nuvu-scan 1.3.7__py3-none-any.whl → 2.0.0__py3-none-any.whl

nuvu_scan/__init__.py

@@ -1,3 +1,3 @@
 """Nuvu - Multi-Cloud Data Asset Control."""
 
-__version__ = "0.1.0"
+__version__ = "2.0.0"

nuvu_scan/cli/commands/scan.py

@@ -2,9 +2,12 @@
 Scan command for Nuvu CLI.
 """
 
+import json
 import os
 import sys
 from datetime import datetime
+from urllib.error import HTTPError, URLError
+from urllib.request import Request, urlopen
 
 import click
 
@@ -39,6 +42,15 @@ from ..formatters.json import JSONFormatter
     multiple=True,
     help="Cloud provider region(s) to scan (can be specified multiple times, default: all regions)",
 )
+@click.option(
+    "--collectors",
+    "-c",
+    multiple=True,
+    help="Specific collector(s) to run (can be specified multiple times). "
+    "AWS: s3, glue, athena, redshift, iam, mwaa. "
+    "GCP: gcs, bigquery, dataproc, pubsub, iam, gemini. "
+    "Default: all collectors.",
+)
 @click.option(
     "--access-key-id",
     envvar="AWS_ACCESS_KEY_ID",
@@ -83,11 +95,34 @@ from ..formatters.json import JSONFormatter
     "--gcp-project",
     help="GCP project ID (default: from service account key or GOOGLE_CLOUD_PROJECT env var)",
 )
+@click.option(
+    "--push",
+    is_flag=True,
+    help="Push scan results to Nuvu Cloud (requires API key)",
+)
+@click.option(
+    "--nuvu-cloud-url",
+    envvar="NUVU_CLOUD_URL",
+    default="https://nuvu.dev",
+    show_default=True,
+    help="Nuvu Cloud base URL",
+)
+@click.option(
+    "--api-key",
+    envvar="NUVU_API_KEY",
+    help="Nuvu Cloud API key (from dashboard account settings)",
+)
+@click.option(
+    "--list-collectors",
+    is_flag=True,
+    help="List available collectors for the specified provider and exit",
+)
 def scan_command(
     provider: str,
     output_format: str,
     output_file: str | None,
     region: tuple,
+    collectors: tuple,
     access_key_id: str | None,
     secret_access_key: str | None,
     session_token: str | None,
@@ -98,9 +133,28 @@ def scan_command(
     role_duration_seconds: int,
     gcp_credentials: str | None,
     gcp_project: str | None,
+    push: bool,
+    nuvu_cloud_url: str | None,
+    api_key: str | None,
+    list_collectors: bool,
 ):
     """Scan cloud provider for data assets."""
 
+    # Handle --list-collectors flag
+    if list_collectors:
+        if provider == "aws":
+            available = AWSScanner.get_available_collectors()
+        elif provider == "gcp":
+            available = GCPScanner.get_available_collectors()
+        else:
+            click.echo(f"Unknown provider: {provider}", err=True)
+            sys.exit(1)
+
+        click.echo(f"Available collectors for {provider.upper()}:")
+        for name in sorted(available):
+            click.echo(f"  - {name}")
+        return
+
     # Build credentials based on provider
     credentials = {}
     account_id = None
@@ -183,6 +237,7 @@ def scan_command(
         credentials=credentials,
         regions=list(region) if region else None,
         account_id=account_id,
+        collectors=list(collectors) if collectors else None,
     )
 
     # Get scanner instance
@@ -255,3 +310,42 @@ def scan_command(
         with open(output_file, "w") as f:
             f.write(content)
         click.echo(f"Report written to {output_file}", err=True)
+
+    if push:
+        if not nuvu_cloud_url:
+            click.echo("Error: --nuvu-cloud-url or NUVU_CLOUD_URL is required for --push", err=True)
+            sys.exit(1)
+        if not api_key:
+            click.echo("Error: --api-key or NUVU_API_KEY is required for --push", err=True)
+            sys.exit(1)
+
+        payload = json.loads(JSONFormatter().format(result))
+        payload["scan_regions"] = list(region) if region else None
+        payload["scan_all_regions"] = False if region else True
+
+        import_url = nuvu_cloud_url.rstrip("/") + "/api/scans/import"
+        request = Request(
+            import_url,
+            data=json.dumps(payload).encode("utf-8"),
+            headers={
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {api_key}",
+            },
+            method="POST",
+        )
+
+        try:
+            with urlopen(request) as response:
+                response_body = response.read().decode("utf-8")
+                click.echo(f"Scan uploaded to Nuvu Cloud: {response.status}", err=True)
+                if response_body:
+                    click.echo(response_body, err=True)
+        except HTTPError as e:
+            error_body = e.read().decode("utf-8")
+            click.echo(f"Failed to upload scan: {e.code} {e.reason}", err=True)
+            if error_body:
+                click.echo(error_body, err=True)
+            sys.exit(1)
+        except URLError as e:
+            click.echo(f"Failed to upload scan: {e.reason}", err=True)
+            sys.exit(1)

nuvu_scan/cli/formatters/html.py

@@ -14,6 +14,9 @@ class HTMLFormatter:
         actual_total = result.summary.get("total_actual_cost_30d")
         estimated_assets_total = result.summary.get("estimated_assets_cost_total")
 
+        # Calculate cost saving opportunities
+        savings_opportunities = self._calculate_savings(result.assets)
+
         summary_cards = f"""
             <div class="summary-card">
                 <h3>Total Assets</h3>
@@ -43,18 +46,27 @@ class HTMLFormatter:
         summary_cards += f"""
             <div class="summary-card">
                 <h3>Unused Assets</h3>
-                <div class="value">{result.summary.get('unused_count', 0)}</div>
+                <div class="value">{result.summary.get("unused_count", 0)}</div>
             </div>
             <div class="summary-card">
                 <h3>No Owner</h3>
-                <div class="value">{result.summary.get('no_owner_count', 0)}</div>
+                <div class="value">{result.summary.get("no_owner_count", 0)}</div>
             </div>
             <div class="summary-card">
                 <h3>Risky Assets</h3>
-                <div class="value">{result.summary.get('risky_count', 0)}</div>
+                <div class="value">{result.summary.get("risky_count", 0)}</div>
             </div>
         """
 
+        # Add savings opportunity card if significant
+        if savings_opportunities["total_potential_savings"] > 100:
+            summary_cards += f"""
+            <div class="summary-card savings">
+                <h3>💰 Potential Savings</h3>
+                <div class="value">${savings_opportunities["total_potential_savings"]:,.2f}/mo</div>
+            </div>
+            """
+
         # Build service costs table if available
         service_costs_html = ""
         service_costs = result.summary.get("actual_costs_30d", {})
@@ -79,14 +91,17 @@ class HTMLFormatter:
     <title>Nuvu Scan Report - {result.provider.upper()}</title>
     <style>
         body {{ font-family: Arial, sans-serif; margin: 20px; background: #f5f5f5; }}
-        .container {{ max-width: 1200px; margin: 0 auto; background: white; padding: 20px; border-radius: 8px; box-shadow: 0 2px 4px rgba(0,0,0,0.1); }}
+        .container {{ max-width: 1400px; margin: 0 auto; background: white; padding: 20px; border-radius: 8px; box-shadow: 0 2px 4px rgba(0,0,0,0.1); }}
         h1 {{ color: #333; border-bottom: 3px solid #4CAF50; padding-bottom: 10px; }}
         h2 {{ color: #555; margin-top: 30px; }}
-        .summary {{ display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 15px; margin: 20px 0; }}
+        .summary {{ display: grid; grid-template-columns: repeat(auto-fit, minmax(180px, 1fr)); gap: 15px; margin: 20px 0; }}
         .summary-card {{ background: #f9f9f9; padding: 15px; border-radius: 5px; border-left: 4px solid #4CAF50; }}
-        .summary-card h3 {{ margin: 0 0 10px 0; color: #666; font-size: 14px; text-transform: uppercase; }}
-        .summary-card .value {{ font-size: 24px; font-weight: bold; color: #333; }}
+        .summary-card.savings {{ border-left-color: #ff9800; background: #fff8e1; }}
+        .summary-card h3 {{ margin: 0 0 10px 0; color: #666; font-size: 13px; text-transform: uppercase; }}
+        .summary-card .value {{ font-size: 22px; font-weight: bold; color: #333; }}
         table {{ width: 100%; border-collapse: collapse; margin: 20px 0; }}
+        table.compact {{ font-size: 13px; }}
+        table.compact th, table.compact td {{ padding: 8px; }}
         th, td {{ padding: 12px; text-align: left; border-bottom: 1px solid #ddd; }}
         th {{ background: #4CAF50; color: white; font-weight: bold; }}
         tr:hover {{ background: #f5f5f5; }}
@@ -94,6 +109,21 @@ class HTMLFormatter:
         .unused {{ color: #ff8800; font-weight: bold; }}
         .no-owner {{ color: #ff4444; font-weight: bold; }}
         .footer {{ margin-top: 40px; padding-top: 20px; border-top: 1px solid #ddd; color: #666; font-size: 12px; text-align: center; }}
+        .insight-box {{ padding: 15px; border-radius: 8px; margin: 15px 0; }}
+        .insight-box h3 {{ margin-top: 0; }}
+        .insight-box.warning {{ background: #fff8e1; border-left: 4px solid #ff9800; }}
+        .insight-box.alert {{ background: #ffebee; border-left: 4px solid #f44336; }}
+        .insight-box.info {{ background: #e3f2fd; border-left: 4px solid #2196f3; }}
+        .insight-box.success {{ background: #e8f5e9; border-left: 4px solid #4caf50; }}
+        .recommendation {{ font-style: italic; color: #666; margin-top: 10px; }}
+        /* Collapsible sections */
+        .collapsible {{ cursor: pointer; padding: 15px; width: 100%; border: none; text-align: left; outline: none; font-size: 18px; font-weight: bold; background: #f5f5f5; border-radius: 5px; margin-top: 20px; color: #555; display: flex; justify-content: space-between; align-items: center; }}
+        .collapsible:hover {{ background: #eee; }}
+        .collapsible:after {{ content: '▼'; font-size: 12px; color: #888; }}
+        .collapsible.active:after {{ content: '▲'; }}
+        .collapsible-content {{ display: none; overflow: hidden; padding: 0; }}
+        .collapsible-content.show {{ display: block; }}
+        .asset-count {{ font-size: 14px; font-weight: normal; color: #888; }}
     </style>
 </head>
 <body>
@@ -108,7 +138,16 @@ class HTMLFormatter:
 {summary_cards}
         </div>
 {service_costs_html}
+"""
+
+        # Add Cost Optimization Section FIRST (before Assets by Category)
+        html += self._build_cost_optimization_section(result.assets)
 
+        # Add Governance Insights Section SECOND
+        html += self._build_governance_section(result.assets)
+
+        # Assets by Category
+        html += """
         <h2>Assets by Category</h2>
         <table>
             <tr><th>Category</th><th>Count</th></tr>
@@ -117,9 +156,12 @@ class HTMLFormatter:
         for category, count in result.summary.get("assets_by_category", {}).items():
             html += f"            <tr><td>{category.replace('_', ' ').title()}</td><td>{count}</td></tr>\n"
 
-        html += """        </table>
+        # All Assets - COLLAPSIBLE
+        asset_count = len(result.assets)
+        html += f"""        </table>
 
-        <h2>All Assets</h2>
+        <button class="collapsible">All Assets <span class="asset-count">({asset_count} items)</span></button>
+        <div class="collapsible-content">
         <table>
             <tr>
                 <th>Name</th>
@@ -151,12 +193,24 @@ class HTMLFormatter:
                 <td>{asset.asset_type}</td>
                 <td>{asset.region}</td>
                 <td>${asset.cost_estimate_usd or 0:.2f}</td>
-                <td class="{owner_class}">{asset.suggested_owner or 'Unknown'}</td>
+                <td class="{owner_class}">{asset.suggested_owner or "Unknown"}</td>
                 <td>{risk_flags_html}</td>
             </tr>
 """
 
         html += """        </table>
+        </div>
+
+        <script>
+        var coll = document.getElementsByClassName("collapsible");
+        for (var i = 0; i < coll.length; i++) {
+            coll[i].addEventListener("click", function() {
+                this.classList.toggle("active");
+                var content = this.nextElementSibling;
+                content.classList.toggle("show");
+            });
+        }
+        </script>
 
         <div class="footer">
             <p>Generated by Nuvu - AWS Data Asset Control</p>
@@ -167,3 +221,201 @@ class HTMLFormatter:
 </html>"""
 
         return html
+
+    def _calculate_savings(self, assets) -> dict:
+        """Calculate potential cost savings from assets."""
+        savings = {
+            "old_manual_snapshots": 0,
+            "stale_crawlers": 0,
+            "unused_etl_jobs": 0,
+            "reservation_opportunities": 0,
+            "total_potential_savings": 0,
+        }
+
+        for asset in assets:
+            metrics = asset.usage_metrics or {}
+
+            # Old MANUAL snapshot savings (automated snapshots are free within retention)
+            if asset.asset_type == "redshift_snapshot":
+                if metrics.get("snapshot_type") == "manual":
+                    if "old_snapshot" in (asset.risk_flags or []):
+                        savings["old_manual_snapshots"] += asset.cost_estimate_usd or 0
+
+            # Reservation savings
+            if asset.asset_type == "redshift_cluster":
+                potential = metrics.get("potential_reservation_savings_usd", 0)
+                savings["reservation_opportunities"] += potential
+
+            # Stale crawler costs
+            if asset.asset_type == "glue_crawler":
+                if "stale_crawler" in (asset.risk_flags or []):
+                    savings["stale_crawlers"] += asset.cost_estimate_usd or 0
+
+        savings["total_potential_savings"] = (
+            savings["old_manual_snapshots"]
+            + savings["reservation_opportunities"]
+            + savings["stale_crawlers"]
+        )
+
+        return savings
+
+    def _build_cost_optimization_section(self, assets) -> str:
+        """Build cost optimization recommendations section."""
+        # Filter relevant assets
+        snapshots = [a for a in assets if a.asset_type == "redshift_snapshot"]
+        manual_snapshots = [
+            a for a in snapshots if (a.usage_metrics or {}).get("snapshot_type") == "manual"
+        ]
+        auto_snapshots = [
+            a for a in snapshots if (a.usage_metrics or {}).get("snapshot_type") == "automated"
+        ]
+        old_manual_snapshots = [
+            a for a in manual_snapshots if "old_snapshot" in (a.risk_flags or [])
+        ]
+        reserved_nodes = [a for a in assets if a.asset_type == "redshift_reserved_node"]
+        expiring_reservations = [
+            a for a in reserved_nodes if "reservation_expiring_soon" in (a.risk_flags or [])
+        ]
+
+        if not snapshots and not reserved_nodes:
+            return ""
+
+        html = """
+        <h2>💰 Cost Optimization Opportunities</h2>
+        """
+
+        # Snapshot analysis - only manual snapshots are chargeable
+        if snapshots:
+            manual_snapshot_cost = sum(a.cost_estimate_usd or 0 for a in manual_snapshots)
+            old_manual_cost = sum(a.cost_estimate_usd or 0 for a in old_manual_snapshots)
+            manual_size = sum((a.size_bytes or 0) / (1024**4) for a in manual_snapshots)  # TB
+
+            html += f"""
+        <div class="insight-box warning">
+            <h3>📦 Redshift Snapshots</h3>
+            <ul>
+                <li><strong>Automated Snapshots:</strong> {len(auto_snapshots)} (included in cluster cost)</li>
+                <li><strong>Manual Snapshots:</strong> {len(manual_snapshots)} ({manual_size:.2f} TB)</li>
+                <li><strong>Manual Snapshot Cost:</strong> ${manual_snapshot_cost:,.2f}/mo</li>
+                <li><strong>Old Manual Snapshots (>90 days):</strong> {len(old_manual_snapshots)} (${old_manual_cost:,.2f}/mo potential savings)</li>
+            </ul>
+            <p class="recommendation">💡 Review old manual snapshots - automated snapshots are retained per retention policy at no extra charge.</p>
+        </div>
+            """
+
+        # Reserved nodes analysis
+        if reserved_nodes:
+            active_reservations = [
+                a for a in reserved_nodes if (a.usage_metrics or {}).get("state") == "active"
+            ]
+            expired = [a for a in reserved_nodes if "reservation_expired" in (a.risk_flags or [])]
+
+            html += f"""
+        <div class="insight-box info">
+            <h3>🎫 Reserved Nodes ({len(reserved_nodes)} total)</h3>
+            <ul>
+                <li><strong>Active Reservations:</strong> {len(active_reservations)}</li>
+                <li><strong>Expired/Retired:</strong> {len(expired)}</li>
+                <li><strong>Expiring Soon:</strong> {len(expiring_reservations)}</li>
+            </ul>
+        </div>
+            """
+
+        return html
+
+    def _build_governance_section(self, assets) -> str:
+        """Build governance insights section."""
+        # Glue crawlers
+        crawlers = [a for a in assets if a.asset_type == "glue_crawler"]
+        stale_crawlers = [
+            a
+            for a in crawlers
+            if "stale_crawler" in (a.risk_flags or []) or "never_run" in (a.risk_flags or [])
+        ]
+
+        # Glue jobs
+        jobs = [a for a in assets if a.asset_type == "glue_job"]
+        stale_jobs = [
+            a
+            for a in jobs
+            if "stale_job" in (a.risk_flags or []) or "never_run" in (a.risk_flags or [])
+        ]
+
+        # Datashares
+        datashares = [a for a in assets if a.asset_type == "redshift_datashare"]
+        cross_account_shares = [
+            a for a in datashares if "cross_account_sharing" in (a.risk_flags or [])
+        ]
+
+        # WLM issues
+        clusters = [a for a in assets if a.asset_type == "redshift_cluster"]
+        wlm_issues = [
+            a
+            for a in clusters
+            if "default_wlm_only" in (a.risk_flags or [])
+            or "unlimited_wlm_queue" in (a.risk_flags or [])
+        ]
+
+        if not any([stale_crawlers, stale_jobs, cross_account_shares, wlm_issues]):
+            return ""
+
+        html = """
+        <h2>🔍 Governance Insights</h2>
+        """
+
+        if stale_crawlers:
+            html += f"""
+        <div class="insight-box warning">
+            <h3>🕷️ Stale/Unused Glue Crawlers ({len(stale_crawlers)})</h3>
+            <table class="compact">
+                <tr><th>Name</th><th>Last Run</th><th>Issue</th></tr>
+            """
+            for crawler in stale_crawlers[:10]:
+                days = (crawler.usage_metrics or {}).get("days_since_last_run", "Never")
+                issues = ", ".join(crawler.risk_flags or [])
+                html += f"<tr><td>{crawler.name}</td><td>{days} days ago</td><td>{issues}</td></tr>"
+            html += "</table></div>"
+
+        if stale_jobs:
+            html += f"""
+        <div class="insight-box warning">
+            <h3>⚙️ Stale/Unused Glue ETL Jobs ({len(stale_jobs)})</h3>
+            <table class="compact">
+                <tr><th>Name</th><th>Last Run</th><th>Issue</th></tr>
+            """
+            for job in stale_jobs[:10]:
+                days = (job.usage_metrics or {}).get("days_since_last_run", "Never")
+                issues = ", ".join(job.risk_flags or [])
+                html += f"<tr><td>{job.name}</td><td>{days} days ago</td><td>{issues}</td></tr>"
+            html += "</table></div>"
+
+        if cross_account_shares:
+            html += f"""
+        <div class="insight-box alert">
+            <h3>🔗 Cross-Account Data Shares ({len(cross_account_shares)})</h3>
+            <p>Data is being shared outside this AWS account. Review for security compliance.</p>
+            <table class="compact">
+                <tr><th>Share Name</th><th>Consumer Account</th><th>Flags</th></tr>
+            """
+            for share in cross_account_shares[:10]:
+                consumers = (share.usage_metrics or {}).get("consumers", [])
+                consumer_ids = ", ".join(c.get("account_id", "?") for c in consumers[:3])
+                flags = ", ".join(share.risk_flags or [])
+                html += f"<tr><td>{share.name}</td><td>{consumer_ids}</td><td>{flags}</td></tr>"
+            html += "</table></div>"
+
+        if wlm_issues:
+            html += f"""
+        <div class="insight-box info">
+            <h3>⚡ WLM Configuration Review ({len(wlm_issues)} clusters)</h3>
+            <p>Some clusters may benefit from WLM tuning:</p>
+            <ul>
+            """
+            for cluster in wlm_issues[:5]:
+                queues = (cluster.usage_metrics or {}).get("wlm_queue_count", 0)
+                auto_wlm = "Yes" if (cluster.usage_metrics or {}).get("wlm_auto_wlm") else "No"
+                flags = ", ".join(f for f in (cluster.risk_flags or []) if "wlm" in f)
+                html += f"<li><strong>{cluster.name}</strong>: {queues} queues, Auto WLM: {auto_wlm} ({flags})</li>"
+            html += "</ul></div>"
+
+        return html

nuvu_scan/cli/main.py

@@ -7,11 +7,12 @@ Usage:
 
 import click
 
+from .. import __version__
 from .commands.scan import scan_command
 
 
 @click.group()
-@click.version_option(version="0.1.0")
+@click.version_option(version=__version__, prog_name="nuvu-scan")
 def cli():
     """Nuvu - Multi-Cloud Data Asset Control CLI."""
     pass

nuvu_scan/core/base.py

@@ -21,10 +21,13 @@ class NormalizedCategory(str, Enum):
     ML_TRAINING = "ml_training"
     DATA_CATALOG = "data_catalog"
     DATA_INTEGRATION = "data_integration"
+    DATA_PIPELINE = "data_pipeline"  # ETL jobs, crawlers, workflows
+    DATA_SHARING = "data_sharing"  # Datashares, cross-account sharing
     QUERY_ENGINE = "query_engine"
     SEARCH = "search"
     DATABASE = "database"
     SECURITY = "security"
+    BILLING = "billing"
 
 
 @dataclass
@@ -66,10 +69,13 @@ class ScanConfig:
     credentials: dict[str, Any]  # Provider-specific credentials
     regions: list[str] = None  # None means all regions
     account_id: str | None = None
+    collectors: list[str] = None  # None means all collectors, otherwise filter by name
 
     def __post_init__(self):
         if self.regions is None:
             self.regions = []
+        if self.collectors is None:
+            self.collectors = []
 
 
 @dataclass

nuvu_scan/core/providers/aws/aws_scanner.py

@@ -33,6 +33,8 @@ class AWSScanner(CloudProviderScan):
     def __init__(self, config: ScanConfig):
         super().__init__(config)
         self.session = self._create_session()
+        if not self.config.regions:
+            self.config.regions = self._resolve_regions()
         self.collectors = self._initialize_collectors()
         self.cost_explorer = CostExplorerCollector(self.session, self.config.regions)
 
@@ -175,7 +177,19 @@ class AWSScanner(CloudProviderScan):
                 region_name=credentials.get("region", "us-east-1"),
             )
         except ClientError as e:
-            raise ValueError(f"Failed to assume role {role_arn}: {str(e)}")
+            raise ValueError(f"Failed to assume role {role_arn}: {str(e)}") from e
+
+    def _resolve_regions(self) -> list[str]:
+        """Resolve regions to scan. If none provided, scan all enabled regions."""
+        try:
+            ec2 = self.session.client("ec2", region_name="us-east-1")
+            response = ec2.describe_regions(AllRegions=False)
+            regions = [region["RegionName"] for region in response.get("Regions", [])]
+            if regions:
+                return regions
+        except Exception:
+            pass
+        return ["us-east-1"]
 
     def _get_account_id(self) -> str:
         """Get AWS account ID from STS get_caller_identity."""
@@ -187,23 +201,49 @@ class AWSScanner(CloudProviderScan):
             # If we can't get account ID, return "unknown"
             return "unknown"
 
+    # Map of collector names to their classes for filtering
+    COLLECTOR_MAP = {
+        "s3": S3Collector,
+        "glue": GlueCollector,
+        "athena": AthenaCollector,
+        "redshift": RedshiftCollector,
+        "iam": IAMCollector,
+        "mwaa": MWAACollector,
+    }
+
+    @classmethod
+    def get_available_collectors(cls) -> list[str]:
+        """Return list of available collector names."""
+        return list(cls.COLLECTOR_MAP.keys())
+
     def _initialize_collectors(self) -> list:
-        """Initialize all AWS service collectors."""
+        """Initialize AWS service collectors based on config."""
         collectors = []
 
-        # Initialize collectors for each service
-        collectors.append(S3Collector(self.session, self.config.regions))
-        collectors.append(GlueCollector(self.session, self.config.regions))
-        collectors.append(AthenaCollector(self.session, self.config.regions))
-        collectors.append(RedshiftCollector(self.session, self.config.regions))
-        collectors.append(IAMCollector(self.session, self.config.regions))
-        collectors.append(MWAACollector(self.session, self.config.regions))
+        # Get requested collectors from config
+        requested = self.config.collectors if self.config.collectors else []
+
+        # Normalize to lowercase
+        requested_lower = [c.lower() for c in requested]
+
+        # If no specific collectors requested, use all
+        if not requested_lower:
+            for collector_cls in self.COLLECTOR_MAP.values():
+                collectors.append(collector_cls(self.session, self.config.regions))
+        else:
+            # Filter to only requested collectors
+            for name, collector_cls in self.COLLECTOR_MAP.items():
+                if name in requested_lower:
+                    collectors.append(collector_cls(self.session, self.config.regions))
+
+            # Warn about unknown collectors
+            known = set(self.COLLECTOR_MAP.keys())
+            unknown = set(requested_lower) - known
+            if unknown:
+                import sys
 
-        # TODO: Add more collectors as needed
-        # collectors.append(OpenSearchCollector(self.session, self.config.regions))
-        # collectors.append(EMRCollector(self.session, self.config.regions))
-        # collectors.append(SageMakerCollector(self.session, self.config.regions))
-        # etc.
+                print(f"Warning: Unknown collectors ignored: {', '.join(unknown)}", file=sys.stderr)
+                print(f"Available collectors: {', '.join(sorted(known))}", file=sys.stderr)
 
         return collectors
 
@@ -250,7 +290,7 @@ class AWSScanner(CloudProviderScan):
                 cost_summary_asset = Asset(
                     provider="aws",
                     asset_type="cost_summary",
-                    normalized_category=NormalizedCategory.SECURITY,  # Using security as placeholder
+                    normalized_category=NormalizedCategory.BILLING,
                     service="Cost Explorer",
                     region="global",
                     arn="arn:aws:ce::cost-summary",

nuvu_scan/core/providers/aws/collectors/athena.py

@@ -23,10 +23,13 @@ class AthenaCollector:
 
     def collect(self) -> list[Asset]:
         """Collect Athena workgroups."""
+        import sys
+
         assets = []
 
         try:
             # List workgroups
+            print("  → Listing Athena workgroups...", file=sys.stderr)
             response = self.athena_client.list_work_groups()
 
             for wg_info in response.get("WorkGroups", []):