@sofagent/ab-test
Advanced tools
sofagent A/B 测试框架——对比实验、指标显著性分析、自动 promote 决策。
# 运行 A/B 对比测试（从 golden-set YAML 加载测试用例）
sofagent ab-test run --current <skill-path> --candidate <skill-path> [options]
# 选项
sofagent ab-test run --current <path> # 当前版本 Agent Skill 路径
sofagent ab-test run --candidate <path> # 候选版本 Agent Skill 路径
sofagent ab-test run --eval-set <path> # golden-set YAML 路径（默认从 @sofagent/eval 的 golden-set.yaml 加载）
sofagent ab-test run --threshold <n> # 晋升阈值（默认 2）
# 测试用例不足时报错退出（不再使用硬编码默认用例）
运行结果持久化到 data/ab-test/latest.json（覆盖写）。
v1.2.4 起，ab-test CLI 的 run 子命令从 @sofagent/eval 的 golden-set YAML 加载测试用例，
与 eval 共享同一套 input + expected。ab-test 的 runner 是 Agent Skill 对比（current vs candidate），
不是 audit runRules——ab-test 只复用 golden set 作为 TestCase 来源。
decidePromotion() — 对比 A/B 方案指标，连续 2 轮胜出 → auto promotepersistABTestResult() — 持久化 A/B 测试结果到 latest.jsonDEFAULT_SCORE_WEIGHTS — 默认评分权重ABConfig / ABTestResult / PromotionDecision / ScoreWeights@sofagent/eval / @sofagent/core / @sofagent/inject / @sofagent/orchestratorFAQs
sofagent A/B 测试框架 — 对比实验 / 指标显著性 / 实验报告
The npm package @sofagent/ab-test receives a total of 0 weekly downloads. As such, @sofagent/ab-test popularity was classified as not popular.
We found that @sofagent/ab-test demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Threat Research
/Security News
Socket uncovered secret-stealing workflows that ran in LiteLLM’s GitHub repository 11 days before the supply chain attack on PyPI and Docker.
Security News
Cloudflare introduces tsrs, a Rust port of TypeScript’s compiler promising faster checks and lower memory use, with the TypeScript team’s help.
Security News
The PHP Foundation says Chainguard broke a security embargo ahead of critical RCE patches, as leaks disrupted the coordinated release.