@vostride/agent-qa-ids 0.2.2 → 0.2.3

package/README.md

@@ -0,0 +1,78 @@
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/vostride/agent-qa/main/docs/assets/readme/banner-dark.jpg">
+  <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/vostride/agent-qa/main/docs/assets/readme/banner-light.png">
+  <img src="https://raw.githubusercontent.com/vostride/agent-qa/main/docs/assets/readme/banner-light.png" alt="agent-qa by vostride — a self-improving QA agent for your software factory" width="100%">
+</picture>
+
+<p align="center">
+  <strong>English</strong> · <a href="https://github.com/vostride/agent-qa/blob/main/README.zh-CN.md">中文</a>
+</p>
+
+<p align="center">
+  <a href="https://www.npmjs.com/package/agent-qa"><img src="https://img.shields.io/npm/v/agent-qa?color=196872" alt="npm version"></a>
+  <a href="https://www.npmjs.com/package/agent-qa"><img src="https://img.shields.io/npm/dm/agent-qa?color=196872" alt="npm downloads per month"></a>
+  <a href="https://github.com/vostride/agent-qa/stargazers"><img src="https://img.shields.io/github/stars/vostride/agent-qa?color=196872" alt="GitHub stars"></a>
+  <a href="https://github.com/vostride/agent-qa/actions/workflows/ci.yml"><img src="https://github.com/vostride/agent-qa/actions/workflows/ci.yml/badge.svg?branch=main" alt="CI"></a>
+  <a href="https://vostride.com/docs/agent-qa"><img src="https://img.shields.io/badge/docs-agent--qa-196872" alt="Documentation"></a>
+  <a href="https://github.com/vostride/agent-qa/blob/main/LICENSE.md"><img src="https://img.shields.io/badge/license-FSL--1.1--ALv2-196872" alt="License: FSL-1.1-ALv2"></a>
+</p>
+
+<p align="center">
+  <a href="https://vostride.com/agent-qa">Website</a> · <a href="https://vostride.com/docs/agent-qa">Docs</a> · <a href="https://vostride.com/demo/agent-qa">Demo</a> · <a href="https://vostride.com/blog">Blog</a> · <a href="https://vostride.com/changelog">Changelog</a>
+</p>
+
+**Your AI QA engineer, with memory.** Describe a user journey in plain language. agent-qa tests it on web, Android or iOS and keeps the evidence. Use the CLI, the dashboard, or your coding agent through MCP and skills.
+
+- **memidex:** remembers facts and working procedures as reviewable files in your repository.
+- **Self-improvement:** validates lessons from runs, retires stale knowledge, and uses your feedback to correct mistakes.
+
+| Benchmark | Rank | Published result |
+| --- | --- | --- |
+| [AndroidWorld](https://vostride.com/benchmark/android-world) | **#1** | **100% pass@1** (116/116 tasks) |
+| [AppControlBench](https://vostride.com/benchmark/app-control-bench) | **#1** | **99.6% completion** (114.5/115 points) |
+
+Read the full benchmark reports, with run evidence and methodology, on [our blog](https://vostride.com/blog). Both used gpt-6-sol with memory and self-improvement off; AppControlBench gives half credit for partial completion.
+
+## See it in action
+
+**Inspect a failure.** The demo catches a cart showing $29 instead of $53, with the failed step and its screenshot side by side.
+
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/vostride/agent-qa/main/docs/assets/readme/evidence-dark.png">
+  <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/vostride/agent-qa/main/docs/assets/readme/evidence-light.png">
+  <img src="https://raw.githubusercontent.com/vostride/agent-qa/main/docs/assets/readme/evidence-light.png" alt="The dashboard shows the deliberate cart-total bug, its failed assertion, and recorded browser evidence" width="100%">
+</picture>
+
+**See what memory contributed.** Inspect the knowledge supplied to a run and trace it back to the steps that used it.
+
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/vostride/agent-qa/main/docs/assets/readme/knowledge-dark.png">
+  <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/vostride/agent-qa/main/docs/assets/readme/knowledge-light.png">
+  <img src="https://raw.githubusercontent.com/vostride/agent-qa/main/docs/assets/readme/knowledge-light.png" alt="The Knowledge tab shows stored facts retrieved for the demo run" width="100%">
+</picture>
+
+**Run from your terminal.** Real output from the demo suite: checkout passes; the deliberate cart-total bug fails.
+
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/vostride/agent-qa/main/docs/assets/readme/cli-dark.png">
+  <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/vostride/agent-qa/main/docs/assets/readme/cli-light.png">
+  <img src="https://raw.githubusercontent.com/vostride/agent-qa/main/docs/assets/readme/cli-light.png" alt="CLI output excerpt showing one passed test, one failed test, and eight of nine steps passing" width="100%">
+</picture>
+
+## Get started
+
+Requires Node.js 24+.
+
+```sh
+npm install -D agent-qa
+npx agent-qa init
+```
+
+Follow the [quickstart](https://vostride.com/docs/agent-qa/quickstart) to connect a model and run the demo, or [set up with your coding agent](https://vostride.com/docs/agent-qa/agent-quickstart).
+
+> [!NOTE]
+> Early stage. Expect bugs. [Report an issue](https://github.com/vostride/agent-qa/issues) when something breaks.
+
+## License
+
+[Functional Source License (FSL-1.1-ALv2)](https://github.com/vostride/agent-qa/blob/main/LICENSE.md).

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@vostride/agent-qa-ids",
-  "version": "0.2.2",
+  "version": "0.2.3",
   "private": false,
   "description": "Canonical ID helpers for agent-qa tests, suites, hooks, and artifacts.",
   "keywords": [
@@ -51,7 +51,7 @@
   },
   "devDependencies": {
     "@types/node": "~24.12.2",
-    "@vostride/agent-qa-arch": "0.2.2",
+    "@vostride/agent-qa-arch": "0.2.3",
     "tsup": "~8.5.1",
     "typescript": "~6.0.3",
     "vitest": "~4.1.5"