fix: atomic writes for manifest/record_run/update_best (tmp+replace)

app/harness/workspace.py

@@ -64,6 +64,21 @@ def _now_iso() -> str:
     return datetime.now(UTC).isoformat()
 
 
+def _atomic_write_json(path: Path, data: dict) -> None:
+    """原子写 JSON：tmp + os.replace（对齐 checkpoint.py 范式，防半截损坏）。
+
+    先写同目录临时文件，再 os.replace 原子替换目标；替换阶段崩溃不会留下半截
+    JSON，原文件保持完好。
+
+    参数:
+        path: 目标 JSON 文件路径。
+        data: 待序列化的字典。
+    """
+    tmp = path.with_name(path.name + ".tmp")
+    tmp.write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
+    os.replace(tmp, path)
+
+
 # ---------------------------------------------------------------------------
 # Workspace 核心函数
 # ---------------------------------------------------------------------------
@@ -108,7 +123,7 @@ def _scaffold_workspace(
         },
         "history": [],
     }
-    (workspace_dir / "manifest.json").write_text(json.dumps(manifest, ensure_ascii=False, indent=2))
+    _atomic_write_json(workspace_dir / "manifest.json", manifest)
 
 
 def init_workspace(
@@ -286,7 +301,7 @@ def update_manifest(workspace_dir: Path, **version_updates: str) -> None:
         raise KeyError(f"无效的 manifest current 字段: {invalid}")
     manifest = load_manifest(workspace_dir)
     manifest["current"].update(version_updates)
-    (workspace_dir / "manifest.json").write_text(json.dumps(manifest, ensure_ascii=False, indent=2))
+    _atomic_write_json(workspace_dir / "manifest.json", manifest)
 
 
 def record_run(workspace_dir: Path, run_id: str) -> Path:
@@ -315,9 +330,7 @@ def record_run(workspace_dir: Path, run_id: str) -> Path:
                 "questions": current["questions"],
             }
         )
-        (workspace_dir / "manifest.json").write_text(
-            json.dumps(manifest, ensure_ascii=False, indent=2)
-        )
+        _atomic_write_json(workspace_dir / "manifest.json", manifest)
 
     run_dir = workspace_dir / "runs" / run_id
     # exist_ok：同 run_id 重跑时 run 目录已存在不应崩溃
@@ -369,7 +382,7 @@ def update_best(
         "run_id": run_id,
         "epoch": epoch,
     }
-    (workspace_dir / "manifest.json").write_text(json.dumps(manifest, ensure_ascii=False, indent=2))
+    _atomic_write_json(workspace_dir / "manifest.json", manifest)
     logger.info("Best 已更新: val_acc={}, run={}, epoch={}", val_acc, run_id, epoch)
 
 

tests/unit/test_harness_workspace.py

@@ -259,6 +259,33 @@ def test_update_manifest_valid(store_dir: Path, workspace_dir: Path) -> None:
     assert manifest["current"]["skills"] == "skills/v2"
 
 
+def test_update_manifest_is_atomic(
+    store_dir: Path, workspace_dir: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    """写 manifest 途中崩溃不产生半截 JSON（原子写：os.replace 失败也不损原文件）。"""
+    from app.harness import workspace as ws
+
+    init_workspace(
+        workspace_dir,
+        store_dir,
+        questions="benchmarks/Video-MME",
+        skills_version="v1",
+        prompts_version="v1",
+    )
+    original = (workspace_dir / "manifest.json").read_text()
+
+    def _boom(_src: object, _dst: object) -> None:
+        raise OSError("crash during replace")
+
+    monkeypatch.setattr(ws.os, "replace", _boom)
+    with pytest.raises(OSError, match="crash during replace"):
+        update_manifest(workspace_dir, skills="skills/v2")
+
+    # 原 manifest 未被破坏（内容不变且仍是合法 JSON）
+    assert (workspace_dir / "manifest.json").read_text() == original
+    assert json.loads((workspace_dir / "manifest.json").read_text())
+
+
 # ---------------------------------------------------------------------------
 # record_run
 # ---------------------------------------------------------------------------