Step vocabulary gains `waitFor`: block until a selector exists, then continue. Nothing is clicked or typed — it is a gate for conditions something outside the run has to satisfy. Unlike every other step it carries no signed-out guard, because the things worth gating on often sit on the login page, where that guard would abort the run at exactly the wrong moment. Honours the dashboard's Stop button, since a two-minute gate that ignored it would be worse than no gate. Session handling. A run that lands on the login page must not continue: once redirected, every selector resolves against a login form, so a click aimed at "Add Account" hits whatever that form renders in the same place. Runs now detect the redirect and stop before sending any input, with a distinct SignedOutError rather than a generic failure. Two ways out of that state, in order: a firm's `authSteps` run and the failed step is retried, or — when none are defined — the run pauses for signedOutWaitSeconds so a human can sign in, then resumes. Auth steps are verified rather than trusted: they can all "succeed" while the site still rejects the sign-in, so the session is re-checked before the retry, and the run stops with "auth steps ran but the session is still signed out" if it did not take. That check polls for up to 20s instead of reading once. Submitting a login form starts a network round trip and then a redirect, so the tab still shows the login URL for a second or two afterwards; checking immediately failed a sign-in that was merely in flight, killing run #15 nine seconds after it had actually worked. Third instance of the same mistake in this system — reading page state immediately after an action that triggers async navigation. The runner reports its version in the heartbeat and the dashboard blocks the buttons when it is behind. A running Python process does not reload when the source changes, so a stale runner fails on step types it predates; that cost a debugging round when a navigate step reached a runner that had never heard of one. lib/automations.ts carries the Tradeify buy-accounts flow: navigate to the dashboard, open Add Account, pick the account type and size, enter the account name, and work through the challenge widget before submitting. Selectors are authored by hand against the live page. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
209 lines
6.6 KiB
Python
209 lines
6.6 KiB
Python
"""Execution of a single automation step: locate the element, then click or type.
|
|
|
|
Shared by the CLI (clicker.py) and the automation runner (runner.py) so there is
|
|
one implementation of the safety checks. Callers differ only in how they report
|
|
progress and how they surface failures.
|
|
"""
|
|
|
|
import random
|
|
|
|
import focus
|
|
|
|
|
|
class StepError(Exception):
|
|
"""A step refused to run, or ran and could not be verified.
|
|
|
|
`code` mirrors the CLI's exit codes: 3 = refused before acting,
|
|
4 = acted but verification failed, 5 = the session is signed out.
|
|
"""
|
|
|
|
def __init__(self, message: str, code: int = 3):
|
|
super().__init__(message)
|
|
self.code = code
|
|
|
|
|
|
class SignedOutError(StepError):
|
|
"""The tab is on the login page, so the session has expired.
|
|
|
|
Distinct from an ordinary failure because nothing is wrong with the
|
|
automation — it just cannot proceed until a human signs in.
|
|
"""
|
|
|
|
def __init__(self, url: str):
|
|
super().__init__(
|
|
f"signed out — the tab is on {url}. Log in to the site, then run this again.",
|
|
code=5,
|
|
)
|
|
|
|
|
|
def check_signed_in(found: dict, signed_out: str) -> None:
|
|
"""Abort if the page redirected to a login screen.
|
|
|
|
Worth doing before every action, not just at the start: a session can expire
|
|
mid-run, and once it does, every selector resolves against a login form. A
|
|
click or a keystroke aimed at the old page would land on whatever that form
|
|
happens to render in the same place.
|
|
"""
|
|
if not signed_out:
|
|
return
|
|
url = found.get("url") or ""
|
|
if signed_out in url:
|
|
raise SignedOutError(url)
|
|
|
|
|
|
# Display scaling factors that actually exist. Anything else means the two sides
|
|
# are describing different things (usually a multi-monitor desktop) rather than a
|
|
# scaled single display.
|
|
KNOWN_SCALES = (1.0, 1.25, 1.5, 1.75, 2.0, 2.5, 3.0)
|
|
|
|
|
|
def scale_factor(found: dict, override: float | None, report=None) -> float:
|
|
"""CSS pixels and desktop pixels match on macOS and unscaled Windows, but
|
|
Windows display scaling breaks that.
|
|
|
|
Deliberately conservative: a raw ratio is only trusted when it lands on a real
|
|
scaling factor. On a multi-monitor desktop the browser reports the display it
|
|
is on while pyautogui reports the primary one, and the resulting ratio is
|
|
meaningless — halving every coordinate would put clicks far from the target.
|
|
Fall back to 1:1 and say so, rather than silently scaling.
|
|
"""
|
|
if override is not None:
|
|
return override
|
|
|
|
try:
|
|
import pyautogui
|
|
except ImportError:
|
|
return 1.0
|
|
|
|
css_width = (found.get("screenSize") or {}).get("width")
|
|
if not css_width:
|
|
return 1.0
|
|
|
|
os_width = pyautogui.size().width
|
|
ratio = os_width / css_width
|
|
|
|
for known in KNOWN_SCALES:
|
|
if abs(ratio - known) < 0.02:
|
|
return known
|
|
|
|
if report:
|
|
report(
|
|
f"screen size disagrees (browser {css_width}px, OS {os_width}px, "
|
|
f"ratio {ratio:.3f}) — assuming 1:1. If clicks land off, pass --scale."
|
|
)
|
|
return 1.0
|
|
|
|
|
|
def perform(
|
|
dash,
|
|
action: str,
|
|
selector: str,
|
|
*,
|
|
index: int = 0,
|
|
url: str = "",
|
|
open_url: str = "",
|
|
signed_out: str = "",
|
|
text: str | None = None,
|
|
clear: bool = False,
|
|
scale: float | None = None,
|
|
timeout: float = 20.0,
|
|
rng: random.Random | None = None,
|
|
activate: bool = True,
|
|
verify: bool = True,
|
|
force: bool = False,
|
|
dry_run: bool = False,
|
|
robotic: bool = False,
|
|
report=None,
|
|
on_located=None,
|
|
) -> dict:
|
|
"""Run one step. Returns the located element's data.
|
|
|
|
Raises DashboardError if the extension can't find it, StepError if the step
|
|
is refused or fails verification.
|
|
"""
|
|
import pyautogui
|
|
import humanize
|
|
|
|
rng = rng or random.Random()
|
|
say = report or (lambda _m: None)
|
|
|
|
found = dash.locate(selector, index, url, timeout, open_url)
|
|
if on_located:
|
|
on_located(found)
|
|
|
|
# Before any check that assumes we are on the real page.
|
|
check_signed_in(found, signed_out)
|
|
|
|
if found.get("covered") and not force:
|
|
raise StepError(
|
|
f"{selector} is covered by {found.get('coveredBy')} — the click would hit that instead"
|
|
)
|
|
|
|
if action == "type" and not found.get("editable", True) and not force:
|
|
kind = found.get("inputType")
|
|
raise StepError(
|
|
f"<{found['tag']}{f' type={kind}' if kind else ''}> is not an editable field "
|
|
"(disabled, read-only, or not an input)"
|
|
)
|
|
|
|
factor = scale_factor(found, scale, report)
|
|
x = found["screen"]["x"] * factor
|
|
y = found["screen"]["y"] * factor
|
|
|
|
screen_w, screen_h = pyautogui.size()
|
|
if not (0 <= x < screen_w and 0 <= y < screen_h):
|
|
raise StepError(
|
|
f"target ({x:.0f}, {y:.0f}) is off-screen ({screen_w}x{screen_h}) — "
|
|
"is the Chrome window on another display?"
|
|
)
|
|
|
|
say(f"at {x:.0f},{y:.0f}")
|
|
|
|
# A click on a background window is consumed activating it and never reaches
|
|
# the page, so raise the browser immediately before pressing.
|
|
if activate:
|
|
focused = focus.ensure_frontmost()
|
|
say(focused.detail)
|
|
if not focused.ok:
|
|
raise StepError(
|
|
"the browser is not frontmost — the click would be consumed "
|
|
"activating its window instead of pressing the element"
|
|
)
|
|
|
|
pyautogui.FAILSAFE = True
|
|
|
|
if robotic:
|
|
pyautogui.moveTo(x, y, duration=0.25)
|
|
if not dry_run:
|
|
pyautogui.click()
|
|
else:
|
|
humanize.click(x, y, rng=rng, press=not dry_run)
|
|
|
|
if action == "click" or dry_run:
|
|
return found
|
|
|
|
# ── type ────────────────────────────────────────────────────────────────
|
|
import time
|
|
time.sleep(0.15) # let the field take focus and any JS handlers settle
|
|
|
|
if clear:
|
|
humanize.clear_field(rng)
|
|
humanize.type_text(text or "", rng)
|
|
|
|
if not verify:
|
|
return found
|
|
|
|
# Typing into a field that never took focus, or that ignores the input, fails
|
|
# silently and is otherwise indistinguishable from success.
|
|
after = dash.locate(selector, index, url, timeout, open_url)
|
|
check_signed_in(after, signed_out)
|
|
got = after.get("value")
|
|
if got is None:
|
|
say("element exposes no value to verify against")
|
|
return found
|
|
if (text or "") in got:
|
|
say(f"verified, field contains {got!r}")
|
|
return after
|
|
|
|
raise StepError(f"verification failed — field contains {got!r}", code=4)
|