From 8eaf522bde672a71003d58fbe9c3fda6d2f0cebb Mon Sep 17 00:00:00 2001 From: Note Flow AI Date: Fri, 2 Oct 2026 07:29:27 +0800 Subject: [PATCH] Release EvalArc 0.17.4 local report viewer and TypeScript report front end --- CHANGELOG.md | 2 +- CITATION.cff | 4 ++-- README.md | 6 +++--- README.zh-CN.md | 6 +++--- package-lock.json | 4 ++-- package.json | 2 +- pyproject.toml | 2 +- src/evalarc/__init__.py | 2 +- 8 files changed, 14 insertions(+), 14 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 691c00e..9c16d19 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,6 +1,6 @@ # Changelog -## Unreleased +## 0.17.4 — 2026-10-02 - Add `evalarc view [DIR]`: a read-only, loopback-only local viewer that lists every report under a folder with its verdict, following the `inspect view` / diff --git a/CITATION.cff b/CITATION.cff index 3df5e58..2f0b2c0 100644 --- a/CITATION.cff +++ b/CITATION.cff @@ -4,8 +4,8 @@ title: "EvalArc: Auditable Evaluations for AI Agents" type: software authors: - name: EvalArc contributors -version: 0.17.3 -date-released: 2026-10-01 +version: 0.17.4 +date-released: 2026-10-02 license: MIT repository-code: "https://github.com/noteflowai/evalarc" url: "https://noteflowai.github.io/evalarc/" diff --git a/README.md b/README.md index 082b96e..03962bf 100644 --- a/README.md +++ b/README.md @@ -66,13 +66,13 @@ and the upgrade gate fails. These checks share two format/schema failures. installs the published wheel, downloads the records and rebuilds the comparison. Verification exits 0 for consistency; comparison exits 1 for the regression. -Install the released reviewer from [PyPI](https://pypi.org/project/evalarc/0.17.3/) +Install the released reviewer from [PyPI](https://pypi.org/project/evalarc/0.17.4/) in a fresh virtual environment: ```bash python3 -m venv .venv . .venv/bin/activate -python -m pip install evalarc==0.17.3 +python -m pip install evalarc==0.17.4 evalarc --version ``` @@ -124,7 +124,7 @@ because checks missing from it cannot be compared; rerun that evaluation to completion and compare again. ```yaml -- uses: noteflowai/evalarc@v0.17.3 # or a full commit SHA +- uses: noteflowai/evalarc@v0.17.4 # or a full commit SHA with: baseline: evals/baseline.json current: results/current.json diff --git a/README.zh-CN.md b/README.zh-CN.md index 8e9cb23..becda52 100644 --- a/README.zh-CN.md +++ b/README.zh-CN.md @@ -52,13 +52,13 @@ EvalArc 是面向 Agent 评测的 Python 命令行复核工具：逐项对比已 3. **本地复算。** [首次复核指南](docs/first-review.zh-CN.md)使用发布的 wheel 和原始记录重建报告； 复核退出 0 表示一致，对照退出 1 表示发现退步。 -在新的虚拟环境中，从 [PyPI](https://pypi.org/project/evalarc/0.17.3/) +在新的虚拟环境中，从 [PyPI](https://pypi.org/project/evalarc/0.17.4/) 安装已发布的复核工具： ```bash python3 -m venv .venv . .venv/bin/activate -python -m pip install evalarc==0.17.3 +python -m pip install evalarc==0.17.4 evalarc --version ``` @@ -102,7 +102,7 @@ PyPI 与 GitHub Releases 提供相同的 wheel 和源码包，也支持 准确率从 0.625 升至 0.8125，同时有三个检查项丢失通过。 ```yaml -- uses: noteflowai/evalarc@v0.17.3 # 或完整的提交 SHA +- uses: noteflowai/evalarc@v0.17.4 # 或完整的提交 SHA with: baseline: evals/baseline.json current: results/current.json diff --git a/package-lock.json b/package-lock.json index f4e0b16..d9adee8 100644 --- a/package-lock.json +++ b/package-lock.json @@ -1,12 +1,12 @@ { "name": "evalarc-evidence-site", - "version": "0.17.3", + "version": "0.17.4", "lockfileVersion": 3, "requires": true, "packages": { "": { "name": "evalarc-evidence-site", - "version": "0.17.3", + "version": "0.17.4", "devDependencies": { "@axe-core/playwright": "4.13.0", "playwright": "1.63.0", diff --git a/package.json b/package.json index d515072..f728a75 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "evalarc-evidence-site", - "version": "0.17.3", + "version": "0.17.4", "private": true, "description": "Browser checks and the TypeScript report front end for EvalArc", "scripts": { diff --git a/pyproject.toml b/pyproject.toml index 52bd014..41b8616 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta" [project] name = "evalarc" -version = "0.17.3" +version = "0.17.4" description = "Find agent regressions behind better scores: compare changed checks, review recorded tool actions and verify evidence offline." readme = "README.md" requires-python = ">=3.11" diff --git a/src/evalarc/__init__.py b/src/evalarc/__init__.py index 196d37d..13a97f3 100644 --- a/src/evalarc/__init__.py +++ b/src/evalarc/__init__.py @@ -1,3 +1,3 @@ """Auditable evaluations for AI agents.""" -__version__ = "0.17.3" +__version__ = "0.17.4"