Import AITURK IDE 1.0.0-beta.1 from Hermes 63279301; preserve MIT license

This commit is contained in:
2026-09-05 13:26:46 +03:00
commit 03634b1ca3
11340 changed files with 3442369 additions and 0 deletions
@@ -0,0 +1,72 @@
#!/usr/bin/env python3
"""Record a HAR file while driving a website with Playwright.
Usage:
python3 har_capture.py <url> <output.har> [--wait SECONDS] \
[--action "fill:SELECTOR:TEXT"] [--action "press:SELECTOR:KEY"] \
[--action "click:SELECTOR"] [--action "goto:URL"] [--action "sleep:SECONDS"]
Actions run in order after page load. The HAR embeds request/response bodies
(record_har_content='embed') so derived clients can see payload shapes.
NOTE: a failing action raises before the HAR is flushed -- you get no file.
Fix the selector (try --headed to watch) and rerun.
"""
import argparse
import sys
import time
from playwright.sync_api import sync_playwright
def run_action(page, spec: str) -> None:
parts = spec.split(":", 2)
kind = parts[0]
if kind == "fill":
page.fill(parts[1], parts[2])
elif kind == "press":
page.press(parts[1], parts[2])
elif kind == "click":
page.click(parts[1])
elif kind == "goto":
page.goto(parts[1] + (":" + parts[2] if len(parts) > 2 else ""))
elif kind == "sleep":
time.sleep(float(parts[1]))
else:
raise ValueError(f"unknown action: {spec}")
def main() -> int:
ap = argparse.ArgumentParser()
ap.add_argument("url")
ap.add_argument("har_path")
ap.add_argument("--wait", type=float, default=3.0,
help="seconds to idle at the end so late XHRs land in the HAR")
ap.add_argument("--action", action="append", default=[],
help="fill:SEL:TEXT | press:SEL:KEY | click:SEL | goto:URL | sleep:SECS")
ap.add_argument("--headed", action="store_true")
args = ap.parse_args()
with sync_playwright() as p:
browser = p.chromium.launch(headless=not args.headed)
context = browser.new_context(
record_har_path=args.har_path,
record_har_content="embed", # keep response bodies in the HAR
)
page = context.new_page()
page.goto(args.url, wait_until="domcontentloaded")
for spec in args.action:
run_action(page, spec)
try:
page.wait_for_load_state("networkidle", timeout=15000)
except Exception:
pass # some pages never fully idle; the trailing --wait covers it
time.sleep(args.wait)
context.close() # flushes the HAR
browser.close()
print(f"HAR written: {args.har_path}")
return 0
if __name__ == "__main__":
sys.exit(main())
@@ -0,0 +1,135 @@
#!/usr/bin/env python3
"""Capture a HAR from a browser you connect to over CDP (not one you launch).
Use this when the browser is owned by someone else and only reachable over the
Chrome DevTools Protocol: Hermes cloud backends (Browserbase, Browser-Use,
Firecrawl), a Camofox session exposing CDP, or anything wired via
`/browser connect <url>` / BROWSER_CDP_URL / browser.cdp_url in config.
Why this exists: Playwright's record_har_path only works on a context you
launched locally. connect_over_cdp() attaches to an existing browser, so
record_har is unavailable — we assemble the HAR from CDP Network.* events
ourselves via page.on("request"/"response").
Usage:
python3 har_capture_cdp.py <cdp_url> <output.har> [--wait S] \
[--goto URL] [--action "fill:SEL:TEXT"] [--action "click:SEL"] ...
<cdp_url> is the ws:// or http:// CDP endpoint. For Hermes: run
`/browser connect` to see the active endpoint, or read BROWSER_CDP_URL.
"""
import argparse
import base64
import json
import sys
import time
from playwright.sync_api import sync_playwright
def run_action(page, spec: str) -> None:
parts = spec.split(":", 2)
kind = parts[0]
if kind == "fill":
page.fill(parts[1], parts[2])
elif kind == "press":
page.press(parts[1], parts[2])
elif kind == "click":
page.click(parts[1])
elif kind == "goto":
page.goto(parts[1] + (":" + parts[2] if len(parts) > 2 else ""))
elif kind == "sleep":
time.sleep(float(parts[1]))
else:
raise ValueError(f"unknown action: {spec}")
def _har_entry(req, resp):
"""Build a minimal HAR entry from a Playwright request/response pair."""
body_text, encoding = "", ""
if resp is not None:
try:
raw = resp.body()
try:
body_text = raw.decode("utf-8")
except UnicodeDecodeError:
body_text = base64.b64encode(raw).decode("ascii")
encoding = "base64"
except Exception:
pass
post = req.post_data
return {
"_resourceType": req.resource_type,
"request": {
"method": req.method,
"url": req.url,
"headers": [{"name": k, "value": v} for k, v in req.headers.items()],
"queryString": [], # har_to_client.py re-parses the URL, so leave empty
"postData": {"mimeType": req.headers.get("content-type", ""),
"text": post} if post else {},
},
"response": {
"status": resp.status if resp else 0,
"headers": [{"name": k, "value": v} for k, v in (resp.headers.items() if resp else [])],
"content": {
"mimeType": (resp.headers.get("content-type", "") if resp else ""),
"text": body_text,
**({"encoding": encoding} if encoding else {}),
},
},
}
def main() -> int:
ap = argparse.ArgumentParser()
ap.add_argument("cdp_url")
ap.add_argument("har_path")
ap.add_argument("--goto", default=None, help="URL to navigate to after attaching")
ap.add_argument("--wait", type=float, default=3.0)
ap.add_argument("--action", action="append", default=[])
args = ap.parse_args()
entries = []
pending = {} # id(request) -> request
with sync_playwright() as p:
browser = p.chromium.connect_over_cdp(args.cdp_url)
context = browser.contexts[0] if browser.contexts else browser.new_context()
page = context.pages[0] if context.pages else context.new_page()
def on_request(req):
pending[id(req)] = req
def on_response(resp):
req = resp.request
pending.pop(id(req), None)
entries.append(_har_entry(req, resp))
page.on("request", on_request)
page.on("response", on_response)
if args.goto:
page.goto(args.goto, wait_until="domcontentloaded")
for spec in args.action:
run_action(page, spec)
try:
page.wait_for_load_state("networkidle", timeout=15000)
except Exception:
pass
time.sleep(args.wait)
page.remove_listener("request", on_request)
page.remove_listener("response", on_response)
# Do NOT close: we connected to someone else's browser.
har = {"log": {"version": "1.2",
"creator": {"name": "har_capture_cdp", "version": "0.1"},
"entries": entries}}
with open(args.har_path, "w", encoding="utf-8") as f:
json.dump(har, f)
print(f"HAR written: {args.har_path} ({len(entries)} entries)")
return 0
if __name__ == "__main__":
sys.exit(main())
@@ -0,0 +1,147 @@
#!/usr/bin/env python3
"""Distill a HAR file into an API summary an agent can turn into a client.
Usage:
python3 har_to_client.py <input.har> [--include-static] [--host SUBSTRING] [--max-body 600]
Filters to XHR/fetch/JSON traffic by default, groups by (method, host, path
template), and prints per-endpoint: query params, interesting request headers,
request body sample, response content-type/status, and a response body sample.
Numeric/UUID-ish path segments are collapsed to {id} so repeated calls group.
Also prints "### Replay hints": the browser User-Agent plus whether cookies or
auth/token headers were present -- send those in the derived client or you may
get a 403/401.
"""
import argparse
import json
import re
import sys
from collections import OrderedDict
from urllib.parse import urlsplit
BORING_HEADERS = {
"accept-encoding", "accept-language", "connection", "content-length",
"host", "origin", "referer", "sec-ch-ua", "sec-ch-ua-mobile",
"sec-ch-ua-platform", "sec-fetch-dest", "sec-fetch-mode", "sec-fetch-site",
"user-agent", "pragma", "cache-control", "priority", "te",
"upgrade-insecure-requests", "cookie",
}
ID_SEG = re.compile(r"^(\d+|[0-9a-f]{8}-[0-9a-f-]{27,}|[0-9a-f]{16,})$", re.I)
STATIC_EXT = re.compile(r"\.(js|css|png|jpe?g|gif|svg|webp|ico|woff2?|ttf|mp4|map)$", re.I)
def path_template(path: str) -> str:
segs = path.split("/")
return "/".join("{id}" if ID_SEG.match(s) else s for s in segs)
def is_api_entry(entry: dict) -> bool:
req = entry["request"]
resp = entry.get("response", {})
rtype = (entry.get("_resourceType") or "").lower()
mime = (resp.get("content", {}).get("mimeType") or "").lower()
if rtype in ("xhr", "fetch"):
return True
if "json" in mime:
return True
if req["method"] not in ("GET", "HEAD") and not STATIC_EXT.search(urlsplit(req["url"]).path):
return True
return False
def trunc(text, n: int) -> str:
text = text if isinstance(text, str) else str(text)
return text if len(text) <= n else text[:n] + f"... [{len(text)} chars total]"
def main() -> int:
ap = argparse.ArgumentParser()
ap.add_argument("har")
ap.add_argument("--include-static", action="store_true")
ap.add_argument("--host", default=None, help="only endpoints whose host contains this")
ap.add_argument("--max-body", type=int, default=600)
args = ap.parse_args()
with open(args.har, encoding="utf-8") as f:
har = json.load(f)
groups = OrderedDict()
for entry in har["log"]["entries"]:
req = entry["request"]
url = urlsplit(req["url"])
if url.scheme not in ("http", "https"):
continue
if args.host and args.host not in url.netloc:
continue
if not args.include_static:
if STATIC_EXT.search(url.path) or not is_api_entry(entry):
continue
key = (req["method"], url.netloc, path_template(url.path))
g = groups.setdefault(key, {"count": 0, "queries": set(), "headers": {},
"req_body": None, "resp": None})
g["count"] += 1
for q in req.get("queryString", []):
g["queries"].add((q["name"], trunc(q["value"], 80)))
for h in req.get("headers", []):
name = h["name"].lower().lstrip(":")
if name in BORING_HEADERS or name in ("method", "path", "scheme", "authority"):
continue
g["headers"][name] = trunc(h["value"], 120)
post = req.get("postData", {})
if post.get("text") and g["req_body"] is None:
g["req_body"] = (post.get("mimeType", ""), trunc(post["text"], args.max_body))
resp = entry.get("response", {})
if g["resp"] is None and resp:
content = resp.get("content", {})
g["resp"] = (resp.get("status"), content.get("mimeType", ""),
trunc(content.get("text") or "", args.max_body))
if not groups:
print("No API-looking entries found. Re-run with --include-static to see everything.")
return 1
# Surface the browser identity so the replay client can match it (many
# sites 403 a default library User-Agent).
ua = None
saw_cookie = saw_auth = False
for entry in har["log"]["entries"]:
for h in entry["request"].get("headers", []):
n = h["name"].lower()
if n == "user-agent" and ua is None:
ua = h["value"]
if n == "cookie":
saw_cookie = True
if n in ("authorization", "x-api-key") or "token" in n:
saw_auth = True
print("### Replay hints")
if ua:
print(f" User-Agent (send this): {ua}")
if saw_cookie:
print(" Cookies present -> session may be auth-gated; capture & resend the Cookie header.")
if saw_auth:
print(" Authorization/token header present -> extract and resend it.")
for (method, host, path), g in groups.items():
print(f"\n=== {method} https://{host}{path} (x{g['count']})")
if g["queries"]:
print(" query params:")
for name, val in sorted(g["queries"]):
print(f" {name} = {val}")
if g["headers"]:
print(" request headers (non-boring):")
for name, val in sorted(g["headers"].items()):
print(f" {name}: {val}")
if g["req_body"]:
print(f" request body ({g['req_body'][0]}):")
print(f" {g['req_body'][1]}")
if g["resp"]:
status, mime, body = g["resp"]
print(f" response: {status} {mime}")
if body:
print(f" {body}")
print(f"\n{len(groups)} distinct endpoints.")
return 0
if __name__ == "__main__":
sys.exit(main())