0
代码
代码
Issues
Pull Requests
讨论
Wiki
分析
0
OopenJiuwen-botfix: fix typing error
1edb2bac创建于 7 天前历史提交
文件最后提交记录最后更新时间
config
feat(online_rl): pydantic builtins replace packaged YAML defaults Refs: #837 Co-authored-by: mengyuanli<limengyuan4@huawei.com> # message auto-generated for no-merge-commit merge: !1259 feat(online_rl): pydantic builtins replace packaged YAML defaults From: @mengyuanli Reviewed-by: @deyang, @iamcandiceguo See merge request: openJiuwen/agent-core!12591 个月前
offline
fix(code): When creating a worktree, TUI does not enter the new worktree working directory. Refs: #914 Co-authored-by: weichenhao<weichenhao3@huawei.com> # message auto-generated for no-merge-commit merge: !1372 fix(code): When creating a worktree, TUI does not enter the new worktree working directory. From: @weichenhao Reviewed-by: @iamcandiceguo, @alan_cheng, @chenchunzhou See merge request: openJiuwen/agent-core!137214 天前
online
fix: fix typing error Co-authored-by: iamcandiceguo<guoqian14@huawei.com> # message auto-generated for no-merge-commit merge: !1503 fix: fix typing error From: @iamcandiceguo Reviewed-by: @deyang, @wangxiaolong100 See merge request: openJiuwen/agent-core!15037 天前
optimizer
feat(agentrl): replace in-memory training queue with Redis backend Co-authored-by: liulili-huawei<liulili715@huawei.com> Co-authored-by: mengyuanli<limengyuan4@huawei.com> Co-authored-by: zhang_xue_tong<zhangxuetong@huawei.com> # message auto-generated for no-merge-commit merge: !971 feat(agentrl): replace in-memory training queue with Redis backend From: @mengyuanli Reviewed-by: @deyang, @alan_cheng See merge request: openJiuwen/agent-core!9711 个月前
rl_trainer
feat(agentrl): replace in-memory training queue with Redis backend Co-authored-by: liulili-huawei<liulili715@huawei.com> Co-authored-by: mengyuanli<limengyuan4@huawei.com> Co-authored-by: zhang_xue_tong<zhangxuetong@huawei.com> # message auto-generated for no-merge-commit merge: !971 feat(agentrl): replace in-memory training queue with Redis backend From: @mengyuanli Reviewed-by: @deyang, @alan_cheng See merge request: openJiuwen/agent-core!9711 个月前
storage
feat(agentrl): replace in-memory training queue with Redis backend Co-authored-by: liulili-huawei<liulili715@huawei.com> Co-authored-by: mengyuanli<limengyuan4@huawei.com> Co-authored-by: zhang_xue_tong<zhangxuetong@huawei.com> # message auto-generated for no-merge-commit merge: !971 feat(agentrl): replace in-memory training queue with Redis backend From: @mengyuanli Reviewed-by: @deyang, @alan_cheng See merge request: openJiuwen/agent-core!9711 个月前
__init__.py
fix(harness): Rectify the Rails directory Co-authored-by: 李志远<lizhiyuan65@huawei.com> # message auto-generated for no-merge-commit merge: !1220 fix(harness): Rectify the Rails directory From: @wncbdj Reviewed-by: @wangxiaolong100, @SnapeK See merge request: openJiuwen/agent-core!12201 个月前
dataset.py
feat(agentrl): replace in-memory training queue with Redis backend Co-authored-by: liulili-huawei<liulili715@huawei.com> Co-authored-by: mengyuanli<limengyuan4@huawei.com> Co-authored-by: zhang_xue_tong<zhangxuetong@huawei.com> # message auto-generated for no-merge-commit merge: !971 feat(agentrl): replace in-memory training queue with Redis backend From: @mengyuanli Reviewed-by: @deyang, @alan_cheng See merge request: openJiuwen/agent-core!9711 个月前
proxy.py
fix(agent_rl): agent rl offline module security vulnerability problem fixed The utility function in the calx example uses eval to compute expression values, posing a security risk. The agent uses 0.0.0.0 as the default IP address, which also poses a security risk. Refs: #769 Co-authored-by: rolandyang<yangdongdong34@huawei.com> # message auto-generated for no-merge-commit merge: !1135 fix(agent_rl): agent rl offline module security vulnerability problem fixed From: @rolandyang Reviewed-by: @deyang, @iamcandiceguo See merge request: openJiuwen/agent-core!11351 个月前
reward.py
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!10651 个月前
rl_rail.py
fix(agent-evolving): modularize and tighten skill evolution pipelines Refactor agent evolution into explicit checkpointing, experience, signal, trajectory, and updater pipelines. - Add shared approval events and approval runtime - Extract experience scoring, tracking, lifecycle, and manager modules - Extract checkpointing archive, record, and projection helpers - Add team skill experience generation and signal detection - Accumulate session trajectories for evolution signal handling - Improve evolution experience index guidance in projected SKILL.md - Update API docs, examples, and unit coverage for the new layout BREAKING CHANGE: remove the legacy skill rewrite API and SkillRewriter exports. Refs: #890 Co-authored-by: zhangzhongteng<zhangzhongteng1@huawei.com> # message auto-generated for no-merge-commit merge: !1337 fix(agent-evolving): modularize and tighten skill evolution pipelines From: @z2tng Reviewed-by: @deyang, @SnapeK See merge request: openJiuwen/agent-core!133721 天前
schemas.py
fix(agent_rl): support token IDs and logprobs on streaming AssistantMessage Refs: 818 Co-authored-by: rolandyang<yangdongdong34@huawei.com> # message auto-generated for no-merge-commit merge: !1228 fix(agent_rl): support token IDs and logprobs on streaming AssistantMessage From: @rolandyang Reviewed-by: @deyang, @iamcandiceguo See merge request: openJiuwen/agent-core!12281 个月前