Add new fields to SpreadsheetParsingConfig and update validation tests (#1042)

.changeset/silent-impalas-chew.md

@@ -0,0 +1,5 @@
+---
+"llama-cloud-services-py": patch
+---
+
+Update spreadsheet parsing config

py/llama_cloud_services/beta/sheets/types.py

@@ -1,5 +1,6 @@
 from datetime import datetime
 from enum import Enum
+from typing import Literal
 
 from pydantic import BaseModel, ConfigDict, Field, field_validator
 
@@ -63,7 +64,7 @@ class SpreadsheetParseResult(BaseModel):
 class SpreadsheetParsingConfig(BaseModel):
     """Configuration for spreadsheet parsing and region extraction"""
 
-    model_config = ConfigDict(extra="forbid")
+    model_config = ConfigDict(extra="ignore")
 
     sheet_names: list[str] | None = Field(
         default=None,
@@ -86,6 +87,16 @@ class SpreadsheetParsingConfig(BaseModel):
         description="Enables experimental processing. Accuracy may be impacted.",
     )
 
+    flatten_hierarchical_tables: bool = Field(
+        default=False,
+        description="Return a flattened dataframe when a detected table is recognized as hierarchical.",
+    )
+
+    table_merge_sensitivity: Literal["strong", "weak"] = Field(
+        default="strong",
+        description="Influences how likely similar-looking regions are merged into a single table. Useful for spreadsheets that either have sparse tables (strong merging) or many distinct tables close together (weak merging).",
+    )
+
 
 class SpreadsheetJob(BaseModel):
     """A spreadsheet parsing job"""

py/tests/beta/sheets/test_sheets.py

@@ -2,11 +2,45 @@ import os
 import tempfile
 import pytest
 import pandas as pd
+from pydantic import ValidationError
 
 from llama_cloud_services.beta.sheets import LlamaSheets
 from llama_cloud_services.beta.sheets.types import SpreadsheetParsingConfig
 
 
+class TestSpreadsheetParsingConfig:
+    """Unit tests for SpreadsheetParsingConfig."""
+
+    def test_default_values(self):
+        """Test that default values are set correctly."""
+        config = SpreadsheetParsingConfig()
+        assert config.flatten_hierarchical_tables is False
+        assert config.table_merge_sensitivity == "strong"
+
+    def test_custom_values(self):
+        """Test setting custom values for new fields."""
+        config = SpreadsheetParsingConfig(
+            flatten_hierarchical_tables=True,
+            table_merge_sensitivity="weak",
+        )
+        assert config.flatten_hierarchical_tables is True
+        assert config.table_merge_sensitivity == "weak"
+
+    def test_table_merge_sensitivity_validation(self):
+        """Test that invalid table_merge_sensitivity values are rejected."""
+        with pytest.raises(ValidationError):
+            SpreadsheetParsingConfig(table_merge_sensitivity="invalid")
+
+    def test_unknown_fields_ignored(self):
+        """Test that unknown fields are silently ignored."""
+        config = SpreadsheetParsingConfig(
+            unknown_field="test",
+            another_unknown=123,
+        )
+        assert not hasattr(config, "unknown_field")
+        assert not hasattr(config, "another_unknown")
+
+
 @pytest.fixture
 def sheets_client():
     """Create a LlamaSheets client for testing."""