agent-browser 0.22.3 → 0.23.0

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/README.md CHANGED
@@ -129,6 +129,7 @@ agent-browser stream enable [--port <port>] # Start runtime WebSocket streaming
129
129
  agent-browser stream status # Show runtime streaming state and bound port
130
130
  agent-browser stream disable # Stop runtime WebSocket streaming
131
131
  agent-browser close # Close browser (aliases: quit, exit)
132
+ agent-browser close --all # Close all active sessions
132
133
  ```
133
134
 
134
135
  ### Get Info
@@ -596,6 +597,32 @@ This is useful for multimodal AI models that can reason about visual layout, unl
596
597
  | `--config <path>` | Use a custom config file (or `AGENT_BROWSER_CONFIG` env) |
597
598
  | `--debug` | Debug output |
598
599
 
600
+ ## Observability Dashboard
601
+
602
+ Monitor agent-browser sessions in real time with a local web dashboard showing a live viewport and command activity feed.
603
+
604
+ ```bash
605
+ # Install the dashboard (one time)
606
+ agent-browser dashboard install
607
+
608
+ # Start the dashboard server (runs in background on port 4848)
609
+ agent-browser dashboard start
610
+ agent-browser dashboard start --port 8080 # Custom port
611
+
612
+ # All sessions are automatically visible in the dashboard
613
+ agent-browser open example.com
614
+
615
+ # Stop the dashboard
616
+ agent-browser dashboard stop
617
+ ```
618
+
619
+ The dashboard runs as a standalone background process on port 4848, independent of browser sessions. It stays available even when no sessions are running. All sessions automatically stream to the dashboard.
620
+
621
+ The dashboard displays:
622
+ - **Live viewport** -- real-time JPEG frames from the browser
623
+ - **Activity feed** -- chronological command/result stream with timing and expandable details
624
+ - **Console output** -- browser console messages (log, warn, error)
625
+
599
626
  ## Configuration
600
627
 
601
628
  Create an `agent-browser.json` file to set persistent defaults instead of repeating flags on every command.
@@ -926,28 +953,28 @@ This is useful when:
926
953
 
927
954
  Stream the browser viewport via WebSocket for live preview or "pair browsing" where a human can watch and interact alongside an AI agent.
928
955
 
929
- ### Enable Streaming
956
+ ### Streaming
930
957
 
931
- For an already-running session, enable streaming at runtime:
958
+ Every session automatically starts a WebSocket stream server on an OS-assigned port. Use `stream status` to see the bound port and connection state:
932
959
 
933
960
  ```bash
934
- agent-browser stream enable
935
961
  agent-browser stream status
936
- agent-browser stream disable
937
962
  ```
938
963
 
939
- `stream enable` binds an available localhost port automatically unless you pass `--port <port>`.
940
- Use `stream status` to inspect whether streaming is enabled, which port is active, whether a browser is attached, and whether screencasting is active.
941
-
942
- If you want streaming to be available immediately when the daemon starts, set `AGENT_BROWSER_STREAM_PORT` before the first command in that session:
964
+ To bind to a specific port, set `AGENT_BROWSER_STREAM_PORT`:
943
965
 
944
966
  ```bash
945
967
  AGENT_BROWSER_STREAM_PORT=9223 agent-browser open example.com
946
968
  ```
947
969
 
948
- The environment variable only affects daemon startup. For sessions that are already running, use `agent-browser stream enable` instead.
970
+ You can also manage streaming at runtime with `stream enable`, `stream disable`, and `stream status`:
971
+
972
+ ```bash
973
+ agent-browser stream enable --port 9223 # Re-enable on a specific port
974
+ agent-browser stream disable # Stop streaming for the session
975
+ ```
949
976
 
950
- Once enabled, the WebSocket server streams the browser viewport and accepts input events.
977
+ The WebSocket server streams the browser viewport and accepts input events.
951
978
 
952
979
  ### WebSocket Protocol
953
980
 
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
Binary file
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "agent-browser",
3
- "version": "0.22.3",
3
+ "version": "0.23.0",
4
4
  "description": "Headless browser automation CLI for AI agents",
5
5
  "type": "module",
6
6
  "files": [
@@ -45,6 +45,7 @@
45
45
  "postinstall": "node scripts/postinstall.js",
46
46
  "changeset": "changeset",
47
47
  "ci:version": "changeset version && pnpm run version:sync && pnpm install --no-frozen-lockfile",
48
- "ci:publish": "pnpm run version:sync && changeset publish"
48
+ "ci:publish": "pnpm run version:sync && changeset publish",
49
+ "build:dashboard": "cd packages/dashboard && pnpm build"
49
50
  }
50
51
  }
@@ -110,6 +110,7 @@ See [references/authentication.md](references/authentication.md) for OAuth, 2FA,
110
110
  # Navigation
111
111
  agent-browser open <url> # Navigate (aliases: goto, navigate)
112
112
  agent-browser close # Close browser
113
+ agent-browser close --all # Close all active sessions
113
114
 
114
115
  # Snapshot
115
116
  agent-browser snapshot -i # Interactive elements with refs (recommended)
@@ -198,11 +199,9 @@ agent-browser diff url <url1> <url2> --wait-until networkidle # Custom wait str
198
199
  agent-browser diff url <url1> <url2> --selector "#main" # Scope to element
199
200
  ```
200
201
 
201
- ## Runtime Streaming
202
+ ## Streaming
202
203
 
203
- Use `agent-browser stream enable` when you need a live WebSocket preview for an already-running session. This is the preferred runtime path because it does not require restarting the daemon. `stream enable` creates the server, `stream status` reports the bound port and connection state, and `stream disable` tears it down cleanly.
204
-
205
- If streaming must be present from the first daemon command, `AGENT_BROWSER_STREAM_PORT` still works at daemon startup, but that environment variable is not retroactive for sessions that are already running.
204
+ Every session automatically starts a WebSocket stream server on an OS-assigned port. Use `agent-browser stream status` to see the bound port and connection state. Use `stream disable` to tear it down, and `stream enable --port <port>` to re-enable on a specific port.
206
205
 
207
206
  ## Batch Execution
208
207
 
@@ -578,9 +577,10 @@ Always close your browser session when done to avoid leaked processes:
578
577
  ```bash
579
578
  agent-browser close # Close default session
580
579
  agent-browser --session agent1 close # Close specific session
580
+ agent-browser close --all # Close all active sessions
581
581
  ```
582
582
 
583
- If a previous session was not closed properly, the daemon may still be running. Use `agent-browser close` to clean it up before starting new work.
583
+ If a previous session was not closed properly, the daemon may still be running. Use `agent-browser close` to clean it up, or `agent-browser close --all` to shut down every session at once.
584
584
 
585
585
  To auto-shutdown the daemon after a period of inactivity (useful for ephemeral/CI environments):
586
586
 
@@ -712,6 +712,26 @@ Supported engines:
712
712
 
713
713
  Lightpanda does not support `--extension`, `--profile`, `--state`, or `--allow-file-access`. Install Lightpanda from https://lightpanda.io/docs/open-source/installation.
714
714
 
715
+ ## Observability Dashboard
716
+
717
+ The dashboard is a standalone background server that shows live browser viewports, command activity, and console output for all sessions.
718
+
719
+ ```bash
720
+ # Install the dashboard once
721
+ agent-browser dashboard install
722
+
723
+ # Start the dashboard server (background, port 4848)
724
+ agent-browser dashboard start
725
+
726
+ # All sessions are automatically visible in the dashboard
727
+ agent-browser open example.com
728
+
729
+ # Stop the dashboard
730
+ agent-browser dashboard stop
731
+ ```
732
+
733
+ The dashboard runs independently of browser sessions on port 4848 (configurable with `--port`). All sessions automatically stream to the dashboard.
734
+
715
735
  ## Ready-to-Use Templates
716
736
 
717
737
  | Template | Description |
@@ -287,6 +287,6 @@ AGENT_BROWSER_SESSION="mysession" # Default session name
287
287
  AGENT_BROWSER_EXECUTABLE_PATH="/path/chrome" # Custom browser path
288
288
  AGENT_BROWSER_EXTENSIONS="/ext1,/ext2" # Comma-separated extension paths
289
289
  AGENT_BROWSER_PROVIDER="browserbase" # Cloud browser provider
290
- AGENT_BROWSER_STREAM_PORT="9223" # WebSocket streaming port
290
+ AGENT_BROWSER_STREAM_PORT="9223" # Override WebSocket streaming port (default: OS-assigned)
291
291
  AGENT_BROWSER_HOME="/path/to/agent-browser" # Custom install location
292
292
  ```