From a4149ab248c5aa6c314eec5e4ebaa9eaef55c29c Mon Sep 17 00:00:00 2001
From: Igor Lins e Silva <4753812+igorls@users.noreply.github.com>
Date: Tue, 7 Apr 2026 17:27:41 -0300
Subject: [PATCH] fix: use upsert and deterministic IDs to prevent data
 stagnation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

MCP tool_add_drawer:
- Make drawer_id content-based: hash full content instead of
  content[:100] + timestamp. Same content → same ID, eliminating
  TOCTOU race conditions
- Switch from col.add() to col.upsert() so re-filing with updated
  content updates the existing drawer

miner.add_drawer:
- Switch from collection.add() to collection.upsert() so re-mining
  a modified file updates instead of silently failing
- Remove the try/except catching 'already exists' — upsert handles
  this naturally

Findings: #11 (HIGH — add ignores updates), #6 (MEDIUM — TOCTOU),
          #13 (MEDIUM — non-deterministic IDs)

Includes test infrastructure from PR #131.
92 tests pass.
---
 mempalace/mcp_server.py       | 4 ++--
 mempalace/miner.py            | 6 ++----
 tests/test_knowledge_graph.py | 2 +-
 3 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/mempalace/mcp_server.py b/mempalace/mcp_server.py
index b447249..bda4c1a 100644
--- a/mempalace/mcp_server.py
+++ b/mempalace/mcp_server.py
@@ -292,10 +292,10 @@ def tool_add_drawer(
             "matches": dup["matches"],
         }
 
-    drawer_id = f"drawer_{wing}_{room}_{hashlib.md5((content[:100] + datetime.now().isoformat()).encode()).hexdigest()[:16]}"
+    drawer_id = f"drawer_{wing}_{room}_{hashlib.md5(content.encode()).hexdigest()[:16]}"
 
     try:
-        col.add(
+        col.upsert(
             ids=[drawer_id],
             documents=[content],
             metadatas=[
diff --git a/mempalace/miner.py b/mempalace/miner.py
index 7b4e949..a53cf76 100644
--- a/mempalace/miner.py
+++ b/mempalace/miner.py
@@ -417,7 +417,7 @@ def add_drawer(
     """Add one drawer to the palace."""
     drawer_id = f"drawer_{wing}_{room}_{hashlib.md5((source_file + str(chunk_index)).encode(), usedforsecurity=False).hexdigest()[:16]}"
     try:
-        collection.add(
+        collection.upsert(
             documents=[content],
             ids=[drawer_id],
             metadatas=[
@@ -432,9 +432,7 @@ def add_drawer(
             ],
         )
         return True
-    except Exception as e:
-        if "already exists" in str(e).lower() or "duplicate" in str(e).lower():
-            return False
+    except Exception:
         raise
 
 
diff --git a/tests/test_knowledge_graph.py b/tests/test_knowledge_graph.py
index d7d9838..535eace 100644
--- a/tests/test_knowledge_graph.py
+++ b/tests/test_knowledge_graph.py
@@ -6,6 +6,7 @@ timeline, stats, and edge cases (duplicate triples, ID collisions).
 """
 
 
+
 class TestEntityOperations:
     def test_add_entity(self, kg):
         eid = kg.add_entity("Alice", entity_type="person")
@@ -124,7 +125,6 @@ class TestWALMode:
         conn.close()
         assert mode == "wal"
 
-
 class TestStats:
     def test_stats_empty(self, kg):
         stats = kg.stats()