The Complete Production SOP: How to Deploy and Run python-docx Legal Contract Builder in Autonomous AI Agents

---
name: "python-docx-contract-builder"
description: "Generate and populate professional Word contracts and agreements with python-docx."
metadata:
  author: "python-openxml"
  version: "1.0.0"
  runtime_compatibility:
    - "codex"
    - "claude-code"
    - "cursor"
    - "windsurf"
triggers:
  - "generate word contract python"
  - "replace variables in docx template"
  - "style table in python-docx"
permissions:
  fs_read: true
  fs_write: "workspace"
  shell_exec: false
  net_access: false
---

# python-docx Legal Contract Builder Rules
1. Always initialize documents using an existing template `doc = Document('templates/master_contract.docx')` to preserve OpenXML style schemas.
2. When performing placeholder replacement, join paragraph runs before inspection to prevent split-run token dropouts.
3. Format financial and indemnification tables with explicit column widths on each cell, setting `cantSplit` on table rows.
4. Save files to the target workspace path and verify generated binary headers.

from docx import Document

def replace_placeholders_in_paragraph(paragraph, replacements: dict[str, str]) -> None:
    full_text = "".join(run.text for run in paragraph.runs)
    for placeholder, value in replacements.items():
        if placeholder in full_text:
            full_text = full_text.replace(placeholder, value)
            # Consolidate text into the first run and clear subsequent runs to preserve style
            if paragraph.runs:
                paragraph.runs[0].text = full_text
                for run in paragraph.runs[1:]:
                    run.text = ""

def replace_in_document(doc: Document, replacements: dict[str, str]) -> None:
    for p in doc.paragraphs:
        replace_placeholders_in_paragraph(p, replacements)
    for table in doc.tables:
        for row in table.rows:
            for cell in row.cells:
                for p in cell.paragraphs:
                    replace_placeholders_in_paragraph(p, replacements)

from docx import Document
from docx.shared import Inches, Pt, RGBColor
from docx.enum.text import WD_ALIGN_PARAGRAPH
from scripts.docx_contract_utils import replace_in_document

def generate_nda(output_path: str, context: dict):
    doc = Document()
    
    # Establish Title
    title = doc.add_paragraph()
    title.alignment = WD_ALIGN_PARAGRAPH.CENTER
    run = title.add_run("MUTUAL NONDISCLOSURE AGREEMENT")
    run.font.size = Pt(14)
    run.font.bold = True
    
    # Add Standard Clauses
    p1 = doc.add_paragraph("This Agreement is entered into as of {{EFFECTIVE_DATE}} by and between:")
    
    # Add Parties Table
    table = doc.add_table(rows=2, cols=2)
    table.style = 'Table Grid'
    table.rows[0].cells[0].text = "Disclosing Party: {{DISCLOSING_PARTY}}"
    table.rows[0].cells[1].text = "Receiving Party: {{RECEIVING_PARTY}}"
    
    # Replace Variables
    replace_in_document(doc, context)
    doc.save(output_path)

if __name__ == "__main__":
    generate_nda("workspace/NDA_Final.docx", {
        "{{EFFECTIVE_DATE}}": "October 24, 2026",
        "{{DISCLOSING_PARTY}}": "Acme Corp",
        "{{RECEIVING_PARTY}}": "Global Tech LLC"
    })

#!/usr/bin/env bash
set -euo pipefail

TARGET_DOC="workspace/NDA_Final.docx"

if [ ! -f "$TARGET_DOC" ]; then
  echo "ERROR: Artifact $TARGET_DOC not found!" >&2
  exit 1
fi

# Inspect OpenXML package for residual unresolved template variables
python - <<EOF
import zipfile, sys
with zipfile.ZipFile('$TARGET_DOC') as z:
    content = z.read('word/document.xml').decode('utf-8')
    if '{{' in content or '}}' in content:
        print('CRITICAL: Residual {{placeholder}} found in final contract document!')
        sys.exit(1)
    print('Verification SUCCESS: No orphaned placeholders detected.')
EOF