haltija 1.1.0

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.
package/LICENSE ADDED
@@ -0,0 +1,190 @@
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 the Licensor for inclusion in the Work by the copyright
52
+ owner or by an individual or Legal Entity authorized to submit on behalf
53
+ of 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
+ Copyright 2025 Tonio Loewald
179
+
180
+ Licensed under the Apache License, Version 2.0 (the "License");
181
+ you may not use this file except in compliance with the License.
182
+ You may obtain a copy of the License at
183
+
184
+ http://www.apache.org/licenses/LICENSE-2.0
185
+
186
+ Unless required by applicable law or agreed to in writing, software
187
+ distributed under the License is distributed on an "AS IS" BASIS,
188
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
189
+ See the License for the specific language governing permissions and
190
+ limitations under the License.
package/README.md ADDED
@@ -0,0 +1,220 @@
1
+ # Haltija
2
+
3
+ **Give AI agents eyes and hands in the browser.** Make any browser tab MCP-compatible.
4
+
5
+ - **See** the live DOM as a semantic tree — what's clickable, what's hidden and why, what inputs exist
6
+ - **Do** things — click buttons, fill forms, navigate, run JavaScript
7
+ - **Watch** what happens — console errors, DOM mutations, user actions, all as meaningful events
8
+
9
+ Unlike screenshot-based tools, Haltija works with the actual DOM. Unlike Playwright, it connects to your real browser — already logged in, same cookies, same bug you're looking at.
10
+
11
+ <!-- TODO: Replace with actual GIF showing: 1) bunx haltija launches app, 2) agent queries tree, 3) agent clicks something, 4) highlight shows result -->
12
+ ![Haltija in action](docs/assets/demo.gif)
13
+
14
+ > *Haltija* (Finnish): a guardian spirit that watches over a place. In this case, your DOM.
15
+
16
+ ---
17
+
18
+ ## Quick Start
19
+
20
+ ### Desktop App (Recommended)
21
+
22
+ ```bash
23
+ bunx haltija
24
+ ```
25
+
26
+ Launches a dedicated browser with the Haltija server embedded. Browse to any page — the widget auto-attaches and your agent can control it immediately. No bookmarklets, no CSP issues.
27
+
28
+ ### Tell your agent
29
+
30
+ Paste this into your agent conversation:
31
+
32
+ > I have the `hj` browser tool. Run `hj tree` to see the page, `hj click <id>` to interact, and `hj docs` for help.
33
+
34
+ Or for Claude Code with MCP: `bunx haltija --setup-mcp`
35
+
36
+ ---
37
+
38
+ ## What Agents Can Do
39
+
40
+ ```bash
41
+ # See the page
42
+ hj tree # Semantic DOM structure with ref IDs
43
+ hj screenshot # Visual capture with metadata
44
+ hj console # Recent errors and logs
45
+
46
+ # Interact
47
+ hj click 42 # Click by ref (from tree output)
48
+ hj type 10 user@example.com # Type text
49
+ hj key Escape # Keyboard input
50
+ hj key s --ctrl # Keyboard shortcuts
51
+
52
+ # Watch for changes
53
+ hj events # Aggregated semantic events
54
+
55
+ # Point things out (draws a visual box on the user's screen)
56
+ hj highlight 5 "Problem here"
57
+ ```
58
+
59
+ Full API: `hj docs` — or `hj api` for complete reference
60
+
61
+ ---
62
+
63
+ ## Why Not Playwright / Puppeteer?
64
+
65
+ | | Haltija | Playwright MCP |
66
+ |---|---------|----------------|
67
+ | **Browser** | Your real browser | Separate headless instance |
68
+ | **State** | Already logged in, cookies, extensions | Clean slate every time |
69
+ | **Setup** | `bunx haltija` | Install Playwright, configure MCP |
70
+ | **Protocol** | Simple REST/curl | Complex CDP |
71
+ | **Visibility** | Watch it happen live | Background process |
72
+
73
+ Haltija connects to the browser you're already using. The one with the bug, the active session, and the weird cookie state. No reproduction script required.
74
+
75
+ ---
76
+
77
+ ## How It Works
78
+
79
+ ```
80
+ Browser Tab Server (Bun) AI Agent
81
+ │ │ │
82
+ │◄── WebSocket ─────►│◄── REST API ─────►│
83
+ │ │ │
84
+ └─ Widget └─ Routes messages └─ curl / MCP / SDK
85
+ ```
86
+
87
+ The widget (auto-injected by the desktop app) connects to a local server via WebSocket. Agents talk to the server via REST. No special libraries, just HTTP.
88
+
89
+ ---
90
+
91
+ ## Key Features
92
+
93
+ ### Semantic Tree with Flags
94
+
95
+ The `/tree` endpoint doesn't dump raw HTML. It produces a semantic structure with actionable flags:
96
+
97
+ ```
98
+ 3: button "Submit" [interactive] [disabled]
99
+ ```
100
+
101
+ Ref IDs (the numbers before `:`) let agents target elements efficiently without CSS selectors. Refs are stable within a page session — they survive DOM updates and re-renders as long as the element stays in the document.
102
+
103
+ ### Noise-Reduced Events
104
+
105
+ Raw DOM events are noise. Haltija aggregates them into intent:
106
+
107
+ | Raw Events | Semantic Event |
108
+ |------------|----------------|
109
+ | 18 keydown, 18 input | `"user typed 'hello@example.com'"` |
110
+ | 200 scroll events | `"user scrolled to #pricing"` |
111
+
112
+ 96% noise reduction in real-world testing.
113
+
114
+ ### Screenshots with Context
115
+
116
+ Screenshots include a chyron (title, URL, timestamp) so agents always know what they're looking at. Disable with `chyron: false` for clean captures.
117
+
118
+ ### Multi-Window & Session Affinity
119
+
120
+ Control multiple tabs. Session headers (`X-Haltija-Session`) give agents sticky window targeting — no need to specify window ID every call.
121
+
122
+ ### Selection Tool
123
+
124
+ User drags to select UI elements. Selection persists visually until the agent retrieves it:
125
+
126
+ ```bash
127
+ hj select-result # Returns selectors, HTML, bounding boxes
128
+ ```
129
+
130
+ ### Test Recording
131
+
132
+ Click record, use your app, get a JSON test:
133
+
134
+ ```json
135
+ {
136
+ "steps": [
137
+ {"action": "type", "selector": "#email", "text": "user@example.com"},
138
+ {"action": "click", "selector": "button[type=submit]"},
139
+ {"action": "assert", "type": "exists", "selector": ".dashboard"}
140
+ ]
141
+ }
142
+ ```
143
+
144
+ ---
145
+
146
+ ## Bring Your Own Browser (Advanced)
147
+
148
+ Want to control your daily driver — Chrome, Edge, Firefox — with your existing sessions and cookies?
149
+
150
+ ```bash
151
+ bunx haltija --server
152
+ ```
153
+
154
+ Then inject the widget into any page:
155
+
156
+ **Bookmarklet** — Visit `http://localhost:8700`, drag to toolbar, click on any page.
157
+
158
+ **Dev snippet** — Auto-disabled in production:
159
+ ```javascript
160
+ /^localhost$|^127\./.test(location.hostname)&&import('http://localhost:8700/dev.js')
161
+ ```
162
+
163
+ Your agent uses the same `hj` commands either way — it doesn't know or care which browser it's talking to.
164
+
165
+ ---
166
+
167
+ ## Installation
168
+
169
+ ```bash
170
+ bunx haltija # Desktop app (recommended)
171
+ bunx haltija --server # Server only (your browser, CI, remote)
172
+ npm install -g haltija # Install globally
173
+
174
+ # Server options
175
+ haltija --https # HTTPS mode
176
+ haltija --port 3000 # Custom port
177
+ haltija --headless # For CI pipelines
178
+ haltija --setup-mcp # Configure Claude Desktop
179
+ ```
180
+
181
+ ---
182
+
183
+ ## Security
184
+
185
+ - Widget is always visible (no silent snooping)
186
+ - User can pause or kill connection anytime
187
+ - Localhost only by default
188
+ - HTTPS mode with auto-generated certs
189
+
190
+ ---
191
+
192
+ ## Use Cases
193
+
194
+ - **AI pair programming** — Agent sees your actual app, not a description of it
195
+ - **Automated QA** — Agent explores, finds bugs, writes repro steps
196
+ - **Accessibility auditing** — Inspect ARIA across the whole page
197
+ - **UX crime detection** — Detects 35+ anti-patterns automatically
198
+ - **Support** — See exactly what customers see
199
+
200
+ ---
201
+
202
+ ## Documentation
203
+
204
+ ```bash
205
+ hj docs # Quick start (plain text, LLM-friendly)
206
+ hj api # Full API reference (markdown)
207
+ hj --help # CLI subcommand reference
208
+ ```
209
+
210
+ - [Full API Reference](./API.md) (auto-generated from schema)
211
+ - [Agent Prompt](docs/agent-prompt.md) — Copy-paste prompt for any AI agent
212
+ - [Recipes](docs/recipes.md) — Common workflows
213
+ - [CI Integration](docs/CI-INTEGRATION.md) — E2E testing with Haltija in GitHub Actions
214
+ - [Roadmap](docs/ROADMAP.md)
215
+
216
+ ---
217
+
218
+ ## License
219
+
220
+ Apache 2.0
@@ -0,0 +1,107 @@
1
+ /**
2
+ * Build the bookmarklet as a javascript: URL
3
+ *
4
+ * The bookmarklet loads inject.js from the tosijs-dev server.
5
+ * The server can be local (localhost:8700) or any hosted instance.
6
+ */
7
+
8
+ import { writeFileSync, mkdirSync } from 'fs'
9
+ import { join } from 'path'
10
+
11
+ const DEFAULT_SERVER = 'http://localhost:8700'
12
+
13
+ // The bookmarklet - just fetches and evals inject.js
14
+ function makeBookmarklet(server: string) {
15
+ return `javascript:(function(){fetch('${server}/inject.js').then(r=>r.text()).then(eval).catch(e=>alert('Dev Channel: Cannot reach ${server}'))})();`
16
+ }
17
+
18
+ const bookmarklet = makeBookmarklet(DEFAULT_SERVER)
19
+
20
+ // Ensure dist exists
21
+ mkdirSync(join(import.meta.dir, '../dist'), { recursive: true })
22
+
23
+ // Output
24
+ console.log('\n=== Dev Channel Bookmarklet ===\n')
25
+ console.log('Bookmarklet (default server ' + DEFAULT_SERVER + '):')
26
+ console.log(bookmarklet)
27
+ console.log('\n')
28
+
29
+ // Write HTML page
30
+ const html = `<!DOCTYPE html>
31
+ <html>
32
+ <head>
33
+ <title>Dev Channel Bookmarklet</title>
34
+ <style>
35
+ body { font-family: system-ui; max-width: 700px; margin: 40px auto; padding: 20px; }
36
+ h1 { color: #333; }
37
+ h2 { color: #555; margin-top: 2em; }
38
+ .bookmarklet {
39
+ display: inline-block;
40
+ padding: 12px 24px;
41
+ background: #6366f1;
42
+ color: white;
43
+ text-decoration: none;
44
+ border-radius: 8px;
45
+ font-weight: 600;
46
+ margin: 10px 0;
47
+ }
48
+ .bookmarklet:hover { background: #4f46e5; }
49
+ pre {
50
+ background: #f3f4f6;
51
+ padding: 16px;
52
+ border-radius: 8px;
53
+ overflow-x: auto;
54
+ font-size: 11px;
55
+ word-break: break-all;
56
+ }
57
+ code { background: #e5e7eb; padding: 2px 6px; border-radius: 4px; }
58
+ .instructions { color: #666; line-height: 1.6; }
59
+ .note { background: #fef3c7; padding: 12px; border-radius: 6px; margin: 1em 0; }
60
+ </style>
61
+ </head>
62
+ <body>
63
+ <h1>Dev Channel</h1>
64
+ <p class="instructions">
65
+ A communication bridge between AI agents and browser pages.
66
+ Allows querying the DOM, watching events, and automating interactions.
67
+ </p>
68
+
69
+ <h2>Bookmarklet</h2>
70
+ <p class="instructions">Drag this to your bookmarks bar:</p>
71
+ <a class="bookmarklet" href="${bookmarklet}">Dev Channel</a>
72
+
73
+ <div class="note">
74
+ <strong>Note:</strong> Start the server first:
75
+ <code>bun run packages/tosijs-dev/bin/server.ts</code>
76
+ </div>
77
+
78
+ <h2>How It Works</h2>
79
+ <ol class="instructions">
80
+ <li>Start the tosijs-dev server</li>
81
+ <li>Click the bookmarklet on any page</li>
82
+ <li>A floating widget appears in the bottom-right corner</li>
83
+ <li>The widget connects via WebSocket to the server</li>
84
+ <li>AI agents can now query the DOM, dispatch events, and record interactions</li>
85
+ <li>Use <kbd>Option+Tab</kbd> to toggle widget visibility</li>
86
+ <li>Click "Kill" to completely remove the channel</li>
87
+ </ol>
88
+
89
+ <h2>Security</h2>
90
+ <p class="instructions">
91
+ The widget is <strong>always visible</strong> when an agent is connected - there's no silent snooping.
92
+ You can pause, resume, or kill the connection at any time.
93
+ </p>
94
+
95
+ <h2>Raw URL</h2>
96
+ <pre>${bookmarklet}</pre>
97
+
98
+ <h2>Custom Server</h2>
99
+ <p class="instructions">
100
+ To use a different server, create a bookmarklet with this pattern:<br>
101
+ <code>javascript:(function(){fetch('YOUR_SERVER/inject.js').then(r=>r.text()).then(eval).catch(e=>alert('Cannot reach server'))})();</code>
102
+ </p>
103
+ </body>
104
+ </html>`
105
+
106
+ writeFileSync(join(import.meta.dir, '../dist/bookmarklet.html'), html)
107
+ console.log('Wrote dist/bookmarklet.html\n')