Squash Odysseus development history

scripts/odysseus-research

@@ -25,21 +25,52 @@ from pathlib import Path
 
 _DATA_DIR = _REPO_ROOT / "data" / "deep_research"
 
+# The CLI's --status takes the user-facing label "complete", but the writer
+# in services/research/research_handler.py stores `status="done"` when a run
+# finishes (and the legacy src/research_handler.py does the same). Without
+# this alias, --status complete filters every finished record out and the
+# user sees an empty list. Map at filter time so the on-disk corpus is the
+# source of truth and the CLI surface stays the friendlier word. The other
+# choices ("running", "cancelled", "error") are stored verbatim, so they
+# fall through unchanged.
+_STATUS_CLI_TO_STORED = {"complete": "done"}
+
+
+def _status_matches(stored, requested: str) -> bool:
+    stored = (stored or "")
+    if not isinstance(stored, str):
+        stored = ""
+    target = _STATUS_CLI_TO_STORED.get(requested, requested)
+    return stored == target
+
+
+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:
+    """Truncated preview tolerant of non-string values. A stored research
+    record whose ``query`` is a non-string (legacy/corrupt JSON) would crash
+    ``(value or "")[:200]`` with a TypeError; coerce non-strings to ""."""
+    text = value if isinstance(value, str) else ""
+    return text[:limit]
 
 
 def _summarize(rp_id: str, data: dict) -> dict:
     return {
         "id": rp_id,
-        "query": (data.get("query") or "")[:200],
+        "query": _preview_text(data.get("query")),
         "category": data.get("category") or "",
         "status": data.get("status") or "",
         "started_at": data.get("started_at") or "",
@@ -56,11 +87,10 @@ 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:
+        if args.status and not _status_matches(data.get("status"), args.status):
             continue
         out.append(_summarize(rp_id, data))
     out.sort(key=lambda r: r.get("started_at") or "", reverse=True)
@@ -100,9 +130,8 @@ 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(),