Feature/eval optimize loop#221
Open
guocfu wants to merge 19 commits into
Open
Conversation
仅实现 Pipeline 配置校验和 Prompt 隔离工作区创建,不执行实际评测、提示词优化、Gate 或报告生成。
添加 Prompt 感知的 fake agent 与确定性候选提供器。 完成 baseline/candidate 的 train/validation 四次评测,并补充输入漂移保护和离线回归测试。
Contributor
AI Code Review我已经完成了全面审查。让我来撰写最终的审查结论。 发现的问题
|
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
关联 Issue
Closes #91
变更说明
本 PR 实现 Evaluation + Optimization 自动回归与提示词优化闭环,覆盖离线验证、Trace 回放和真实模型集成三种运行方式。
主要流程:
主要能力
AgentOptimizer(update_source=False),候选生成期间不直接修改源 Prompt。运行模式
offline:真实LlmAgent配合确定性模型和确定性评测规则。trace:回放预录制轨迹,不执行 Agent。real:真实业务模型配合真实AgentOptimizer反思模型。真实模式必须显式传入
--run-real,连接信息从环境变量读取,优化模型参数通过命令行参数传入。测试覆盖
执行:
pytest -q tests/evaluation/test_eval_optimize_loop_*.py本功能相关测试全部通过。