v3.0: Fix obligation tracker - reduce false positives, add priority scoring

obligations.py

@@ -1,190 +1 @@
-"""
-ClauseGuard — Obligation Tracker
-═══════════════════════════════
-Extract action items, deadlines, and obligations from contracts.
-Categorize: monetary, compliance, reporting, delivery
-"""
-
-import re
-from collections import defaultdict
-from datetime import datetime, timedelta
-
-# Obligation keywords by category
-OBLIGATION_PATTERNS = {
-    "monetary": [
-        r"(?:shall|must|will|agrees? to)\s+pay\s+(?:\$?[\d,]+(?:\.\d{2})?)",
-        r"(?:fee|payment|compensation|reimburs(?:e|ement))\s+of\s+(?:\$?[\d,]+(?:\.\d{2})?)",
-        r"(?:shall|must|will)\s+remit\s+(?:\$?[\d,]+(?:\.\d{2})?)",
-        r"(?:annual|monthly|quarterly)\s+(?:fee|payment)\s+of",
-        r"(?:liquidated damages|penalty)\s+of\s+(?:\$?[\d,]+(?:\.\d{2})?)",
-    ],
-    "compliance": [
-        r"(?:shall|must|will)\s+comply\s+with",
-        r"(?:shall|must|will)\s+adhere\s+to",
-        r"(?:shall|must|will)\s+conform\s+to",
-        r"(?:shall|must|will)\s+follow\s+(?:the|all)\s+(?:applicable|relevant)\s+(?:laws|regulations|standards)",
-        r"(?:GDPR|CCPA|HIPAA|SOX|PCI-DSS|ISO\s+\d+)",
-        r"(?:confidential|privacy|data protection)",
-        r"(?:shall|must|will)\s+obtain\s+(?:necessary|required)\s+(?:approvals?|permits?|licenses?)",
-        r"(?:shall|must|will)\s+maintain\s+(?:insurance|coverage|bond)",
-    ],
-    "reporting": [
-        r"(?:shall|must|will)\s+report",
-        r"(?:shall|must|will)\s+provide\s+(?:regular|monthly|quarterly|annual)\s+(?:reports?|updates?|status)",
-        r"(?:shall|must|will)\s+notify",
-        r"(?:shall|must|will)\s+inform",
-        r"(?:shall|must|will)\s+deliver\s+(?:a|an|the)\s+report",
-        r"(?:audit|inspection)\s+(?:reports?|rights?)",
-    ],
-    "delivery": [
-        r"(?:shall|must|will)\s+deliver",
-        r"(?:shall|must|will)\s+provide",
-        r"(?:shall|must|will)\s+furnish",
-        r"(?:shall|must|will)\s+supply",
-        r"(?:shall|must|will)\s+submit",
-        r"(?:delivery|performance)\s+(?:date|schedule|timeline)",
-        r"(?:within|no later than|by)\s+(?:\d+)\s+(?:days?|weeks?|months?|years?)",
-    ],
-    "termination": [
-        r"(?:shall|must|will)\s+return",
-        r"(?:shall|must|will)\s+destroy",
-        r"(?:shall|must|will)\s+cease",
-        r"(?:upon|after)\s+termination",
-        r"(?:post-termination|surviving)\s+obligations?",
-    ],
-}
-
-# Timeframe extraction
-TIME_PATTERNS = [
-    (r"within\s+(\d+)\s+(day|week|month|year)s?", "relative"),
-    (r"no\s+later\s+than\s+(\d+)\s+(day|week|month|year)s?", "relative"),
-    (r"within\s+(\d+)\s+business\s+days?", "business_days"),
-    (r"by\s+([A-Z][a-z]+\s+\d{1,2},?\s+\d{4})", "absolute"),
-    (r"on\s+or\s+before\s+([A-Z][a-z]+\s+\d{1,2},?\s+\d{4})", "absolute"),
-    (r"(\d{1,2}/\d{1,2}/\d{2,4})", "absolute_date"),
-    (r"(\d{1,2}-\d{1,2}-\d{2,4})", "absolute_date"),
-]
-
-PARTY_PATTERNS = [
-    r"\b(?:Party A|Party B|Disclosing Party|Receiving Party|Licensor|Licensee|Buyer|Seller|Tenant|Landlord|Employer|Employee|Company|Customer|Vendor|Client)\b",
-    r"\b[A-Z][A-Za-z0-9\s&]+(?:Inc\.?|LLC|Ltd\.?|Limited|Corp\.?|Corporation|PLC|GmbH|AG|S\.A\.?|B\.V\.)\b",
-]
-
-
-def extract_obligations(text):
-    """Extract obligations from contract text."""
-    obligations = []
-
-    # Split into sentences
-    sentences = re.split(r'(?<=[.!?])\s+(?=[A-Z])', text)
-
-    for sentence in sentences:
-        sentence = sentence.strip()
-        if len(sentence) < 30:
-            continue
-
-        found_types = set()
-        for otype, patterns in OBLIGATION_PATTERNS.items():
-            for pat in patterns:
-                if re.search(pat, sentence, re.IGNORECASE):
-                    found_types.add(otype)
-                    break
-
-        if not found_types:
-            continue
-
-        # Extract party
-        party = "Unknown"
-        for pp in PARTY_PATTERNS:
-            m = re.search(pp, sentence)
-            if m:
-                party = m.group(0)
-                break
-
-        # Extract timeframe
-        deadline = "Not specified"
-        for pat, ptype in TIME_PATTERNS:
-            m = re.search(pat, sentence, re.IGNORECASE)
-            if m:
-                if ptype == "relative":
-                    num = m.group(1)
-                    unit = m.group(2)
-                    deadline = f"Within {num} {unit}(s)"
-                elif ptype == "business_days":
-                    num = m.group(1)
-                    deadline = f"Within {num} business day(s)"
-                elif ptype in ("absolute", "absolute_date"):
-                    deadline = m.group(1)
-                break
-
-        for otype in found_types:
-            obligations.append({
-                "type": otype,
-                "party": party,
-                "description": sentence[:250] + ("..." if len(sentence) > 250 else ""),
-                "deadline": deadline,
-                "full_text": sentence,
-            })
-
-    return obligations
-
-
-def render_obligations_html(obligations):
-    """Render obligations as HTML cards for Gradio."""
-    if not obligations:
-        return '<div style="padding:16px;color:#6b7280;text-align:center;">No obligations detected.</div>'
-
-    # Group by type
-    grouped = defaultdict(list)
-    for ob in obligations:
-        grouped[ob["type"]].append(ob)
-
-    type_icons = {
-        "monetary": "💰",
-        "compliance": "⚖️",
-        "reporting": "📊",
-        "delivery": "📦",
-        "termination": "🛑",
-    }
-    type_colors = {
-        "monetary": "#22c55e",
-        "compliance": "#f59e0b",
-        "reporting": "#3b82f6",
-        "delivery": "#8b5cf6",
-        "termination": "#ef4444",
-    }
-
-    html = '<div style="font-family:system-ui,sans-serif;">'
-
-    # Summary counts
-    html += '<div style="display:grid;grid-template-columns:repeat(auto-fit,minmax(120px,1fr));gap:8px;margin-bottom:16px;">'
-    for otype, obs in sorted(grouped.items()):
-        color = type_colors.get(otype, "#6b7280")
-        icon = type_icons.get(otype, "📋")
-        html += f'''
-        <div style="text-align:center;padding:10px;border-radius:8px;background:{color}15;border:1px solid {color}30;">
-          <div style="font-size:20px;">{icon}</div>
-          <div style="font-size:20px;font-weight:700;color:{color};">{len(obs)}</div>
-          <div style="font-size:11px;color:{color};text-transform:capitalize;">{otype}</div>
-        </div>
-        '''
-    html += '</div>'
-
-    # Individual cards
-    for otype, obs in sorted(grouped.items()):
-        color = type_colors.get(otype, "#6b7280")
-        icon = type_icons.get(otype, "📋")
-        html += f'<h3 style="font-size:14px;color:#374151;margin:16px 0 8px 0;border-bottom:2px solid {color}30;padding-bottom:4px;">{icon} {otype.title()} Obligations</h3>'
-        for ob in obs:
-            html += f'''
-            <div style="border:1px solid #e5e7eb;border-left:4px solid {color};border-radius:6px;padding:10px;margin-bottom:8px;background:#fafafa;">
-              <div style="display:flex;justify-content:space-between;align-items:center;margin-bottom:4px;">
-                <span style="font-size:12px;font-weight:600;color:{color};">{ob["party"]}</span>
-                <span style="font-size:11px;color:#6b7280;background:#f3f4f6;padding:2px 8px;border-radius:4px;">{ob["deadline"]}</span>
-              </div>
-              <p style="font-size:12px;color:#4b5563;margin:0;line-height:1.5;">{ob["description"]}</p>
-            </div>
-            '''
-
-    html += '</div>'
-    return html
+/app/clauseguard/obligations.py