lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Robust Evaluation, Blocking File Open, Grader Sensitivity, and LibreOffice Writer Fixes (#217)

Browse Source 
* Refactor evaluator structure in LibreOffice Writer example JSON to support multiple expected and result files, enhancing evaluation flexibility.

* Update instance type to t3.large and add VNC access URL logging for allocated VMs, enhancing remote access capabilities.

* Update instance type to t3.large and add VNC access URL logging for allocated VMs, enhancing remote access capabilities.

* Update time format in get_vm_file function to include hours, minutes, and seconds for more precise file naming with time suffix.

* More delay for 936321ce-5236-426a-9a20-e0e3c5dc536f; support one more potential solutions.

* Enhance SetupController with configurable retry limit and improved error handling for file opening requests. Introduce new function to compare unique training records, and update logging for better debugging. Adjust JSON examples for evaluation to support multiple expected and result files.

* Clean debug code

---------

Co-authored-by: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>
This commit is contained in:
Tianbao Xie
2025-06-16 21:37:19 +08:00
committed by GitHub
parent 347238e17e
commit 4e11eafd1d
13 changed files with 523 additions and 135 deletions
Download Patch File Download Diff File Expand all files Collapse all files

66
desktop_env/providers/aws/provider.py
View File

@@ -63,10 +63,24 @@ class AWSProvider(Provider):
for reservation in response['Reservations']:
for instance in reservation['Instances']:
private_ip_address = instance.get('PrivateIpAddress', '')
public_ip_address = instance.get('PublicIpAddress', '')
if public_ip_address:
vnc_url = f"http://{public_ip_address}:5910/vnc.html"
logger.info("="*80)
logger.info(f"🖥️ VNC Web Access URL: {vnc_url}")
logger.info(f"📡 Public IP: {public_ip_address}")
logger.info(f"🏠 Private IP: {private_ip_address}")
logger.info("="*80)
print(f"\n🌐 VNC Web Access URL: {vnc_url}")
print(f"📍 Please open the above address in the browser for remote desktop access\n")
else:
logger.warning("No public IP address available for VNC access")
return private_ip_address
return '' # Return an empty string if no IP address is found
except ClientError as e:
logger.error(f"Failed to retrieve private IP address for the instance {path_to_vm}: {str(e)}")
logger.error(f"Failed to retrieve IP address for the instance {path_to_vm}: {str(e)}")
raise
def save_state(self, path_to_vm: str, snapshot_name: str):
@@ -74,7 +88,7 @@ class AWSProvider(Provider):
ec2_client = boto3.client('ec2', region_name=self.region)
try:
image_response = ec2_client.create_image(InstanceId=path_to_vm, ImageId=snapshot_name)
image_response = ec2_client.create_image(InstanceId=path_to_vm, Name=snapshot_name)
image_id = image_response['ImageId']
logger.info(f"AMI {image_id} created successfully from instance {path_to_vm}.")
return image_id
@@ -83,7 +97,7 @@ class AWSProvider(Provider):
raise
def revert_to_snapshot(self, path_to_vm: str, snapshot_name: str):
logger.info(f"Reverting AWS VM to snapshot: {snapshot_name}...")
logger.info(f"Reverting AWS VM to snapshot AMI: {snapshot_name}...")
ec2_client = boto3.client('ec2', region_name=self.region)
try:
@@ -93,23 +107,21 @@ class AWSProvider(Provider):
security_groups = [sg['GroupId'] for sg in instance['SecurityGroups']]
subnet_id = instance['SubnetId']
instance_type = instance['InstanceType']
instance_snapshot = instance_details['Reservations'][0]['Instances'][0]['ImageId']
# Step 2: Terminate the old instance
ec2_client.terminate_instances(InstanceIds=[path_to_vm])
logger.info(f"Old instance {path_to_vm} has been terminated.")
# Step 3: Launch a new instance from the snapshot
logger.info(f"Launching a new instance from snapshot {instance_snapshot}...")
new_instance = ec2_client.run_instances(
MaxCount = 1,
MinCount = 1,
ImageId = instance_snapshot,
InstanceType = instance_type,
EbsOptimized = True,
NetworkInterfaces = [
# Step 3: Launch a new instance from the snapshot(AMI) with performance optimization
logger.info(f"Launching a new instance from AMI {snapshot_name}...")
run_instances_params = {
"MaxCount": 1,
"MinCount": 1,
"ImageId": snapshot_name,
"InstanceType": instance_type,
"EbsOptimized": True,
"NetworkInterfaces": [
{
"SubnetId": subnet_id,
"AssociatePublicIpAddress": True,
@@ -117,13 +129,31 @@ class AWSProvider(Provider):
"Groups": security_groups
}
]
)
}
new_instance = ec2_client.run_instances(**run_instances_params)
new_instance_id = new_instance['Instances'][0]['InstanceId']
logger.info(f"New instance {new_instance_id} launched from snapshot {snapshot_name}.")
logger.info(f"New instance {new_instance_id} launched from AMI {snapshot_name}.")
logger.info(f"Waiting for instance {new_instance_id} to be running...")
ec2_client.get_waiter('instance_running').wait(InstanceIds=[new_instance_id])
logger.info(f"Instance {new_instance_id} is ready.")
try:
instance_details = ec2_client.describe_instances(InstanceIds=[new_instance_id])
instance = instance_details['Reservations'][0]['Instances'][0]
public_ip = instance.get('PublicIpAddress', '')
if public_ip:
vnc_url = f"http://{public_ip}:5910/vnc.html"
logger.info("="*80)
logger.info(f"🖥️ New Instance VNC Web Access URL: {vnc_url}")
logger.info(f"📡 Public IP: {public_ip}")
logger.info(f"🆔 New Instance ID: {new_instance_id}")
logger.info("="*80)
print(f"\n🌐 New Instance VNC Web Access URL: {vnc_url}")
print(f"📍 Please open the above address in the browser for remote desktop access\n")
except Exception as e:
logger.warning(f"Failed to get VNC address for new instance {new_instance_id}: {e}")
return new_instance_id