feat: Editor.read + file size检查

metagpt/tools/libs/editor.py

@@ -104,14 +104,18 @@ class Editor(BaseModel):
 
     async def read(self, path: str) -> FileBlock:
         """Read the whole content of a file. Using absolute paths as the argument for specifying the file location."""
+        error = FileBlock(
+            file_path=str(path),
+            block_content="The file is too large to read. Use `Editor.similarity_search` to read the file instead.",
+        )
+        path = Path(path)
+        if path.stat().st_size > 5 * DEFAULT_MIN_TOKEN_COUNT:
+            return error
         content = await File.read_text_file(path)
         if not content:
             return FileBlock(file_path=str(path), block_content="")
         if self.is_large_file(content=content):
-            return FileBlock(
-                file_path=str(path),
-                block_content="The file is too large to read. Use `Editor.similarity_search` to read the file instead.",
-            )
+            return error
         self.resource.report(str(path), "path")
 
         lines = content.splitlines(keepends=True)

tests/metagpt/tools/libs/test_editor.py

@@ -9,6 +9,7 @@ from metagpt.tools.libs.editor import Editor
 from metagpt.tools.libs.index_repo import (
     CHATS_INDEX_ROOT,
     CHATS_ROOT,
+    DEFAULT_MIN_TOKEN_COUNT,
     UPLOAD_ROOT,
     IndexRepo,
 )
@@ -780,8 +781,10 @@ async def test_similarity_search(query, filename):
 @pytest.mark.asyncio
 async def test_read():
     editor = Editor()
-    content = await editor.read(str(TEST_DATA_PATH / "pdf/9112674.pdf"))
-    assert "similarity_search" in content.block_content
+    filename = TEST_DATA_PATH / "pdf/9112674.pdf"
+    content = await editor.read(str(filename))
+    size = filename.stat().st_size
+    assert "similarity_search" in content.block_content and size > 5 * DEFAULT_MIN_TOKEN_COUNT
 
 
 if __name__ == "__main__":