Repository navigation
feat: support PG-OPD unified training flow - #198
Merged
Merged
Conversation
added 4 commits
September 17, 2026 11:47
- 增加 pg-opd 训练类型与 teacher_model 请求传递 - 支持本地数据集自动上传及可选 Rollout/Reward 组件 - 修正函数启动脚本写入路径并补充示例与回归测试
- 将 SDK 请求和示例中的训练类型调整为 pg_opd - 更新中英文文档与 OPD 单元测试
- 补 tests/__init__.py 与 tests/unit/__init__.py:仓库测试从 namespace 目录变
为正规包,避免被 site-packages 中同名 tests 包遮蔽(本机 2026-09-02 实测:
环境被装入了带 __init__.py 的 tests 包后,tests.unit.mock_server 无法导入)
- setup.py find_packages 的 exclude=("tests") 裸字符串按字符拆分、实际不排除
任何包;改为 ("tests", "tests.*"),防止 tests 进入 wheel
- 为 test_opd.py 与 test_agentic_rl_cli_opd.py 补 utf-8 编码声明 - 按仓库锁定的 black 23.3.0(line-length=79)重排两个测试文件 - test_opd.py 增加 redefined-outer-name 豁免(pytest fixture 标准用法)
caogaoshuai
force-pushed
the
feat/pg-opd
branch
from
September 17, 2026 03:57
8e1bd1b to
c7e7808
Compare
added 2 commits
September 17, 2026 12:12
- fix-encoding-pragma 钩子会把只含 coding pragma 的文件截断为空,__init__.py 恢复为空文件(pre-commit-hooks v4.3.0 特殊分支) - add-trailing-comma 钩子要求 AsyncMock 调用补尾随逗号
- --teacher-model 存在性改由 typer get_command 命令模型校验（不再断言渲染文本） - rich 在不同终端宽度/平台（Linux CI 80 列）会截断或连字符换行 option 名，导致误报 - help 文档散文断言保留，增加 ANSI 剥离
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
概述
支持 PG-OPD 统一训练流程，统一 OPD 训练类型值，并修复测试包结构问题。
改动内容
测试