| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
fix(skill): Fix issues with skill invocation across Windows/Linux environments, and implement skill registration by directory. Refs: #680 Co-authored-by: zhiting gao<gaozhiting1@huawei.com> # message auto-generated for no-merge-commit merge: !932 fix(skill manager): Fix issues with skill invocation across Windows/Linux environments, and implement skill registration by directory. From: @AFSDFASD Reviewed-by: @SnapeK, @iamcandiceguo See merge request: openJiuwen/agent-core!932 | 6 个月前 | |
feat(agent_rl): Move to evolving dir and supports online module Move agentrl to agent_evolving directory and suport online/offline agent rl. Refs: #727 Co-authored-by: rolandyang<yangdongdong34@huawei.com> # message auto-generated for no-merge-commit merge: !1065 feat(agent_rl): Move to evolving dir and supports online module From: @rolandyang Reviewed-by: @deyang, @iamcandiceguo See merge request: openJiuwen/agent-core!1065 | 5 个月前 | |
refactor(auto-harness): extract pipeline and stage runtime | 5 个月前 | |
fix(deepagent): add explore agent for plan execution mode Refs: #703 Co-authored-by: zhangyaomaggie<zhangyao128@huawei.com> # message auto-generated for no-merge-commit merge: !1023 fix(deepagent): add explore agent for plan execution mode From: @zhangyaomaggie Reviewed-by: @SnapeK, @wangxiaolong100 See merge request: openJiuwen/agent-core!1023 | 5 个月前 | |
feat(agent_rl): Move to evolving dir and supports online module Move agentrl to agent_evolving directory and suport online/offline agent rl. Refs: #727 Co-authored-by: rolandyang<yangdongdong34@huawei.com> # message auto-generated for no-merge-commit merge: !1065 feat(agent_rl): Move to evolving dir and supports online module From: @rolandyang Reviewed-by: @deyang, @iamcandiceguo See merge request: openJiuwen/agent-core!1065 | 5 个月前 | |
feat(tests): add system tests for custom headers in LLM model invocations Refs: #714 Co-authored-by: ipanyin<pan.yin@huawei.com> # message auto-generated for no-merge-commit merge: !1066 feat(tests): add system tests for custom headers in LLM model invocations From: @ipanyin Reviewed-by: @iamcandiceguo, @alan_cheng, @deyang See merge request: openJiuwen/agent-core!1066 | 5 个月前 | |
fix(deepagent): improve performance for plan execution mode for code agent Refs: #703 Co-authored-by: zhangyaomaggie<zhangyao128@huawei.com> # message auto-generated for no-merge-commit merge: !986 fix(deepagent): improve performance for plan execution mode for code agent From: @zhangyaomaggie Reviewed-by: @SnapeK, @wangxiaolong100 See merge request: openJiuwen/agent-core!986 | 5 个月前 | |
feature: handle coding memory conflicts Refs: #705 Co-authored-by: ldstyle8<liudongdong46@huawei.com> # message auto-generated for no-merge-commit merge: !1028 feature: handle coding memory conflicts From: @ldstyle8 Reviewed-by: @iamcandiceguo, @SnapeK, @alan_cheng See merge request: openJiuwen/agent-core!1028 | 5 个月前 | |
feat(rail): add force-finish signal for immediate agent loop termination Allow rails to terminate the ReAct loop and return a custom result via ctx.request_force_finish(). The signal is checked after every railed operation (_call_model, _execute_tool_call). When set in a before hook, the decorated method body is skipped entirely. Refs: #499 Co-authored-by: sally kang<kangjiayuan@huawei.com> # message auto-generated for no-merge-commit merge: !728 feat(rail): add force-finish signal for immediate agent loop termination From: @SnapeK Reviewed-by: @alan_cheng, @yangzequ See merge request: openJiuwen/agent-core!728 | 6 个月前 | |
feat(a2a-integration) Add a2a client and agentcard conversion Refs: #700 Co-authored-by: wangyuejoanna<wangyue335@h-partners.com> # message auto-generated for no-merge-commit merge: !888 feat(a2a-integration): Add a2a client From: @gcw_XiLNLWHF Reviewed-by: @alan_cheng, @iamcandiceguo See merge request: openJiuwen/agent-core!888 | 5 个月前 | |
fix(llm): llm client type support client_registry Refs: #599 Co-authored-by: iamcandiceguo<guoqian14@huawei.com> # message auto-generated for no-merge-commit merge: !837 fix(llm): llm client type support client_registry From: @iamcandiceguo Reviewed-by: @alan_cheng, @SnapeK, @deyang See merge request: openJiuwen/agent-core!837 | 6 个月前 | |
style(context):context engine codecheck fix Refs: #80 Co-authored-by: yan_zj<yanzhijun5@huawei.com> # message auto-generated for no-merge-commit merge: !100 merge develop into develop style(context): context engine codecheck fix Created-by: yan_zj Commit-by: yan_zj Merged-by: openJiuwen-bot Description: <!-- Thanks for sending a pull request! Here are some tips for you: 1) If this is your first time, please read our contributor guidelines: https://gitcode.com/openJiuwen/community/blob/master/CONTRIBUTING.md 2) If you want to contribute your code but don't know who will review and merge, please add label openjiuwen-assistant to the pull request, we will find and do it as soon as possible. --> **What type of PR is this?** <!-- 选择下面一种标签替换下方 /kind <label>，可选标签类型有： - /kind bug - /kind task - /kind feature - /kind refactor - /kind clean_code 如PR描述不符合规范，修改PR描述后需要/check-pr重新检查PR规范。 --> - /kind clean_code **Self-checklist**:（**请自检，在[ ]内打上x，我们将检视你的完成情况，否则会导致pr无法合入**） + - [ ] **设计**：PR对应的方案是否已经经过Maintainer评审，方案检视意见是否均已答复并完成方案修改 + - [x] **测试**：PR中的代码是否已有UT/ST测试用例进行充分的覆盖，新增测试用例是否随本PR一并上库或已经上库 + - [ ] **验证**：PR描述信息中是否已包含对该PR对应的Feature、Refactor、Bugfix的预期目标达成情况的详细验证结果描述 + - [x] **接口**：是否涉及对外接口变更，相应变更已得到接口评审组织的通过，API对应的注释信息已经刷新正确 + - [ ] **文档**：是否涉及官网文档修改，如果涉及请及时提交资料到Doc仓 <!-- **Special notes for your reviewers**: --> <!-- + - [x] 是否导致无法前向兼容 --> <!-- + - [x] 是否涉及依赖的三方库变更 --> See merge request: openJiuwen/agent-core!100 | 8 个月前 | |
style: fix session/runner/worklfow/tool codecheck Refs: #80 Co-authored-by: wangguanggge<wangguangge@huawei.com> # message auto-generated for no-merge-commit merge: !235 merge develop_0124_codecheck into develop fix(session/runner/worklfow/tool): fix codecheck Created-by: wangguangge Commit-by: wangguanggge Merged-by: openJiuwen-bot Description: <!-- Thanks for sending a pull request! Here are some tips for you: 1) If this is your first time, please read our contributor guidelines: https://gitcode.com/openJiuwen/community/blob/master/CONTRIBUTING.md 2) If you want to contribute your code but don't know who will review and merge, please add label openjiuwen-assistant to the pull request, we will find and do it as soon as possible. --> **What type of PR is this?** <!-- 选择下面一种标签替换下方 /kind <label>，可选标签类型有： - /kind bug - /kind task - /kind feature - /kind refactor - /kind clean_code 如PR描述不符合规范，修改PR描述后需要/check-pr重新检查PR规范。 --> /kind clean_code **Self-checklist**:（**请自检，在[ ]内打上x，我们将检视你的完成情况，否则会导致pr无法合入**） + - [ ] **设计**：PR对应的方案是否已经经过Maintainer评审，方案检视意见是否均已答复并完成方案修改 + - [x] **测试**：PR中的代码是否已有UT/ST测试用例进行充分的覆盖，新增测试用例是否随本PR一并上库或已经上库 + - [ ] **验证**：PR描述信息中是否已包含对该PR对应的Feature、Refactor、Bugfix的预期目标达成情况的详细验证结果描述 + - [ ] **接口**：是否涉及对外接口变更，相应变更已得到接口评审组织的通过，API对应的注释信息已经刷新正确 + - [ ] **文档**：是否涉及官网文档修改，如果涉及请及时提交资料到Doc仓 <!-- **Special notes for your reviewers**: --> <!-- + - [ ] 是否导致无法前向兼容 --> <!-- + - [ ] 是否涉及依赖的三方库变更 --> See merge request: openJiuwen/agent-core!235 | 8 个月前 | |
Initial commit | 9 个月前 |
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 6 个月前 | ||
| 5 个月前 | ||
| 5 个月前 | ||
| 5 个月前 | ||
| 5 个月前 | ||
| 5 个月前 | ||
| 5 个月前 | ||
| 5 个月前 | ||
| 6 个月前 | ||
| 5 个月前 | ||
| 6 个月前 | ||
| 8 个月前 | ||
| 8 个月前 | ||
| 9 个月前 |