Feat/update ec2 add s3 (#18)

* refactor(ec2): move account ID retrieval to common module

* feat(s3): implement S3 bucket cleanup functionality

* feat(s3): enhance bucket cataloging by region filtering

* feat(s3): implement object cataloging and cleanup functions

* refactor(tests): rename test functions for consistency

* feat(orchestrator): enhance service orchestration with task tracking

* test(orchestrator): enhance service orchestration tests

* feat(tests): add comprehensive tests for costcutter services

Author: HYP3R00T

src/costcutter/conf/config.yaml

@@ -1,11 +1,11 @@
 dry_run: true
 logging:
-  enabled: false
+  enabled: true
   level: INFO
   dir: ~/.local/share/costcutter/logs
 reporting:
   csv:
-    enabled: false
+    enabled: true
     path: ~/.local/share/costcutter/reports/events.csv
 aws:
   profile: default
@@ -20,5 +20,6 @@ aws:
     - ap-south-1
   services:
     # - all to scan for all services (WIP)
-    - ec2
-    - lambda
+    # - ec2
+    - s3
+    # - lambda

src/costcutter/orchestrator.py

@@ -8,16 +8,18 @@
 
 from costcutter.conf.config import get_config
 from costcutter.core.session_helper import create_aws_session
+from costcutter.reporter import get_reporter
 
 # Reporter no longer needed at service-level (resource handlers still record events)
 from costcutter.services.ec2 import cleanup_ec2
+from costcutter.services.s3 import cleanup_s3
 
 logger = logging.getLogger(__name__)
 
 SERVICE_HANDLERS = {
     # Each value can be a functional entrypoint `run(session, region, dry_run, reporter)`
     "ec2": cleanup_ec2,
-    # "s3": cleanup_s3
+    "s3": cleanup_s3,
     # "lambda": cleanup_lambda,
 }
 
@@ -55,7 +57,7 @@ def process_region_service(
 
 def orchestrate_services(
     dry_run: bool = False,
-) -> dict[str, int]:
+) -> dict[str, Any]:
     config = get_config()
 
     # Resolve services
@@ -125,6 +127,9 @@ def orchestrate_services(
         total_tasks = max(1, len(tasks))
         max_workers = min(32, total_tasks)
 
+    # Execute tasks concurrently and track successes/failures
+    succeeded = 0
+    failed = 0
     with ThreadPoolExecutor(max_workers=max_workers) as executor:
         future_map: dict[Any, tuple[str, str]] = {}
         for region, service_key, handler_entry in tasks:
@@ -134,6 +139,23 @@ def orchestrate_services(
         for future in as_completed(future_map):
             region, svc_name = future_map[future]
             try:
-                logger.info("[%s][%s] Task completed", region, svc_name)
+                # Propagate exceptions from the task so callers can observe failures
+                future.result()
             except Exception as e:
+                failed += 1
                 logger.exception("[%s][%s] Task failed: %s", region, svc_name, e)
+            else:
+                succeeded += 1
+                logger.info("[%s][%s] Task completed", region, svc_name)
+
+    # After all work is finished, gather recorded events from the global reporter
+    reporter = get_reporter()
+    events = reporter.to_dicts()
+
+    # Return a small summary including counters and serialized events
+    return {
+        "processed": succeeded,
+        "skipped": skipped,
+        "failed": failed,
+        "events": events,
+    }

src/costcutter/services/ec2/__init__.py

@@ -1,27 +1,11 @@
-import logging
-
 from boto3.session import Session
 
 from costcutter.services.ec2.instances import cleanup_instances
 from costcutter.services.ec2.key_pairs import cleanup_key_pairs
 
-logger = logging.getLogger(__name__)
-_ACCOUNT_ID: str | None = None
 _HANDLERS = {"instances": cleanup_instances, "key_pairs": cleanup_key_pairs}
 
 
-def _get_account_id(session: Session) -> str:
-    """Return (and cache) the current AWS account id (simple module cache)."""
-    global _ACCOUNT_ID
-    if _ACCOUNT_ID is None:
-        try:
-            _ACCOUNT_ID = session.client("sts").get_caller_identity().get("Account", "")
-        except Exception as e:  # pragma: no cover
-            logger.error("Failed to resolve account id: %s", e)
-            _ACCOUNT_ID = ""
-    return _ACCOUNT_ID
-
-
 def cleanup_ec2(session: Session, region: str, dry_run: bool = True, max_workers: int = 1):
     # targets: list[str] or None => run all registered
     for fn in _HANDLERS.values():

src/costcutter/services/ec2/common.py

@@ -0,0 +1,19 @@
+import logging
+
+from boto3.session import Session
+
+_ACCOUNT_ID: str | None = None
+
+logger = logging.getLogger(__name__)
+
+
+def _get_account_id(session: Session) -> str:
+    """Return (and cache) the current AWS account id (simple module cache)."""
+    global _ACCOUNT_ID
+    if _ACCOUNT_ID is None:
+        try:
+            _ACCOUNT_ID = session.client("sts").get_caller_identity().get("Account", "")
+        except Exception as e:  # pragma: no cover
+            logger.error("Failed to resolve account id: %s", e)
+            _ACCOUNT_ID = ""
+    return _ACCOUNT_ID

src/costcutter/services/ec2/instances.py

@@ -6,7 +6,7 @@
 from botocore.exceptions import ClientError
 
 from costcutter.reporter import get_reporter
-from costcutter.services.ec2 import _get_account_id
+from costcutter.services.ec2.common import _get_account_id
 
 SERVICE: str = "ec2"
 RESOURCE: str = "instance"

src/costcutter/services/ec2/key_pairs.py

@@ -5,7 +5,7 @@
 from botocore.exceptions import ClientError
 
 from costcutter.reporter import get_reporter
-from costcutter.services.ec2 import _get_account_id
+from costcutter.services.ec2.common import _get_account_id
 
 SERVICE: str = "ec2"
 RESOURCE: str = "key_pair"

src/costcutter/services/s3/__init__.py

@@ -0,0 +1,11 @@
+from boto3.session import Session
+
+from costcutter.services.s3.buckets import cleanup_buckets
+
+_HANDLERS = {"buckets": cleanup_buckets}
+
+
+def cleanup_s3(session: Session, region: str, dry_run: bool = True, max_workers: int = 1):
+    # targets: list[str] or None => run all registered
+    for fn in _HANDLERS.values():
+        fn(session=session, region=region, dry_run=dry_run, max_workers=max_workers)