refactor: Update diff processing limits and improve frontend submodule synchronization comments

Author: rostilos

deployment/build/production-build.sh

@@ -11,20 +11,20 @@ CONFIG_PATH="deployment/config"
 
 cd "$(dirname "$0")/../../"
 
-echo "--- 1. Ensuring frontend submodule is synchronized ---"
-if [ -d "$FRONTEND_DIR" ] && [ ! -f "$FRONTEND_DIR/.git" ]; then
-   echo "Stale frontend directory detected (not a submodule). Removing and re-initializing..."
-   rm -rf "$FRONTEND_DIR"
-   git submodule update --init -- "$FRONTEND_DIR"
-elif [ ! -d "$FRONTEND_DIR" ]; then
-   echo "Initializing frontend submodule..."
-   git submodule update --init -- "$FRONTEND_DIR"
-else
-   echo "Frontend submodule exists."
-fi
-echo "Fetching latest from origin and resetting to origin/$FRONTEND_BRANCH..."
-(cd "$FRONTEND_DIR" && git fetch origin "$FRONTEND_BRANCH" && git reset --hard "origin/$FRONTEND_BRANCH")
-echo "Frontend at: $(cd "$FRONTEND_DIR" && git log --oneline -1)"
+# echo "--- 1. Ensuring frontend submodule is synchronized ---"
+# if [ -d "$FRONTEND_DIR" ] && [ ! -f "$FRONTEND_DIR/.git" ]; then
+#    echo "Stale frontend directory detected (not a submodule). Removing and re-initializing..."
+#    rm -rf "$FRONTEND_DIR"
+#    git submodule update --init -- "$FRONTEND_DIR"
+# elif [ ! -d "$FRONTEND_DIR" ]; then
+#    echo "Initializing frontend submodule..."
+#    git submodule update --init -- "$FRONTEND_DIR"
+# else
+#    echo "Frontend submodule exists."
+# fi
+# echo "Fetching latest from origin and resetting to origin/$FRONTEND_BRANCH..."
+# (cd "$FRONTEND_DIR" && git fetch origin "$FRONTEND_BRANCH" && git reset --hard "origin/$FRONTEND_BRANCH")
+# echo "Frontend at: $(cd "$FRONTEND_DIR" && git log --oneline -1)"
 
 echo "--- 2. Injecting Environment Configurations ---"
 

deployment/config/inference-orchestrator/.env.sample

@@ -44,11 +44,11 @@ SERVICE_SECRET=change-me-to-a-random-secret
 # Maximum file size in bytes (default: 25KB - same as LargeContentFilter.DEFAULT_SIZE_THRESHOLD_BYTES)
 # DIFF_MAX_FILE_SIZE=25600
 # Maximum files to include in review (default: 100)
-# DIFF_MAX_FILES=100
-# Maximum total diff size in bytes (default: 500KB)
-# DIFF_MAX_TOTAL_SIZE=500000
+# DIFF_MAX_FILES=400
+# Maximum total diff size in bytes (default: 1MB)
+# DIFF_MAX_TOTAL_SIZE=1000000
 # Maximum lines per file (default: 1000)
-# DIFF_MAX_LINES_PER_FILE=1000
+# DIFF_MAX_LINES_PER_FILE=3000
 
 # === LLM Reranking (for large PRs) ===
 # Enable LLM-based reranking for large PRs

python-ecosystem/inference-orchestrator/utils/diff_processor.py

@@ -22,9 +22,9 @@
 DEFAULT_FILE_SIZE_THRESHOLD_BYTES = 25 * 1024  # 25KB - same as LargeContentFilter.DEFAULT_SIZE_THRESHOLD_BYTES
 
 MAX_FILE_SIZE_BYTES = int(os.environ.get("DIFF_MAX_FILE_SIZE", str(DEFAULT_FILE_SIZE_THRESHOLD_BYTES)))
-MAX_FILES_IN_DIFF = int(os.environ.get("DIFF_MAX_FILES", "100"))  # Maximum files to process
-MAX_DIFF_SIZE_BYTES = int(os.environ.get("DIFF_MAX_TOTAL_SIZE", "500000"))  # 500KB total diff size
-MAX_LINES_PER_FILE = int(os.environ.get("DIFF_MAX_LINES_PER_FILE", "1000"))  # Maximum lines per file
+MAX_FILES_IN_DIFF = int(os.environ.get("DIFF_MAX_FILES", "400"))  # Maximum files to process
+MAX_DIFF_SIZE_BYTES = int(os.environ.get("DIFF_MAX_TOTAL_SIZE", "1000000"))  # 1MB total diff size
+MAX_LINES_PER_FILE = int(os.environ.get("DIFF_MAX_LINES_PER_FILE", "3000"))  # Maximum lines per file
 
 # Placeholder message matching LargeContentFilter.FILTERED_PLACEHOLDER
 FILTERED_PLACEHOLDER = "[CodeCrow Filter: file too large (>25KB), omitted from analysis]"