Releases: MigoXLab/webqa-agent
Releases · MigoXLab/webqa-agent
Release v0.3.0.1
Release v0.3.0
What's Changed
🚀 WebQA Agent v0.3.0 Released
This update marks a major evolution for WebQA Agent! We have not only deeply refactored the underlying Agent toolchain but also introduced an out-of-the-box Web GUI, officially upgrading from a pure CLI tool to a fully-featured, full-stack autonomous testing platform.
🌟 Key Highlights
🖥️ Brand New Web GUI: You can now perform visual task management, scheduling, as well as tracking and in-depth analysis of historical test results through an intuitive web interface.
🛠️ Comprehensive Agent Toolchain Refactoring: The underlying Tool system has been deeply refactored and enhanced. It not only supports a variety of built-in testing tools but also optimizes the extensibility mechanism for custom tools, giving the Agent stronger adaptability across different scenarios.
⚙️ Dual-Engine Architecture Upgrade: Re-engineered both the "Autonomous Exploration (Gen)" and "Case Execution (Run)" engines.
🎬 Watch Demo: One-click testing of Baidu.com
Full Changelog: v0.2.3.3...v0.3.0
Release v0.2.3.3
Hotfix: Rename index_en_US.js to index_en-US.js
Full Changelog: v0.2.3.2...v0.2.3.3
Release v0.2.3.2
🚀 Release v0.2.3.2
📦 Docker Images
mmmay0722/webqa-agent:v0.2.3.2mmmay0722/webqa-agent:latest
📝 Changes since v0.2.3.1
- hotfix HTML report (a2a531a)
Release v0.2.3.1
🚀 Release v0.2.3.1
📦 Docker Images
mmmay0722/webqa-agent:v0.2.3.1mmmay0722/webqa-agent:latest
📝 Changes since v0.2.3
- update version id (cb05dcc)
- fix: different strategy for PDF page in run mode and gen mode (56fc544)
- docs: add logo-title SVG for README (cb47860)
- update report and add webqa logo (e31faf4)
- fix: pre-process cookies in run mode to support file path loading (c89d9b1)
- feat: change monitoring errors from FAILED to WARNING status (af5397b)
- 清除debug log (06fb2e2)
- pdf页面不注入js (069483d)
- session.py 更新： 1. session pool 手动计数 -> semaphore 2. worker 持有 session，避免空闲 session 占用资源 3. 环境隔离：执行用例前清理 session 缓存数据避免复用时污染 4. RUN 模式 config 分组串行 -> 混合并发：避免不同config竞争浏览器资源导致创建session失败 (f76cb52)
Release v0.2.3
🚀 Release v0.2.3
📦 Docker Images
mmmay0722/webqa-agent:v0.2.3mmmay0722/webqa-agent:latest
📝 Changes since v0.2.2
- Add baidu-image.gif (5e7c5df)
- Update Readme (5582bb8)
- fix: cross-platform path handling and config group isolation (d59bc00)
- refactor: enhance report generation with unified utilities and LLM summaries (ec6bdf0)
- feat:adopt webqa (29e1afa)
- fix:improve timestamp precision and explicit data flow for monitoring (7119010)
- feat: enhance screenshot handling with file paths and parallel execution support (9153efa)
- 更新 snapshot 默认存储路径为：reports 文件夹 (a3879d5)
- 重命名 snapshot/use_snapshot (6e7ab82)
- 新增浏览器状态存储功能：保存前置用例执行后的浏览器状态，避免重复执行相同前置操作 (9f32a5a)
- fix: docs descriptions and default value of dynamic_step_generation (#125) (7a7c827)
- fix: unexpected page closing under run mode (#124) (a90a7c4)
- update readme (22d8cee)
- fix package config path (0ab5533)
Release v0.2.2
What's Changed
Full Changelog: v0.2.1...v0.2.2
Release v0.2.1
🚀 Release v0.2.1
📦 Docker Images
mmmay0722/webqa-agent:v0.2.1mmmay0722/webqa-agent:latest
📝 Changes since v0.2.0
- 0.2.1 version (7c6066f)
- fix bugs (45551cd)
- 0.2.1 parallel execution (6f3a4b8)
- modified graph supporting parallel execution (5d3e13e)
- graph-new node-async io并发 (5135aef)
- graph send版 - batch阻塞并发 (021a165)
- update: modify disable_tab_interception as public variable (3d06ccd)
- Update webqa_agent/browser/session.py (d582e13)
- fix: 1.fix wrong labels in reports; 2. fix race condition in default mode; 3. lint check (f120685)
- [fix] fix the issue of missing init.py file. (7020624)
- Update webqa_agent/browser/session.py (efd1f72)
- Update webqa_agent/browser/session.py (614c3e1)
- 新增cancel场景设置browser failed (af6b05e)
- 0.2.1.1 fix cookie，去除go to page硬编码等待时间 (dba80ba)
- 0.2.1.1 新增session pool 合并session+driver (239f08d)
- Improve docs (12000a0)
- feat: CLI interface support (34c25bc)
Release v0.2.0
🚀 Release v0.2.0
📦 Docker Images
mmmay0722/webqa-agent:v0.2.0mmmay0722/webqa-agent:latest
📝 Changes since v0.1.6
- v0.2.0: Two-phase Planning, GPT-5 Responses API & Enhanced Execution (540c351)
- Merge remote-tracking branch 'origin/main' into dev_0.2.0 (2fce5ce)
- refactor: change Scroll action to element-based navigation (0eb668a)
- checkpoint: minor update (5a47221)
- checkpoint: fix cookie injection (3626c6c)
- update webqa to webqa agent in html (f83742c)
- checkpoint: 1. fix dynamically generate steps and optimize its prompt; 2. optimize verify under comparison mode; (98ae5c0)
- feat: Migrate GPT-5 to the Responses API (f35ac22)
- feat: add GPT-5 reasoning/text controls and enhance test planning prompts (f991d6a)
- checkpoint: support window.history.back() for different domain scenarios. (057c043)
- feat: Add uv package manager support with improved dependency management (2a322ac)
- checkpoint: 1. support comparing before state with after state in verify function; 2. add focus_region parameter in verify function; 3. add language detection prompts; 4. unify single-tab mode among all prompts; 5. remove functional_criticality and cleanup_requirements phrase in planning_prompts.py; 6. add instructions for avoiding specific element id in cases (87ae5b6)
- checkpoint: minor fix (c33d4c8)
- checkpoint: single-tab support (5fb52fb)
- checkpoint: support multi-tab feature (25cf0c6)
- feat: 1. update docs and example config fix: 1. change the error level of uncrawlable scenarios (09bd66c)
- minor update (b686a5d)
- minor update (06f6826)
- feat: 1. add switch for saving screenshots to local; add context for verify stage fix: 1. remove deprecated prompt in action stage; 2. abort steps and cases when unable to crawl the current page (ca2a84b)
- Enhanced multiple features and fixed issues (#86) (8e126ce)
- feat: 1. support container scroll; fix: 1. coordinates conversion; 2. clarify screenshot parameters (82b7c0e)
- fix: update agent prompt example (049ca9a)
- feat: add UX verification tool and case recording system (#84) (b99e6ae)
- feat: 1. support max tokens and filter parameters; 2. support interactive elements and text via LLM filtering; 3. support dynamically plan recovery steps (c704a56)
- [WIP]feat: support full page planning and scroll (3084ddb)
- feat: 1. add schema for action tool and verify tool; 2.synchronize actions with action_executor.py; 3. update crawl parameters (8322704)
- feat: 1. update docs and example config fix: 1. change the error level of uncrawlable scenarios (a526f15)
- minor update (4fd0b0d)
- minor update (d0d570c)
- feat: 1. add switch for saving screenshots to local; add context for verify stage fix: 1. remove deprecated prompt in action stage; 2. abort steps and cases when unable to crawl the current page (e41da1e)
- Enhanced multiple features and fixed issues (#86) (693737a)
- feat: 1. support container scroll; fix: 1. coordinates conversion; 2. clarify screenshot parameters (05096c6)
- fix: update agent prompt example (190c3ae)
- feat: add UX verification tool and case recording system (#84) (72d2bc5)
- feat: 1. support max tokens and filter parameters; 2. support interactive elements and text via LLM filtering; 3. support dynamically plan recovery steps (2535171)
- [WIP]feat: support full page planning and scroll (a1a3710)
- feat: 1. add schema for action tool and verify tool; 2.synchronize actions with action_executor.py; 3. update crawl parameters (86dccf7)
Release v0.1.6
🚀 Release v0.1.6
📦 Docker Images
mmmay0722/webqa-agent:v0.1.6mmmay0722/webqa-agent:latest