assuremind 1.4.0 → 1.4.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/LICENSE +201 -21
  2. package/README.md +452 -451
  3. package/package.json +2 -2
package/LICENSE CHANGED
@@ -1,21 +1,201 @@
1
- MIT License
2
-
3
- Copyright (c) 2026 Deepak Hiremath
4
-
5
- Permission is hereby granted, free of charge, to any person obtaining a copy
6
- of this software and associated documentation files (the "Software"), to deal
7
- in the Software without restriction, including without limitation the rights
8
- to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9
- copies of the Software, and to permit persons to do so, subject to the
10
- following conditions:
11
-
12
- The above copyright notice and this permission notice shall be included in all
13
- copies or substantial portions of the Software.
14
-
15
- THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16
- IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17
- FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18
- AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19
- LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20
- OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21
- SOFTWARE.
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ APPENDIX: How to apply the Apache License to your work.
179
+
180
+ To apply the Apache License to your work, attach the following
181
+ boilerplate notice, with the fields enclosed by brackets "[]"
182
+ replaced with your own identifying information. (Don't include
183
+ the brackets!) The text should be enclosed in the appropriate
184
+ comment syntax for the file format. We also recommend that a
185
+ file or class name and description of purpose be included on the
186
+ same "printed page" as the copyright notice for easier
187
+ identification within third-party archives.
188
+
189
+ Copyright 2026 Deepak Hiremath
190
+
191
+ Licensed under the Apache License, Version 2.0 (the "License");
192
+ you may not use this file except in compliance with the License.
193
+ You may obtain a copy of the License at
194
+
195
+ http://www.apache.org/licenses/LICENSE-2.0
196
+
197
+ Unless required by applicable law or agreed to in writing, software
198
+ distributed under the License is distributed on an "AS IS" BASIS,
199
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200
+ See the License for the specific language governing permissions and
201
+ limitations under the License.
package/README.md CHANGED
@@ -1,451 +1,452 @@
1
- # Assuremind Studio
2
-
3
- **AI-powered codeless UI & API test automation framework**
4
-
5
- [![npm version](https://img.shields.io/npm/v/assuremind.svg)](https://www.npmjs.com/package/assuremind)
6
- [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
7
- [![Node.js](https://img.shields.io/badge/node-%3E%3D18-brightgreen.svg)](https://nodejs.org)
8
- [![Playwright](https://img.shields.io/badge/powered%20by-Playwright-2EAD33.svg)](https://playwright.dev)
9
-
10
- Describe tests in plain English. AI generates Playwright code. Run anywhere.
11
-
12
- > ### 🌐 [AssureMind Community Hub → https://assuremind.in/](https://assuremind.in/)
13
- > Report bugs · request features · share ideas & feedback · ask questions.
14
- > 📧 Contact: [assuremind.contact@gmail.com](mailto:assuremind.contact@gmail.com)
15
-
16
- ---
17
-
18
- ## Why Assuremind?
19
-
20
- | Capability | What it does |
21
- |-----------|-------------|
22
- | **Zero coding** | Write steps in plain English — AI generates Playwright code automatically |
23
- | **MCP-sighted generation** | AI sees real page elements via Playwright MCP accessibility snapshots (~90-95% accuracy) |
24
- | **3 suite types** | **UI** (browser automation) · **API** (HTTP tests) · **Audit** (Playwright + Lighthouse) |
25
- | **5-level self-healing** | Broken selectors are auto-fixed by AI during runs smart retry AI regen → multi-selector → visual → decompose |
26
- | **12 AI providers** | Anthropic · OpenAI · Gemini · Groq · DeepSeek · Together · Qwen · Perplexity · Ollama · Bedrock · Azure OpenAI · Custom |
27
- | **Device emulation** | iPhone, Pixel, iPad, Galaxy full Playwright device descriptors from UI or `--device` CLI flag |
28
- | **Studio UI** | Browser-based editor, run dashboard, reports, healing review, git control center with dark mode |
29
- | **RAG memory** | AI learns from every run retrieves similar past steps & healing fixes for smarter generation |
30
- | **Test Recorder** | Record tests by clicking in a real browser locators verified against Playwright's accessibility tree, zero AI cost. Recorder + AI both handle iframes (click & fill), Shadow DOM, JS alerts, and keyboard actions |
31
- | **Cost-optimised** | Template engine + code cache + RAG handle ~80% of steps with zero AI calls |
32
- | **CI-ready** | `npx assuremind run --all --ci` exit code 0/1, works with any pipeline |
33
- | **File-based** | Plain JSON storage, fully Git-friendly, no database |
34
- | **Faker Data** | 100+ @faker-js/faker generators across 16 categories — random emails, names, addresses, sequences — no code, no stale data |
35
- | **File upload & download** | Upload fixtures from the Studio and insert as `{{FILE:…}}` tokens; downloads auto-captured per run and viewable in Reports |
36
- | **Visual regression** | Pixel-diff screenshot comparison with baselines approve/reject visual changes in Studio |
37
- | **CI/CD integration** | Quality gates, PR comments (GitHub/GitLab), Slack/Teams notifications |
38
-
39
- ---
40
-
41
- ## Quick Start
42
-
43
- ```bash
44
- npm install assuremind
45
- npx assuremind init # folders, config, Playwright browsers
46
- npx playwright install # if browser install was skipped or failed during init
47
- npx assuremind studio # opens http://localhost:4400
48
- ```
49
-
50
- > **First-time setup:** `npx assuremind init` installs the Playwright browsers automatically. If that step is skipped (`--skip-playwright`) or fails (network/permissions), install them manually with `npx playwright install` (add `--with-deps` on Linux to pull OS libraries). Run `npx assuremind doctor` to verify your setup.
51
-
52
- ### System Requirements
53
-
54
- | | Minimum | Recommended |
55
- |---|---|---|
56
- | **Node.js** | 18 LTS | 20 LTS or newer |
57
- | **OS** | macOS / Linux / Windows 10+ | |
58
- | **RAM** | 4 GB | 8 GB+ |
59
- | **Disk** | ~2 GB (app + Playwright browsers) | 5 GB+ |
60
- | **Java** | | JDK 17+ only for Allure HTML reports |
61
-
62
- `npx assuremind init` installs the Playwright browsers. Using a **cloud AI provider** (Anthropic, OpenAI, Gemini, …) needs only an API key and the specs above. Running a **local model via Ollama** has heavier requirements — see below.
63
-
64
- ### Configure AI Provider
65
-
66
- Edit `.env` — pick one provider:
67
-
68
- ```bash
69
- # Anthropic # OpenAI # Google
70
- AI_PROVIDER=anthropic AI_PROVIDER=openai AI_PROVIDER=google
71
- ANTHROPIC_API_KEY=sk-ant-... OPENAI_API_KEY=sk-... GOOGLE_API_KEY=AIza...
72
- ANTHROPIC_MODEL=claude-sonnet.. OPENAI_MODEL=gpt-4o GOOGLE_MODEL=gemini-2.5-pro
73
- ```
74
-
75
- See `.env.example` for all 12 providers including Gemini, OpenAI, Anthropic, Ollama (local/free), etc.
76
-
77
- ### Local & Free — Ollama
78
-
79
- Run models entirely on your own machine (no API key, no cost). AssureMind uses the model to turn
80
- plain-English steps into Playwright code, so a **code-tuned model with strong instruction-following**
81
- works best.
82
-
83
- ```bash
84
- # 1. Install Ollama → https://ollama.com/download
85
- ollama serve # starts the server on http://localhost:11434
86
- ollama pull qwen2.5-coder:7b # 2. pull the recommended model
87
- ```
88
-
89
- ```bash
90
- # 3. .env
91
- AI_PROVIDER=ollama
92
- OLLAMA_MODEL=qwen2.5-coder:7b
93
- OLLAMA_BASE_URL=http://localhost:11434
94
- AI_TIMEOUT=120 # local inference is slower than cloud APIs
95
- ```
96
-
97
- **Recommended models (by hardware):**
98
-
99
- | Hardware | Model | Notes |
100
- |----------|-------|-------|
101
- | 16 GB+ RAM, GPU 8 GB+ VRAM | `qwen2.5-coder:14b` | Highest accuracy — best for complex steps / iframes |
102
- | 16 GB RAM (GPU optional) | `qwen2.5-coder:7b` | **Best balance** of quality & speed for this task |
103
- | 8 GB RAM, no GPU | `llama3.2` (3B) / `qwen2.5-coder:3b` | Usable; good for simpler steps |
104
- | ≤4–6 GB RAM | `llama3.2:1b` / `phi3:mini` | Lightweight; navigation & clicks only |
105
-
106
- **Ollama system requirements:**
107
-
108
- - **RAM is the floor** — a model needs roughly its file size **+ ≈2 GB free**. A 7B model (≈4.7 GB)
109
- wants **8 GB free RAM minimum, 16 GB comfortable**; a 14B model wants **≈16 GB+**.
110
- - **GPU is optional but transformative** CPU-only works (hence `AI_TIMEOUT=120`), but a GPU with
111
- **8 GB+ VRAM** (NVIDIA CUDA / Apple Silicon / modern AMD) makes 7B models fast. Apple Silicon (M-series) is excellent thanks to unified memory.
112
- - **Disk** a few GB per model; keep **10–20 GB free** if trying several.
113
- - **Tips** — enable **MCP** (Settings live page snapshots) for far more accurate locators with local
114
- models. Avoid `deepseek-r1` here: its `<think>` reasoning output is slow and pollutes generated code.
115
-
116
- ---
117
-
118
- ## CLI
119
-
120
- ```bash
121
- npx assuremind run --all # run everything
122
- npx assuremind run --type ui --tag smoke # filter by type + tag
123
- npx assuremind run --suite "Login" --browser chromium # run a suite
124
- npx assuremind run --all --device "iPhone 15 Pro" --ci # mobile + CI mode
125
- npx assuremind generate --story "User resets password" # AI generates full suite
126
- npx assuremind apply-healing --yes # accept all healed selectors
127
- npx assuremind validate # check config health
128
- npx assuremind doctor # system diagnostics
129
- ```
130
-
131
- | Flag | Description |
132
- |------|-------------|
133
- | `--all` | Run every suite |
134
- | `--type <ui\|api\|audit>` | Filter by suite type |
135
- | `--suite <name>` | Partial name match |
136
- | `--tag <tag>` | Filter by tag |
137
- | `--device <name>` | Emulate device (e.g. `"iPhone 15 Pro"`, `"Pixel 7"`) |
138
- | `--browser <list>` | `chromium` `firefox` `webkit` |
139
- | `--ci` | CI mode exit code reflects pass/fail |
140
- | `--headed` | Show browser window |
141
- | `--no-healing` | Disable self-healing |
142
-
143
- Full reference → [docs/CLI-REFERENCE.md](docs/CLI-REFERENCE.md)
144
-
145
- ---
146
-
147
- ## Studio UI
148
-
149
- Start with `npx assuremind studio` — opens at `http://localhost:4400`.
150
-
151
- **Dashboard** · **Smart Tests** · **Test Editor** · **Run Config** · **Reports** · **Variables** · **Self-Healing** · **Step Library** · **Faker Data** · **CI/CD** · **Git Control** · **Settings** · **Docs**
152
-
153
- Full walkthrough → [docs/STUDIO.md](docs/STUDIO.md)
154
-
155
- ---
156
-
157
- ## MCP Integration
158
-
159
- AI sees **real page elements** during code generation via the official `@playwright/mcp` server. Enabled by default.
160
-
161
- | Mode | Accuracy | Latency | Config |
162
- |------|----------|---------|--------|
163
- | Blind (MCP off) | ~50-70% | Fastest | `mcp.enabled: false` |
164
- | **Snapshot-driven** | ~90-95% | +2-5s first page | `mcp.enabled: true` (default) |
165
- | Act-then-script | ~98-100% | +5-10s/step | `mcp.actThenScript: true` |
166
-
167
- - MCP is **only used during code generation** — test execution is never affected
168
- - Silent fallback if MCP fails, generation continues blindly without error
169
- - Configure in **Settings MCP Integration** or `autotest.config.json`
170
-
171
- ---
172
-
173
- ## Test Recorder
174
-
175
- Record tests by interacting with your application in a real browser — **zero AI, zero cost, zero guesswork**.
176
-
177
- Click **Record** in the Test Editor, perform your actions, and stop. Each interaction becomes a step with verified Playwright code, ready to run.
178
-
179
- ### How it works
180
-
181
- > Available for **UI** and **Audit** suites only (not API suites).
182
-
183
- 1. A headed Chromium browser opens your app's URL
184
- 2. Every click, fill, navigation, and keyboard action is captured in real time — **including inside iframes and shadow roots**
185
- 3. Locators are resolved against Playwright's **accessibility tree** the recorder tries 6 strategies (data-testid, getByRole, getByLabel, getByPlaceholder, getByText, CSS) and verifies each with `count() === 1`
186
- 4. **Iframe-aware** — elements inside iframes automatically generate `page.frameLocator('#iframe').getByRole(...)` code with the correct frame chain
187
- 5. **Shadow DOM** — `composedPath()[0]` pierces shadow roots; generates `host >> inner` pierce locators automatically
188
- 6. **JS dialogs** — alerts/confirms are auto-accepted during recording; `page.once('dialog', ...)` is prepended to the triggering step's code
189
- 7. **Keyboard** — Tab, Shift+Tab, arrows, Enter, Escape, Ctrl+A, and Space on buttons are all captured
190
- 8. Assertions via keyboard shortcuts: **Shift+Click** (element visible), **Ctrl+Shift+U** (URL), **Ctrl+Shift+T** (page title)
191
- 9. On stop, each action is added as a step with **pre-generated Playwright code** no AI call needed
192
-
193
- ### What makes it stand out vs other recorders
194
-
195
- | Feature | Selenium IDE | Playwright Codegen | Assuremind Recorder |
196
- |---------|-------------|-------------------|---------------------|
197
- | Locator quality | CSS/XPath | Good | Best — 6 strategies, verified against live page |
198
- | Accessibility tree | No | Partial | Fullevery locator checked via Playwright API |
199
- | **Iframe support** | Partial | Manual | **Full**detects iframes, generates `frameLocator()` code click **and** fill both work |
200
- | **Shadow DOM** | No | Limited | `>>` pierce combinatorelements inside shadow roots are reachable |
201
- | **JS Alert handling** | No | No | `page.once('dialog', ...)` registered automatically before triggering action |
202
- | **Keyboard actions** | No | No | `page.keyboard.press()` / `.type()` for keys, shortcuts, and character input |
203
- | Assertions | Manual | Manual | Shift+Click (hard), Ctrl+Shift+Click (soft), URL & title shortcuts |
204
- | Plain-English steps | No | No | Yes human-readable instructions auto-generated |
205
- | Self-healing after | No | No | Yes — 5-level AI healing cascade |
206
- | RAG memory | No | No | Yes — recorded steps feed the learning loop |
207
- | Cost | Free | Free | Free |
208
-
209
- ### Biggest pain points in test automation — solved
210
-
211
- | Pain Point | How the Recorder Solves It |
212
- |-----------|---------------------------|
213
- | Writing tests is slow | Record a full test in 30 seconds |
214
- | Selectors break constantly | Locators verified against Playwright's accessibility tree in real time |
215
- | AI costs money | Recording + code generation = $0, zero AI calls |
216
- | Non-technical testers can't write tests | Anyone who can click a browser can create tests |
217
- | Assertions are hard to write | Shift+Click for hard, Ctrl+Shift+Click for soft, Ctrl+Shift+U for URL, Ctrl+Shift+T for title |
218
- | Hard vs soft assertions | Soft assertions (`expect.soft()`) let the test continue all failures reported at end |
219
- | Recorded tests are fragile | 6-strategy locator resolution + post-run 5-level self-healing |
220
- | Apps use iframes (SAP, Salesforce) | Recorder auto-detects iframe context, generates `frameLocator()` chains **click and fill** both work |
221
- | Shadow DOM / Web Components | Recorder pierces shadow roots via `composedPath()`, generates `>>` locators automatically |
222
- | JavaScript alerts & popups | Recorder auto-accepts dialogs; `page.once('dialog', ...)` prepended to triggering step |
223
- | Keyboard interactions | Recorder captures Tab, Shift+Tab, arrows, Ctrl+A, Enter, Escape, and Space |
224
-
225
- ---
226
-
227
- ## RAG Memory (Retrieval-Augmented Generation)
228
-
229
- The AI learns from every test run, building semantic memory that improves accuracy over time — **zero setup required**:
230
-
231
- | Corpus | What it stores | When it's used |
232
- |--------|---------------|----------------|
233
- | **Code Corpus** | Instruction-to-code mappings from successful runs | During generation — similar past steps are retrieved as AI examples or used directly (score >= 0.90) |
234
- | **Healing Corpus** | Past healing events (error + fix pairs) | During self-healingproven past fixes are injected into the repair prompt |
235
- | **Error Catalog** | Recurring error patterns per URL | During generationthe AI is warned about known-bad selectors to avoid |
236
-
237
- **Zero cost, zero database** — uses local TF-IDF embeddings and file-based JSON storage (`results/.rag/`). Enabled by default — works automatically from the very first run.
238
-
239
- ### How it improves over time
240
-
241
- - **Run 1** — memory is empty, AI generates code normally
242
- - **Run 2+**RAG kicks in silently: similar instructions are retrieved instead of making API calls (free + faster), healing uses proven past fixes
243
- - **Run 10+** — most common steps are served from RAG memory at zero cost, self-healing resolves issues on the first attempt
244
-
245
- ### Consumer FAQ
246
-
247
- | Question | Answer |
248
- |----------|--------|
249
- | Do I need to configure anything? | No. RAG is ON by default with zero setup. |
250
- | Does it cost anything? | No. TF-IDF embedder runs locally. RAG direct hits replace paid AI calls. |
251
- | Does it slow down my tests? | No. RAG lookup is <1ms. It actually speeds up generation. |
252
- | Does it work in CI/CD? | Yes. Cache `results/.rag/` between CI runs to persist memory. |
253
- | How do I share memory across team? | Commit `results/.rag/` to Git or use a CI cache step. |
254
- | How do I reset memory? | Delete the `results/.rag/` folder. |
255
-
256
- ### When to use Settings → RAG Memory
257
-
258
- Most users never need to touch RAG settings. The Settings card exists for power-user scenarios:
259
-
260
- | Scenario | Action |
261
- |----------|--------|
262
- | Debugging a flaky test | Turn OFF Code Corpus — forces fresh AI generation |
263
- | Healing keeps suggesting a bad fix | Turn OFF Healing Corpus — clears bad fix influence |
264
- | Major app redesign | Turn OFF RAG entirelyold memory is now misleading |
265
- | Error warnings are outdated | Turn OFF Error Catalogstops avoiding selectors that are fine now |
266
- | Want deterministic CI runs | Disable RAG in CI config, keep ON locally |
267
-
268
- ---
269
-
270
- ## Self-Healing
271
-
272
- When your app's UI changes (button renamed, element moved, DOM restructured), tests break. Instead of failing immediately, Assuremind automatically attempts to fix the broken selector through a 5-level cascade — **fully automated, no manual intervention needed**:
273
-
274
- | Level | What happens | Example | AI Cost |
275
- |-------|-------------|---------|---------|
276
- | 1 | **Smart retry** — waits for the element with exponential backoff | Element was loading slowly; retry finds it after 2s | Free |
277
- | 2 | **AI regeneration** — AI rewrites the Playwright code using current page context | `#login-btn` removed AI generates `page.getByRole('button', { name: 'Sign In' })` | 1 call |
278
- | 3 | **Multi-selector** — AI generates 5 alternative selector strategies, tries each | Tries rolelabel placeholder text CSS until one works | 1 call |
279
- | 4 | **Visual analysis** — takes a screenshot, AI visually locates the element | Button has no text/role but AI sees it in the screenshot | 1 call |
280
- | 5 | **Decompose** — breaks the failing step into 3-5 simpler micro-actions | "Fill login form and submit" separate fill email + fill password + click submit | 1 call |
281
-
282
- If all 5 levels fail, the step is marked **failed** and saved to the healing report for your review.
283
-
284
- ### How you use it
285
-
286
- 1. **During test runs** — healing happens automatically. If Level 2 fixes a broken `#login-btn`, your test **passes** and continues.
287
- 2. **After the run** — healed selectors are saved as **pending suggestions** (not auto-applied to source files).
288
- 3. **Review & accept** — in Studio **Self-Healing** page, or from CLI:
289
- ```bash
290
- npx assuremind apply-healing # interactive review: accept/reject each fix
291
- npx assuremind apply-healing --yes # accept all in CI
292
- ```
293
- 4. **Accepted fixes** are written back to your `.test.json` files — next run uses the healed code permanently.
294
-
295
- > **CI/CD tip:** Add `npx assuremind apply-healing --yes` as a post-test step so healed selectors are committed back automatically. Enable `healing.autoPR` in Settings to auto-create a GitHub PR with the fixes.
296
-
297
- ---
298
-
299
- ## CI/CD
300
-
301
- ```yaml
302
- # GitHub Actions
303
- - name: Run tests
304
- env:
305
- AI_PROVIDER: google
306
- GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
307
- GOOGLE_MODEL: gemini-2.5-pro
308
- run: npx assuremind run --all --ci
309
- ```
310
-
311
- Also supports **GitLab CI** and **Jenkins** — or use the built-in **CI Config Generator** in Studio (Run Config → Generate CI Config).
312
-
313
- **CI Config Generator** (Run Config → Generate CI Config):
314
- - Generates a workflow for **GitHub Actions**, **GitLab CI**, or **Jenkins** from your current run config.
315
- - The YAML is shown in a **preview**; click **✎ Edit** to customise it (branches, Node version, extra steps…). Your edits apply to Copy, Download, and Write to repo. Use **↺ Reset** to regenerate.
316
- - **Copy** / **Download** are always available.
317
- - **Write to repo** (opt-in) writes the file into your project at its standard path (`.github/workflows/assuremind.yml`, `.gitlab-ci.yml`, or `Jenkinsfile`). Enable it in **Settings → CI/CD Integration → "Write CI files to repo"**. It only **writes the file** — it does **not** commit or push. Review the change and commit it from the **Git Control Center** when ready.
318
-
319
- Exit code `0` = all passed · `1` = failures.
320
-
321
- ---
322
-
323
- ## Enterprise Features
324
-
325
- ### Faker Data
326
-
327
- 100+ @faker-js/faker generators across 16 categories — generate realistic random data without code.
328
-
329
- | Generator | Example output |
330
- |-----------|---------------|
331
- | `person.fullName` | Sarah Johnson |
332
- | `internet.email` | sarah.johnson@gmail.com |
333
- | `phone.number` | +1-555-123-4567 |
334
- | `finance.amount` | 249.99 |
335
- | `location.city` | San Francisco |
336
- | Sequence `USER-{n}` | USER-001, USER-002, USER-003 |
337
-
338
- Browse by category or search, select multiple tokens at once — selected tokens appear as removable chips, and clicking "Insert N tokens" inserts them all comma-separated (e.g. `{{FAKE_PERSON_FIRSTNAME}}, {{FAKE_PERSON_LASTNAME}}, {{FAKE_INTERNET_EMAIL}}`). Great for form filling. Tokens resolve to fresh random values on every test run — no more "email already exists" failures.
339
-
340
- ### File Upload & Download
341
-
342
- **Upload** — In the Test Editor, click the **Files** button (next to *Fake Data*) to upload a fixture file. It's saved in the repo at `fixtures/uploads/` (so it's committed and works in CI) and inserted into your step as a **`{{FILE:name}}`** token. The token resolves to the file's path at runtime:
343
-
344
- ```
345
- Step: Upload {{FILE:resume.pdf}} to the Resume field
346
- Code: await page.getByLabel('Resume').setInputFiles('{{FILE:resume.pdf}}');
347
- ```
348
-
349
- For a file-chooser button, register the listener before the click (in one step):
350
- ```js
351
- const fileChooserPromise = page.waitForEvent('filechooser');
352
- await page.getByRole('button', { name: 'Choose File' }).click();
353
- (await fileChooserPromise).setFiles('{{FILE:resume.pdf}}');
354
- ```
355
-
356
- **Download** — Downloads are **captured automatically** during a run (no `saveAs`, no `fs` needed) and saved to `results/downloads/<runId>/`. The step waits until the file finishes downloading. After the run, open **Reports → Run Reports**, expand the run, and the **Downloads** panel lists every captured file — click any to save it to your machine.
357
-
358
- **Example steps** (type these in plain English):
359
-
360
- ```text
361
- # Upload
362
- Upload {{FILE:resume.pdf}} to the Resume field
363
- Upload {{FILE:resume.pdf}} to the Resume field and wait for 'Upload complete' # most reliable
364
- Upload {{FILE:photo.png}} # page's file input
365
-
366
- # Download (file finishes downloading before the step passes)
367
- Download the "Export CSV" link
368
- Click the "Export" button to download
369
- Download the file by clicking "Report PDF"
370
- ```
371
-
372
- Tip: for uploads, the `…and wait for '<success text>'` form is the most reliable (uploads have no completion event); otherwise the step waits for the network to settle.
373
-
374
- ### Visual Regression
375
-
376
- Pixel-perfect screenshot comparison — catch UI changes that functional tests miss. Configure in **Settings** → Visual Regression. Review diffs in **Reports** → Visual Diffs tab.
377
-
378
- 1. Enable in **Settings** → Visual Regression, then toggle the **Eye icon** on any step in the Test Editor
379
- 2. First run captures **baseline** screenshots (committed to git)
380
- 3. Subsequent runs **compare** pixel-by-pixel using `pixelmatch`
381
- 4. Diff > threshold → step **fails** with highlighted diff image
382
- 5. Review in **Reports**Visual Diffs → **Approve** (update baseline) or **Reject** (it's a bug)
383
-
384
- ```
385
- baselines/ # committed to git
386
- ├── login-suite/login-test/
387
- ├── step-3-chromium-1920x1080.png
388
- └── step-3-firefox-1920x1080.png
389
- results/visual-diffs/{runId}/ # gitignored, per-run
390
- ├── step-3-baseline.png
391
- ├── step-3-actual.png
392
- └── step-3-diff.png # red highlights
393
- ```
394
-
395
- ### CI/CD Integration
396
-
397
- Quality gates, PR comments, and notifications — configured from Studio, executed in pipelines.
398
-
399
- | Feature | What it does |
400
- |---------|-------------|
401
- | **Quality gates** | Set min pass rate (95%), max duration, required tags — pipeline fails if gate fails |
402
- | **PR comments** | Auto-post test results as GitHub PR comment or GitLab MR note |
403
- | **Notifications** | Slack, Teams, Email, custom webhook trigger on failure, every run, or healing events |
404
-
405
- ```yaml
406
- # GitHub Actions — full integration
407
- - name: Run tests
408
- env:
409
- AI_PROVIDER: anthropic
410
- ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
411
- run: npx assuremind run --all --ci
412
- # Quality gate auto-evaluates, PR comment auto-posts, Slack notifies on failure
413
- ```
414
-
415
- ---
416
-
417
- ## Documentation
418
-
419
- | Resource | Location |
420
- |----------|----------|
421
- | Getting started | [docs/GETTING-STARTED.md](docs/GETTING-STARTED.md) |
422
- | Writing test steps (UI & API examples) | [docs/WRITING-STEPS.md](docs/WRITING-STEPS.md) |
423
- | Studio walkthrough | [docs/STUDIO.md](docs/STUDIO.md) |
424
- | CLI reference | [docs/CLI-REFERENCE.md](docs/CLI-REFERENCE.md) |
425
- | Contributing | [CONTRIBUTING.md](CONTRIBUTING.md) |
426
- | All AI providers | `.env.example` |
427
- | Built-in docs | Studio → **Docs** page |
428
- | Enterprise features | Studio → **Faker Data**, **CI/CD** pages; Visual Regression in **Settings** + **Reports** |
429
-
430
- ---
431
-
432
- ## Community & Support
433
-
434
- Have a question, found a bug, or want to shape what comes next? Join the **[AssureMind Community Hub](https://assuremind.in/)**:
435
-
436
- - 🐞 **Report bugs**
437
- - **Request new features**
438
- - 💡 **Share ideas and feedback**
439
- - **Ask questions**
440
-
441
- 👉 Visit **[https://assuremind.in/](https://assuremind.in/)** &nbsp;|&nbsp; 📧 **[assuremind.contact@gmail.com](mailto:assuremind.contact@gmail.com)**
442
-
443
- ---
444
-
445
- ## License
446
-
447
- MIT — see [LICENSE](LICENSE) for details.
448
-
449
- ---
450
-
451
- *Built by [Deepak Hiremath](https://www.linkedin.com/in/deepak-hiremath-0017937a/)*
1
+ # AssureMind Studio
2
+
3
+ **AI-powered codeless UI & API test automation framework**
4
+
5
+ [![npm version](https://img.shields.io/npm/v/assuremind.svg)](https://www.npmjs.com/package/assuremind)
6
+ [![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
7
+ [![Node.js](https://img.shields.io/badge/node-%3E%3D18-brightgreen.svg)](https://nodejs.org)
8
+ [![Playwright](https://img.shields.io/badge/powered%20by-Playwright-2EAD33.svg)](https://playwright.dev)
9
+
10
+ Describe tests in plain English. AI generates Playwright code. Run anywhere.
11
+
12
+ > ### 🌐 Website [https://assuremind.in/](https://assuremind.in/)
13
+ > ### 💬 Community Hub [https://assuremind.in/community/](https://assuremind.in/community/)
14
+ > Report bugs · request features · share ideas & feedback · ask questions.
15
+ > 📧 Contact: [assuremind.contact@gmail.com](mailto:assuremind.contact@gmail.com)
16
+
17
+ ---
18
+
19
+ ## Why AssureMind?
20
+
21
+ | Capability | What it does |
22
+ |-----------|-------------|
23
+ | **Zero coding** | Write steps in plain English AI generates Playwright code automatically |
24
+ | **MCP-sighted generation** | AI sees real page elements via Playwright MCP accessibility snapshots (~90-95% accuracy) |
25
+ | **3 suite types** | **UI** (browser automation) · **API** (HTTP tests) · **Audit** (Playwright + Lighthouse) |
26
+ | **5-level self-healing** | Broken selectors are auto-fixed by AI during runs smart retry AI regen multi-selector visual decompose |
27
+ | **12 AI providers** | Anthropic · OpenAI · Gemini · Groq · DeepSeek · Together · Qwen · Perplexity · Ollama · Bedrock · Azure OpenAI · Custom |
28
+ | **Device emulation** | iPhone, Pixel, iPad, Galaxy full Playwright device descriptors from UI or `--device` CLI flag |
29
+ | **Studio UI** | Browser-based editor, run dashboard, reports, healing review, git control center with dark mode |
30
+ | **RAG memory** | AI learns from every runretrieves similar past steps & healing fixes for smarter generation |
31
+ | **Test Recorder** | Record tests by clicking in a real browser locators verified against Playwright's accessibility tree, zero AI cost. Recorder + AI both handle iframes (click & fill), Shadow DOM, JS alerts, and keyboard actions |
32
+ | **Cost-optimised** | Template engine + code cache + RAG handle ~80% of steps with zero AI calls |
33
+ | **CI-ready** | `npx assuremind run --all --ci` — exit code 0/1, works with any pipeline |
34
+ | **File-based** | Plain JSON storage, fully Git-friendly, no database |
35
+ | **Faker Data** | 100+ @faker-js/faker generators across 16 categories random emails, names, addresses, sequences no code, no stale data |
36
+ | **File upload & download** | Upload fixtures from the Studio and insert as `{{FILE:…}}` tokens; downloads auto-captured per run and viewable in Reports |
37
+ | **Visual regression** | Pixel-diff screenshot comparison with baselines — approve/reject visual changes in Studio |
38
+ | **CI/CD integration** | Quality gates, PR comments (GitHub/GitLab), Slack/Teams notifications |
39
+
40
+ ---
41
+
42
+ ## Quick Start
43
+
44
+ ```bash
45
+ npm install assuremind
46
+ npx assuremind init # folders, config, Playwright browsers
47
+ npx playwright install # if browser install was skipped or failed during init
48
+ npx assuremind studio # opens http://localhost:4400
49
+ ```
50
+
51
+ > **First-time setup:** `npx assuremind init` installs the Playwright browsers automatically. If that step is skipped (`--skip-playwright`) or fails (network/permissions), install them manually with `npx playwright install` (add `--with-deps` on Linux to pull OS libraries). Run `npx assuremind doctor` to verify your setup.
52
+
53
+ ### System Requirements
54
+
55
+ | | Minimum | Recommended |
56
+ |---|---|---|
57
+ | **Node.js** | 18 LTS | 20 LTS or newer |
58
+ | **OS** | macOS / Linux / Windows 10+ | — |
59
+ | **RAM** | 4 GB | 8 GB+ |
60
+ | **Disk** | ~2 GB (app + Playwright browsers) | 5 GB+ |
61
+ | **Java** | — | JDK 17+ — only for Allure HTML reports |
62
+
63
+ `npx assuremind init` installs the Playwright browsers. Using a **cloud AI provider** (Anthropic, OpenAI, Gemini, …) needs only an API key and the specs above. Running a **local model via Ollama** has heavier requirements — see below.
64
+
65
+ ### Configure AI Provider
66
+
67
+ Edit `.env` — pick one provider:
68
+
69
+ ```bash
70
+ # Anthropic # OpenAI # Google
71
+ AI_PROVIDER=anthropic AI_PROVIDER=openai AI_PROVIDER=google
72
+ ANTHROPIC_API_KEY=sk-ant-... OPENAI_API_KEY=sk-... GOOGLE_API_KEY=AIza...
73
+ ANTHROPIC_MODEL=claude-sonnet.. OPENAI_MODEL=gpt-4o GOOGLE_MODEL=gemini-2.5-pro
74
+ ```
75
+
76
+ See `.env.example` for all 12 providers including Gemini, OpenAI, Anthropic, Ollama (local/free), etc.
77
+
78
+ ### Local & Free — Ollama
79
+
80
+ Run models entirely on your own machine (no API key, no cost). AssureMind uses the model to turn
81
+ plain-English steps into Playwright code, so a **code-tuned model with strong instruction-following**
82
+ works best.
83
+
84
+ ```bash
85
+ # 1. Install Ollama https://ollama.com/download
86
+ ollama serve # starts the server on http://localhost:11434
87
+ ollama pull qwen2.5-coder:7b # 2. pull the recommended model
88
+ ```
89
+
90
+ ```bash
91
+ # 3. .env
92
+ AI_PROVIDER=ollama
93
+ OLLAMA_MODEL=qwen2.5-coder:7b
94
+ OLLAMA_BASE_URL=http://localhost:11434
95
+ AI_TIMEOUT=120 # local inference is slower than cloud APIs
96
+ ```
97
+
98
+ **Recommended models (by hardware):**
99
+
100
+ | Hardware | Model | Notes |
101
+ |----------|-------|-------|
102
+ | 16 GB+ RAM, GPU 8 GB+ VRAM | `qwen2.5-coder:14b` | Highest accuracy best for complex steps / iframes |
103
+ | 16 GB RAM (GPU optional) | `qwen2.5-coder:7b` | **Best balance** of quality & speed for this task |
104
+ | 8 GB RAM, no GPU | `llama3.2` (3B) / `qwen2.5-coder:3b` | Usable; good for simpler steps |
105
+ | ≤4–6 GB RAM | `llama3.2:1b` / `phi3:mini` | Lightweight; navigation & clicks only |
106
+
107
+ **Ollama system requirements:**
108
+
109
+ - **RAM is the floor** a model needs roughly its file size **+ ≈2 GB free**. A 7B model (≈4.7 GB)
110
+ wants **8 GB free RAM minimum, 16 GB comfortable**; a 14B model wants **≈16 GB+**.
111
+ - **GPU is optional but transformative** CPU-only works (hence `AI_TIMEOUT=120`), but a GPU with
112
+ **8 GB+ VRAM** (NVIDIA CUDA / Apple Silicon / modern AMD) makes 7B models fast. Apple Silicon (M-series) is excellent thanks to unified memory.
113
+ - **Disk** — a few GB per model; keep **10–20 GB free** if trying several.
114
+ - **Tips** enable **MCP** (Settings live page snapshots) for far more accurate locators with local
115
+ models. Avoid `deepseek-r1` here: its `<think>` reasoning output is slow and pollutes generated code.
116
+
117
+ ---
118
+
119
+ ## CLI
120
+
121
+ ```bash
122
+ npx assuremind run --all # run everything
123
+ npx assuremind run --type ui --tag smoke # filter by type + tag
124
+ npx assuremind run --suite "Login" --browser chromium # run a suite
125
+ npx assuremind run --all --device "iPhone 15 Pro" --ci # mobile + CI mode
126
+ npx assuremind generate --story "User resets password" # AI generates full suite
127
+ npx assuremind apply-healing --yes # accept all healed selectors
128
+ npx assuremind validate # check config health
129
+ npx assuremind doctor # system diagnostics
130
+ ```
131
+
132
+ | Flag | Description |
133
+ |------|-------------|
134
+ | `--all` | Run every suite |
135
+ | `--type <ui\|api\|audit>` | Filter by suite type |
136
+ | `--suite <name>` | Partial name match |
137
+ | `--tag <tag>` | Filter by tag |
138
+ | `--device <name>` | Emulate device (e.g. `"iPhone 15 Pro"`, `"Pixel 7"`) |
139
+ | `--browser <list>` | `chromium` `firefox` `webkit` |
140
+ | `--ci` | CI mode exit code reflects pass/fail |
141
+ | `--headed` | Show browser window |
142
+ | `--no-healing` | Disable self-healing |
143
+
144
+ Full reference → [docs/CLI-REFERENCE.md](docs/CLI-REFERENCE.md)
145
+
146
+ ---
147
+
148
+ ## Studio UI
149
+
150
+ Start with `npx assuremind studio` — opens at `http://localhost:4400`.
151
+
152
+ **Dashboard** · **Smart Tests** · **Test Editor** · **Run Config** · **Reports** · **Variables** · **Self-Healing** · **Step Library** · **Faker Data** · **CI/CD** · **Git Control** · **Settings** · **Docs**
153
+
154
+ Full walkthrough → [docs/STUDIO.md](docs/STUDIO.md)
155
+
156
+ ---
157
+
158
+ ## MCP Integration
159
+
160
+ AI sees **real page elements** during code generation via the official `@playwright/mcp` server. Enabled by default.
161
+
162
+ | Mode | Accuracy | Latency | Config |
163
+ |------|----------|---------|--------|
164
+ | Blind (MCP off) | ~50-70% | Fastest | `mcp.enabled: false` |
165
+ | **Snapshot-driven** | ~90-95% | +2-5s first page | `mcp.enabled: true` (default) |
166
+ | Act-then-script | ~98-100% | +5-10s/step | `mcp.actThenScript: true` |
167
+
168
+ - MCP is **only used during code generation** test execution is never affected
169
+ - Silent fallback if MCP fails, generation continues blindly without error
170
+ - Configure in **Settings → MCP Integration** or `autotest.config.json`
171
+
172
+ ---
173
+
174
+ ## Test Recorder
175
+
176
+ Record tests by interacting with your application in a real browser — **zero AI, zero cost, zero guesswork**.
177
+
178
+ Click **Record** in the Test Editor, perform your actions, and stop. Each interaction becomes a step with verified Playwright code, ready to run.
179
+
180
+ ### How it works
181
+
182
+ > Available for **UI** and **Audit** suites only (not API suites).
183
+
184
+ 1. A headed Chromium browser opens your app's URL
185
+ 2. Every click, fill, navigation, and keyboard action is captured in real time **including inside iframes and shadow roots**
186
+ 3. Locators are resolved against Playwright's **accessibility tree** — the recorder tries 6 strategies (data-testid, getByRole, getByLabel, getByPlaceholder, getByText, CSS) and verifies each with `count() === 1`
187
+ 4. **Iframe-aware** — elements inside iframes automatically generate `page.frameLocator('#iframe').getByRole(...)` code with the correct frame chain
188
+ 5. **Shadow DOM** — `composedPath()[0]` pierces shadow roots; generates `host >> inner` pierce locators automatically
189
+ 6. **JS dialogs** — alerts/confirms are auto-accepted during recording; `page.once('dialog', ...)` is prepended to the triggering step's code
190
+ 7. **Keyboard** Tab, Shift+Tab, arrows, Enter, Escape, Ctrl+A, and Space on buttons are all captured
191
+ 8. Assertions via keyboard shortcuts: **Shift+Click** (element visible), **Ctrl+Shift+U** (URL), **Ctrl+Shift+T** (page title)
192
+ 9. On stop, each action is added as a step with **pre-generated Playwright code** — no AI call needed
193
+
194
+ ### What makes it stand out vs other recorders
195
+
196
+ | Feature | Selenium IDE | Playwright Codegen | AssureMind Recorder |
197
+ |---------|-------------|-------------------|---------------------|
198
+ | Locator quality | CSS/XPath | Good | Best6 strategies, verified against live page |
199
+ | Accessibility tree | No | Partial | Full — every locator checked via Playwright API |
200
+ | **Iframe support** | Partial | Manual | **Full** detects iframes, generates `frameLocator()` code click **and** fill both work |
201
+ | **Shadow DOM** | No | Limited | `>>` pierce combinator elements inside shadow roots are reachable |
202
+ | **JS Alert handling** | No | No | `page.once('dialog', ...)` registered automatically before triggering action |
203
+ | **Keyboard actions** | No | No | `page.keyboard.press()` / `.type()` for keys, shortcuts, and character input |
204
+ | Assertions | Manual | Manual | Shift+Click (hard), Ctrl+Shift+Click (soft), URL & title shortcuts |
205
+ | Plain-English steps | No | No | Yes — human-readable instructions auto-generated |
206
+ | Self-healing after | No | No | Yes — 5-level AI healing cascade |
207
+ | RAG memory | No | No | Yes — recorded steps feed the learning loop |
208
+ | Cost | Free | Free | Free |
209
+
210
+ ### Biggest pain points in test automation — solved
211
+
212
+ | Pain Point | How the Recorder Solves It |
213
+ |-----------|---------------------------|
214
+ | Writing tests is slow | Record a full test in 30 seconds |
215
+ | Selectors break constantly | Locators verified against Playwright's accessibility tree in real time |
216
+ | AI costs money | Recording + code generation = $0, zero AI calls |
217
+ | Non-technical testers can't write tests | Anyone who can click a browser can create tests |
218
+ | Assertions are hard to write | Shift+Click for hard, Ctrl+Shift+Click for soft, Ctrl+Shift+U for URL, Ctrl+Shift+T for title |
219
+ | Hard vs soft assertions | Soft assertions (`expect.soft()`) let the test continue — all failures reported at end |
220
+ | Recorded tests are fragile | 6-strategy locator resolution + post-run 5-level self-healing |
221
+ | Apps use iframes (SAP, Salesforce) | Recorder auto-detects iframe context, generates `frameLocator()` chains **click and fill** both work |
222
+ | Shadow DOM / Web Components | Recorder pierces shadow roots via `composedPath()`, generates `>>` locators automatically |
223
+ | JavaScript alerts & popups | Recorder auto-accepts dialogs; `page.once('dialog', ...)` prepended to triggering step |
224
+ | Keyboard interactions | Recorder captures Tab, Shift+Tab, arrows, Ctrl+A, Enter, Escape, and Space |
225
+
226
+ ---
227
+
228
+ ## RAG Memory (Retrieval-Augmented Generation)
229
+
230
+ The AI learns from every test run, building semantic memory that improves accuracy over time — **zero setup required**:
231
+
232
+ | Corpus | What it stores | When it's used |
233
+ |--------|---------------|----------------|
234
+ | **Code Corpus** | Instruction-to-code mappings from successful runs | During generationsimilar past steps are retrieved as AI examples or used directly (score >= 0.90) |
235
+ | **Healing Corpus** | Past healing events (error + fix pairs) | During self-healingproven past fixes are injected into the repair prompt |
236
+ | **Error Catalog** | Recurring error patterns per URL | During generation — the AI is warned about known-bad selectors to avoid |
237
+
238
+ **Zero cost, zero database** — uses local TF-IDF embeddings and file-based JSON storage (`results/.rag/`). Enabled by default — works automatically from the very first run.
239
+
240
+ ### How it improves over time
241
+
242
+ - **Run 1**memory is empty, AI generates code normally
243
+ - **Run 2+** — RAG kicks in silently: similar instructions are retrieved instead of making API calls (free + faster), healing uses proven past fixes
244
+ - **Run 10+** — most common steps are served from RAG memory at zero cost, self-healing resolves issues on the first attempt
245
+
246
+ ### Consumer FAQ
247
+
248
+ | Question | Answer |
249
+ |----------|--------|
250
+ | Do I need to configure anything? | No. RAG is ON by default with zero setup. |
251
+ | Does it cost anything? | No. TF-IDF embedder runs locally. RAG direct hits replace paid AI calls. |
252
+ | Does it slow down my tests? | No. RAG lookup is <1ms. It actually speeds up generation. |
253
+ | Does it work in CI/CD? | Yes. Cache `results/.rag/` between CI runs to persist memory. |
254
+ | How do I share memory across team? | Commit `results/.rag/` to Git or use a CI cache step. |
255
+ | How do I reset memory? | Delete the `results/.rag/` folder. |
256
+
257
+ ### When to use Settings → RAG Memory
258
+
259
+ Most users never need to touch RAG settings. The Settings card exists for power-user scenarios:
260
+
261
+ | Scenario | Action |
262
+ |----------|--------|
263
+ | Debugging a flaky test | Turn OFF Code Corpus — forces fresh AI generation |
264
+ | Healing keeps suggesting a bad fix | Turn OFF Healing Corpusclears bad fix influence |
265
+ | Major app redesign | Turn OFF RAG entirelyold memory is now misleading |
266
+ | Error warnings are outdated | Turn OFF Error Catalog stops avoiding selectors that are fine now |
267
+ | Want deterministic CI runs | Disable RAG in CI config, keep ON locally |
268
+
269
+ ---
270
+
271
+ ## Self-Healing
272
+
273
+ When your app's UI changes (button renamed, element moved, DOM restructured), tests break. Instead of failing immediately, AssureMind automatically attempts to fix the broken selector through a 5-level cascade — **fully automated, no manual intervention needed**:
274
+
275
+ | Level | What happens | Example | AI Cost |
276
+ |-------|-------------|---------|---------|
277
+ | 1 | **Smart retry** — waits for the element with exponential backoff | Element was loading slowly; retry finds it after 2s | Free |
278
+ | 2 | **AI regeneration** — AI rewrites the Playwright code using current page context | `#login-btn` removedAI generates `page.getByRole('button', { name: 'Sign In' })` | 1 call |
279
+ | 3 | **Multi-selector** — AI generates 5 alternative selector strategies, tries each | Tries role label placeholder text CSS until one works | 1 call |
280
+ | 4 | **Visual analysis** — takes a screenshot, AI visually locates the element | Button has no text/role but AI sees it in the screenshot | 1 call |
281
+ | 5 | **Decompose** — breaks the failing step into 3-5 simpler micro-actions | "Fill login form and submit" → separate fill email + fill password + click submit | 1 call |
282
+
283
+ If all 5 levels fail, the step is marked **failed** and saved to the healing report for your review.
284
+
285
+ ### How you use it
286
+
287
+ 1. **During test runs** — healing happens automatically. If Level 2 fixes a broken `#login-btn`, your test **passes** and continues.
288
+ 2. **After the run** — healed selectors are saved as **pending suggestions** (not auto-applied to source files).
289
+ 3. **Review & accept** — in Studio → **Self-Healing** page, or from CLI:
290
+ ```bash
291
+ npx assuremind apply-healing # interactive review: accept/reject each fix
292
+ npx assuremind apply-healing --yes # accept all in CI
293
+ ```
294
+ 4. **Accepted fixes** are written back to your `.test.json` files — next run uses the healed code permanently.
295
+
296
+ > **CI/CD tip:** Add `npx assuremind apply-healing --yes` as a post-test step so healed selectors are committed back automatically. Enable `healing.autoPR` in Settings to auto-create a GitHub PR with the fixes.
297
+
298
+ ---
299
+
300
+ ## CI/CD
301
+
302
+ ```yaml
303
+ # GitHub Actions
304
+ - name: Run tests
305
+ env:
306
+ AI_PROVIDER: google
307
+ GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
308
+ GOOGLE_MODEL: gemini-2.5-pro
309
+ run: npx assuremind run --all --ci
310
+ ```
311
+
312
+ Also supports **GitLab CI** and **Jenkins** — or use the built-in **CI Config Generator** in Studio (Run Config → Generate CI Config).
313
+
314
+ **CI Config Generator** (Run Config Generate CI Config):
315
+ - Generates a workflow for **GitHub Actions**, **GitLab CI**, or **Jenkins** from your current run config.
316
+ - The YAML is shown in a **preview**; click **✎ Edit** to customise it (branches, Node version, extra steps…). Your edits apply to Copy, Download, and Write to repo. Use **↺ Reset** to regenerate.
317
+ - **Copy** / **Download** are always available.
318
+ - **Write to repo** (opt-in) writes the file into your project at its standard path (`.github/workflows/assuremind.yml`, `.gitlab-ci.yml`, or `Jenkinsfile`). Enable it in **Settings → CI/CD Integration → "Write CI files to repo"**. It only **writes the file** — it does **not** commit or push. Review the change and commit it from the **Git Control Center** when ready.
319
+
320
+ Exit code `0` = all passed · `1` = failures.
321
+
322
+ ---
323
+
324
+ ## Enterprise Features
325
+
326
+ ### Faker Data
327
+
328
+ 100+ @faker-js/faker generators across 16 categories — generate realistic random data without code.
329
+
330
+ | Generator | Example output |
331
+ |-----------|---------------|
332
+ | `person.fullName` | Sarah Johnson |
333
+ | `internet.email` | sarah.johnson@gmail.com |
334
+ | `phone.number` | +1-555-123-4567 |
335
+ | `finance.amount` | 249.99 |
336
+ | `location.city` | San Francisco |
337
+ | Sequence `USER-{n}` | USER-001, USER-002, USER-003 |
338
+
339
+ Browse by category or search, select multiple tokens at once — selected tokens appear as removable chips, and clicking "Insert N tokens" inserts them all comma-separated (e.g. `{{FAKE_PERSON_FIRSTNAME}}, {{FAKE_PERSON_LASTNAME}}, {{FAKE_INTERNET_EMAIL}}`). Great for form filling. Tokens resolve to fresh random values on every test run — no more "email already exists" failures.
340
+
341
+ ### File Upload & Download
342
+
343
+ **Upload** — In the Test Editor, click the **Files** button (next to *Fake Data*) to upload a fixture file. It's saved in the repo at `fixtures/uploads/` (so it's committed and works in CI) and inserted into your step as a **`{{FILE:name}}`** token. The token resolves to the file's path at runtime:
344
+
345
+ ```
346
+ Step: Upload {{FILE:resume.pdf}} to the Resume field
347
+ Code: await page.getByLabel('Resume').setInputFiles('{{FILE:resume.pdf}}');
348
+ ```
349
+
350
+ For a file-chooser button, register the listener before the click (in one step):
351
+ ```js
352
+ const fileChooserPromise = page.waitForEvent('filechooser');
353
+ await page.getByRole('button', { name: 'Choose File' }).click();
354
+ (await fileChooserPromise).setFiles('{{FILE:resume.pdf}}');
355
+ ```
356
+
357
+ **Download** — Downloads are **captured automatically** during a run (no `saveAs`, no `fs` needed) and saved to `results/downloads/<runId>/`. The step waits until the file finishes downloading. After the run, open **Reports → Run Reports**, expand the run, and the **Downloads** panel lists every captured file — click any to save it to your machine.
358
+
359
+ **Example steps** (type these in plain English):
360
+
361
+ ```text
362
+ # Upload
363
+ Upload {{FILE:resume.pdf}} to the Resume field
364
+ Upload {{FILE:resume.pdf}} to the Resume field and wait for 'Upload complete' # most reliable
365
+ Upload {{FILE:photo.png}} # page's file input
366
+
367
+ # Download (file finishes downloading before the step passes)
368
+ Download the "Export CSV" link
369
+ Click the "Export" button to download
370
+ Download the file by clicking "Report PDF"
371
+ ```
372
+
373
+ Tip: for uploads, the `…and wait for '<success text>'` form is the most reliable (uploads have no completion event); otherwise the step waits for the network to settle.
374
+
375
+ ### Visual Regression
376
+
377
+ Pixel-perfect screenshot comparison — catch UI changes that functional tests miss. Configure in **Settings** → Visual Regression. Review diffs in **Reports** → Visual Diffs tab.
378
+
379
+ 1. Enable in **Settings** → Visual Regression, then toggle the **Eye icon** on any step in the Test Editor
380
+ 2. First run captures **baseline** screenshots (committed to git)
381
+ 3. Subsequent runs **compare** pixel-by-pixel using `pixelmatch`
382
+ 4. Diff > thresholdstep **fails** with highlighted diff image
383
+ 5. Review in **Reports** → Visual Diffs → **Approve** (update baseline) or **Reject** (it's a bug)
384
+
385
+ ```
386
+ baselines/ # committed to git
387
+ ├── login-suite/login-test/
388
+ ├── step-3-chromium-1920x1080.png
389
+ │ └── step-3-firefox-1920x1080.png
390
+ results/visual-diffs/{runId}/ # gitignored, per-run
391
+ ├── step-3-baseline.png
392
+ ├── step-3-actual.png
393
+ └── step-3-diff.png # red highlights
394
+ ```
395
+
396
+ ### CI/CD Integration
397
+
398
+ Quality gates, PR comments, and notifications — configured from Studio, executed in pipelines.
399
+
400
+ | Feature | What it does |
401
+ |---------|-------------|
402
+ | **Quality gates** | Set min pass rate (95%), max duration, required tags pipeline fails if gate fails |
403
+ | **PR comments** | Auto-post test results as GitHub PR comment or GitLab MR note |
404
+ | **Notifications** | Slack, Teams, Email, custom webhook — trigger on failure, every run, or healing events |
405
+
406
+ ```yaml
407
+ # GitHub Actions — full integration
408
+ - name: Run tests
409
+ env:
410
+ AI_PROVIDER: anthropic
411
+ ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
412
+ run: npx assuremind run --all --ci
413
+ # Quality gate auto-evaluates, PR comment auto-posts, Slack notifies on failure
414
+ ```
415
+
416
+ ---
417
+
418
+ ## Documentation
419
+
420
+ | Resource | Location |
421
+ |----------|----------|
422
+ | Getting started | [docs/GETTING-STARTED.md](docs/GETTING-STARTED.md) |
423
+ | Writing test steps (UI & API examples) | [docs/WRITING-STEPS.md](docs/WRITING-STEPS.md) |
424
+ | Studio walkthrough | [docs/STUDIO.md](docs/STUDIO.md) |
425
+ | CLI reference | [docs/CLI-REFERENCE.md](docs/CLI-REFERENCE.md) |
426
+ | Contributing | [CONTRIBUTING.md](CONTRIBUTING.md) |
427
+ | All AI providers | `.env.example` |
428
+ | Built-in docs | Studio → **Docs** page |
429
+ | Enterprise features | Studio → **Faker Data**, **CI/CD** pages; Visual Regression in **Settings** + **Reports** |
430
+
431
+ ---
432
+
433
+ ## Community & Support
434
+
435
+ Have a question, found a bug, or want to shape what comes next? Join the **[AssureMind Community Hub](https://assuremind.in/community/)**:
436
+
437
+ - 🐞 **Report bugs**
438
+ - **Request new features**
439
+ - 💡 **Share ideas and feedback**
440
+ - ❓ **Ask questions**
441
+
442
+ 🌐 **Website:** [https://assuremind.in/](https://assuremind.in/) &nbsp;|&nbsp; 💬 **Community Hub:** [https://assuremind.in/community/](https://assuremind.in/community/) &nbsp;|&nbsp; 📧 **[assuremind.contact@gmail.com](mailto:assuremind.contact@gmail.com)**
443
+
444
+ ---
445
+
446
+ ## License
447
+
448
+ Apache 2.0 — see [LICENSE](LICENSE) for details.
449
+
450
+ ---
451
+
452
+ *Built by [Deepak Hiremath](https://www.linkedin.com/in/deepak-hiremath-0017937a/)*
package/package.json CHANGED
@@ -1,9 +1,9 @@
1
1
  {
2
2
  "name": "assuremind",
3
- "version": "1.4.0",
3
+ "version": "1.4.1",
4
4
  "description": "AI-powered codeless UI & API automation framework",
5
5
  "author": "Deepak Hiremath",
6
- "license": "MIT",
6
+ "license": "Apache-2.0",
7
7
  "bin": {
8
8
  "assuremind": "./dist/cli/index.js"
9
9
  },