Merge branch 'main' of github.com:emagedoc/CodeClash

Author: john-b-yang

.cursor/rules/style.mdc

@@ -21,6 +21,8 @@ alwaysApply: true
 13. Write concise code and thing of elegant solution.
 14. When logging exceptions, always include `exc_info=True` to capture the full traceback.
 15. Command line arguments should be parsed with `argparse`.
+16. Generally prefer to use keyword arguments over positional arguments. If there are somewhat specific optional arguments, mark them as keyword-only.
+17. Use logger instead of print statements.
 
 ## Test style
 

aws/README.md

@@ -1,5 +1,20 @@
 # AWS
 
-## Overview
+## Usage
 
-* `setup/`: Everything needed to set up AWS to run codeclash jobs
+```bash
+# Hello world example
+aws/run_job.py --show-logs -- echo "hello world"
+
+# Run main.py with a config file
+# Remember to use the docker_and_sync.sh wrapper script!
+# ❌ aws/run_job.py --show-logs -- python main.py configs/test/battlesnake_pvp_test.yaml
+aws/run_job.py --show-logs -- aws/docker_and_sync.sh python main.py configs/test/battlesnake_pvp_test.yaml
+```
+
+> [!WARNING]
+> Everything needs to be committed & pushed to the repo! You can use a different branch than main for this.
+
+## Setup
+
+* `setup/`: Everything needed to set up AWS to run codeclash jobs. Advanced user stuff.

aws/docker_and_sync.sh

@@ -1,12 +1,17 @@
 #!/bin/bash
 
+# This wrapper is used together with a script like main.py to run a command in a container
+# while ensuring that docker is alive and guaranteeing to sync logs to S3 on exit.
+
+echo "═══════════════════════════════════════════════════════════════════════════════"
+echo "🚀 Wrapper script docker_and_sync.sh"
+echo "═══════════════════════════════════════════════════════════════════════════════"
+
 set -x
 set -euo pipefail
 
 echo "📅 Container built at: $BUILD_TIMESTAMP"
 
-echo "Git pull"
-git pull
 
 # Function to sync logs on exit
 cleanup() {
@@ -56,13 +61,10 @@ done
 docker run hello-world
 
 # Pull images from ECR so we don't have to build them
-DOCKER_REGISTRY="039984708918.dkr.ecr.us-east-1.amazonaws.com"
-aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin $DOCKER_REGISTRY
-
-for game in battlesnake; do
-    docker pull $DOCKER_REGISTRY/codeclash/$game
-    docker tag $DOCKER_REGISTRY/codeclash/$game codeclash/$game
-done
+export AWS_DOCKER_REGISTRY="039984708918.dkr.ecr.us-east-1.amazonaws.com"
+aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin $AWS_DOCKER_REGISTRY
+export AWS_S3_BUCKET="codeclash"
+export AWS_S3_PREFIX="logs"
 
 # Create logs directory
 mkdir -p logs
@@ -73,3 +75,7 @@ ulimit -n 65536
 
 # Execute the command passed to container
 "$@"
+
+echo "═══════════════════════════════════════════════════════════════════════════════"
+echo "✅ Wrapper script docker_and_sync.sh finished"
+echo "═══════════════════════════════════════════════════════════════════════════════"

aws/get_job_log.py

@@ -63,10 +63,6 @@ def main():
     parser = argparse.ArgumentParser(
         description="Retrieve logs for AWS Batch jobs",
         formatter_class=argparse.RawDescriptionHelpFormatter,
-        epilog="""
-Examples:
-  %(prog)s abc123-def456-ghi789
-        """,
     )
 
     parser.add_argument("job_id", help="Job ID to retrieve logs for")

aws/run_job.py

@@ -14,32 +14,28 @@
 import argparse
 import json
 import shlex
-import subprocess
 import sys
 import time
 from typing import Any
 
 import boto3
 
+from codeclash.utils.git_utils import get_current_git_branch, has_unpushed_commits, is_git_repo_dirty
 from codeclash.utils.log import get_logger
 
 logger = get_logger("launch", emoji="🚀")
 
 
-def get_current_git_branch() -> str:
-    """Get the current git branch name."""
-    try:
-        result = subprocess.run(
-            ["git", "rev-parse", "--abbrev-ref", "HEAD"], capture_output=True, text=True, check=True
-        )
-        return result.stdout.strip()
-    except subprocess.CalledProcessError as e:
-        logger.error(f"Failed to get git branch: {e}")
-        raise
+def check_git_status_and_confirm() -> None:
+    if not is_git_repo_dirty() and not has_unpushed_commits():
+        return
+
+    if input("Git repository dirty/unpushed, continue anyway? (y/N): ").strip().lower() not in ("y", "yes"):
+        sys.exit(1)
 
 
 class AWSBatchJobLauncher:
-    def __init__(self, job_definition_name: str = "codeclash-yolo-test", job_queue: str = "codeclash-test-queue"):
+    def __init__(self, job_definition_name: str = "codeclash-default-job", job_queue: str = "codeclash-queue"):
         self.batch_client = boto3.client("batch")
         self.logs_client = boto3.client("logs")
         self.job_definition_name = job_definition_name
@@ -154,11 +150,9 @@ def main():
     )
     parser.add_argument("--job-name", help="Custom job name (auto-generated if not specified)")
     parser.add_argument(
-        "--job-definition", default="codeclash-yolo-test", help="Job definition name (default: codeclash-yolo-test)"
-    )
-    parser.add_argument(
-        "--job-queue", default="codeclash-test-queue", help="Job queue name (default: codeclash-test-queue)"
+        "--job-definition", default="codeclash-default-job", help="Job definition name (default: codeclash-default-job)"
     )
+    parser.add_argument("--job-queue", default="codeclash-queue", help="Job queue name (default: codeclash-queue)")
     parser.add_argument("--wait", action="store_true", help="Wait for the job to complete before exiting")
     parser.add_argument("--show-logs", action="store_true", help="Show job logs after completion (implies --wait)")
 
@@ -171,6 +165,8 @@ def main():
 
     args = parser.parse_args(aws_args)
 
+    check_git_status_and_confirm()
+
     launcher = AWSBatchJobLauncher(job_definition_name=args.job_definition, job_queue=args.job_queue)
 
     # Submit the job

aws/setup/batch/clean_old_job_definitions.py

@@ -0,0 +1,57 @@
+#!/usr/bin/env python3
+
+import argparse
+import json
+import logging
+from pathlib import Path
+
+import boto3
+
+logging.basicConfig(level=logging.INFO, format="%(levelname)s: %(message)s")
+logger = logging.getLogger(__name__)
+
+
+def clean_old_job_definitions(job_name: str, batch_client) -> int:
+    response = batch_client.describe_job_definitions(jobDefinitionName=job_name, status="ACTIVE")
+
+    job_definitions = response["jobDefinitions"]
+
+    if not job_definitions:
+        logger.info(f"No active job definitions found for: {job_name}")
+        return 0
+
+    job_definitions.sort(key=lambda x: x["revision"])
+    old_revisions = job_definitions[:-1]
+
+    logger.info(f"Found {len(job_definitions)} active revisions for {job_name}")
+    logger.info(f"Latest revision: {job_definitions[-1]['revision']}")
+
+    if not old_revisions:
+        logger.info("No old revisions to clean up")
+        return 0
+
+    for job_def in old_revisions:
+        logger.info(f"Deregistering old revision: {job_name}:{job_def['revision']}")
+        batch_client.deregister_job_definition(jobDefinition=job_def["jobDefinitionArn"])
+
+    logger.info(f"✅ Successfully cleaned up {len(old_revisions)} old revisions for {job_name}")
+    return len(old_revisions)
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("job_definition_json", nargs="?", default="job_definition.json")
+    parser.add_argument("--region", default="us-east-1")
+
+    args = parser.parse_args()
+
+    json_path = Path(args.job_definition_json)
+    data = json.loads(json_path.read_text())
+    job_name = data["jobDefinitionName"]
+
+    batch_client = boto3.client("batch", region_name=args.region)
+    clean_old_job_definitions(job_name, batch_client)
+
+
+if __name__ == "__main__":
+    main()

aws/setup/batch/environment.json

@@ -0,0 +1,51 @@
+{
+  "computeEnvironmentName": "codeclash-batch",
+  "computeEnvironmentArn": "arn:aws:batch:us-east-1:039984708918:compute-environment/codeclash-batch",
+  "ecsClusterArn": "arn:aws:ecs:us-east-1:039984708918:cluster/AWSBatch-codeclash-batch-1561352c-9234-3de1-999a-dcd1c9989b32",
+  "tags": {
+    "project": "codeclash",
+    "author": "kilian"
+  },
+  "type": "MANAGED",
+  "state": "ENABLED",
+  "status": "VALID",
+  "statusReason": "ComputeEnvironment Healthy",
+  "computeResources": {
+    "type": "EC2",
+    "allocationStrategy": "BEST_FIT_PROGRESSIVE",
+    "minvCpus": 2,
+    "maxvCpus": 16,
+    "desiredvCpus": 2,
+    "instanceTypes": [
+      "optimal"
+    ],
+    "subnets": [
+      "subnet-02f03254ff2613e05",
+      "subnet-0e2125855c3ef70da",
+      "subnet-08945e7d77f277c44",
+      "subnet-030c8969a2f8b25eb",
+      "subnet-06521a7e32f9320a8",
+      "subnet-0440a980c38055bfa"
+    ],
+    "securityGroupIds": [
+      "sg-014723b4566a8214d"
+    ],
+    "instanceRole": "arn:aws:iam::039984708918:instance-profile/kilian-codeclash-ecsInstanceRole",
+    "launchTemplate": {
+      "launchTemplateName": "kilian-codeclash-launch-template",
+      "version": "$Latest"
+    },
+    "ec2Configuration": [
+      {
+        "imageType": "ECS_AL2"
+      }
+    ]
+  },
+  "serviceRole": "arn:aws:iam::039984708918:role/aws-service-role/batch.amazonaws.com/AWSServiceRoleForBatch",
+  "updatePolicy": {
+    "terminateJobsOnUpdate": false,
+    "jobExecutionTimeoutMinutes": 30
+  },
+  "containerOrchestrationType": "ECS",
+  "uuid": "f413880a-eecc-3dfd-b139-0e9143381b4d"
+}

aws/setup/batch/iam-ebs.json

@@ -0,0 +1,30 @@
+{
+  "Role": {
+    "Path": "/",
+    "RoleName": "kilian-codeclash-ecs-role-for-ebs-volumes",
+    "AssumeRolePolicyDocument": {
+      "Version": "2012-10-17",
+      "Statement": [
+        {
+          "Effect": "Allow",
+          "Principal": {
+            "Service": "ecs.amazonaws.com"
+          },
+          "Action": "sts:AssumeRole"
+        }
+      ]
+    },
+    "Description": "ECS Infrastructure role for managing EBS volumes",
+    "MaxSessionDuration": 3600,
+    "Tags": [
+      {
+        "Key": "project",
+        "Value": "codeclash"
+      },
+      {
+        "Key": "author",
+        "Value": "kilian"
+      }
+    ]
+  }
+}

aws/setup/batch/iam-environment-role.json

@@ -0,0 +1,37 @@
+{
+  "Role": {
+    "Path": "/",
+    "RoleName": "kilian-codeclash-ecsInstanceRole",
+    "RoleId": "AROAQST2GHU3K4I5VM26G",
+    "Arn": "arn:aws:iam::039984708918:role/kilian-codeclash-ecsInstanceRole",
+    "CreateDate": "2025-09-24 02:40:57+00:00",
+    "AssumeRolePolicyDocument": {
+      "Version": "2012-10-17",
+      "Statement": [
+        {
+          "Effect": "Allow",
+          "Principal": {
+            "Service": "ec2.amazonaws.com"
+          },
+          "Action": "sts:AssumeRole"
+        }
+      ]
+    },
+    "Description": "Allows EC2 instances to call AWS services on your behalf.",
+    "MaxSessionDuration": 3600,
+    "Tags": [
+      {
+        "Key": "project",
+        "Value": "codeclash"
+      },
+      {
+        "Key": "author",
+        "Value": "kilian"
+      }
+    ],
+    "RoleLastUsed": {
+      "LastUsedDate": "2025-09-25 19:28:45+00:00",
+      "Region": "us-east-1"
+    }
+  }
+}

aws/setup/batch/iam-execution-role.json

@@ -0,0 +1,38 @@
+{
+  "Role": {
+    "Path": "/",
+    "RoleName": "kilian-codeclash-execution-role",
+    "RoleId": "AROAQST2GHU3FIDU7YRBJ",
+    "Arn": "arn:aws:iam::039984708918:role/kilian-codeclash-execution-role",
+    "CreateDate": "2025-09-24 17:49:33+00:00",
+    "AssumeRolePolicyDocument": {
+      "Version": "2012-10-17",
+      "Statement": [
+        {
+          "Sid": "",
+          "Effect": "Allow",
+          "Principal": {
+            "Service": "ecs-tasks.amazonaws.com"
+          },
+          "Action": "sts:AssumeRole"
+        }
+      ]
+    },
+    "Description": "Allows ECS tasks to call AWS services on your behalf.",
+    "MaxSessionDuration": 3600,
+    "Tags": [
+      {
+        "Key": "project",
+        "Value": "codeclash"
+      },
+      {
+        "Key": "author",
+        "Value": "kilian"
+      }
+    ],
+    "RoleLastUsed": {
+      "LastUsedDate": "2025-09-25 19:02:55+00:00",
+      "Region": "us-east-1"
+    }
+  }
+}