feat: implement download and concatenate script for workflow artifacts

scripts/run_historical_adsb_action.py

@@ -38,7 +38,7 @@ def generate_date_chunks(start_date_str, end_date_str, chunk_days=15):
     return chunks
 
 
-def trigger_workflow(start_date, end_date, chunk_days=3, branch='main', dry_run=False):
+def trigger_workflow(start_date, end_date, chunk_days=1, branch='main', dry_run=False):
     """Trigger the historical-adsb workflow via GitHub CLI."""
     cmd = [
         'gh', 'workflow', 'run', 'historical-adsb.yaml',
@@ -50,18 +50,36 @@ def trigger_workflow(start_date, end_date, chunk_days=3, branch='main', dry_run=
     
     if dry_run:
         print(f"[DRY RUN] Would run: {' '.join(cmd)}")
-        return True
+        return True, None
     
     print(f"Triggering workflow: {start_date} to {end_date} (on {branch})")
     result = subprocess.run(cmd, capture_output=True, text=True)
     
     if result.returncode == 0:
         print(f"✓ Successfully triggered workflow for {start_date} to {end_date}")
-        return True
+        
+        # Get the run ID of the workflow we just triggered
+        # Wait a moment for it to appear
+        import time
+        time.sleep(2)
+        
+        # Get the most recent run (should be the one we just triggered)
+        list_cmd = [
+            'gh', 'run', 'list',
+            '--workflow', 'historical-adsb.yaml',
+            '--branch', branch,
+            '--limit', '1',
+            '--json', 'databaseId',
+            '--jq', '.[0].databaseId'
+        ]
+        list_result = subprocess.run(list_cmd, capture_output=True, text=True)
+        run_id = list_result.stdout.strip() if list_result.returncode == 0 else None
+        
+        return True, run_id
     else:
         print(f"✗ Failed to trigger workflow for {start_date} to {end_date}")
         print(f"Error: {result.stderr}")
-        return False
+        return False, None
 
 
 def main():
@@ -81,8 +99,8 @@ def main():
     parser.add_argument(
         '--chunk-days',
         type=int,
-        default=3,
-        help='Days per job chunk within each workflow run (default: 3)'
+        default=1,
+        help='Days per job chunk within each workflow run (default: 1)'
     )
     parser.add_argument(
         '--workflow-chunk-days',
@@ -139,18 +157,27 @@ def main():
     # Trigger workflows
     import time
     success_count = 0
+    triggered_runs = []
     
     for i, chunk in enumerate(chunks, 1):
         print(f"\n[{i}/{len(chunks)}] ", end='')
         
-        if trigger_workflow(
+        success, run_id = trigger_workflow(
             chunk['start'],
             chunk['end'],
             chunk_days=args.chunk_days,
             branch=args.branch,
             dry_run=args.dry_run
-        ):
+        )
+        
+        if success:
             success_count += 1
+            if run_id:
+                triggered_runs.append({
+                    'run_id': run_id,
+                    'start': chunk['start'],
+                    'end': chunk['end']
+                })
         
         # Add delay between triggers (except for last one)
         if i < len(chunks) and not args.dry_run:
@@ -158,6 +185,22 @@ def main():
     
     print(f"\n\nSummary: {success_count}/{len(chunks)} workflows triggered successfully")
     
+    # Save triggered run IDs to a file
+    if triggered_runs and not args.dry_run:
+        import json
+        timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
+        runs_file = f"./triggered_runs_{timestamp}.json"
+        with open(runs_file, 'w') as f:
+            json.dump({
+                'start_date': args.start_date,
+                'end_date': args.end_date,
+                'branch': args.branch,
+                'runs': triggered_runs
+            }, f, indent=2)
+        print(f"\nRun IDs saved to: {runs_file}")
+        print(f"\nTo download and concatenate these artifacts, run:")
+        print(f"  python scripts/download_and_concat_runs.py {runs_file}")
+    
     if success_count < len(chunks):
         sys.exit(1)