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

56
desktop_env/providers/aws/provider_with_proxy.py
View File

@@ -163,16 +163,34 @@ echo "$(date): Configured proxy {self.current_proxy.host}:{self.current_proxy.po
logger.info(f"Created new instance {instance_id} with proxy configuration")
# 等待实例运行
logger.info(f"Waiting for instance {instance_id} to be running...")
ec2_client.get_waiter('instance_running').wait(InstanceIds=[instance_id])
logger.info(f"Instance {instance_id} is ready.")
try:
instance_details = ec2_client.describe_instances(InstanceIds=[instance_id])
instance = instance_details['Reservations'][0]['Instances'][0]
public_ip = instance.get('PublicIpAddress', '')
if public_ip:
vnc_url = f"http://{public_ip}:5910/vnc.html"
logger.info("="*80)
logger.info(f"🖥️ VNC Web Access URL: {vnc_url}")
logger.info(f"📡 Public IP: {public_ip}")
logger.info(f"🆔 Instance ID: {instance_id}")
if self.current_proxy:
logger.info(f"🌐 Proxy: {self.current_proxy.host}:{self.current_proxy.port}")
logger.info("="*80)
print(f"\n🌐 VNC Web Access URL: {vnc_url}")
if self.current_proxy:
print(f"🔄 Current Proxy: {self.current_proxy.host}:{self.current_proxy.port}")
print(f"📍 Please open the above address in the browser for remote desktop access\n")
except Exception as e:
logger.warning(f"Failed to get VNC address for instance {instance_id}: {e}")
return instance_id
except ClientError as e:
logger.error(f"Failed to create instance with proxy: {str(e)}")
# 如果当前代理失败，尝试轮换代理
if self.current_proxy:
proxy_pool = get_global_proxy_pool()
proxy_pool.mark_proxy_failed(self.current_proxy)
@@ -188,10 +206,28 @@ echo "$(date): Configured proxy {self.current_proxy.host}:{self.current_proxy.po
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}")
if self.current_proxy:
logger.info(f"🌐 Proxy: {self.current_proxy.host}:{self.current_proxy.port}")
logger.info("="*80)
print(f"\n🌐 VNC Web Access URL: {vnc_url}")
if self.current_proxy:
print(f"🔄 Current Proxy: {self.current_proxy.host}:{self.current_proxy.port}")
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 ''
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):
@@ -212,24 +248,28 @@ echo "$(date): Configured proxy {self.current_proxy.host}:{self.current_proxy.po
ec2_client = boto3.client('ec2', region_name=self.region)
try:
# 获取原实例详情
# Get original instance details for config.
instance_details = ec2_client.describe_instances(InstanceIds=[path_to_vm])
instance = instance_details['Reservations'][0]['Instances'][0]
security_groups = [sg['GroupId'] for sg in instance['SecurityGroups']]
subnet_id = instance['SubnetId']
instance_type = instance['InstanceType']
# 终止旧实例
# Terminate the old instance. This is a non-blocking call.
logger.info(f"Initiating termination for old instance {path_to_vm}...")
ec2_client.terminate_instances(InstanceIds=[path_to_vm])
logger.info(f"Old instance {path_to_vm} has been terminated.")
logger.info(f"Old instance {path_to_vm} termination initiated.")
# 轮换到新的代理
# Rotate to a new proxy
self._rotate_proxy()
# 创建新实例
# Create a new instance
new_instance_id = self.create_instance_with_proxy(
snapshot_name, instance_type, security_groups, subnet_id
)
# Note: VNC address is displayed within create_instance_with_proxy
logger.info(f"Successfully launched new instance {new_instance_id} for revert.")
return new_instance_id