Fix/move cross document validation

lending-poc/app/main.py

@@ -4,10 +4,10 @@
 from fastapi import FastAPI
 from sqlalchemy import text
 
-from app.api.cases import router as cases_router
 from app.api.health import router as health_router
 from app.config import logger, settings
 from app.database import async_session, engine
+from cross_document_validation.api import router as cases_router
 
 
 @asynccontextmanager

lending-poc/app/api/cases.py → lending-poc/cross_document_validation/api.py

@@ -2,11 +2,11 @@
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.database import get_db
-from app.schemas.case import CaseCreateRequest, CaseCreateResponse, ValidationResultOut
-from app.services.case_parsing import parse_case
-from app.services.persistence import save_pipeline_result
-from app.services.pipeline import run_pipeline
-from app.utils.json_safe import json_safe
+from cross_document_validation.schemas.case import CaseCreateRequest, CaseCreateResponse, ValidationResultOut
+from cross_document_validation.services.case_parsing import parse_case
+from cross_document_validation.services.persistence import save_pipeline_result
+from cross_document_validation.services.pipeline import run_pipeline
+from cross_document_validation.utils.json_safe import json_safe
 
 router = APIRouter(tags=["cases"])
 

lending-poc/app/services/business_validation.py → lending-poc/cross_document_validation/services/business_validation.py

@@ -6,9 +6,9 @@
 from calendar import monthrange
 from datetime import date, timedelta
 
-from app.matching.fuzzy import employer_similarity
-from app.services import validation_config as cfg
-from app.services.dto import (
+from cross_document_validation.matching.fuzzy import employer_similarity
+from cross_document_validation.services import validation_config as cfg
+from cross_document_validation.services.dto import (
     BankStatementDoc,
     BankTransaction,
     CaseInput,
@@ -135,7 +135,12 @@ def _validate_salary_slip(
             score=0.0,
             document_id=slip.doc_id,
             failure_reason="no_matching_credit_in_window",
-            evidence={"window": window},
+            evidence={
+                "source_text": slip.salary_month.strftime("%B %Y"),
+                "target_text": None,
+                "match_type": "DATE_MATCH",
+                "window": window,
+            },
         )
 
     txn, score = selection
@@ -145,7 +150,12 @@ def _validate_salary_slip(
         passed=True,
         score=score,
         document_id=slip.doc_id,
-        evidence={"matched_transaction": txn},
+        evidence={
+            "source_text": slip.salary_month.strftime("%B %Y"),
+            "target_text": txn.txn_date.strftime("%Y-%m") if txn.txn_date else None,
+            "match_type": "DATE_MATCH",
+            "matched_transaction": txn,
+        },
     )
 
 
@@ -187,6 +197,11 @@ def _employer_match_for_slip(
         score=score,
         document_id=slip.doc_id,
         failure_reason=None if passed else "employer_narration_mismatch",
+        evidence={
+            "source_text": slip.employer_name,
+            "target_text": matched_txn.narration,
+            "match_type": "FUZZY",
+        },
     )
 
 
@@ -206,9 +221,12 @@ def _salary_credit_count(
         check_type=CheckType.SALARY_CREDIT_COUNT,
         passed=(matched_slips == total_slips),
         score=confidence_score,
+        document_id=bank_statement.doc_id,
         evidence={
+            "source_value": total_slips,
+            "target_value": matched_slips,
+            "match_type": "COUNT_MATCH",
             "stmt_duration": stmt_duration,
-            "no_of_matches": matched_slips,
             "total_slips": total_slips,
             "confidence_score": confidence_score,
         },

lending-poc/app/services/case_parsing.py → lending-poc/cross_document_validation/services/case_parsing.py

@@ -5,7 +5,7 @@
 
 from datetime import date, datetime
 
-from app.services.dto import (
+from cross_document_validation.services.dto import (
     AadhaarDoc,
     AddressProofDoc,
     BankStatementDoc,

lending-poc/app/services/decision_engine.py → lending-poc/cross_document_validation/services/decision_engine.py

@@ -1,7 +1,7 @@
 """Final PASS / FAIL / NEEDS_REVIEW logic."""
 
-from app.services import validation_config as cfg
-from app.services.dto import CheckType, Decision, DecisionResult, ScoreResult, ValidationResult
+from cross_document_validation.services import validation_config as cfg
+from cross_document_validation.services.dto import CheckType, Decision, DecisionResult, ScoreResult, ValidationResult
 
 MANDATORY_CHECK_TYPES = {CheckType.NAME, CheckType.AADHAAR, CheckType.PAN, CheckType.DOB}
 

lending-poc/app/services/golden_record.py → lending-poc/cross_document_validation/services/golden_record.py

@@ -11,10 +11,10 @@
 rather than silently adopting an unrelated "fuller" name.
 """
 
-from app.matching.embeddings import get_address_embedding
-from app.matching.fuzzy import name_similarity
-from app.services import validation_config as cfg
-from app.services.dto import CaseInput, GoldenRecord
+from cross_document_validation.matching.embeddings import get_address_embedding
+from cross_document_validation.matching.fuzzy import name_similarity
+from cross_document_validation.services import validation_config as cfg
+from cross_document_validation.services.dto import CaseInput, GoldenRecord
 
 FULLER_NAME_RELATEDNESS_THRESHOLD = cfg.NAME_MATCH_THRESHOLD
 

lending-poc/app/services/identity_validation.py → lending-poc/cross_document_validation/services/identity_validation.py

@@ -3,10 +3,10 @@
 the Golden Record at all, regardless of why they're missing.
 """
 
-from app.matching import exact, fuzzy
-from app.matching.embeddings import address_similarity
-from app.services import validation_config as cfg
-from app.services.dto import CaseInput, CheckType, GoldenRecord, ValidationResult
+from cross_document_validation.matching import exact, fuzzy
+from cross_document_validation.matching.embeddings import address_similarity
+from cross_document_validation.services import validation_config as cfg
+from cross_document_validation.services.dto import CaseInput, CheckType, GoldenRecord, ValidationResult
 
 MANDATORY_GOLDEN_FIELDS = {
     CheckType.NAME: "name",
@@ -31,7 +31,9 @@ def check_mandatory_presence(golden: GoldenRecord) -> list[ValidationResult]:
     return results
 
 
-def _exact_result_to_validation(check_type: CheckType, outcome, document_id: str) -> ValidationResult:
+def _exact_result_to_validation(
+    check_type: CheckType, outcome, document_id: str, source_text, target_text
+) -> ValidationResult:
     passed = outcome.result == exact.MatchResult.MATCH
     score = 100.0 if passed else (50.0 if outcome.result == exact.MatchResult.INCONCLUSIVE else 0.0)
     return ValidationResult(
@@ -40,6 +42,7 @@ def _exact_result_to_validation(check_type: CheckType, outcome, document_id: str
         score=score,
         document_id=document_id,
         failure_reason=None if passed else outcome.reason,
+        evidence={"source_text": source_text, "target_text": target_text, "match_type": "EXACT"},
     )
 
 
@@ -64,6 +67,7 @@ def validate_document_against_golden(
                 score=score,
                 document_id=document_id,
                 failure_reason=None if passed else "name_below_threshold",
+                evidence={"source_text": golden.name, "target_text": doc_name, "match_type": "FUZZY"},
             )
         )
 
@@ -78,20 +82,31 @@ def validate_document_against_golden(
                 score=score,
                 document_id=document_id,
                 failure_reason=None if passed else "address_below_threshold",
+                evidence={"source_text": golden.address, "target_text": doc_address, "match_type": "SEMANTIC"},
             )
         )
 
     if doc_aadhaar is not None:
         outcome = exact.aadhaar_match(golden.aadhaar_number, doc_aadhaar)
-        results.append(_exact_result_to_validation(CheckType.AADHAAR, outcome, document_id))
+        results.append(
+            _exact_result_to_validation(
+                CheckType.AADHAAR, outcome, document_id, golden.aadhaar_number, doc_aadhaar
+            )
+        )
 
     if doc_pan is not None:
         outcome = exact.pan_match(golden.pan_number, doc_pan)
-        results.append(_exact_result_to_validation(CheckType.PAN, outcome, document_id))
+        results.append(
+            _exact_result_to_validation(CheckType.PAN, outcome, document_id, golden.pan_number, doc_pan)
+        )
 
     if doc_dob is not None:
         outcome = exact.dob_match(golden.date_of_birth, doc_dob)
-        results.append(_exact_result_to_validation(CheckType.DOB, outcome, document_id))
+        results.append(
+            _exact_result_to_validation(
+                CheckType.DOB, outcome, document_id, golden.date_of_birth, doc_dob
+            )
+        )
 
     return results
 

lending-poc/app/services/persistence.py → lending-poc/cross_document_validation/services/persistence.py

@@ -1,19 +1,19 @@
 """Persists one pipeline run (CaseInput + PipelineResult) to the database.
 
-The in-memory dataclasses in app.services.dto reference documents by their
-string doc_id (e.g. "AADHAAR", "SALARY_SLIP-0"). This module inserts the
-Document rows first and keeps a doc_id -> Document.id map so
-ValidationResult.document_id (also a doc_id string) can be resolved to the
+The in-memory dataclasses in cross_document_validation.services.dto reference
+documents by their string doc_id (e.g. "AADHAAR", "SALARY_SLIP-0"). This
+module inserts the Document rows first and keeps a doc_id -> Document.id map
+so ValidationResult.document_id (also a doc_id string) can be resolved to the
 real foreign key.
 """
 
 import uuid
 
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from app.services.dto import CaseInput, Decision, DocType
-from app.services.dto import PipelineResult as PipelineResultDTO
-from app.utils.json_safe import json_safe
+from cross_document_validation.services.dto import CaseInput, Decision, DocType
+from cross_document_validation.services.dto import PipelineResult as PipelineResultDTO
+from cross_document_validation.utils.json_safe import json_safe
 from db.models.case import Case, CaseStatus
 from db.models.document import Document
 from db.models.golden_record import GoldenRecord as GoldenRecordModel

lending-poc/app/services/pipeline.py → lending-poc/cross_document_validation/services/pipeline.py

@@ -2,10 +2,10 @@
 Decision in one call, with a simple in-memory audit log.
 """
 
-from app.services import business_validation, decision_engine, golden_record, scoring
-from app.services import validation_config as cfg
-from app.services.dto import CaseInput, Decision, DecisionResult, PipelineResult
-from app.services.identity_validation import run_identity_validation
+from cross_document_validation.services import business_validation, decision_engine, golden_record, scoring
+from cross_document_validation.services import validation_config as cfg
+from cross_document_validation.services.dto import CaseInput, Decision, DecisionResult, PipelineResult
+from cross_document_validation.services.identity_validation import run_identity_validation
 
 
 def run_pipeline(case: CaseInput) -> PipelineResult:

lending-poc/app/services/scoring.py → lending-poc/cross_document_validation/services/scoring.py

@@ -2,8 +2,8 @@
 
 from collections import defaultdict
 
-from app.services import validation_config as cfg
-from app.services.dto import ScoreResult, ValidationResult
+from cross_document_validation.services import validation_config as cfg
+from cross_document_validation.services.dto import ScoreResult, ValidationResult
 
 
 def compute_score(validation_results: list[ValidationResult]) -> ScoreResult:

lending-poc/docs/cases_api.md

@@ -92,14 +92,37 @@ Notes:
       "passed": true,
       "score": 94.5,
       "document_id": "PAN",
-      "evidence": null
+      "evidence": {
+        "source_text": "Sneha Sunil Lokhande",
+        "target_text": "Sneha Lokhande",
+        "match_type": "FUZZY"
+      }
     },
     {
       "check_type": "SALARY_DATE",
       "passed": false,
       "score": 0.0,
       "document_id": "SALARY_SLIP-3",
-      "evidence": { "window": ["2026-05-27", "2026-07-31"] }
+      "evidence": {
+        "source_text": "June 2026",
+        "target_text": null,
+        "match_type": "DATE_MATCH",
+        "window": ["2026-05-27", "2026-07-31"]
+      }
+    },
+    {
+      "check_type": "SALARY_CREDIT_COUNT",
+      "passed": false,
+      "score": 75.0,
+      "document_id": "BANK_STATEMENT",
+      "evidence": {
+        "source_value": 4,
+        "target_value": 3,
+        "match_type": "COUNT_MATCH",
+        "stmt_duration": { "start": "2026-04-01", "end": "2026-07-04" },
+        "total_slips": 4,
+        "confidence_score": 75.0
+      }
     }
   ]
 }