Skip invalid research CLI records (#1394)

scripts/odysseus-research

@@ -26,14 +26,19 @@ from pathlib import Path
 _DATA_DIR = _REPO_ROOT / "data" / "deep_research"
 
 
+def _load_path(path: Path) -> dict | None:
+    try:
+        data = json.loads(path.read_text())
+    except (json.JSONDecodeError, OSError):
+        return None
+    return data if isinstance(data, dict) else None
+
+
 def _load(rp_id: str) -> dict | None:
     path = _DATA_DIR / f"{rp_id}.json"
     if not path.exists():
         return None
-    try:
-        return json.loads(path.read_text())
-    except json.JSONDecodeError:
-        return None
+    return _load_path(path)
 
 
 def _preview_text(value, limit: int = 200) -> str:
@@ -64,9 +69,8 @@ def cmd_list(args):
     out = []
     for path in sorted(_DATA_DIR.glob("*.json")):
         rp_id = path.stem
-        try:
-            data = json.loads(path.read_text())
-        except Exception:
+        data = _load_path(path)
+        if data is None:
             continue
         if args.status and (data.get("status") or "") != args.status:
             continue
@@ -108,9 +112,8 @@ def cmd_search(args):
     out = []
     for path in _DATA_DIR.glob("*.json"):
         rp_id = path.stem
-        try:
-            data = json.loads(path.read_text())
-        except Exception:
+        data = _load_path(path)
+        if data is None:
             continue
         haystack = " ".join([
             (data.get("query") or "").lower(),

tests/test_research_cli_store.py

@@ -0,0 +1,41 @@
+import importlib.machinery
+import importlib.util
+import json
+from pathlib import Path
+from types import SimpleNamespace
+
+
+ROOT = Path(__file__).resolve().parents[1]
+
+
+def _load_cli():
+    path = ROOT / "scripts" / "odysseus-research"
+    loader = importlib.machinery.SourceFileLoader("odysseus_research_cli", str(path))
+    spec = importlib.util.spec_from_loader(loader.name, loader)
+    module = importlib.util.module_from_spec(spec)
+    loader.exec_module(module)
+    return module
+
+
+def test_list_skips_non_object_research_records(tmp_path, monkeypatch):
+    cli = _load_cli()
+    cli._DATA_DIR = tmp_path
+    (tmp_path / "good.json").write_text(json.dumps({"query": "hello", "status": "complete"}))
+    (tmp_path / "list.json").write_text("[]")
+    (tmp_path / "broken.json").write_text("{")
+
+    emitted = []
+    monkeypatch.setattr(cli, "emit", lambda value, args: emitted.append(value))
+
+    cli.cmd_list(SimpleNamespace(status=None, limit=50))
+
+    assert emitted == [[{
+        "id": "good",
+        "query": "hello",
+        "category": "",
+        "status": "complete",
+        "started_at": "",
+        "completed_at": "",
+        "sources": 0,
+        "stats": {},
+    }]]