feat(history-rewrite): enhance object checks in history rewrite scripts to focus on blob types and improve logging

scripts/history-rewrite/clean_history.sh

@@ -125,7 +125,17 @@ preview_removals() {
   echo "=== Preview: objects in paths ===" | tee -a "$logfile"
   # List objects for the given paths
   for p in $paths_list; do
-    git rev-list --objects --all -- "$p" | tee -a "$logfile" | awk '{print $1, $2}' | head -n 50 | tee -a "$logfile"
+    echo "Path: $p" | tee -a "$logfile"
+    git rev-list --objects --all -- "$p" | while read -r line; do
+      oid=$(printf '%s' "$line" | awk '{print $1}')
+      label=$(printf '%s' "$line" | awk '{print $2}')
+      type=$(git cat-file -t "$oid" 2>/dev/null || true)
+      if [ "$type" = "blob" ]; then
+        echo "$oid $label" | tee -a "$logfile"
+      else
+        echo "[${type^^}] $oid $label" | tee -a "$logfile"
+      fi
+    done | head -n 50 | tee -a "$logfile"
   done
 
   echo "=== Example large objects (candidate for --strip-size) ===" | tee -a "$logfile"

scripts/history-rewrite/preview_removals.sh

@@ -84,10 +84,20 @@ if [ "$FORMAT" = "json" ]; then
   done
   printf '],'
 else
-  echo "--- Objects in paths ---"
-  for p in $paths_list; do
-    git rev-list --objects --all -- "$p" | nl -ba | sed -n '1,100p'
-  done
+  echo "--- Objects in paths (blob objects shown; tags highlighted) ---"
+    for p in $paths_list; do
+      echo "Path: $p"
+      git rev-list --objects --all -- "$p" | while read -r line; do
+        oid=$(printf '%s' "$line" | awk '{print $1}')
+        label=$(printf '%s' "$line" | awk '{print $2}')
+        type=$(git cat-file -t "$oid" 2>/dev/null || true)
+        if [ "$type" = "blob" ]; then
+          echo "$oid  $label"
+        else
+          echo "[${type^^}] $oid  $label"
+        fi
+      done | nl -ba | sed -n '1,100p'
+    done
 fi
 
 echo "--- Example large objects larger than ${STRIP_SIZE}M ---"

scripts/history-rewrite/tests/clean_history.dryrun.bats

@@ -4,6 +4,9 @@ setup() {
   TMPREPO=$(mktemp -d)
   cd "$TMPREPO"
   git init -q
+  # Set local git identity for test commits
+  git config user.email "test@example.com"
+  git config user.name "Test Runner"
   # create a directory that matches the paths to be pruned
   mkdir -p backend/codeql-db
   # add a large fake blob file

scripts/history-rewrite/tests/validate_after_rewrite.bats

@@ -5,6 +5,9 @@ setup() {
   TMPREPO=$(mktemp -d)
   cd "$TMPREPO"
   git init -q
+  # Set local git identity for test commits
+  git config user.email "test@example.com"
+  git config user.name "Test Runner"
   echo 'initial' > README.md
   git add README.md && git commit -m 'init' -q
   # Make a minimal .venv pre-commit stub