# === BULK_FILE_IMPORT TOOL ===
echo ""
echo "=== bulk_file_import Tool ==="
echo ""
# Create test CSV
CSV_FILE="/tmp/test_bulk_import_$$.csv"
LOG_FILE="/tmp/test_bulk_import_$$.log"
cat > "$CSV_FILE" << EOF
location_name,location_id,directory_path,date_range,sample_rate,file_count
Test Location,$LOCATION_ID,/nonexistent/path,2024-01,250000,0
EOF
echo "Created test CSV: $CSV_FILE"
# Test 5: Non-existent CSV
echo ""
echo "Test 5: Non-existent CSV file (should fail)"
result=$(send_request "tools/call" '{"name":"bulk_file_import","arguments":{"dataset_id":"'"$DATASET_ID"'","csv_path":"/nonexistent/file.csv","log_file_path":"/tmp/test.log"}}' "$DB_PATH")
run_test "Reject non-existent CSV" "false" "$result"
# Test 6: Invalid dataset ID
echo ""
echo "Test 6: Invalid dataset_id for bulk import (should fail)"
result=$(send_request "tools/call" '{"name":"bulk_file_import","arguments":{"dataset_id":"INVALID123456","csv_path":"'"$CSV_FILE"'","log_file_path":"'"$LOG_FILE"'"}}' "$DB_PATH")
run_test "Reject invalid dataset_id" "false" "$result"
# Test 7: Valid CSV but nonexistent directories (tests CSV parsing)
echo ""
echo "Test 7: Valid CSV parsing (directory errors expected)"
result=$(send_request "tools/call" '{"name":"bulk_file_import","arguments":{"dataset_id":"'"$DATASET_ID"'","csv_path":"'"$CSV_FILE"'","log_file_path":"'"$LOG_FILE"'"}}' "$DB_PATH")
# This will fail because directory doesn't exist, but CSV parsing should work
is_err=$(echo "$result" | jq -r '.result.isError // false')
if [ "$is_err" = "true" ]; then
    # Check if it's a directory error (expected) vs CSV parsing error
    error_msg=$(echo "$result" | jq -r '.result.content[0].text // ""')
    if echo "$error_msg" | grep -qi "directory\|not found\|no such"; then
        echo -e "${GREEN}✓${NC} CSV parsed correctly, directory error expected"
        ((TESTS_RUN++))
        ((TESTS_PASSED++))
    else
        echo -e "${YELLOW}⚠${NC} Unexpected error: $error_msg"
        ((TESTS_RUN++))
        ((TESTS_PASSED++))
    fi
else
    echo -e "${GREEN}✓${NC} Bulk import executed"
    ((TESTS_RUN++))
    ((TESTS_PASSED++))
fi
# Cleanup
rm -f "$CSV_FILE" "$LOG_FILE"

# Test 8: Non-existent folder
echo "Test 8: Non-existent folder (should fail)"

# Test 5: Non-existent folder
echo "Test 5: Non-existent folder (should fail)"

# Test 9: Invalid location ID

# Test 6: Invalid location ID

echo "Test 9: Invalid location_id (should fail)"

echo "Test 6: Invalid location_id (should fail)"

echo ""
echo "For bulk import, use the CLI tool:"
echo "  skraak import bulk --db ./db/skraak.duckdb --dataset abc123 --csv import.csv --log progress.log"

- **Import tools (4)**: `import_audio_files`, `import_audio_file`, `import_ml_selections`, `bulk_file_import`

- **Import tools (3)**: `import_audio_files`, `import_audio_file`, `import_ml_selections`

	mcp.AddTool(server, &mcp.Tool{
		Name:        "bulk_file_import",
		Description: "Batch import WAV files across multiple locations/clusters using a CSV file. CSV must have columns (in order): location_name, location_id, directory_path, date_range, sample_rate, file_count. Auto-creates clusters using date_range as cluster name. Logs progress to file for monitoring. Synchronous/fail-fast execution.",
	}, mcpBulkFileImport)

func mcpBulkFileImport(ctx context.Context, req *mcp.CallToolRequest, input tools.BulkFileImportInput) (*mcp.CallToolResult, tools.BulkFileImportOutput, error) {
	output, err := tools.BulkFileImport(ctx, input)
	return &mcp.CallToolResult{}, output, err
}

- `bulk_file_import` - Bulk import from CSV across multiple locations

6. **test_bulk_import.sh [db_path]** - Tests bulk_file_import tool (CSV-based bulk import)

7. **test_resources_prompts.sh [db_path]** - Tests resources and prompts
8. **test_all_prompts.sh [db_path]** - Tests all 6 prompts

6. **test_resources_prompts.sh [db_path]** - Tests resources and prompts
7. **test_all_prompts.sh [db_path]** - Tests all 6 prompts

- `bulk_file_import` - Batch import WAV files across multiple locations/clusters using CSV
  - **Input**: CSV file (see format below)
  - **Auto-creates clusters**: Creates clusters if they don't exist for location/date_range combinations
  - **Progress logging**: Writes detailed progress to log file for real-time monitoring (use `tail -f`)
  - **Synchronous execution**: Processes locations sequentially, fail-fast on errors
  - **Summary statistics**: Returns counts for clusters, files, duplicates, errors
  - **Duplicate handling**: Skips files with duplicate hashes across all clusters
  - **Use cases**: Bulk import across many locations, automated pipelines, large-scale migration
  **CSV Format:**
  - **Header required:** First row must contain column names
  - **Columns (in order):**
    1. `location_name` - Human-readable location name (string, can have spaces)
    2. `location_id` - 12-character location ID from database (must exist)
    3. `directory_path` - Absolute path to folder containing WAV files
    4. `date_range` - Cluster name (e.g., "20240101-20240107" or any string)
    5. `sample_rate` - Sample rate in Hz (integer, e.g., 8000, 48000, 250000)
    6. `file_count` - Expected file count (integer, informational only)
  
  **Important:**
  - `date_range` becomes the cluster name in the database
  - If cluster already exists for location+date_range, it will be reused
  - All `location_id` values must exist in the database (use `execute_sql` to query)
  - Paths should be absolute (relative paths may fail)
  
  **Example CSV:**
  ```csv
  location_name,location_id,directory_path,date_range,sample_rate,file_count
  "MOK RW 05","Ucfh8ng4DuEa","/media/david/Data/MOK RW 05","20240706-20240714","8000","432"
  "MOK RW 06","rDmmSPsJvNtD","/media/david/Data/MOK RW 06","20240706-20240714","8000","432"
  "mokas__01","EsDkvXosAp4C","/media/david/Data/mokas__01","20240520-20240528","8000","432"
  ```
  
  **Tool Call Example:**
  ```json
  {
    "name": "bulk_file_import",
    "arguments": {
      "dataset_id": "abc123xyz789",
      "csv_path": "/path/to/import.csv",
      "log_file_path": "/path/to/progress.log"
    }
  }
  ```