Files
BrowserOS/packages/browseros-agent/apps/eval/scripts/build-infinity-dataset.py
shivammittal274 01d649da9a feat(eval): bring deterministic graders to dev + drop omnizon (#824)
* feat: deterministic eval graders (AGI SDK + WebArena-Infinity) (#664)

* feat: add deterministic eval graders (AGI SDK + WebArena-Infinity)

Two new benchmark integrations with programmatic grading — no LLM judge.

AGI SDK / REAL Bench (52 tasks):
- 11 React/Next.js clones of consumer apps (DoorDash, Amazon, Gmail, etc.)
- Grader navigates browser to /finish, extracts state diff from <pre> tag
- Python verifier checks exact values via jmespath queries

WebArena-Infinity (50 hard tasks):
- 13 LLM-generated SaaS clones (Gmail, GitLab, Linear, Figma, etc.)
- InfinityAppManager starts fresh app server per task per worker
- Python verifier calls /api/state and asserts on JSON state

Infrastructure:
- GraderInput extended with mcpUrl + infinityAppUrl for parallel workers
- Each worker gets isolated ports (no cross-worker state contamination)
- CI workflow: pip install agisdk, clone webarena-infinity repo

* chore: switch eval configs back to kimi-k2p5

* fix: register deterministic graders in pass rate calculation

Add agisdk_state_diff and infinity_state to PASS_FAIL_GRADER_ORDER
in both runner types and weekly report script, so scores show correctly
in the dashboard.

* chore: temp switch to opus 4.6 for eval run

* chore: restore kimi-k2p5 as default eval config

* ci: add timeout and continue-on-error for trend report step

* fix(eval): drop omnizon from AGISDK dataset (DMCA takedown)

evals-omnizon.vercel.app returns HTTP 451 ("This content has been
blocked for legal reasons / DMCA_TAKEDOWN"). All 5 omnizon-* tasks
fail grading with "Failed to fetch /finish endpoint: JSON Parse error".

Adds an EXCLUDED_WEBSITES set to the dataset builder and regenerates
agisdk-real.jsonl (52 → 47 tasks).

* fix(eval): correct Infinity port-assignment bugs

Two related bugs in the Infinity eval runner that cause silent port
collisions / fallbacks under parallel execution:

1. build-infinity-dataset.py emitted "app_port" but task-executor and
   the committed JSONL both read "app_base_port". Re-running the build
   script would silently make every task fall back to the 8000 default,
   ignoring per-app port assignments. Renamed the key to match.

2. task-executor derived workerIndex as `base_server_port - 9110`, but
   parallel-executor doesn't override base_server_port per worker —
   only server_url. Every worker computed workerIndex = 0, causing all
   parallel workers to spawn Infinity app servers on the same port.
   Threading workerIndex explicitly through TaskExecutor instead.

Also drops an unused app_name parameter from load_tasks().
2026-04-27 21:35:43 +05:30

119 lines
3.3 KiB
Python
Vendored

#!/usr/bin/env python3
"""
Dataset generator for WebArena-Infinity benchmark.
Reads real-tasks.json from each app directory and outputs JSONL
in the eval framework's TaskSchema format.
Usage:
python build-infinity-dataset.py --apps-dir /path/to/webarena-infinity/apps
python build-infinity-dataset.py --apps-dir /path/to/apps --apps gmail linear --difficulty medium
"""
import argparse
import json
import os
import sys
def load_tasks(app_dir: str) -> list[dict]:
tasks_file = os.path.join(app_dir, "real-tasks.json")
if not os.path.exists(tasks_file):
print(f"Warning: No real-tasks.json found in {app_dir}", file=sys.stderr)
return []
with open(tasks_file) as f:
return json.load(f)
def build_task_entry(
app_name: str,
task: dict,
base_port: int,
) -> dict:
task_id = task.get("id", task.get("task_id", "unknown"))
difficulty = task.get("difficulty", "unknown")
query = task.get("query", task.get("instruction", task.get("task", "")))
verifier_path = task.get(
"verify",
task.get("verifier_path", f"real-tasks/{task_id}.py"),
)
return {
"query_id": f"infinity-{app_name}-{task_id}",
"dataset": "webarena-infinity",
"query": query,
"graders": ["infinity_state"],
"start_url": f"http://localhost:{base_port}",
"setup_script": f"POST http://localhost:{base_port}/api/reset",
"metadata": {
"original_task_id": f"{app_name}-{task_id}",
"website": app_name,
"category": "webarena-infinity",
"additional": {
"app_name": app_name,
"difficulty": difficulty,
"verifier_path": verifier_path,
"app_base_port": base_port,
},
},
}
def main():
parser = argparse.ArgumentParser(
description="Generate JSONL dataset from WebArena-Infinity apps"
)
parser.add_argument(
"--apps-dir",
required=True,
help="Path to webarena-infinity/apps/ directory",
)
parser.add_argument(
"--apps",
nargs="*",
default=None,
help="Filter to specific app names (default: all)",
)
parser.add_argument(
"--difficulty",
choices=["easy", "medium", "hard"],
default=None,
help="Filter by difficulty tier",
)
parser.add_argument(
"--base-port",
type=int,
default=8000,
help="Starting port number for apps (default: 8000)",
)
args = parser.parse_args()
if not os.path.isdir(args.apps_dir):
print(f"Error: {args.apps_dir} is not a directory", file=sys.stderr)
sys.exit(1)
app_dirs = sorted(os.listdir(args.apps_dir))
if args.apps:
app_dirs = [d for d in app_dirs if d in args.apps]
port = args.base_port
for app_name in app_dirs:
app_path = os.path.join(args.apps_dir, app_name)
if not os.path.isdir(app_path):
continue
tasks = load_tasks(app_path)
for task in tasks:
difficulty = task.get("difficulty", "unknown")
if args.difficulty and difficulty != args.difficulty:
continue
entry = build_task_entry(app_name, task, port)
print(json.dumps(entry))
port += 1
if __name__ == "__main__":
main()