perf: defer pandas import in ResponseToFileExtractor

airbyte_cdk/sources/declarative/extractors/response_to_file_extractor.py

@@ -10,7 +10,6 @@
 from math import nan
 from typing import Any, Dict, Iterable, Mapping, Optional, Tuple
 
-import pandas as pd
 import requests
 
 from airbyte_cdk.sources.declarative.extractors.record_extractor import RecordExtractor
@@ -139,6 +138,9 @@ def _read_with_chunks(
             ValueError: If an IO/Error occurs while reading the temporary data.
         """
 
+        # Imported lazily: pandas (and numpy) are slow to import and only needed for CSV parsing.
+        import pandas as pd
+
         try:
             with open(path, "r", encoding=file_encoding) as data:
                 # When preserving NA values, disable pandas' default NA parsing so strings like "NA"/"N/A" are kept as-is,

unit_tests/source_declarative_manifest/test_source_declarative_manifest_imports.py

@@ -0,0 +1,60 @@
+# Copyright (c) 2026 Airbyte, Inc., all rights reserved.
+
+import json
+import subprocess
+import sys
+from pathlib import Path
+
+SCRIPT = """
+import json
+import sys
+from unittest.mock import patch
+
+import requests_mock
+import yaml
+
+from airbyte_cdk.cli.source_declarative_manifest import _run
+
+manifest_path, config_path = sys.argv[1:]
+with open(manifest_path) as manifest_file:
+    manifest = yaml.safe_load(manifest_file)
+
+with patch(
+    "airbyte_cdk.cli.source_declarative_manifest._run._is_local_manifest_command",
+    return_value=True,
+):
+    with patch(
+        "airbyte_cdk.cli.source_declarative_manifest._run.YamlDeclarativeSource._read_and_parse_yaml_file",
+        return_value=manifest,
+    ):
+        with requests_mock.Mocker() as mocker:
+            mocker.get(
+                "https://pokeapi.co/api/v2/pokemon/blastoise",
+                json={"name": "blastoise"},
+            )
+            _run.handle_command(["spec"])
+            _run.handle_command(["check", "--config", config_path])
+            _run.handle_command(["discover", "--config", config_path])
+
+print("LOADED_HEAVY_MODULES=" + json.dumps(sorted(m for m in ("pandas", "numpy") if m in sys.modules)))
+"""
+
+
+def test_spec_check_discover_do_not_import_pandas_or_numpy() -> None:
+    manifest_path = Path(__file__).parent.parent / "resources" / "valid_local_manifest.yaml"
+    config_path = Path(__file__).parent.parent / "resources" / "valid_local_pokeapi_config.json"
+
+    result = subprocess.run(
+        [sys.executable, "-c", SCRIPT, str(manifest_path), str(config_path)],
+        capture_output=True,
+        text=True,
+        timeout=120,
+    )
+
+    assert result.returncode == 0, result.stderr
+    assert '"connectionStatus":{"status":"SUCCEEDED"}' in result.stdout
+    assert '"catalog"' in result.stdout
+    marker = next(
+        line for line in result.stdout.splitlines() if line.startswith("LOADED_HEAVY_MODULES=")
+    )
+    assert json.loads(marker.split("=", 1)[1]) == []