Commit Graph

394 Commits

Author SHA1 Message Date
Keyang Ru
d3d7f960b5 [router] Switch MCP tests from DeepWiki to self-hosted Brave search server (#12849) 2025-11-07 16:16:07 -08:00
Chang Su
e434187289 [router][grpc] Move all error logs to their call sites (#12859) 2025-11-07 15:55:34 -08:00
Chang Su
fe19a580fb [router][grpc] Refactor: Add builders for chat and responses (#12852) 2025-11-07 15:43:32 -08:00
Keyang Ru
5c9273c032 [router] Support structured model output for openai and grpc router (#12431) 2025-11-07 10:16:45 -08:00
Chang Su
2cb42dc184 [router][grpc] Add more mcp test cases to responses api (#12749) 2025-11-06 10:20:00 -08:00
Keyang Ru
8be0e1bc9c fix ci (#12760) 2025-11-06 00:21:11 -08:00
Keyang Ru
74630ba310 [router][ci] Disable cache (#12752) 2025-11-05 22:49:03 -08:00
Chang Su
837b08eb2e [router][grpc] Support mixin tool calls in Responses API (#12736) 2025-11-05 21:29:45 -08:00
Keyang Ru
74243dffa2 Revert "[router] web_search_preview tool basic implementation" (#12716) 2025-11-05 18:57:39 -08:00
Keyang Ru
7ef1964a66 [router] add basic ci tests for gpt-oss model support (#12651)
Co-authored-by: Chang Su <chang.s.su@oracle.com>
2025-11-05 15:45:11 -08:00
Keyang Ru
b0476a0642 [router][quick fix] Add minimal option for reasoning effort in spec (#12711) 2025-11-05 15:43:19 -08:00
Chang Su
ffba61a100 [router][grpc] Make harmony parser checks recipient first before channel (#12713) 2025-11-05 15:33:52 -08:00
Keyang Ru
80802c4cc6 [router][ci] speed up python binding to 1.5 min (#12673) 2025-11-05 14:52:33 -08:00
wyx
3651cfbf62 [router] fix: validate HTTP status codes in health check (#12631) 2025-11-05 13:37:17 -08:00
Chang Su
4fe53e5888 [router][grpc] Support streaming parsing with Tool Choice in chat completions API (#12677) 2025-11-05 12:12:21 -08:00
Chang Su
9f5e701879 [router][grpc] Implement tool_choice support for Responses API (#12668) 2025-11-04 21:43:42 -08:00
Chang Su
1357ab025a [router][grpc] Emit OutputItemDone event and store output item array (#12656) 2025-11-04 17:01:03 -08:00
Chang Su
887742a1e7 [router][grpc] Fix index issues in reasoning content and missing streaming events (#12650) 2025-11-04 15:38:43 -08:00
Chang Su
0e82fd3df4 [router][grpc] Fix model validation, tool call check, streaming logic and misc in responses (#12616) 2025-11-04 02:21:58 -08:00
fzyzcjy
d84790db39 Support aggregating engine metrics in sgl-router (#11456) 2025-11-04 01:59:50 -08:00
Chang Su
83804bc626 [router][grpc] Restructure modules and code clean up (#12598) 2025-11-03 23:59:27 -08:00
Chang Su
0b41a293fa [router][grpc] Consolidate error messages build in error.rs (#12301) 2025-11-03 14:41:45 -08:00
Keyang Ru
72b5f3d0bb [ci] install released version router (#12410) 2025-10-30 21:59:08 -07:00
Simo Lin
6237754842 [router] 0.2.2 release (#12399) 2025-10-30 14:40:13 -07:00
Keyang Ru
96ac24c09e [router] web_search_preview tool basic implementation (#12290) 2025-10-30 14:37:28 -07:00
Keyang Ru
4d2f17bd0b [router] Function call support for openai router Responses API (#12386) 2025-10-30 12:45:10 -07:00
Keyang Ru
69bf801173 [router] Fix safety_identifier missing (#12404) 2025-10-30 10:40:50 -07:00
rongfu.leng
2cf3d0f89f [router] use safety_identifier replace user on chat history storage (#12185) 2025-10-30 08:47:22 -07:00
Simo Lin
700daa3463 [router] harmony responses api streaming support (#12395) 2025-10-30 07:30:48 -07:00
Simo Lin
03b3e89aea [router] Harmony Pipeline: Chat Completion & Responses API with MCP Support (#12153)
Co-authored-by: Chang Su <chang.s.su@oracle.com>
2025-10-29 18:52:56 -07:00
Simo Lin
5259becd3c [bug] fix router installation to include additional dependency (#12348) 2025-10-29 12:45:18 -07:00
Chang Su
d717e73ea8 [router] refactor mcp to use LRU and fix pooling bug (#12346) 2025-10-29 12:18:54 -07:00
Simo Lin
b53d9e11c6 [bug] fix router pypi license file (#12345) 2025-10-29 10:05:00 -07:00
Chang Su
400bddf24c [router] fix router release workflow and add build test in PR (#12315) 2025-10-29 08:11:45 -07:00
Feng Su
1e90fe2ed1 [Bug fix] trace: fix import error in mini_lb if sgl-router image does not install sglang (#12338) 2025-10-29 07:45:08 -07:00
Chang Su
b48354c537 [router][grpc] Fix inconsistent behavior of conversation_id not found (#12299) 2025-10-28 16:24:43 -07:00
Simo Lin
84a9d0eab2 [router] support arm, windows, mac, linux, reduce wheel size and number (#12285) 2025-10-28 12:18:51 -07:00
Keyang Ru
737b58d6dc [rust][ci] Add end-to-end tests for Oracle history backend (#12233) 2025-10-28 10:57:32 -07:00
Simo Lin
25e73640f4 [router] upgrade grpc dependency and py 3.13 3.14 support (#12284) 2025-10-28 08:51:32 -07:00
Keyang Ru
9288544180 [router] Fix type unmatch during validation (#12257) 2025-10-28 06:04:54 -07:00
Feng Su
ea96106000 [Feature] Sglang Tracing: Fine-Grained Tracking for Request Latency - Part 2 (#10804)
Signed-off-by: Feng Su <sufeng@linux.alibaba.com>
2025-10-28 01:25:46 -07:00
Simo Lin
d85d6dba3b [router] configure workflow retries and timeout based on routerConfig (#12252) 2025-10-28 00:41:20 -07:00
Simo Lin
c5642a7a7a [router] use mcp struct from sdk and clean up code across codebase (#12249) 2025-10-28 00:33:10 -07:00
Simo Lin
83b2240074 [router] remove code duplication (#12245) 2025-10-27 23:01:44 -07:00
rongfu.leng
09af0a7b5a [sgl-route] Optimize the use of constant slices and retain to simplif… (#12159)
Signed-off-by: rongfu.leng <lenronfu@gmail.com>
2025-10-26 21:14:33 -07:00
Chang Su
a124b517f6 [router] Remove SharedXxxStorage type aliases to make Arc explicit (#12171) 2025-10-26 14:48:07 -07:00
Chang Su
d05a968ba8 [router][grpc] Add ResponsesContext and fix error propagation in responses api (#12164) 2025-10-26 14:07:19 -07:00
Simo Lin
9e949e5877 [router] centralize mcp tool args handling (#12155) 2025-10-26 01:47:12 -07:00
Chang Su
6dbb569bc3 [router][grpc] Fix tool call id in parse_json_schema_response (#12152) 2025-10-26 01:40:53 -07:00
Chang Su
773d89da8c [router] cleaned up all the redundant comments in the config module (#12147) 2025-10-25 23:10:59 -07:00