Add unit test for saving extra modules (#8290)

* add test

* better test

Author: chenmoneygithub

docs/docs/tutorials/saving/index.md

@@ -98,14 +98,15 @@ You can pick the suitable saving approach based on your needs.
 
 ### Serializing Imported Modules
 
-When saving a program with `save_program=True`, you might need to include custom modules that your program depends on.
+When saving a program with `save_program=True`, you might need to include custom modules that your program depends on. This is
+necessary if your program depends on these modules, but at loading time these modules are not imported before calling `dspy.load`.
 
 You can specify which custom modules should be serialized with your program by passing them to the `modules_to_serialize`
 parameter when calling `save`. This ensures that any dependencies your program relies on are included during serialization and
 available when loading the program later.
 
-This uses cloudpickle's `cloudpickle.register_pickle_by_value` function in order to register a module as picklable by value. When
-a module is registered this way, cloudpickle will serialize the module by value rather than by reference, ensuring that the
+Under the hood this uses cloudpickle's `cloudpickle.register_pickle_by_value` function to register a module as picklable by value.
+When a module is registered this way, cloudpickle will serialize the module by value rather than by reference, ensuring that the
 module contents are preserved with the saved program.
 
 For example, if your program uses custom modules:

tests/primitives/test_module.py

@@ -115,6 +115,65 @@ def dummy_metric(example, pred, trace=None):
     assert new_cot.predict.demos == compiled_cot.predict.demos
 
 
+def test_save_with_extra_modules(tmp_path):
+    import sys
+
+    # Create a temporary Python file with our custom module
+    custom_module_path = tmp_path / "custom_module.py"
+    with open(custom_module_path, "w") as f:
+        f.write("""
+import dspy
+
+class MyModule(dspy.Module):
+    def __init__(self):
+        self.cot = dspy.ChainOfThought(dspy.Signature("q -> a"))
+
+    def forward(self, q):
+        return self.cot(q=q)
+""")
+
+    # Add the tmp_path to Python path so we can import the module
+    sys.path.insert(0, str(tmp_path))
+    try:
+        import custom_module
+
+        cot = custom_module.MyModule()
+
+        cot.save(tmp_path, save_program=True)
+        # Remove the custom module from sys.modules to simulate it not being available
+        sys.modules.pop("custom_module", None)
+        # Also remove it from sys.path
+        sys.path.remove(str(tmp_path))
+        del custom_module
+
+        # Test the loading fails without using `modules_to_serialize`
+        with pytest.raises(ModuleNotFoundError):
+            dspy.load(tmp_path)
+
+        sys.path.insert(0, str(tmp_path))
+        import custom_module
+
+        cot.save(
+            tmp_path,
+            modules_to_serialize=[custom_module],
+            save_program=True,
+        )
+
+        # Remove the custom module from sys.modules to simulate it not being available
+        sys.modules.pop("custom_module", None)
+        # Also remove it from sys.path
+        sys.path.remove(str(tmp_path))
+        del custom_module
+
+        loaded_module = dspy.load(tmp_path)
+        assert loaded_module.cot.predict.signature == cot.cot.predict.signature
+
+    finally:
+        # Only need to clean up sys.path
+        if str(tmp_path) in sys.path:
+            sys.path.remove(str(tmp_path))
+
+
 def test_load_with_version_mismatch(tmp_path):
     from dspy.primitives.module import logger