qz-browser-agent 0.0.0-stage → 0.1.1

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.
package/LICENSE ADDED
@@ -0,0 +1,202 @@
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright [yyyy] [name of copyright owner]
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
package/README.md CHANGED
@@ -1,3 +1,467 @@
1
- # Temporary Holding Version
1
+ # qz command line and MCP
2
2
 
3
- This version is a temporary placeholder for this package. An operational version to replace this has been submitted for review and is awaiting a staged release.
3
+ Run browser tasks, manage results, and connect external agents to qz through CLI or MCP.
4
+ Requires Node.js 24 or later and Chrome. CLI and MCP share the same browser connection.
5
+
6
+ ## Quick start
7
+
8
+ Install [qz from the Chrome Web Store](https://chromewebstore.google.com/detail/dknbdgkgoinlgjpfebapkklbmjjgdblm)
9
+ with **Add to Chrome**. Open the qz side panel, complete its first-use data notice, and configure
10
+ your provider and model in Settings.
11
+
12
+ Run the published package with npx:
13
+
14
+ ```bash
15
+ npx qz-browser-agent@latest connect
16
+ npx qz-browser-agent@latest create "Summarize the current page." --stream
17
+ ```
18
+
19
+ `npx qz-browser-agent@latest install` opens the same Chrome Web Store page. For a manual ZIP
20
+ installation, download the [latest GitHub release](https://github.com/alibaba/qz-browser-agent/releases/latest)
21
+ and follow the [manual installation steps](https://github.com/alibaba/qz-browser-agent/blob/main/README.md#manual-installation).
22
+
23
+ `connect` starts the local MCP service and opens its connection page for first pairing. Use the
24
+ Chrome profile where qz is installed. The first new profile is named `default`;
25
+ accepting the data notice alone does not enable the local connection. Repeating `connect` reuses
26
+ an online browser. Add further profiles with a [pairing URL](#pair-a-selected-browser-from-the-shell)
27
+ or from their own qz Settings.
28
+
29
+ The examples and suggested next commands use `qz`. Replace it with
30
+ `npx qz-browser-agent@latest`, or install the command globally:
31
+
32
+ ```sh
33
+ npm install --global qz-browser-agent@latest
34
+ qz --version
35
+ ```
36
+
37
+ On Windows, use PowerShell 7.3 or newer with its default native argument passing. After a global
38
+ install, use `qz.ps1` for commands containing JSON or quoted names; Windows command suggestions
39
+ use that wrapper. For automation, pin a compatible release version verified with your extension.
40
+
41
+ ## Connect and stop
42
+
43
+ ```bash
44
+ qz connect
45
+ qz status
46
+ qz browsers
47
+ qz mcp
48
+ qz stop
49
+ ```
50
+
51
+ `connect` reuses the healthy service already running for this installation. It prefers port 18765;
52
+ if that port belongs to another program, the service chooses a free port. `status` shows the actual
53
+ service address, and `mcp` prints its MCP URL. Both commands are read-only. To request a custom port,
54
+ run `qz connect --port 18766`; an existing service on another port remains running and the command
55
+ reports its address. The extension connects only to its configured address.
56
+
57
+ The connection page can be closed once `qz browsers` shows the profile online. Connections start
58
+ only through `qz connect` or **qz Settings → Advanced → CLI → Connect CLI**. For ordinary connection
59
+ failures, the extension makes at most three recovery attempts, 30 seconds apart, then pauses.
60
+ After a browser or background restart, it may first wait once for the previous connection to expire.
61
+ The saved retry budget survives worker restarts. Click **Connect CLI** in that browser's settings to retry.
62
+
63
+ To disconnect one browser, click **Disconnect: NAME** in its qz Settings. `qz stop` stops the local
64
+ service and disconnects every browser and MCP client using it. Browser tasks already running
65
+ remain in the extension; stopping the service does not cancel them. Use `qz cancel TASK_ID` to stop
66
+ a task, adding `--client NAME|UUID` when needed.
67
+
68
+ ### Pair a selected browser from the shell
69
+
70
+ Get a pairing URL without opening the default browser or waiting for a connection:
71
+
72
+ ```bash
73
+ qz connect --no-open --json
74
+ qz connect --no-open --name work --json
75
+ ```
76
+
77
+ The JSON envelope contains `result.endpoint`, `result.url`, `result.mcpUrl`, and
78
+ `result.opened: false`. The command starts or reuses the service even when other browsers are
79
+ already connected. Open the exact returned URL in the intended browser Profile with qz installed.
80
+
81
+ Set `QZ_PAIRING_URL` to that URL and `QZ_PROFILE_DIRECTORY` to the selected profile's directory
82
+ name, such as `Default` or `Profile 2`. These are directory names, not Chrome's display labels.
83
+ Use a Profile already chosen by the user. On macOS:
84
+
85
+ ```sh
86
+ open -na "Google Chrome" --args --profile-directory="$QZ_PROFILE_DIRECTORY" "$QZ_PAIRING_URL"
87
+ ```
88
+
89
+ For Chrome on Linux:
90
+
91
+ ```sh
92
+ google-chrome --profile-directory="$QZ_PROFILE_DIRECTORY" "$QZ_PAIRING_URL"
93
+ ```
94
+
95
+ For Chrome installed under Program Files on Windows, set `$QzProfileDirectory` and
96
+ `$QzPairingUrl` to those same values in PowerShell:
97
+
98
+ ```powershell
99
+ & "$env:ProgramFiles\Google\Chrome\Application\chrome.exe" "--profile-directory=$QzProfileDirectory" $QzPairingUrl
100
+ ```
101
+
102
+ Use the installed browser's executable or app name. For an existing custom data directory, also
103
+ pass `--user-data-dir` with its exact path; for example on macOS:
104
+
105
+ ```sh
106
+ open -na "Google Chrome" --args --user-data-dir="$QZ_USER_DATA_DIR" --profile-directory="$QZ_PROFILE_DIRECTORY" "$QZ_PAIRING_URL"
107
+ ```
108
+
109
+ The [Chrome profile documentation](https://chromium.googlesource.com/chromium/src/+/master/docs/user_data_dir.md)
110
+ distinguishes the data directory from the Profile inside it. A new data directory needs its own
111
+ extension installation and first-use setup.
112
+
113
+ `--name work` adds `?name=work` to the URL. The Profile opening it receives that identifier,
114
+ including when it already has a connection. Without `--name`, a registered Profile keeps its name;
115
+ a new Profile receives the next available name: `default`, `browser-2`, and so on. A name conflict
116
+ requires another name. `qz connect --name work` opens the URL automatically and returns immediately.
117
+ These URL-returning commands do not confirm that a browser connected. Verify it with:
118
+
119
+ ```bash
120
+ qz browsers --json
121
+ qz create "Summarize the current page." --client UUID --stream
122
+ ```
123
+
124
+ Read `result.browsers`, then use the intended online entry's `clientId` UUID. `--client` selects an
125
+ existing connection and cannot be combined with `--no-open` or `--name`. `--port` works with either
126
+ pairing mode and follows the existing-service behavior above.
127
+
128
+ ### Add and select browsers
129
+
130
+ You can also pair from **qz Settings → Advanced → CLI** in the intended Profile. Enter a distinct
131
+ browser identifier and connect. Use the service address printed by `qz status` in **Local service address** if
132
+ its port differs from 18765. Names use 1–64 letters, digits, underscores, or hyphens, beginning with
133
+ a letter or digit; names are case-sensitive. UUID-shaped names are reserved for profile IDs.
134
+
135
+ ```bash
136
+ qz browsers
137
+ qz create "Summarize the current page." --client work --stream
138
+ qz show TASK_ID --client work
139
+ qz data --client work
140
+ ```
141
+
142
+ `--client NAME|UUID` and `-c NAME|UUID` select a profile. With exactly one online browser, the CLI
143
+ selects it automatically. With several online browsers, a selection is required; `default` is a
144
+ name, not a routing preference. An unknown or offline selection fails without opening or using
145
+ another browser. Each command resolves its name once and carries the UUID through subsequent
146
+ requests. JSON task results and suggested next commands include that UUID.
147
+
148
+ Names remain registered while their browsers are offline and across service restarts. To release
149
+ an offline name, remove its registration explicitly:
150
+
151
+ ```bash
152
+ qz browsers forget work
153
+ ```
154
+
155
+ An online browser must first disconnect in its settings. Forgetting a registration leaves the
156
+ browser's tasks and data intact. A browser can then explicitly pair using the released name.
157
+
158
+ ### Update the connection
159
+
160
+ Use the current CLI and extension together. Source edits and a newer npm package leave a healthy
161
+ running service in place; `qz status` reports an available update. An incompatible service returns
162
+ an update instruction instead of being stopped automatically.
163
+
164
+ 1. Use the latest CLI and let current tasks finish.
165
+ 2. Run `npx --yes qz-browser-agent@latest stop`. This disconnects all browsers using that service.
166
+ 3. Update qz from the [Chrome Web Store](https://chromewebstore.google.com/detail/dknbdgkgoinlgjpfebapkklbmjjgdblm).
167
+ For a manual ZIP installation, replace its extracted files with the
168
+ [latest release](https://github.com/alibaba/qz-browser-agent/releases/latest) and reload it at `chrome://extensions`.
169
+ 4. Run `npx --yes qz-browser-agent@latest connect`, then reconnect additional profiles using their
170
+ pairing URL or settings.
171
+
172
+ ## Connect an MCP client
173
+
174
+ Run `qz connect`, then `qz mcp`. Copy the returned URL into your MCP client's HTTP configuration:
175
+
176
+ ```toml
177
+ [mcp_servers.qz]
178
+ url = "http://127.0.0.1:18765/mcp"
179
+ ```
180
+
181
+ Use the URL printed by your command if its port differs. `qz mcp --json` returns the URL as JSON
182
+ for scripts. The `qingzhou_*` MCP tool names and extension protocol remain available. Responses
183
+ to pending input bind to an explicit `waitId`. Use `qingzhou_bridge_status` to list browser names
184
+ and UUIDs, then pass `clientId: "work"` or a UUID to browser tools. Selection is required with
185
+ multiple online browsers. Task results include the resolved `clientId`. MCP initialization and streaming are handled by your
186
+ client's MCP implementation.
187
+
188
+ ### Task and resource operations
189
+
190
+ CLI and MCP use the same task observer and browser operations. The task and resource commands map to these MCP operations:
191
+
192
+ | CLI | MCP tool |
193
+ | --- | --- |
194
+ | `browsers`, `browsers forget` | `qingzhou_bridge_status`, `qingzhou_forget_browser` |
195
+ | `create`, `send`, `cancel` | `qingzhou_create_session`, `qingzhou_send_message`, `qingzhou_stop_session` |
196
+ | `tasks`, `show`, `watch` | `qingzhou_list_sessions`, `qingzhou_get_session_snapshot`, `qingzhou_watch_task` |
197
+ | `show`, `submit` / `approve` / `reject` | `qingzhou_get_session_snapshot`, `qingzhou_respond_to_user_input` |
198
+ | `data list` / `delete` / `export` | `qingzhou_list_data_tables`, `qingzhou_delete_data_table`, `qingzhou_export_data_table` |
199
+ | `images list` / `delete` / `export` | `qingzhou_list_image_collections`, `qingzhou_delete_image_collection`, `qingzhou_export_image_collection` |
200
+ | `skills list` / `show` / `read` / `tools` / `export` | `qingzhou_list_skills`, `qingzhou_get_skill`, `qingzhou_get_skill_resource`, `qingzhou_list_plugins`, `qingzhou_export_skill` |
201
+ | `settings get` / `set` | `qingzhou_get_settings`, `qingzhou_update_settings` |
202
+ | `automations list` / `run` | `qingzhou_list_automations`, `qingzhou_run_automation` |
203
+
204
+ MCP creation, message submission, and input responses accept `wait: true` to wait for completion;
205
+ `stream: true` also sends assistant text through standard MCP progress notifications. A watch call
206
+ always waits. For example, call `qingzhou_create_session` with:
207
+
208
+ ```json
209
+ {"firstMessage":"Summarize the current page.","stream":true}
210
+ ```
211
+
212
+ Supply `_meta.progressToken` on the MCP request to receive progress. Each notification includes a
213
+ readable `message` and its structured event in `params._meta["qz/task-event"]`. Events include
214
+ `created`, `status`, `text`, `replace`, and `input`. Input events include the current form, exact
215
+ field IDs, option values, and `responseTemplate`. Fill that template and pass it to
216
+ `qingzhou_respond_to_user_input`; another CLI or MCP connection can answer while the original call
217
+ keeps waiting. Native Chrome permissions still require the user's click in the side panel.
218
+
219
+ MCP `timeoutSeconds` bounds each browser request (180 seconds by default).
220
+ `waitTimeoutSeconds` bounds the whole observation; omit it for no overall deadline. Configure your
221
+ MCP client's own request deadline for long tasks. On timeout or cancellation, the browser task
222
+ continues; error details include the task ID and a recovery tool call. `send_message` supports
223
+ `steer: true` and follows its returned `clientMessageId`, including when steering stays in the same
224
+ run. A long observation stays bound to the browser selected when it started.
225
+
226
+ ## Run a task
227
+
228
+ ```bash
229
+ qz create "Compare these two laptops."
230
+ qz create "Summarize the current page." --title "Research" --wait
231
+ qz create "Find the main differences between these pages." --stream
232
+ qz send TASK_ID "Add the source links." --stream
233
+ qz send TASK_ID "Focus on open-source options." --steer --stream
234
+ qz tasks
235
+ qz show TASK_ID
236
+ qz cancel TASK_ID
237
+ ```
238
+
239
+ `create` starts a task and returns its ID. The title is optional. `--wait` waits for the result;
240
+ `--stream` also displays progress as it arrives. Both stay connected while the task waits for user
241
+ input and continue automatically after you respond. Task observation has no default time limit.
242
+ Add `--timeout SECONDS` to set a total deadline, including time spent waiting for input. Each
243
+ individual connection request remains bounded (180 seconds by default). A timeout or Ctrl-C ends
244
+ watching; `qz watch TASK_ID --stream` resumes observation and `qz cancel TASK_ID` stops the task.
245
+ Each CLI command initializes one MCP connection on its first tool call and reuses it for subsequent
246
+ reads and responses. Completion, errors, and Ctrl-C close that connection. Transport failures are
247
+ reported without automatically repeating browser actions.
248
+
249
+ Provide the task text directly after `create`, or read it from stdin with `qz create -`.
250
+ Use `--parent TASK_ID` to create a child task, and `qz tasks --limit N` to limit the task list.
251
+ `send TASK_ID MESSAGE` sends a follow-up to the specified task; `qz send TASK_ID -` reads the message
252
+ from stdin. A busy task queues a follow-up for its next run. Add `--steer` to deliver the message
253
+ to the current run at its next safe boundary. Both start a new run when the task is idle. Pending
254
+ questions and permissions still require a response.
255
+
256
+ `--wait` and `--stream` track the submitted message. Streaming starts after that message, including
257
+ when steering continues the same run. Pending questions from the preceding run remain visible so
258
+ you can answer them and let a queued follow-up proceed. A connection failure never resends a message
259
+ automatically.
260
+
261
+ ## Respond to a task
262
+
263
+ ```bash
264
+ qz show TASK_ID
265
+ qz submit TASK_ID '{"selectedIds":["option-a"]}' --stream
266
+ qz approve TASK_ID --wait
267
+ qz reject TASK_ID
268
+ qz watch TASK_ID --stream
269
+ ```
270
+
271
+ `show` and pending-input notices include the current question, labeled field IDs,
272
+ option values, descriptions, image URLs, and a submission template with the actual field IDs.
273
+ Edit its placeholder values and run the displayed command to respond. `submit` takes a JSON object
274
+ keyed by field IDs; use option values for choices and arrays for multiple choices. Use
275
+ `qz submit TASK_ID -` to read answers from stdin. Invalid or stale submissions return the current
276
+ input and its template so you can correct the response directly.
277
+ `approve` continues a confirmation after you finish the requested action. `reject` declines the
278
+ current request; `cancel` stops the whole task.
279
+
280
+ Each response reads the current wait ID before sending. To answer a specific request you already
281
+ read, pass `--wait-id WAIT_ID` to `submit`, `approve`, or `reject`. A stale or invalid response
282
+ leaves the request pending. Review the application consent notice included in the pending input,
283
+ such as location sharing, before approving. Native Chrome permissions require a click in the qz side panel; CLI
284
+ approval reports that action is needed and preserves the wait without opening a browser page.
285
+ With `--wait` or `--stream`, the command stays connected while you grant permission in Chrome.
286
+ Location approval reads the current disclosure version and includes it in the response. Human
287
+ terminal output shows the notice before submitting the explicit approval; JSON output remains a
288
+ single final result. MCP callers should show the notice to the user before sending approval with
289
+ the returned `consentVersion`.
290
+
291
+ `submit`, `approve`, and `reject` accept `--wait` and `--stream` to follow the task until it finishes, including
292
+ further questions and permission requests. Each new request is shown once. Respond in the side
293
+ panel or another terminal; the original command continues automatically. `watch` follows an
294
+ existing task without resubmitting anything. Timeouts and Ctrl-C stop watching, while the task
295
+ continues in the browser.
296
+
297
+ ## Browser selection and MCP tools
298
+
299
+ Use `--client NAME|UUID` or `-c NAME|UUID` to select a browser. `qz browsers` lists registered names,
300
+ UUIDs, and online status. See [browser selection](#add-and-select-browsers) for pairing and name reuse.
301
+ Use `-t` for `--title`. Run `qz help COMMAND` or `qz COMMAND --help` for command-specific options.
302
+
303
+ MCP clients can inspect browser tool schemas with `qingzhou_list_tools` and `qingzhou_get_tool`,
304
+ then call `qingzhou_execute_tool` in a task. Set `wait: false` to receive a job ID and read the result
305
+ with `qingzhou_get_tool_job`. Pass `runId` to bind execution to a particular task run. MCP also
306
+ provides `qingzhou_get_trace` and `qingzhou_clear_trace` for diagnostics.
307
+
308
+ If a request times out or its connection is interrupted, an operation already started in the
309
+ browser may still be running. Check the task before repeating it. Disconnected MCP requests are
310
+ cancelled in the service, and reconnecting does not replay their browser actions.
311
+
312
+ ## Data, images, and Skills
313
+
314
+ ```bash
315
+ qz data
316
+ qz data export TABLE
317
+ qz data export TABLE --format csv
318
+ qz data delete TABLE
319
+ qz images
320
+ qz images export COLLECTION
321
+ qz images delete COLLECTION
322
+ qz skills --query research
323
+ qz skills show NAME
324
+ qz skills read NAME scripts/run.js --limit 20000
325
+ qz skills tools --session TASK_ID
326
+ qz skills export NAME
327
+ ```
328
+
329
+ Use the exact names printed by each list; quote names containing spaces. Data exports default to
330
+ Excel (`xlsx`); `--format csv` selects CSV. Image collections export as a ZIP containing available
331
+ image files and metadata. Missing local images are reported in the result. Skill exports contain
332
+ one user-installed Skill and its resources; built-in Skills require the extension and cannot be
333
+ exported independently.
334
+
335
+ `skills show` includes the resource paths. `skills read NAME PATH` reads one resource, with a
336
+ default limit of 20,000 characters. Use `--start` and `--limit` to select a chunk; truncated text
337
+ includes the command for the next chunk. `skills tools` lists contributed tools and whether they
338
+ are active in the selected task's context.
339
+ `skills --scope all|global|site|resident` filters by activation scope. Exports accept `--filename NAME`.
340
+ `automations --limit N` limits the automation list.
341
+
342
+ Exports use Chrome downloads. The result includes the download status, ID, filename, and path when
343
+ Chrome provides it. Check pending downloads in `chrome://downloads`. `delete` removes the named table
344
+ or image collection and its rows. Image blobs shared by other collections or task history remain
345
+ in the asset store.
346
+
347
+ ## Settings and automations
348
+
349
+ ```bash
350
+ qz settings
351
+ qz settings get model
352
+ qz settings set model MODEL_ID
353
+ qz settings set vision true
354
+ qz settings set '{"modelParameters":{"temperature":0.5}}'
355
+ qz settings set - < settings.json
356
+ qz automations
357
+ qz automations run AUTOMATION_ID
358
+ ```
359
+
360
+ `settings` returns current values, editable fields, provider IDs, and protocol IDs. Credentials are
361
+ redacted; `qz settings get apiKey` reports whether a key is configured. `set KEY VALUE` parses JSON
362
+ values such as booleans, numbers, objects, and arrays; other values are strings. `set JSON` applies
363
+ a patch containing the supplied top-level fields. Follow the field descriptions for values that
364
+ replace an entire object, such as `modelParameters`.
365
+
366
+ Read credential patches from stdin to keep them out of shell history. JSON is validated before
367
+ connecting. The extension validates field names and values before saving. Browser commands accept
368
+ `--client NAME|UUID` to select a profile. `automations run` starts an existing automation and
369
+ returns its task ID.
370
+
371
+ The CLI uses the same browser operations as MCP. Its commands correspond to tasks, data,
372
+ images, Skills, settings, and automations. `qz mcp` only returns the connection URL for MCP
373
+ clients.
374
+
375
+ ## Terminal output
376
+
377
+ Interactive terminals show readable text; pipes and redirected output receive JSON. Use `--json`
378
+ to request JSON explicitly or `--plain` to keep text when redirecting output. `--no-color` or the
379
+ `NO_COLOR` environment variable disables color. `qz mcp` prints only the MCP URL by default;
380
+ `qz mcp --json` returns a JSON result.
381
+
382
+ In JSON mode, `--wait` and `--stream` emit one final JSON result on stdout. Complete pending-input
383
+ notices and submission templates appear on stderr so you can respond while preserving
384
+ machine-readable output. MCP snapshots and rejected responses include `input`, with a
385
+ `responseTemplate` that binds answers to the current session and wait. Chrome-native permission
386
+ requests provide user instructions instead of an approval template.
387
+ Exit codes are `0` for success (including reading pending input), `1` for an operation or
388
+ task failure or a rejected submission, `2` for invalid arguments, and `130` for Ctrl-C.
389
+ Connection errors include the GitHub setup guide and installation link.
390
+
391
+ ## Local access
392
+
393
+ The service listens on loopback. It validates Host and Origin, rejects redirects, and accepts
394
+ extension polling only from extension origins or local clients. Ordinary websites cannot send
395
+ requests through the MCP endpoint. Local programs can control connected qz tasks while the
396
+ service is running. Run `qz stop` to disconnect.
397
+
398
+ Connection metadata and browser registrations are stored in `~/.qz-browser-agent/run/`;
399
+ `QZ_STATE_DIR` selects another local directory for isolated tests. Registration writes are atomic;
400
+ a failed write leaves the previous registration active. Private pairing proofs stay in local storage
401
+ and are omitted from status output. Atomic startup locks prevent duplicate services. Development copies
402
+ and published installations use separate identities. The client verifies the service identity,
403
+ protocol version, instance, and process before reusing or stopping it. Editing source files or
404
+ running a newer package keeps the healthy service and its connections alive. `status` reports
405
+ when a different build is available. To load the new service code, finish active work, run
406
+ `qz stop`, then `qz connect`.
407
+
408
+ ## Package development
409
+
410
+ The npm package name is `qz-browser-agent`; the executable name is `qz`. Local development uses
411
+ this same package name. The repository root stays private, and this service directory is the
412
+ publishable package. Publishing requires separate authorization and ownership of the npm name.
413
+
414
+ From the repository root, install the locked dependencies and run the local source:
415
+
416
+ ```bash
417
+ npm ci
418
+ npm run qz -- --version
419
+ npm run qz -- connect
420
+ npm run qz -- create "Summarize the current page." --stream
421
+ ```
422
+
423
+ Keep the `--` separator when forwarding options through npm. For a local `qz` executable,
424
+ run `npm link` in `services/mcp-bridge`. JavaScript runs directly on Node.js. The published
425
+ package contains the runtime files, tool catalog, README, and license.
426
+
427
+ ```bash
428
+ npm test -- services --match node
429
+ node tests/release/npm-package.mjs
430
+ ```
431
+
432
+ The package check packs the service and installs that tarball in two clean temporary directories
433
+ using the public npm registry. It checks the installed command, versions, MCP tools, service reuse,
434
+ and shutdown on an isolated port. The test owns its npm configuration, cache, connection state,
435
+ and service process. It requires network access to download dependencies.
436
+
437
+ Use `--output tests/results/npm/qz-browser-agent-0.1.1.tgz` to retain the verified tarball.
438
+ Use `--tarball PATH` to check an existing tarball. The check also runs through
439
+ `npm test -- release --match npm-package`.
440
+
441
+ ## Publish to npm
442
+
443
+ Choose the package version in `services/mcp-bridge/package.json`, complete the repository checks,
444
+ and commit the intended source before publishing. CLI and MCP report that same package version.
445
+ Each published version identifies immutable package contents; use a new version for updates.
446
+
447
+ The **npm package** GitHub Actions workflow tests the CLI and the installed package on Linux,
448
+ macOS, and Windows. On a manual run, provide the expected version. With **publish** left unchecked,
449
+ it only validates the package and retains the tested tarball. Publishing requires a manual run
450
+ from `main` with **publish** checked; all three platforms must pass first.
451
+
452
+ Configure the npm package's trusted publisher for the `alibaba/qz-browser-agent` repository,
453
+ workflow `npm-package.yml`, and GitHub environment `npm`. Enable direct publishing in that
454
+ trusted publisher configuration. The publish job uses OIDC and uploads the exact Linux-tested
455
+ tarball. The npm package must be created under an account with publishing rights before this
456
+ trusted publisher can be configured. See [npm trusted publishing](https://docs.npmjs.com/trusted-publishers/).
457
+
458
+ For the first manual release, log in with npm, verify the saved tarball, and publish it:
459
+
460
+ ```bash
461
+ npm login --registry=https://registry.npmjs.org
462
+ node tests/release/npm-package.mjs --output tests/results/npm/qz-browser-agent-0.1.1.tgz
463
+ npm publish tests/results/npm/qz-browser-agent-0.1.1.tgz --access public --registry=https://registry.npmjs.org
464
+ ```
465
+
466
+ The root package stays private. Publishing the service does not publish the Chrome extension.
467
+ After publication, check `npx qz-browser-agent@0.1.1 --version` from a directory outside the repository.