From 1b1854e5ae0b0a120db02b4cf44479a580e04f82 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Fri, 24 Apr 2026 05:25:34 +0000
Subject: [PATCH] fix(init): address registry review feedback

Agent-Logs-Url: https://github.com/MemPalace/mempalace/sessions/76794fde-2383-4674-ab36-f89ad803eeb2

Co-authored-by: igorls <4753812+igorls@users.noreply.github.com>
---
 mempalace/cli.py                      |  2 +-
 mempalace/miner.py                    | 30 +++++++++++++++++++--------
 tests/test_known_entities_registry.py |  7 +++++++
 3 files changed, 29 insertions(+), 10 deletions(-)

diff --git a/mempalace/cli.py b/mempalace/cli.py
index ec185c3..714c64c 100644
--- a/mempalace/cli.py
+++ b/mempalace/cli.py
@@ -125,7 +125,7 @@ def cmd_init(args):
         # global registry the miner reads at mine time.
         if confirmed["people"] or confirmed["projects"]:
             entities_path = Path(args.dir).expanduser().resolve() / "entities.json"
-            with open(entities_path, "w") as f:
+            with open(entities_path, "w", encoding="utf-8") as f:
                 json.dump(confirmed, f, indent=2, ensure_ascii=False)
             print(f"  Entities saved: {entities_path}")
 
diff --git a/mempalace/miner.py b/mempalace/miner.py
index 61b95f1..9e8ff5e 100644
--- a/mempalace/miner.py
+++ b/mempalace/miner.py
@@ -507,6 +507,12 @@ def add_to_known_entities(entities_by_category: dict) -> str:
         except (_json.JSONDecodeError, OSError):
             existing = {}
 
+    def _coerce_name(value):
+        if not value:
+            return None
+        name = str(value)
+        return name if name else None
+
     for category, names in entities_by_category.items():
         if not isinstance(names, list) or not names:
             continue
@@ -514,27 +520,33 @@ def add_to_known_entities(entities_by_category: dict) -> str:
         if isinstance(current, list):
             seen_lower = {str(n).lower() for n in current}
             for n in names:
-                if not n:
+                name = _coerce_name(n)
+                if not name:
                     continue
-                if str(n).lower() not in seen_lower:
-                    current.append(n)
-                    seen_lower.add(str(n).lower())
+                if name.lower() not in seen_lower:
+                    current.append(name)
+                    seen_lower.add(name.lower())
         elif isinstance(current, dict):
+            seen_lower = {str(name).lower() for name in current}
             for n in names:
-                if n and n not in current:
-                    current[n] = None
+                name = _coerce_name(n)
+                if not name or name.lower() in seen_lower:
+                    continue
+                current[name] = None
+                seen_lower.add(name.lower())
         else:
             # Missing or unrecognized shape — seed as a fresh list, deduped
             seen: set = set()
             ordered: list = []
             for n in names:
-                if not n:
+                name = _coerce_name(n)
+                if not name:
                     continue
-                key = str(n).lower()
+                key = name.lower()
                 if key in seen:
                     continue
                 seen.add(key)
-                ordered.append(n)
+                ordered.append(name)
             existing[category] = ordered
 
     registry_path.write_text(_json.dumps(existing, indent=2, ensure_ascii=False), encoding="utf-8")
diff --git a/tests/test_known_entities_registry.py b/tests/test_known_entities_registry.py
index cd558e3..300cfb6 100644
--- a/tests/test_known_entities_registry.py
+++ b/tests/test_known_entities_registry.py
@@ -114,6 +114,13 @@ def test_dict_format_existing_category_gets_new_keys(temp_registry):
     assert data["people"]["Carol"] is None
 
 
+def test_dict_format_dedupes_case_insensitively_and_stringifies_new_names(temp_registry):
+    temp_registry.write_text(json.dumps({"people": {"Alice": "ALC"}}))
+    miner.add_to_known_entities({"people": ["alice", 123]})
+    data = json.loads(temp_registry.read_text())
+    assert data["people"] == {"Alice": "ALC", "123": None}
+
+
 # ── error tolerance ───────────────────────────────────────────────────