname from difyApiUrl (#3257) 2026-01-19 11:54:14 +08:00
rinfx
1199946d36 special handling for cases where extracted content is empty and add unit test (#3251) 2026-01-19 11:54:14 +08:00
rinfx
b1571de6f0 Cross provider lb bugfix (#3252) 2026-01-19 11:54:13 +08:00
Wangzy
6f4ef33590 Add tool-search server (#3136)
Co-authored-by: 澄潭 <zty98751@alibaba-inc.com>
2026-01-19 11:54:13 +08:00
Kent Dong
fef8ecc822 fix: Switch to the new HasRequestBody logic in ai-proxy (#3211) 2026-01-19 11:53:58 +08:00
rinfx
0ade9504be [feat] ai-security-guard support checking prompt and image in request body (#3206) 2026-01-19 11:53:58 +08:00
rinfx
6311fecfce add rebuild logic for ai-cache (#3185) 2026-01-19 11:53:58 +08:00
Kent Dong
5c225de080 fix: Enlarge the request body buffer size when processing multipart data in model-router (#3237) 2026-01-19 11:53:58 +08:00
rinfx
bf9ef5eefd support vertex's claude (#3236) 2026-01-19 11:53:57 +08:00
007gzs
c9253264ef Rust Plugin add Rule matcher test (#3230) 2026-01-19 11:53:43 +08:00
woody
8c80084ada fix(ai-proxy): ensure basePathHandling works with original protocol (#3225) 2026-01-19 11:53:43 +08:00
rinfx
698a395e89 vertex support global region (#3213) 2026-01-19 11:53:43 +08:00
澄潭
2c72767203 feat: enhance model mapper and router with rebuild triggers and path extensions (#3218) 2026-01-19 11:53:43 +08:00
Liang Deng
bb3ac59834 feat(ai-proxy): support handle array content in chatToolMessage2BedrockMessage (#3200)
Signed-off-by: Liang Deng <ytdengliang@gmail.com>
Co-authored-by: rinfx <yucheng.lxr@alibaba-inc.com>
2026-01-19 11:53:42 +08:00
johnlanni
6c1fe57034 fix(ai-proxy): only perform protocol conversion for non-original protocols
Change-Id: Ib8ae3ebf6b47284108663c97777032d6282bb53c
2026-01-19 11:53:25 +08:00
johnlanni
5c5cc6ac90 update go sum 2026-01-19 11:53:25 +08:00
johnlanni
265da8e4d6 add wrapper.WithRebuildMaxMemBytes(200MB) to ai-statistics&ai-proxy 2026-01-19 11:53:25 +08:00
johnlanni
119698eea4 update wasm-go dep of mcp-server 2026-01-19 11:53:25 +08:00
rinfx
18d20ca135 doubao support configuration for domain (#3184) 2026-01-19 11:53:24 +08:00
rinfx
9978db2ac6 [feat] ai-security-guard refactor & support checking multimoadl input (#3075) 2026-01-19 11:53:24 +08:00
Kent Dong
1582fa6ef9 fix: Bypass the response body processing for MCP streamable transport (#3187) 2026-01-19 11:53:24 +08:00
woody
2b49fd5b26 implement generic provider for vendor-agnostic passthrough (#3175) 2026-01-19 11:53:24 +08:00
woody
48433a6549 Fix OpenAI capability rewrite dropping query string (#3168) 2026-01-19 11:52:50 +08:00
rinfx
8ec48b3b85 [feat] load balancing across different clusters and endpoints based on metrics (#3063) 2026-01-19 11:52:43 +08:00
rinfx
32007d2ab8 remove omitempty for toolcall index (#3148)
Co-authored-by: 澄潭 <zty98751@alibaba-inc.com>
2026-01-19 11:52:33 +08:00
xujingfeng
c3077d7981 fix(ai-proxy): 调整日志级别以减少冗余警告信息 || fix(ai-proxy): Adjust log level to reduce redundant warning messages (#3120) 2025-11-13 19:24:14 +08:00
澄潭
ca64c9a1c7 Update proxy release binanry and fix golang-filter dependencies (#3123) 2025-11-13 15:20:18 +08:00
woody
8a3c0bb342 feat(ai-proxy): add video-related API paths and capabilities (#3108) 2025-11-11 19:39:49 +08:00
victorserbu2709
1300e09e28 groq add responses capability (#3029)
Co-authored-by: 澄潭 <zty98751@alibaba-inc.com>
2025-11-11 19:36:26 +08:00
rinfx
d4e6704f33 [bugfix] add claude usage & bedrock tool_call index (#3095) 2025-11-10 10:03:01 +08:00
澄潭
36df9ba5e8 test(mcp-server): add UT (#3097) 2025-11-06 10:36:00 +08:00
澄潭
826c4e8b4a feat(mcp-server): add server-level default authentication and MCP proxy server support (#3096) 2025-11-05 22:23:41 +08:00
rinfx
1900609fd5 include usage if stream is true (#3084) 2025-11-03 15:36:18 +08:00
johnlanni
f79e3b9556 update wasm-go sdk for wasmplugins which use redis call
Change-Id: Ifc5efb21f4860fc85d096604a53a10e85797d813
2025-11-03 15:05:03 +08:00
Tsukilc
1602b6f94a feat: add higress api mcp server (#2923)
Co-authored-by: 澄潭 <zty98751@alibaba-inc.com>
Co-authored-by: Se7en <chengzw258@163.com>
2025-10-31 15:46:14 +08:00
nohup
d745bc0d0b feat: impl nginx migration mcp server (#2916)
Co-authored-by: 韩贤涛 <601803023@qq.com>
2025-10-31 13:59:15 +08:00
Jun
ef6baf29e8 fix: rag add python example code (#3043) 2025-10-30 20:16:11 +08:00