Upload app.py

app.py

@@ -6,6 +6,9 @@ Features:
   • 4-tier risk scoring (Critical / High / Medium / Low)
   • Legal NER: parties, dates, monetary values, jurisdictions, defined terms
   • NLI contradiction & missing-clause detection
+  • Contract comparison engine (diff between 2 contracts)
+  • Obligation tracker (monetary, compliance, reporting, delivery)
+  • Compliance checker (GDPR, CCPA, SOX, HIPAA, FINRA)
   • PDF / DOCX / TXT parsing
   • Professional 3-panel Gradio UI
   • JSON & CSV export
@@ -20,7 +23,6 @@ import re
 import json
 import csv
 import io
-import textwrap
 from collections import defaultdict
 from datetime import datetime
 
@@ -49,6 +51,11 @@ try:
 except Exception:
     _HAS_TORCH = False
 
+# ── Import submodules ───────────────────────────────────────────────
+from compare import compare_contracts, render_comparison_html
+from obligations import extract_obligations, render_obligations_html
+from compliance import check_compliance, render_compliance_html
+
 # ═══════════════════════════════════════════════════════════════════════
 # 1. CONFIGURATION
 # ═══════════════════════════════════════════════════════════════════════
@@ -70,7 +77,6 @@ CUAD_LABELS = [
     "Third Party Beneficiary", "Other"
 ]
 
-# Original 8 unfair-clause labels (backward-compat + consumer contracts)
 _UNFAIR_LABELS = [
     "Limitation of liability", "Unilateral termination", "Unilateral change",
     "Content removal", "Contract by using", "Choice of law",
@@ -87,6 +93,7 @@ RISK_MAP = {
     "Termination for Convenience": "CRITICAL",
     "Limitation of liability": "CRITICAL",
     "Unilateral termination": "CRITICAL",
+    "Liquidated Damages": "CRITICAL",
     # High
     "Non-Compete": "HIGH",
     "Exclusivity": "HIGH",
@@ -95,7 +102,6 @@ RISK_MAP = {
     "No-Solicit of Employees": "HIGH",
     "Unilateral change": "HIGH",
     "Content removal": "HIGH",
-    "Liquidated Damages": "HIGH",
     "Anti-Assignment": "HIGH",
     # Medium
     "Governing Law": "MEDIUM",
@@ -107,6 +113,7 @@ RISK_MAP = {
     "Non-Disparagement": "MEDIUM",
     "Most Favored Nation": "MEDIUM",
     "Revenue/Profit Sharing": "MEDIUM",
+    "Warranty Duration": "MEDIUM",
     # Low
     "Document Name": "LOW",
     "Parties": "LOW",
@@ -125,7 +132,6 @@ RISK_MAP = {
     "Post-Termination Services": "LOW",
     "Audit Rights": "LOW",
     "Cap on Liability": "LOW",
-    "Warranty Duration": "LOW",
     "Insurance": "LOW",
     "Covenant Not to Sue": "LOW",
     "Third Party Beneficiary": "LOW",
@@ -162,12 +168,19 @@ DESC_MAP.update({
     "Warranty Duration": "Length of time warranties remain in effect.",
     "Covenant Not to Sue": "Agreement not to bring legal action against a party.",
     "Third Party Beneficiary": "Non-party who benefits from the contract terms.",
+    "Insurance": "Insurance coverage requirements.",
+    "Revenue/Profit Sharing": "Revenue or profit sharing arrangements between parties.",
+    "Price Restriction": "Restrictions on pricing or discounting.",
+    "Minimum Commitment": "Minimum purchase or usage commitment.",
+    "Volume Restriction": "Limits on volume of goods or services.",
+    "License Grant": "Permission to use intellectual property.",
+    "Non-Transferable License": "License that cannot be transferred to third parties.",
+    "Irrevocable or Perpetual License": "License that cannot be revoked or lasts indefinitely.",
+    "Unlimited/All-You-Can-Eat License": "License with no usage limits.",
 })
 
-# Risk weights for scoring
 RISK_WEIGHTS = {"CRITICAL": 40, "HIGH": 20, "MEDIUM": 10, "LOW": 3}
 
-# Color / badge styles
 RISK_STYLES = {
     "CRITICAL": ("#dc2626", "#fef2f2", "⚠️"),
     "HIGH":     ("#ea580c", "#fff7ed", "⚡"),
@@ -190,7 +203,6 @@ def _load_cuad_model():
     try:
         base = "nlpaueb/legal-bert-base-uncased"
         adapter = "Mokshith31/legalbert-contract-clause-classification"
-
         print(f"[ClauseGuard] Loading CUAD classifier: {adapter}")
         cuad_tokenizer = AutoTokenizer.from_pretrained(base)
         base_model = AutoModelForSequenceClassification.from_pretrained(
@@ -256,7 +268,6 @@ def parse_document(file_path):
 # ═══════════════════════════════════════════════════════════════════════
 
 def split_clauses(text):
-    """Split contract text into individual clauses."""
     text = re.sub(r'\n{3,}', '\n\n', text.strip())
     parts = re.split(
         r'(?<=[.!?])\s+(?=[A-Z0-9(])|(?:\n\n)(?=\d+[.)]\s|\([a-z]\)\s|[A-Z][A-Z\s]{2,})',
@@ -270,10 +281,8 @@ def split_clauses(text):
     return clauses
 
 def classify_cuad(clause_text):
-    """Classify a single clause using the CUAD model."""
     if cuad_model is None or cuad_tokenizer is None:
         return _classify_regex(clause_text)
-
     try:
         inputs = cuad_tokenizer(
             clause_text,
@@ -285,8 +294,6 @@ def classify_cuad(clause_text):
         with torch.no_grad():
             logits = cuad_model(**inputs).logits
         probs = torch.softmax(logits, dim=-1)[0]
-
-        # Multi-label: return all labels above threshold
         threshold = 0.15
         results = []
         for i, prob in enumerate(probs):
@@ -299,9 +306,7 @@ def classify_cuad(clause_text):
                     "risk": risk,
                     "description": DESC_MAP.get(label, label),
                 })
-        # Sort by confidence descending
         results.sort(key=lambda x: x["confidence"], reverse=True)
-        # If no labels above threshold, take top-1
         if not results:
             top_idx = int(probs.argmax())
             label = CUAD_LABELS[top_idx] if top_idx < len(CUAD_LABELS) else "Other"
@@ -332,6 +337,10 @@ _REGEX_PATTERNS = {
     "IP Ownership Assignment": [r"assign.*intellectual property", r"ownership of.*ip", r"all rights.*assign"],
     "Uncapped Liability": [r"unlimited liability", r"uncapped", r"no.*limit.*liability"],
     "Cap on Liability": [r"cap on liability", r"maximum liability", r"liability.*shall not exceed"],
+    "Indemnification": [r"indemnif", r"hold harmless", r"defend"],
+    "Confidentiality": [r"confidential", r"non-disclosure", r"nda"],
+    "Force Majeure": [r"force majeure", r"act of god", r"beyond.*control"],
+    "Penalties": [r"penalt", r"late fee", r"default charge", r"interest on overdue"],
 }
 
 def _classify_regex(text):
@@ -358,9 +367,7 @@ def _classify_regex(text):
 # ═══════════════════════════════════════════════════════════════════════
 
 def extract_entities(text):
-    """Extract legal entities using regex patterns."""
     entities = []
-
     # Dates
     date_patterns = [
         (r'\b(?:January|February|March|April|May|June|July|August|September|October|November|December)\s+\d{1,2},?\s+\d{4}\b', "DATE"),
@@ -371,7 +378,6 @@ def extract_entities(text):
     for pat, etype in date_patterns:
         for m in re.finditer(pat, text, re.IGNORECASE):
             entities.append({"text": m.group(), "type": etype, "start": m.start(), "end": m.end()})
-
     # Monetary values
     money_patterns = [
         (r'\$\d{1,3}(?:,\d{3})*(?:\.\d{2})?(?:\s*(?:million|billion|thousand|M|B|K))?', "MONEY"),
@@ -380,16 +386,14 @@ def extract_entities(text):
     for pat, etype in money_patterns:
         for m in re.finditer(pat, text, re.IGNORECASE):
             entities.append({"text": m.group(), "type": etype, "start": m.start(), "end": m.end()})
-
     # Party names
     party_patterns = [
         (r'\b[A-Z][A-Za-z0-9\s&]+(?:Inc\.|LLC|Ltd\.|Limited|Corp\.|Corporation|PLC|GmbH|AG|S\.A\.|B\.V\.)\b', "PARTY"),
-        (r'\b(?:Party A|Party B|Licensor|Licensee|Buyer|Seller|Tenant|Landlord|Employer|Employee|Company|Customer)\b', "PARTY_ROLE"),
+        (r'\b(?:Party A|Party B|Disclosing Party|Receiving Party|Licensor|Licensee|Buyer|Seller|Tenant|Landlord|Employer|Employee|Company|Customer|Vendor|Client)\b', "PARTY_ROLE"),
     ]
     for pat, etype in party_patterns:
         for m in re.finditer(pat, text):
             entities.append({"text": m.group(), "type": etype, "start": m.start(), "end": m.end()})
-
     # Jurisdictions
     jurisdiction_patterns = [
         (r'\b(?:State|Laws?) of [A-Z][a-zA-Z\s]+', "JURISDICTION"),
@@ -398,7 +402,6 @@ def extract_entities(text):
     for pat, etype in jurisdiction_patterns:
         for m in re.finditer(pat, text, re.IGNORECASE):
             entities.append({"text": m.group(), "type": etype, "start": m.start(), "end": m.end()})
-
     # Defined Terms
     defined_patterns = [
         (r'"([A-Z][A-Z\s]+)"', "DEFINED_TERM"),
@@ -407,8 +410,7 @@ def extract_entities(text):
     for pat, etype in defined_patterns:
         for m in re.finditer(pat, text):
             entities.append({"text": m.group(1), "type": etype, "start": m.start(), "end": m.end()})
-
-    # Deduplicate overlapping
+    # Deduplicate
     entities.sort(key=lambda x: (x["start"], -(x["end"] - x["start"])))
     filtered = []
     last_end = -1
@@ -434,16 +436,10 @@ _CONTRADICTION_PAIRS = [
 ]
 
 def detect_contradictions(clause_results):
-    """Detect contradictions and missing critical clauses."""
     contradictions = []
     labels_found = set()
-    texts_found = {}
-
     for cr in clause_results:
         labels_found.add(cr["label"])
-        texts_found[cr["label"]] = cr.get("text", "")
-
-    # Contradiction pairs
     for group_a, group_b, explanation in _CONTRADICTION_PAIRS:
         found_a = any(l in labels_found for l in group_a)
         found_b = any(l in labels_found for l in group_b)
@@ -454,8 +450,6 @@ def detect_contradictions(clause_results):
                 "severity": "HIGH",
                 "clauses": list(set(group_a + group_b)),
             })
-
-    # Missing critical clauses
     critical_clauses = ["Governing Law", "Termination for Convenience", "Limitation of liability", "Arbitration"]
     for cc in critical_clauses:
         if cc not in labels_found:
@@ -465,7 +459,6 @@ def detect_contradictions(clause_results):
                 "severity": "MEDIUM",
                 "clauses": [cc],
             })
-
     return contradictions
 
 # ═══════════════════════════════════════════════════════════════════════
@@ -477,19 +470,15 @@ def compute_risk_score(clause_results, total_clauses):
     for cr in clause_results:
         sev = cr.get("risk", "LOW")
         sev_counts[sev] += 1
-
     if total_clauses == 0:
         return 0, "A", sev_counts
-
     weighted = sum(sev_counts[s] * RISK_WEIGHTS[s] for s in sev_counts)
     risk = min(100, round(weighted / max(1, total_clauses) * 10))
-
     if risk >= 70: grade = "F"
     elif risk >= 50: grade = "D"
     elif risk >= 30: grade = "C"
     elif risk >= 15: grade = "B"
     else: grade = "A"
-
     return risk, grade, sev_counts
 
 # ═══════════════════════════════════════════════════════════════════════
@@ -499,12 +488,9 @@ def compute_risk_score(clause_results, total_clauses):
 def analyze_contract(text):
     if not text or len(text.strip()) < 50:
         return None, "Document too short (minimum 50 characters)"
-
     clauses = split_clauses(text)
     if not clauses:
         return None, "No clauses detected in document"
-
-    # Analyze each clause
     clause_results = []
     for clause in clauses:
         predictions = classify_cuad(clause)
@@ -517,17 +503,11 @@ def analyze_contract(text):
                     "risk": pred["risk"],
                     "description": pred["description"],
                 })
-
-    # NER
     entities = extract_entities(text)
-
-    # NLI / contradictions
     contradictions = detect_contradictions(clause_results)
-
-    # Risk scoring
     risk, grade, sev_counts = compute_risk_score(clause_results, len(clauses))
-
-    # Build result object
+    obligations = extract_obligations(text)
+    compliance = check_compliance(text)
     result = {
         "metadata": {
             "analysis_date": datetime.now().isoformat(),
@@ -543,9 +523,10 @@ def analyze_contract(text):
         "clauses": clause_results,
         "entities": entities,
         "contradictions": contradictions,
+        "obligations": obligations,
+        "compliance": compliance,
         "raw_text": text,
     }
-
     return result, None
 
 # ═══════════════════════════════════════════════════════════════════════
@@ -580,19 +561,15 @@ def export_csv(result):
 def render_summary(result):
     if result is None:
         return ""
-
     risk = result["risk"]
     score = risk["score"]
     grade = risk["grade"]
     breakdown = risk["breakdown"]
-
     grade_color = {
         "A": "#16a34a", "B": "#65a30d", "C": "#ca8a04",
         "D": "#ea580c", "F": "#dc2626",
     }.get(grade, "#6b7280")
-
     crit, high, med, low = breakdown["CRITICAL"], breakdown["HIGH"], breakdown["MEDIUM"], breakdown["LOW"]
-
     html = f"""
     <div style="font-family:system-ui,sans-serif;padding:16px;border:1px solid #e5e7eb;border-radius:12px;background:#fff;">
       <div style="text-align:center;margin-bottom:16px;">
@@ -631,35 +608,27 @@ def render_summary(result):
 def render_clause_cards(result):
     if result is None:
         return ""
-
     clauses = result.get("clauses", [])
     if not clauses:
         return '<div style="padding:24px;text-align:center;color:#6b7280;">No clauses detected.</div>'
-
-    # Group by clause text
     grouped = defaultdict(list)
     for cr in clauses:
         grouped[cr["text"]].append(cr)
-
     html = '<div style="font-family:system-ui,sans-serif;">'
     for text, items in grouped.items():
         max_risk = max(items, key=lambda x: {"CRITICAL":4,"HIGH":3,"MEDIUM":2,"LOW":1}[x["risk"]])["risk"]
         border, bg, icon = RISK_STYLES[max_risk]
-
         tags = ""
         for item in items:
             tag_bg = RISK_STYLES[item["risk"]][1]
             tag_color = RISK_STYLES[item["risk"]][0]
             tags += f'<span style="background:{tag_bg};color:{tag_color};border:1px solid {tag_color}33;padding:2px 8px;border-radius:12px;font-size:11px;font-weight:500;margin-right:4px;">{item["label"]} ({item["confidence"]})</span>'
-
         descs = "".join(
             f'<p style="font-size:12px;color:#6b7280;margin:4px 0 0 0;">{item["description"]}</p>'
             for item in items
         )
-
         preview = text[:300] + ("..." if len(text) > 300 else "")
         preview = preview.replace("<", "&lt;").replace(">", "&gt;")
-
         html += f"""
         <div style="border:1px solid #e5e7eb;border-left:4px solid {border};border-radius:8px;padding:14px;margin-bottom:10px;background:#fafafa;">
           <div style="display:flex;align-items:center;gap:6px;margin-bottom:6px;">
@@ -677,16 +646,12 @@ def render_clause_cards(result):
 def render_entities(result):
     if result is None:
         return ""
-
     entities = result.get("entities", [])
     if not entities:
         return '<div style="padding:16px;color:#6b7280;">No entities detected.</div>'
-
-    # Group by type
     grouped = defaultdict(list)
     for e in entities:
         grouped[e["type"]].append(e["text"])
-
     html = '<div style="font-family:system-ui,sans-serif;">'
     for etype, texts in grouped.items():
         unique = list(dict.fromkeys(texts))[:20]
@@ -697,12 +662,10 @@ def render_entities(result):
             "JURISDICTION": "#f59e0b",
             "DEFINED_TERM": "#ec4899",
         }.get(etype, "#6b7280")
-
         items_html = "".join(
             f'<span style="display:inline-block;background:{color}15;color:{color};border:1px solid {color}40;padding:3px 10px;border-radius:6px;font-size:12px;margin:3px;">{t}</span>'
             for t in unique
         )
-
         html += f"""
         <div style="margin-bottom:12px;">
           <div style="font-size:12px;font-weight:600;color:#374151;margin-bottom:6px;text-transform:uppercase;">{etype}</div>
@@ -715,11 +678,9 @@ def render_entities(result):
 def render_contradictions(result):
     if result is None:
         return ""
-
     contradictions = result.get("contradictions", [])
     if not contradictions:
         return '<div style="padding:16px;color:#16a34a;">✓ No contradictions or missing clauses detected.</div>'
-
     html = '<div style="font-family:system-ui,sans-serif;">'
     for c in contradictions:
         sev_color = RISK_STYLES[c["severity"]][0]
@@ -739,10 +700,8 @@ def render_contradictions(result):
 def render_document_viewer(result):
     if result is None:
         return ""
-
     text = result.get("raw_text", "")
     entities = sorted(result.get("entities", []), key=lambda x: x["start"])
-
     html_parts = []
     last_end = 0
     for e in entities:
@@ -760,10 +719,8 @@ def render_document_viewer(result):
                 f'<mark style="background:{color};padding:1px 2px;border-radius:2px;font-size:12px;" title="{label}">{e["text"].replace("<","&lt;").replace(">","&gt;")}</mark>'
             )
             last_end = e["end"]
-
     html_parts.append(text[last_end:].replace("<", "&lt;").replace(">", "&gt;"))
     highlighted = "".join(html_parts)
-
     return f"""
     <div style="font-family:monospace;font-size:13px;line-height:1.6;padding:16px;border:1px solid #e5e7eb;border-radius:8px;background:#fff;max-height:600px;overflow-y:auto;white-space:pre-wrap;">
       {highlighted}
@@ -771,7 +728,19 @@ def render_document_viewer(result):
     """
 
 # ═══════════════════════════════════════════════════════════════════════
-# 11. GRADIO UI
+# 11. COMPARISON UI FUNCTIONS
+# ═══════════════════════════════════════════════════════════════════════
+
+def run_comparison(text_a, text_b):
+    if not text_a or len(text_a.strip()) < 50:
+        return "Contract A is too short", ""
+    if not text_b or len(text_b.strip()) < 50:
+        return "Contract B is too short", ""
+    result = compare_contracts(text_a, text_b)
+    return render_comparison_html(result), json.dumps(result, indent=2)
+
+# ═══════════════════════════════════════════════════════════════════════
+# 12. GRADIO UI
 # ═══════════════════════════════════════════════════════════════════════
 
 def process_upload(file):
@@ -784,36 +753,35 @@ def process_upload(file):
 
 def run_analysis(text):
     if not text or len(text.strip()) < 50:
-        return [""] * 5 + [None, None, "Document too short (minimum 50 characters)"]
-
+        err_html = '<p style="color:#dc2626;padding:16px;">Document too short (minimum 50 characters)</p>'
+        return [err_html] * 7 + [None, None, ""]
     result, error = analyze_contract(text)
     if error:
         err_html = f'<p style="color:#dc2626;padding:16px;">{error}</p>'
-        return [err_html] * 5 + [None, None, error]
-
+        return [err_html] * 7 + [None, None, error]
     # Save export files
     json_path = "/tmp/clauseguard_report.json"
     with open(json_path, "w") as f:
         json.dump(result, f, indent=2, default=str)
-
     csv_content = export_csv(result)
     csv_path = "/tmp/clauseguard_report.csv"
     with open(csv_path, "w") as f:
         f.write(csv_content)
-
     return [
         render_summary(result),
         render_clause_cards(result),
         render_entities(result),
         render_contradictions(result),
         render_document_viewer(result),
+        render_obligations_html(result.get("obligations", [])),
+        render_compliance_html(result.get("compliance", {})),
         json_path,
         csv_path,
         "Analysis complete",
     ]
 
 def do_clear():
-    return [""] * 5 + [None, None, ""]
+    return [""] * 7 + [None, None, ""]
 
 # ── Example contracts ──
 SPOTIFY_TOS = """By using the Spotify Service, you agree to be bound by these Terms of Use.
@@ -858,10 +826,42 @@ This Non-Disclosure Agreement (the "Agreement") is entered into as of January 15
 
 7. Non-Compete. During the term of this Agreement and for a period of two (2) years thereafter, the Receiving Party shall not engage in any business that competes with the Disclosing Party."""
 
+COMPLEX_CONTRACT = """MASTER SERVICE AGREEMENT
+
+This Master Service Agreement ("MSA") is entered into as of March 1, 2024 (the "Effective Date") by and between CloudTech Solutions, Inc., a Delaware corporation ("Provider") and Global Retail Partners LLC, a New York limited liability company ("Customer").
+
+1. SERVICES. Provider shall provide cloud hosting and data processing services as described in Exhibit A. Provider shall comply with all applicable laws including GDPR and CCPA.
+
+2. TERM AND RENEWAL. The initial term is twelve (12) months, automatically renewing for successive one (1) year periods unless terminated in accordance with Section 7.
+
+3. FEES AND PAYMENT. Customer shall pay a monthly fee of $25,000 within 30 days of invoice. Late payments incur a penalty of 1.5% per month. The total contract value is $300,000.
+
+4. LIABILITY. Provider's aggregate liability shall not exceed $1,000,000. IN NO EVENT SHALL PROVIDER BE LIABLE FOR LOST PROFITS OR CONSEQUENTIAL DAMAGES. Customer assumes all risk of data loss.
+
+5. INDEMNIFICATION. Each party shall indemnify the other for third-party claims arising from breach of this Agreement. Customer shall indemnify Provider for claims arising from Customer Data.
+
+6. INTELLECTUAL PROPERTY. Provider retains all IP rights. Customer receives a non-transferable, non-exclusive license for the term. Upon termination, Customer shall return or destroy all Provider materials within 10 business days.
+
+7. TERMINATION. Either party may terminate for convenience with 90 days notice. Provider may terminate immediately for non-payment. Upon termination, Customer shall pay all outstanding fees.
+
+8. GOVERNING LAW. This Agreement is governed by the laws of the State of Delaware. Disputes shall be resolved by binding arbitration in Wilmington, Delaware.
+
+9. FORCE MAJEURE. Neither party shall be liable for delays due to acts of God, war, terrorism, or government action.
+
+10. AUDIT RIGHTS. Customer may audit Provider's compliance annually. Provider shall provide SOC 2 Type II reports within 30 days of request.
+
+11. INSURANCE. Provider shall maintain general liability insurance of at least $5,000,000 and cyber liability insurance of at least $2,000,000.
+
+12. CONFIDENTIALITY. Both parties agree to keep Confidential Information secure for five (5) years. This obligation survives termination.
+
+13. ASSIGNMENT. Neither party may assign this Agreement without prior written consent. Any attempted assignment is void.
+
+14. THIRD PARTY BENEFICIARY. No third party shall have rights under this Agreement except as expressly provided."""
+
 with gr.Blocks(
     title="ClauseGuard — AI Contract Analysis",
     css="""
-        .gradio-container { max-width: 1400px !important; }
+        .gradio-container { max-width: 1600px !important; }
     """
 ) as demo:
 
@@ -869,66 +869,119 @@ with gr.Blocks(
     <div style="display:flex;align-items:center;justify-content:space-between;padding:12px 0;border-bottom:2px solid #e5e7eb;margin-bottom:16px;">
       <div>
         <h1 style="font-size:24px;font-weight:700;margin:0;color:#1f2937;">🛡️ ClauseGuard</h1>
-        <p style="font-size:13px;color:#6b7280;margin:4px 0 0 0;">AI-Powered Legal Contract Analysis · 41 Clause Categories · Risk Scoring · NER · NLI</p>
+        <p style="font-size:13px;color:#6b7280;margin:4px 0 0 0;">AI-Powered Legal Contract Analysis · 41 Clause Categories · Risk Scoring · NER · NLI · Compliance · Obligations</p>
       </div>
-      <div style="font-size:12px;color:#9ca3af;">v2.0 · World's Best Legal AI</div>
+      <div style="font-size:12px;color:#9ca3af;">v2.0 · World's Best Open-Source Legal AI</div>
     </div>
     """)
 
-    # ── Upload / Input ──
-    with gr.Row():
-        with gr.Column(scale=1):
-            file_input = gr.File(
-                label="📁 Upload Contract (PDF/DOCX/TXT)",
-                file_types=[".pdf", ".docx", ".doc", ".txt", ".md"],
-            )
-            load_btn = gr.Button("Load Document", variant="secondary", size="sm")
-            load_status = gr.Textbox(label="Status", interactive=False, lines=1)
-
-        with gr.Column(scale=3):
-            text_input = gr.Textbox(
-                label="📄 Contract Text",
-                placeholder="Paste contract text here, or upload a file above...",
-                lines=14,
-                max_lines=40,
-                show_copy_button=True,
-            )
-
-        with gr.Column(scale=1):
-            scan_btn = gr.Button("🔍 Analyze Contract", variant="primary", size="lg")
-            clear_btn = gr.Button("Clear", variant="secondary", size="sm")
-            status_msg = gr.Textbox(label="Analysis Status", interactive=False, lines=1)
-
-    # ── Examples ──
-    with gr.Row():
-        gr.Examples(
-            examples=[[SPOTIFY_TOS], [RENTAL_AGREEMENT], [NDA_SAMPLE]],
-            inputs=[text_input],
-            label="Example Contracts",
-        )
-
-    # ── Results ──
-    with gr.Row():
-        # Left: Summary + Export
-        with gr.Column(scale=1):
-            gr.Markdown("### 📊 Risk Summary")
-            summary_html = gr.HTML()
-
-            gr.Markdown("### 📥 Export Reports")
-            json_file = gr.File(label="JSON Report")
-            csv_file = gr.File(label="CSV Report")
-
-        # Center: Main Content Tabs
-        with gr.Column(scale=3):
-            with gr.Tabs():
-                with gr.Tab("📄 Document"):
-                    doc_html = gr.HTML(label="Document Viewer")
-                with gr.Tab("⚠️ Clauses (41 Categories)"):
-                    clauses_html = gr.HTML(label="Detected Clauses")
-                with gr.Tab("🏷️ Entities"):
-                    entities_html = gr.HTML(label="Named Entities")
-                with gr.Tab("🔍 Contradictions"):
-                    nli_html = gr.HTML(label="Contradictions & Missing Clauses")
+    # ── Main Tabs: Analysis vs Comparison ──
+    with gr.Tabs() as main_tabs:
+
+        # ═══════ TAB 1: Single Contract Analysis ═══════
+        with gr.Tab("📄 Single Contract Analysis"):
+            with gr.Row():
+                with gr.Column(scale=1):
+                    file_input = gr.File(
+                        label="📁 Upload Contract (PDF/DOCX/TXT)",
+                        file_types=[".pdf", ".docx", ".doc", ".txt", ".md"],
+                    )
+                    load_btn = gr.Button("Load Document", variant="secondary", size="sm")
+                    load_status = gr.Textbox(label="Status", interactive=False, lines=1)
+
+                with gr.Column(scale=3):
+                    text_input = gr.Textbox(
+                        label="📄 Contract Text",
+                        placeholder="Paste contract text here, or upload a file above...",
+                        lines=14,
+                        max_lines=40,
+                        show_copy_button=True,
+                    )
+
+                with gr.Column(scale=1):
+                    scan_btn = gr.Button("🔍 Analyze Contract", variant="primary", size="lg")
+                    clear_btn = gr.Button("Clear", variant="secondary", size="sm")
+                    status_msg = gr.Textbox(label="Analysis Status", interactive=False, lines=1)
+
+            # ── Examples ──
+            with gr.Row():
+                gr.Examples(
+                    examples=[[SPOTIFY_TOS], [RENTAL_AGREEMENT], [NDA_SAMPLE], [COMPLEX_CONTRACT]],
+                    inputs=[text_input],
+                    label="Example Contracts",
+                )
+
+            # ── Results ──
+            with gr.Row():
+                with gr.Column(scale=1):
+                    gr.Markdown("### 📊 Risk Summary")
+                    summary_html = gr.HTML()
+
+                    gr.Markdown("### 📥 Export Reports")
+                    json_file = gr.File(label="JSON Report")
+                    csv_file = gr.File(label="CSV Report")
+
+                with gr.Column(scale=3):
+                    with gr.Tabs():
+                        with gr.Tab("📄 Document"):
+                            doc_html = gr.HTML(label="Document Viewer")
+                        with gr.Tab("⚠️ Clauses (41 Categories)"):
+                            clauses_html = gr.HTML(label="Detected Clauses")
+                        with gr.Tab("🏷️ Entities"):
+                            entities_html = gr.HTML(label="Named Entities")
+                        with gr.Tab("🔍 Contradictions"):
+                            nli_html = gr.HTML(label="Contradictions & Missing Clauses")
+                        with gr.Tab("📋 Obligations"):
+                            obligations_html = gr.HTML(label="Obligation Tracker")
+                        with gr.Tab("⚖️ Compliance"):
+                            compliance_html = gr.HTML(label="Compliance Checker")
+
+        # ═══════ TAB 2: Contract Comparison ═══════
+        with gr.Tab("🔀 Compare Contracts"):
+            with gr.Row():
+                with gr.Column(scale=1):
+                    comp_file_a = gr.File(
+                        label="📁 Contract A (PDF/DOCX/TXT)",
+                        file_types=[".pdf", ".docx", ".doc", ".txt"],
+                    )
+                    comp_load_a = gr.Button("Load A", variant="secondary", size="sm")
+                    comp_status_a = gr.Textbox(label="Status A", interactive=False, lines=1)
+
+                with gr.Column(scale=3):
+                    comp_text_a = gr.Textbox(
+                        label="Contract A",
+                        placeholder="Paste contract A here...",
+                        lines=12,
+                        show_copy_button=True,
+                    )
+
+                with gr.Column(scale=1):
+                    comp_file_b = gr.File(
+                        label="📁 Contract B (PDF/DOCX/TXT)",
+                        file_types=[".pdf", ".docx", ".doc", ".txt"],
+                    )
+                    comp_load_b = gr.Button("Load B", variant="secondary", size="sm")
+                    comp_status_b = gr.Textbox(label="Status B", interactive=False, lines=1)
+
+                with gr.Column(scale=3):
+                    comp_text_b = gr.Textbox(
+                        label="Contract B",
+                        placeholder="Paste contract B here...",
+                        lines=12,
+                        show_copy_button=True,
+                    )
+
+            with gr.Row():
+                with gr.Column(scale=1):
+                    comp_btn = gr.Button("🔀 Compare Contracts", variant="primary", size="lg")
+                with gr.Column(scale=5):
+                    comp_status = gr.Textbox(label="Comparison Status", interactive=False, lines=1)
+
+            with gr.Row():
+                with gr.Column(scale=4):
+                    comp_result_html = gr.HTML(label="Comparison Results")
+                with gr.Column(scale=2):
+                    comp_json = gr.JSON(label="Raw Comparison Data")
 
     # ── Events ──
     def _load_file(file):
@@ -938,25 +991,35 @@ with gr.Blocks(
         return text, "Loaded successfully" if not err else err
 
     load_btn.click(_load_file, inputs=[file_input], outputs=[text_input, load_status])
+    comp_load_a.click(_load_file, inputs=[comp_file_a], outputs=[comp_text_a, comp_status_a])
+    comp_load_b.click(_load_file, inputs=[comp_file_b], outputs=[comp_text_b, comp_status_b])
 
     scan_btn.click(
         run_analysis,
         inputs=[text_input],
         outputs=[summary_html, clauses_html, entities_html, nli_html,
-                 doc_html, json_file, csv_file, status_msg]
+                 doc_html, obligations_html, compliance_html,
+                 json_file, csv_file, status_msg]
     )
 
     clear_btn.click(
         do_clear,
         outputs=[summary_html, clauses_html, entities_html, nli_html,
-                 doc_html, json_file, csv_file, status_msg]
+                 doc_html, obligations_html, compliance_html,
+                 json_file, csv_file, status_msg]
+    )
+
+    comp_btn.click(
+        run_comparison,
+        inputs=[comp_text_a, comp_text_b],
+        outputs=[comp_result_html, comp_json]
     )
 
     gr.HTML("""
     <div style="margin-top:24px;padding:16px 0;border-top:1px solid #e5e7eb;text-align:center;">
       <p style="font-size:11px;color:#9ca3af;">
         ⚠️ Not legal advice. For informational purposes only.
-        · Model: <a href="https://huggingface.co/Mokshith31/legalbert-contract-clause-classification" style="color:#6b7280;">Legal-BERT + CUAD</a>
+        · Model: <a href="https://huggingface.co/Mokshith31/legalbert-contract-clause-classification" style="color:#6b7280;">Legal-BERT + CUAD (41 classes)</a>
         · Dataset: <a href="https://huggingface.co/datasets/theatticusproject/cuad-qa" style="color:#6b7280;">CUAD</a>
         · <a href="https://huggingface.co/spaces/gaurv007/ClauseGuard" style="color:#6b7280;">ClauseGuard Space</a>
       </p>