myagent-ai 1.0.0

package/skills/pdf/scripts/add_zai_metadata.py

@@ -0,0 +1,172 @@
+#!/usr/bin/env python3
+"""
+Add Z.ai branding metadata to PDF documents.
+
+This script adds Z.ai metadata (Author, Creator, Producer) to PDF files.
+It can process single files or batch process multiple PDFs.
+"""
+
+import os
+import sys
+import argparse
+from pypdf import PdfReader, PdfWriter
+
+
+def add_zai_metadata(input_pdf_path, output_pdf_path=None, custom_title=None, verbose=True):
+    """
+    Add Z.ai branding metadata to a PDF document.
+
+    Args:
+        input_pdf_path: Path to input PDF
+        output_pdf_path: Path to output PDF (default: overwrites input)
+        custom_title: Custom title to use (default: preserves original or uses filename)
+        verbose: Print status messages (default: True)
+
+    Sets:
+        - Author: Z.ai
+        - Creator: Z.ai
+        - Producer: http://z.ai
+        - Title: Custom title, original title, or filename (in that priority)
+
+    Returns:
+        Path to the output PDF file
+    """
+    # Validate input file exists
+    if not os.path.exists(input_pdf_path):
+        print(f"Error: Input file not found: {input_pdf_path}", file=sys.stderr)
+        sys.exit(1)
+
+    # Read the PDF
+    try:
+        reader = PdfReader(input_pdf_path)
+    except Exception as e:
+        print(f"Error: Cannot open PDF: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    writer = PdfWriter()
+
+    # Copy all pages
+    for page in reader.pages:
+        writer.add_page(page)
+
+    # Determine title
+    if custom_title:
+        title = custom_title
+    else:
+        original_meta = reader.metadata
+        if original_meta and original_meta.title and original_meta.title not in ['(anonymous)', 'unspecified', None]:
+            title = original_meta.title
+        else:
+            # Use filename without extension as title
+            title = os.path.splitext(os.path.basename(input_pdf_path))[0]
+
+    # Add Z.ai metadata
+    writer.add_metadata({
+        '/Title': title,
+        '/Author': 'Z.ai',
+        '/Creator': 'Z.ai',
+        '/Producer': 'http://z.ai',
+    })
+
+    # Write output
+    if output_pdf_path is None:
+        output_pdf_path = input_pdf_path
+
+    try:
+        with open(output_pdf_path, "wb") as output:
+            writer.write(output)
+    except Exception as e:
+        print(f"Error: Cannot write output file: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    # Print status
+    if verbose:
+        print(f"✓ Updated metadata for: {os.path.basename(input_pdf_path)}")
+        print(f"  Title: {title}")
+        print(f"  Author: Z.ai")
+        print(f"  Creator: Z.ai")
+        print(f"  Producer: http://z.ai")
+        if output_pdf_path != input_pdf_path:
+            print(f"  Output: {output_pdf_path}")
+
+    return output_pdf_path
+
+
+def main():
+    """Command-line interface for add_zai_metadata."""
+    parser = argparse.ArgumentParser(
+        description='Add Z.ai branding metadata to PDF documents',
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+  # Add metadata to a single PDF (in-place)
+  %(prog)s document.pdf
+
+  # Add metadata to a single PDF (create new file)
+  %(prog)s input.pdf -o output.pdf
+
+  # Add metadata with custom title
+  %(prog)s report.pdf -t "Q4 Financial Analysis"
+
+  # Batch process all PDFs in current directory
+  %(prog)s *.pdf
+
+  # Quiet mode (no output)
+  %(prog)s document.pdf -q
+        """
+    )
+
+    parser.add_argument(
+        'input',
+        nargs='+',
+        help='Input PDF file(s) to process'
+    )
+
+    parser.add_argument(
+        '-o', '--output',
+        help='Output PDF path (only for single input file)'
+    )
+
+    parser.add_argument(
+        '-t', '--title',
+        help='Custom title for the PDF'
+    )
+
+    parser.add_argument(
+        '-q', '--quiet',
+        action='store_true',
+        help='Quiet mode (no status messages)'
+    )
+
+    args = parser.parse_args()
+
+    # Check if output is specified for multiple files
+    if args.output and len(args.input) > 1:
+        print("Error: --output can only be used with a single input file", file=sys.stderr)
+        sys.exit(1)
+
+    # Process each input file
+    for input_path in args.input:
+        # Determine output path
+        if len(args.input) == 1 and args.output:
+            output_path = args.output
+        else:
+            output_path = None  # Overwrite in-place
+
+        # Determine title
+        if args.title:
+            custom_title = args.title
+        else:
+            custom_title = None
+
+        # Add metadata
+        add_zai_metadata(
+            input_path,
+            output_pdf_path=output_path,
+            custom_title=custom_title,
+            verbose=not args.quiet
+        )
+
+
+if __name__ == '__main__':
+    main()

package/skills/pdf/scripts/check_bounding_boxes.py

@@ -0,0 +1,70 @@
+from dataclasses import dataclass
+import json
+import sys
+
+
+# Script to check that the `fields.json` file that GLM creates when analyzing PDFs
+# does not have overlapping bounding boxes. See forms.md.
+
+
+@dataclass
+class RectAndField:
+    rect: list[float]
+    rect_type: str
+    field: dict
+
+
+# Returns a list of messages that are printed to stdout for GLM to read.
+def get_bounding_box_messages(fields_json_stream) -> list[str]:
+    messages = []
+    fields = json.load(fields_json_stream)
+    messages.append(f"Read {len(fields['form_fields'])} fields")
+
+    def rects_intersect(r1, r2):
+        disjoint_horizontal = r1[0] >= r2[2] or r1[2] <= r2[0]
+        disjoint_vertical = r1[1] >= r2[3] or r1[3] <= r2[1]
+        return not (disjoint_horizontal or disjoint_vertical)
+
+    rects_and_fields = []
+    for f in fields["form_fields"]:
+        rects_and_fields.append(RectAndField(f["label_bounding_box"], "label", f))
+        rects_and_fields.append(RectAndField(f["entry_bounding_box"], "entry", f))
+
+    has_error = False
+    for i, ri in enumerate(rects_and_fields):
+        # This is O(N^2); we can optimize if it becomes a problem.
+        for j in range(i + 1, len(rects_and_fields)):
+            rj = rects_and_fields[j]
+            if ri.field["page_number"] == rj.field["page_number"] and rects_intersect(ri.rect, rj.rect):
+                has_error = True
+                if ri.field is rj.field:
+                    messages.append(f"FAILURE: intersection between label and entry bounding boxes for `{ri.field['description']}` ({ri.rect}, {rj.rect})")
+                else:
+                    messages.append(f"FAILURE: intersection between {ri.rect_type} bounding box for `{ri.field['description']}` ({ri.rect}) and {rj.rect_type} bounding box for `{rj.field['description']}` ({rj.rect})")
+                if len(messages) >= 20:
+                    messages.append("Aborting further checks; fix bounding boxes and try again")
+                    return messages
+        if ri.rect_type == "entry":
+            if "entry_text" in ri.field:
+                font_size = ri.field["entry_text"].get("font_size", 14)
+                entry_height = ri.rect[3] - ri.rect[1]
+                if entry_height < font_size:
+                    has_error = True
+                    messages.append(f"FAILURE: entry bounding box height ({entry_height}) for `{ri.field['description']}` is too short for the text content (font size: {font_size}). Increase the box height or decrease the font size.")
+                    if len(messages) >= 20:
+                        messages.append("Aborting further checks; fix bounding boxes and try again")
+                        return messages
+
+    if not has_error:
+        messages.append("SUCCESS: All bounding boxes are valid")
+    return messages
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: check_bounding_boxes.py [fields.json]")
+        sys.exit(1)
+    # Input file should be in the `fields.json` format described in forms.md.
+    with open(sys.argv[1]) as f:
+        messages = get_bounding_box_messages(f)
+    for msg in messages:
+        print(msg)

package/skills/pdf/scripts/check_bounding_boxes_test.py

@@ -0,0 +1,226 @@
+import unittest
+import json
+import io
+from check_bounding_boxes import get_bounding_box_messages
+
+
+# Currently this is not run automatically in CI; it's just for documentation and manual checking.
+class TestGetBoundingBoxMessages(unittest.TestCase):
+    
+    def create_json_stream(self, data):
+        """Helper to create a JSON stream from data"""
+        return io.StringIO(json.dumps(data))
+    
+    def test_no_intersections(self):
+        """Test case with no bounding box intersections"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [60, 10, 150, 30]
+                },
+                {
+                    "description": "Email",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 40, 50, 60],
+                    "entry_bounding_box": [60, 40, 150, 60]
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("SUCCESS" in msg for msg in messages))
+        self.assertFalse(any("FAILURE" in msg for msg in messages))
+    
+    def test_label_entry_intersection_same_field(self):
+        """Test intersection between label and entry of the same field"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 60, 30],
+                    "entry_bounding_box": [50, 10, 150, 30]  # Overlaps with label
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("FAILURE" in msg and "intersection" in msg for msg in messages))
+        self.assertFalse(any("SUCCESS" in msg for msg in messages))
+    
+    def test_intersection_between_different_fields(self):
+        """Test intersection between bounding boxes of different fields"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [60, 10, 150, 30]
+                },
+                {
+                    "description": "Email",
+                    "page_number": 1,
+                    "label_bounding_box": [40, 20, 80, 40],  # Overlaps with Name's boxes
+                    "entry_bounding_box": [160, 10, 250, 30]
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("FAILURE" in msg and "intersection" in msg for msg in messages))
+        self.assertFalse(any("SUCCESS" in msg for msg in messages))
+    
+    def test_different_pages_no_intersection(self):
+        """Test that boxes on different pages don't count as intersecting"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [60, 10, 150, 30]
+                },
+                {
+                    "description": "Email",
+                    "page_number": 2,
+                    "label_bounding_box": [10, 10, 50, 30],  # Same coordinates but different page
+                    "entry_bounding_box": [60, 10, 150, 30]
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("SUCCESS" in msg for msg in messages))
+        self.assertFalse(any("FAILURE" in msg for msg in messages))
+    
+    def test_entry_height_too_small(self):
+        """Test that entry box height is checked against font size"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [60, 10, 150, 20],  # Height is 10
+                    "entry_text": {
+                        "font_size": 14  # Font size larger than height
+                    }
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("FAILURE" in msg and "height" in msg for msg in messages))
+        self.assertFalse(any("SUCCESS" in msg for msg in messages))
+    
+    def test_entry_height_adequate(self):
+        """Test that adequate entry box height passes"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [60, 10, 150, 30],  # Height is 20
+                    "entry_text": {
+                        "font_size": 14  # Font size smaller than height
+                    }
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("SUCCESS" in msg for msg in messages))
+        self.assertFalse(any("FAILURE" in msg for msg in messages))
+    
+    def test_default_font_size(self):
+        """Test that default font size is used when not specified"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [60, 10, 150, 20],  # Height is 10
+                    "entry_text": {}  # No font_size specified, should use default 14
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("FAILURE" in msg and "height" in msg for msg in messages))
+        self.assertFalse(any("SUCCESS" in msg for msg in messages))
+    
+    def test_no_entry_text(self):
+        """Test that missing entry_text doesn't cause height check"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [60, 10, 150, 20]  # Small height but no entry_text
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("SUCCESS" in msg for msg in messages))
+        self.assertFalse(any("FAILURE" in msg for msg in messages))
+    
+    def test_multiple_errors_limit(self):
+        """Test that error messages are limited to prevent excessive output"""
+        fields = []
+        # Create many overlapping fields
+        for i in range(25):
+            fields.append({
+                "description": f"Field{i}",
+                "page_number": 1,
+                "label_bounding_box": [10, 10, 50, 30],  # All overlap
+                "entry_bounding_box": [20, 15, 60, 35]   # All overlap
+            })
+        
+        data = {"form_fields": fields}
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        # Should abort after ~20 messages
+        self.assertTrue(any("Aborting" in msg for msg in messages))
+        # Should have some FAILURE messages but not hundreds
+        failure_count = sum(1 for msg in messages if "FAILURE" in msg)
+        self.assertGreater(failure_count, 0)
+        self.assertLess(len(messages), 30)  # Should be limited
+    
+    def test_edge_touching_boxes(self):
+        """Test that boxes touching at edges don't count as intersecting"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [50, 10, 150, 30]  # Touches at x=50
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("SUCCESS" in msg for msg in messages))
+        self.assertFalse(any("FAILURE" in msg for msg in messages))
+    
+
+if __name__ == '__main__':
+    unittest.main()

package/skills/pdf/scripts/check_fillable_fields.py

@@ -0,0 +1,12 @@
+import sys
+from pypdf import PdfReader
+
+
+# Script for GLM to run to determine whether a PDF has fillable form fields. See forms.md.
+
+
+reader = PdfReader(sys.argv[1])
+if (reader.get_fields()):
+    print("This PDF has fillable form fields")
+else:
+    print("This PDF does not have fillable form fields; you will need to visually determine where to enter data")

package/skills/pdf/scripts/convert_pdf_to_images.py

@@ -0,0 +1,35 @@
+import os
+import sys
+
+from pdf2image import convert_from_path
+
+
+# Converts each page of a PDF to a PNG image.
+
+
+def convert(pdf_path, output_dir, max_dim=1000):
+    images = convert_from_path(pdf_path, dpi=200)
+
+    for i, image in enumerate(images):
+        # Scale image if needed to keep width/height under `max_dim`
+        width, height = image.size
+        if width > max_dim or height > max_dim:
+            scale_factor = min(max_dim / width, max_dim / height)
+            new_width = int(width * scale_factor)
+            new_height = int(height * scale_factor)
+            image = image.resize((new_width, new_height))
+        
+        image_path = os.path.join(output_dir, f"page_{i+1}.png")
+        image.save(image_path)
+        print(f"Saved page {i+1} as {image_path} (size: {image.size})")
+
+    print(f"Converted {len(images)} pages to PNG images")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 3:
+        print("Usage: convert_pdf_to_images.py [input pdf] [output directory]")
+        sys.exit(1)
+    pdf_path = sys.argv[1]
+    output_directory = sys.argv[2]
+    convert(pdf_path, output_directory)

package/skills/pdf/scripts/create_validation_image.py

@@ -0,0 +1,41 @@
+import json
+import sys
+
+from PIL import Image, ImageDraw
+
+
+# Creates "validation" images with rectangles for the bounding box information that
+# GLM creates when determining where to add text annotations in PDFs. See forms.md.
+
+
+def create_validation_image(page_number, fields_json_path, input_path, output_path):
+    # Input file should be in the `fields.json` format described in forms.md.
+    with open(fields_json_path, 'r') as f:
+        data = json.load(f)
+
+        img = Image.open(input_path)
+        draw = ImageDraw.Draw(img)
+        num_boxes = 0
+        
+        for field in data["form_fields"]:
+            if field["page_number"] == page_number:
+                entry_box = field['entry_bounding_box']
+                label_box = field['label_bounding_box']
+                # Draw red rectangle over entry bounding box and blue rectangle over the label.
+                draw.rectangle(entry_box, outline='red', width=2)
+                draw.rectangle(label_box, outline='blue', width=2)
+                num_boxes += 2
+        
+        img.save(output_path)
+        print(f"Created validation image at {output_path} with {num_boxes} bounding boxes")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 5:
+        print("Usage: create_validation_image.py [page number] [fields.json file] [input image path] [output image path]")
+        sys.exit(1)
+    page_number = int(sys.argv[1])
+    fields_json_path = sys.argv[2]
+    input_image_path = sys.argv[3]
+    output_image_path = sys.argv[4]
+    create_validation_image(page_number, fields_json_path, input_image_path, output_image_path)