From 20b228cb0fc99d99220404c00d4f97acb8247c71 Mon Sep 17 00:00:00 2001
From: Fang Zhiyuan <300441457+olong75@users.noreply.github.com>
Date: Mon, 31 Aug 2026 02:30:49 +0800
Subject: [PATCH] fix: add encoding="utf-8" to state_store.py
 read_text/write_text calls

---
 backend/app/faros/runtime/state_store.py      | 12 ++--
 .../tests/test_pr_b21_state_store_encoding.py | 59 +++++++++++++++++++
 2 files changed, 65 insertions(+), 6 deletions(-)
 create mode 100644 backend/tests/test_pr_b21_state_store_encoding.py

diff --git a/backend/app/faros/runtime/state_store.py b/backend/app/faros/runtime/state_store.py
index 6d01e300..6549c05a 100644
--- a/backend/app/faros/runtime/state_store.py
+++ b/backend/app/faros/runtime/state_store.py
@@ -82,7 +82,7 @@ def list_runs(self) -> List[Dict[str, Any]]:
         runs = []
         for path in sorted(self.root.glob("*/run.json"), reverse=True):
             try:
-                runs.append(json.loads(path.read_text()))
+                runs.append(json.loads(path.read_text(encoding="utf-8")))
             except Exception:
                 continue
         return runs
@@ -91,7 +91,7 @@ def get_run(self, run_id: str) -> Optional[Dict[str, Any]]:
         path = self._run_path(run_id)
         if not path.is_file():
             return None
-        return json.loads(path.read_text())
+        return json.loads(path.read_text(encoding="utf-8"))
 
     def update_run(self, run_id: str, updates: Dict[str, Any]) -> Dict[str, Any]:
         record = self.get_run(run_id)
@@ -120,7 +120,7 @@ def list_events(self, run_id: str) -> List[Dict[str, Any]]:
         path = self._events_path(run_id)
         if not path.is_file():
             return []
-        return json.loads(path.read_text())
+        return json.loads(path.read_text(encoding="utf-8"))
 
     def append_event(self, run_id: str, event: Dict[str, Any]) -> None:
         events = self.list_events(run_id)
@@ -131,7 +131,7 @@ def list_artifacts(self, run_id: str) -> List[Dict[str, Any]]:
         path = self._artifacts_path(run_id)
         if not path.is_file():
             return []
-        return json.loads(path.read_text())
+        return json.loads(path.read_text(encoding="utf-8"))
 
     def append_artifacts(self, run_id: str, artifacts: List[Dict[str, Any]]) -> None:
         existing: List[Dict[str, Any]] = []
@@ -158,7 +158,7 @@ def get_memory(self, run_id: str) -> Dict[str, Any]:
         path = self._memory_path(run_id)
         if not path.is_file():
             return {}
-        return json.loads(path.read_text())
+        return json.loads(path.read_text(encoding="utf-8"))
 
     def save_memory(self, run_id: str, memory: Dict[str, Any]) -> None:
         self._save_json(self._memory_path(run_id), memory)
@@ -181,4 +181,4 @@ def _validate_step_updates(self, current_step: Dict[str, Any], updates: Dict[str
 
     def _save_json(self, path: Path, payload: Any) -> None:
         path.parent.mkdir(parents=True, exist_ok=True)
-        path.write_text(json.dumps(payload, indent=2, default=str))
+        path.write_text(json.dumps(payload, indent=2, default=str), encoding="utf-8")
diff --git a/backend/tests/test_pr_b21_state_store_encoding.py b/backend/tests/test_pr_b21_state_store_encoding.py
new file mode 100644
index 00000000..95d0d7fc
--- /dev/null
+++ b/backend/tests/test_pr_b21_state_store_encoding.py
@@ -0,0 +1,59 @@
+"""Regression: FAROS state store must persist non-ASCII run data on any locale.
+
+read_text()/write_text() in state_store omitted encoding="utf-8", so run
+records containing Chinese paper titles or Unicode agent outputs raised
+UnicodeEncodeError/UnicodeDecodeError on hosts whose default locale is
+not UTF-8 (Windows cp1252, minimal C/POSIX containers).
+"""
+
+import os
+import sys
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
+
+from app.faros.runtime.state_store import FarosStateStore
+
+
+def _make_run(store):
+    return store.create_run(
+        blueprint_id="bp_test",
+        profile_id="pf_test",
+        execution_mode="sequential",
+        inputs={"topic": "基于检索增强的科学写作框架研究"},
+        steps=[],
+    )
+
+
+def test_run_roundtrip_preserves_chinese_inputs(tmp_path):
+    store = FarosStateStore(root=tmp_path)
+    run = _make_run(store)
+
+    loaded = store.get_run(run["id"])
+
+    assert loaded is not None
+    assert loaded["inputs"]["topic"] == "基于检索增强的科学写作框架研究"
+
+
+def test_list_runs_survives_nonascii_records(tmp_path):
+    store = FarosStateStore(root=tmp_path)
+    _make_run(store)
+
+    runs = store.list_runs()
+
+    assert len(runs) == 1
+    assert runs[0]["inputs"]["topic"] == "基于检索增强的科学写作框架研究"
+
+
+def test_memory_and_events_preserve_unicode(tmp_path):
+    store = FarosStateStore(root=tmp_path)
+    run = _make_run(store)
+
+    store.save_memory(run["id"], {"summary": "实验结果表明方法有效 ✓"})
+    store.append_event(run["id"], {"type": "log", "message": "步骤完成：数据预处理"})
+    store.append_artifacts(run["id"], [{"name": "图表", "path": "/tmp/图表.png"}])
+
+    assert store.get_memory(run["id"])["summary"] == "实验结果表明方法有效 ✓"
+    assert store.list_events(run["id"])[0]["message"] == "步骤完成：数据预处理"
+    assert store.list_artifacts(run["id"])[0]["name"] == "图表"
+
+    print("PASS: state store non-ASCII round-trips")