fix(state): persist json checkpoints as utf-8 (#7257)

* fix(state): persist json checkpoints as utf-8

* test: import pathlib Path in checkpoint tests

---------

Co-authored-by: Vidit Ostwal <110953813+Vidit-Ostwal@users.noreply.github.com>

lib/crewai/src/crewai/state/provider/json_provider.py

@@ -63,7 +63,7 @@ class JsonProvider(BaseProvider):
         file_path = _build_path(location, branch, parent_id)
         file_path.parent.mkdir(parents=True, exist_ok=True)
 
-        with open(file_path, "w") as f:
+        with open(file_path, "w", encoding="utf-8") as f:
             f.write(data)
         return str(file_path)
 
@@ -91,7 +91,7 @@ class JsonProvider(BaseProvider):
         file_path = _build_path(location, branch, parent_id)
         await aiofiles.os.makedirs(str(file_path.parent), exist_ok=True)
 
-        async with aiofiles.open(file_path, "w") as f:
+        async with aiofiles.open(file_path, "w", encoding="utf-8") as f:
             await f.write(data)
         return str(file_path)
 
@@ -129,7 +129,7 @@ class JsonProvider(BaseProvider):
         Returns:
             The raw JSON string.
         """
-        return Path(location).read_text()
+        return Path(location).read_text(encoding="utf-8")
 
     async def afrom_checkpoint(self, location: str) -> str:
         """Read a JSON checkpoint file asynchronously.
@@ -140,7 +140,7 @@ class JsonProvider(BaseProvider):
         Returns:
             The raw JSON string.
         """
-        async with aiofiles.open(location) as f:
+        async with aiofiles.open(location, encoding="utf-8") as f:
             return await f.read()
 
 

lib/crewai/tests/test_checkpoint.py

@@ -8,6 +8,7 @@ import os
 import sqlite3
 import tempfile
 import time
+from pathlib import Path
 from typing import Any
 from unittest.mock import MagicMock, patch
 
@@ -378,6 +379,25 @@ class TestJsonProviderFork:
             assert path.endswith(".json")
             assert os.path.isfile(path)
 
+    def test_checkpoint_uses_utf8_for_non_ascii_json(self) -> None:
+        provider = JsonProvider()
+        data = '{"message": "olá niño"}'
+        with tempfile.TemporaryDirectory() as d:
+            path = provider.checkpoint(data, d, branch="main")
+
+            assert Path(path).read_bytes() == data.encode("utf-8")
+            assert provider.from_checkpoint(path) == data
+
+    @pytest.mark.asyncio
+    async def test_acheckpoint_uses_utf8_for_non_ascii_json(self) -> None:
+        provider = JsonProvider()
+        data = '{"message": "olá niño"}'
+        with tempfile.TemporaryDirectory() as d:
+            path = await provider.acheckpoint(data, d, branch="main")
+
+            assert Path(path).read_bytes() == data.encode("utf-8")
+            assert await provider.afrom_checkpoint(path) == data
+
     def test_checkpoint_fork_branch_subdir(self) -> None:
         provider = JsonProvider()
         with tempfile.TemporaryDirectory() as d: