woody
|
94b40aab9a
|
feat(ai-proxy): support Qwen reranks and conversations paths (#3724)
|
2026-04-16 15:52:58 +08:00 |
|
woody
|
26e17c48eb
|
fix(ai-proxy): migrate Qwen responses endpoint to new compatible path (#3722)
|
2026-04-16 10:13:25 +08:00 |
|
JianweiWang
|
b1187cc14d
|
feat(ai-security-guard): enhance risk action resolution and support sensitive data masking (#3690)
Co-authored-by: rinfx <yucheng.lxr@alibaba-inc.com>
|
2026-04-15 11:14:56 +08:00 |
|
johnlanni
|
e2beb6cd45
|
Revert "feat(model-mapper): 新增 modelToHeader 配置项并优化 header 更新逻辑 || feat(model-mapper): Added modelToHeader configuration item and optimized header update logic (#3689)"
This reverts commit 60ce07d297.
|
2026-04-11 07:57:38 +08:00 |
|
github-actions[bot]
|
899633ea5e
|
Add release notes (#3696)
Co-authored-by: EndlessSeeker <153817598+EndlessSeeker@users.noreply.github.com>
|
2026-04-10 13:56:25 +08:00 |
|
woody
|
bf96860a78
|
fix(vertex): add API Key auth for Vertex Raw Express Mode and fix tok… (#3695)
|
2026-04-10 09:55:27 +08:00 |
|
EndlessSeeker
|
2c15f97246
|
Release 2.2.1 (#3692)
v2.2.1
|
2026-04-09 20:11:46 +08:00 |
|
icylord
|
69523292cb
|
feat(helm): Optimize Helm charts, fine-tune the imagePullPolicy configuration for gateway, plugin server, and controller pods (#3550)
|
2026-04-08 21:47:48 +08:00 |
|
rinfx
|
60ce07d297
|
feat(model-mapper): 新增 modelToHeader 配置项并优化 header 更新逻辑 || feat(model-mapper): Added modelToHeader configuration item and optimized header update logic (#3689)
|
2026-04-08 17:12:46 +08:00 |
|
rinfx
|
228eb27e6a
|
feat(ai-proxy): 新增 providerBasePath 配置并优化 providerDomain 处理方式 (#3686)
|
2026-04-08 15:23:15 +08:00 |
|
JianweiWang
|
1c9e981bf2
|
feat(ai-security-guard): replace denyMessage with structured DenyResponseBody (#3642)
Co-authored-by: rinfx <yucheng.lxr@alibaba-inc.com>
|
2026-04-01 19:38:01 +08:00 |
|
woody
|
89587c1c9b
|
fix: remove non-standard thinking/reasoning_max_tokens from Claude-to… (#3667)
|
2026-04-01 09:40:14 +08:00 |
|
woody
|
cd8ed99db5
|
Vertex structured outputs (#3649)
|
2026-03-30 17:26:55 +08:00 |
|
woody
|
889ea67013
|
feat(provider): 优化 Azure multipart 处理 || feat(provider): Optimize Azure multipart processing (#3651)
|
2026-03-30 13:45:41 +08:00 |
|
Kent Dong
|
83461887dc
|
fix: Remove unused pilot values in the helm chart (#3657)
|
2026-03-30 13:45:13 +08:00 |
|
Kent Dong
|
983c57f404
|
fix: Fix a bug in template processor occurred when mixing default and non-default namespaces in one config (#3652)
|
2026-03-27 20:02:22 +08:00 |
|
rinfx
|
231ba1cd23
|
support gemini & claude domain setting (#3638)
|
2026-03-26 11:12:30 +08:00 |
|
Jholly
|
3fc01913cf
|
docs: replace broken higress.io links (#3644)
Co-authored-by: Kent Dong <kentstl@163.com>
|
2026-03-26 09:39:44 +08:00 |
|
shiyan
|
213286bb9e
|
fix(kingress): include header match in duplicate-route dedup key (#3580)
Fix incorrect duplicate-route detection in the KIngress controller that caused header-differentiated routes to be silently dropped.
|
2026-03-24 16:17:46 +08:00 |
|
shiyan
|
c75f741104
|
fix: update kingress status logic (#3575)
Signed-off-by: shi_yan <shi_yan@trip.com>
|
2026-03-24 14:58:01 +08:00 |
|
rinfx
|
cce53203ce
|
ai-statistics: increase default value_length_limit and emit AILog during streaming usage (#3624)
|
2026-03-23 14:04:02 +08:00 |
|
daofeng
|
23a0299d3b
|
feat: add CI workflow to build and push plugin-server image on release (#3632)
|
2026-03-22 22:11:03 +08:00 |
|
澄潭
|
36a1680952
|
Update model configurations for new GPT-5.4 versions
|
2026-03-22 16:16:49 +08:00 |
|
Kent Dong
|
ca22fcb90b
|
feat: Add responses to the default path suffix list of model-router and model-mapper (#3585)
|
2026-03-20 13:52:49 +08:00 |
|
Sunrisea
|
70ec36107a
|
chore(nacos): upgrade nacos-sdk-go/v2 from v2.3.2 to v2.3.5 (#3587)
|
2026-03-20 13:46:41 +08:00 |
|
澄潭
|
ca7ee6ef5f
|
feat(ai-proxy): add promoteThinkingOnEmpty and hiclawMode config options (#3625)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-03-20 00:39:47 +08:00 |
|
woody
|
045238944d
|
Feat/new api path support (#3620)
|
2026-03-19 19:25:55 +08:00 |
|
woody
|
62df71aadf
|
feat(ai-proxy): 添加Amazon Bedrock Prompt Cache保留策略配置及优化缓存处理逻辑 (#3609)
|
2026-03-18 20:37:04 +08:00 |
|
woody
|
8961db2e90
|
fix: vertex streaming chunk parse (#3599)
|
2026-03-16 21:13:18 +08:00 |
|
woody
|
94f0d7179f
|
fix: bedrock canonical URI sig (#3590)
|
2026-03-16 14:54:19 +08:00 |
|
澄潭
|
f1e305844e
|
feat(ai-proxy): add mergeConsecutiveMessages option to merge consecutive same-role messages (#3598)
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-03-16 14:28:17 +08:00 |
|
woody
|
68d6090e36
|
feat(bedrock): prompt caching params transform (#3563)
|
2026-03-12 17:44:42 +08:00 |
|
LiuXiang
|
65aba909d7
|
Fix duplicate import (#3582)
Signed-off-by: LiuXiang <lx1036@126.com>
|
2026-03-11 09:42:21 +08:00 |
|
Kent Dong
|
528e6c9908
|
rel: Upgrade console to v2.2.1 and release higress v2.2.1 (#3570)
|
2026-03-09 11:52:59 +08:00 |
|
Damos chen
|
13b808c1e4
|
fix(mcp-session): send SSE endpoint event via local goroutine InjectData (#3567)
|
2026-03-05 20:17:16 +08:00 |
|
johnlanni
|
aa502e7e62
|
remove openai-compat in developerRoleSupportedProviders
|
2026-03-05 10:09:47 +08:00 |
|
johnlanni
|
2e3f6868df
|
Revert "openai compatiable developer replace"
This reverts commit 6c9747d778.
|
2026-03-05 10:07:54 +08:00 |
|
johnlanni
|
6c9747d778
|
openai compatiable developer replace
|
2026-03-04 19:57:31 +08:00 |
|
woody
|
c12183cae5
|
修复 ai-proxy 插件 Bedrock Provider 在 AWS AK/SK 鉴权模式下仅对部分 API 进行 SigV4 签名的问题 || Fixed the problem of ai-proxy plug-in Bedrock Provider only performing SigV4 signature on some APIs in AWS AK/SK authentication mode (#3549)
|
2026-03-02 09:55:31 +08:00 |
|
woody
|
e2a22d1171
|
[ai-proxy] vertex image edits & variations (#3536)
|
2026-02-27 10:18:30 +08:00 |
|
Jingze
|
e9aecb6e1f
|
fix(ai-proxy): update anthropic messages endpoint path for qwen provider (#3530)
|
2026-02-25 10:26:25 +08:00 |
|
github-actions[bot]
|
b3fb6324a4
|
Add release notes (#3524)
Co-authored-by: johnlanni <6763318+johnlanni@users.noreply.github.com>
|
2026-02-22 20:14:09 +08:00 |
|
澄潭
|
8576128e4c
|
feat(ai-statistics): add Claude/Anthropic streaming tool calls parsing support (#3523)
|
2026-02-21 14:14:22 +08:00 |
|
澄潭
|
caa5317723
|
feat: share hub parameter between deployments and plugins with separate namespaces (#3521)
|
2026-02-20 23:30:48 +08:00 |
|
澄潭
|
093ef9a2c0
|
Update index.ts
|
2026-02-19 12:47:34 +08:00 |
|
澄潭
|
9346f1340b
|
refactor: migrate MCP SDK to main repo (#3516)
|
2026-02-16 23:39:18 +08:00 |
|
澄潭
|
87c6cc9c9f
|
Fix model pattern for Dashscope entry
|
2026-02-16 22:40:37 +08:00 |
|
澄潭
|
ac29ba6984
|
Rename qwen3-coder-plus to qwen3.5-plus
|
2026-02-16 22:24:58 +08:00 |
|
澄潭
|
1c847dd553
|
feat(ai-proxy): strip dynamic cch field from billing header to enable caching (#3518)
|
2026-02-15 23:57:08 +08:00 |
|
澄潭
|
a07f5024a9
|
fix(ai-proxy): convert OpenAI tool role to Claude user role with tool_result (#3517)
|
2026-02-15 22:45:09 +08:00 |
|