ci: avoid redundant S3 uploads (#326)

Co-authored-by: Hermes Agent <hermes-agent@users.noreply.github.com>

.github/workflows/build_master.yml

@@ -153,9 +153,20 @@ jobs:
           role-to-assume: ${{ secrets.AWS_ROLE_ARN }}
           aws-region: us-east-1
       
-      # Sync the build to S3
+      # Sync the build to S3. mdBook refreshes mtimes on every build, so first
+      # age byte-identical files based on S3 ETags; `s3 sync` then uploads only
+      # genuinely changed/new output while retaining normal --delete behavior.
       - name: Sync to S3
-        run: aws s3 sync ./book s3://hacktricks-cloud/en --delete
+        run: |
+          aws s3api list-objects-v2 \
+            --bucket hacktricks-cloud \
+            --prefix en/ \
+            --output json > /tmp/s3-en-manifest.json
+          python3 scripts/mark_unchanged_s3_files.py \
+            --source ./book \
+            --manifest /tmp/s3-en-manifest.json \
+            --remote-prefix en/
+          aws s3 sync ./book s3://hacktricks-cloud/en --delete
 
       - name: Upload root sitemap index
         run: |

.github/workflows/translate_all.yml

@@ -84,6 +84,7 @@ jobs:
           wget -O /tmp/compare_and_fix_refs.py https://raw.githubusercontent.com/HackTricks-wiki/hacktricks-cloud/master/scripts/compare_and_fix_refs.py
           wget -O /tmp/translator.py https://raw.githubusercontent.com/HackTricks-wiki/hacktricks-cloud/master/scripts/translator.py
           wget -O /tmp/seo_postprocess.py https://raw.githubusercontent.com/HackTricks-wiki/hacktricks-cloud/master/scripts/seo_postprocess.py
+          cp scripts/mark_unchanged_s3_files.py /tmp/mark_unchanged_s3_files.py
 
       - name: Run get_and_save_refs.py
         run: |
@@ -272,6 +273,16 @@ jobs:
           echo "Current branch:"
           git rev-parse --abbrev-ref HEAD
           echo "Syncing $BRANCH to S3"
+          # mdBook refreshes mtimes on every build. Age byte-identical files
+          # based on single-part S3 ETags so `s3 sync` skips redundant PUTs.
+          aws s3api list-objects-v2 \
+            --bucket hacktricks-cloud \
+            --prefix "$BRANCH/" \
+            --output json > /tmp/s3-branch-manifest.json
+          python3 /tmp/mark_unchanged_s3_files.py \
+            --source ./book \
+            --manifest /tmp/s3-branch-manifest.json \
+            --remote-prefix "$BRANCH/"
           aws s3 sync ./book s3://hacktricks-cloud/$BRANCH --delete
           echo "Sync completed"
           echo "Cat 3 files from the book"