From e79e2380f8b590506e4f80c9bbba303053a48cab Mon Sep 17 00:00:00 2001
From: Nubenetes Bot <bot@nubenetes.com>
Date: Fri, 22 May 2026 17:35:30 +0200
Subject: [PATCH] perf: implement frequent inventory backup to cache in Video
 Hub workflow

---
 .github/workflows/agentic_v2_videos.yml | 15 +++++++++++++++
 src/enrich_videos.py                    | 12 ++++++++----
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/agentic_v2_videos.yml b/.github/workflows/agentic_v2_videos.yml
index 7ca9dace..4bd599a7 100644
--- a/.github/workflows/agentic_v2_videos.yml
+++ b/.github/workflows/agentic_v2_videos.yml
@@ -32,6 +32,14 @@ jobs:
           python-version: '3.11'
           cache: 'pip'
 
+      - name: Restore Incremental Inventory Cache
+        uses: actions/cache/restore@v4
+        with:
+          path: data/inventory.yaml
+          key: inventory-v2-${{ github.run_id }}-${{ github.run_attempt }}
+          restore-keys: |
+            inventory-v2-
+
       - name: Dependency Installation
         run: |
           python -m pip install --upgrade pip
@@ -61,3 +69,10 @@ jobs:
             git pull --rebase origin develop
             git push origin develop
           fi
+
+      - name: Persist Incremental Inventory Cache
+        if: always()
+        uses: actions/cache/save@v4
+        with:
+          path: data/inventory.yaml
+          key: inventory-v2-${{ github.run_id }}-${{ github.run_attempt }}
diff --git a/src/enrich_videos.py b/src/enrich_videos.py
index 878dcf4a..b90edf90 100644
--- a/src/enrich_videos.py
+++ b/src/enrich_videos.py
@@ -88,10 +88,14 @@ async def main():
     for i in range(0, len(tasks), batch_size):
         batch = tasks[i:i+batch_size]
         await asyncio.gather(*batch)
-        await asyncio.sleep(2) # Safety delay
-
-    with open(INVENTORY_PATH, "w") as f:
-        yaml.dump(inventory, f, sort_keys=False, allow_unicode=True)
+        
+        # Incremental Persistence: Save after each batch
+        with open(INVENTORY_PATH, "w") as f:
+            yaml.dump(inventory, f, sort_keys=False, allow_unicode=True)
+        log_event(f"    [💾] Saved progress: {min(i + batch_size, len(tasks))}/{len(tasks)} videos.")
+        
+        if i + batch_size < len(tasks):
+            await asyncio.sleep(2) # Safety delay
     
     log_event("✅ Video Hub Enrichment Complete.")