pw-repl 0.6.0 → 0.6.1

package/AGENTS.md

@@ -49,8 +49,6 @@ If you hit a limitation or write a workaround, consider adding the capability to
 - Don't race the clock in a test: a page that changes on a timer, or a command timed against a budget,
   fails on a busy machine. Have the page change when the test asks (eval), or measure the thing itself
   (frames drawn, not clicks timed). A click waits for its element to hold still for two frames.
-- A test that times out in a run much slower than usual (the machine is busy) may be load, not a bug:
-  run it again, alone. If it fails alone too, find out why before going on.
 - For anything the tests can't reach, exercise the change in a running REPL of your own: on a socket of
   your own, with `--launch` unless the change needs the user's browser, and then in a tab of your own.
 - `skill/SKILL.md` is how agents learn to use the REPL: keep it in step with a change to how it is

package/README.md

@@ -159,7 +159,8 @@ pw-repl where           # which REPL send would reach
 ```
 
 `pw-repl send` sends one command and prints its result, through the server when it is running and through the
-`playwright-repl` tmux session otherwise.
+`playwright-repl` tmux session otherwise. Chain several in the shell: `&&` stops at the first that fails or
+is not confirmed (exit 1 or 2), `;` runs on.
 
 Several agents can share one REPL: `pw-repl send -c <name>` (or `PW_CLIENT=<name>`) sends as a client with a
 selected tab of its own, shown in the pane as `[server:<name>]`. `modes` says which client turned each mode on,

package/lib/help.js

@@ -93,7 +93,9 @@ Server: pw-repl serve also takes commands on /tmp/playwright-repl.sock; they sho
 Clients: pw-repl send -c <name> (or $PW_CLIENT) sends as a client of its own. It has a selected tab of
 its own, so clients do not move each other's; its commands show as [server:<name>] lines. modes and tab
 say which client turned each mode on and opened each tab, and modes off --mine turns off only the
-sender's own. Senders without a name share the prompt's selected tab.
+sender's own. Senders without a name share the prompt's selected tab. Other clients' commands can run
+between a client's own: its selected tab, and the previous command that wait request and wait load count
+from, are its own; a tab's requests, console and watch are shared.
 
 The prompt is pw[serve]> while the server is on and pw> without it. Before it are the modes on in the
 selected tab, if any: (watch network:off routes:2 capture) pw>. modes lists them for every tab.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pw-repl",
-  "version": "0.6.0",
+  "version": "0.6.1",
   "description": "Text REPL for driving an existing Chromium through Playwright over CDP",
   "keywords": [
     "playwright",

package/skill/SKILL.md

@@ -114,6 +114,22 @@ spaces and all: `pw-repl send click "text=Your name"`. It works however the REPL
 `pw-repl where` says which one a command would reach (the server, or the tmux pane running the
 REPL), or why neither is reachable, without running anything.
 
+`send` takes one command; chain several in your shell. Use `&&` when a step only makes sense if the one
+before it worked: it stops at any exit status but 0, a failure and an outcome not confirmed included.
+Use `;` when the steps do not depend on each other. `-t` is each command's own limit. Write each
+`pw-repl send` out in full, not in a shell variable, which hides it from permission rules that allow
+`pw-repl` commands:
+
+```bash
+pw-repl send -c cart-bug click e5 && pw-repl send -c cart-bug wait load &&
+  pw-repl send -c cart-bug screenshot
+pw-repl send -c cart-bug count .item; pw-repl send -c cart-bug text h1
+```
+
+Other clients' commands can run between yours. Your selected tab is your own, and so is the previous
+command that `wait request` and `wait load` count from; a tab's requests, console and watch are shared
+with whoever else uses that tab.
+
 Every command you run and its output show in the REPL's pane, or in `attach` and the log for a
 background REPL (server commands as `[server]` lines), so whoever looks there sees what you do. The pane
 shows REPL commands only, not what was clicked in the browser (unless `watch on --live` is on); for