fix: store full AI response in convo_miner exchange chunking

mempalace/convo_miner.py

@@ -70,7 +70,7 @@ def _chunk_by_exchange(lines: list) -> list:
                     ai_lines.append(next_line.strip())
                 i += 1
 
-            ai_response = " ".join(ai_lines[:8])
+            ai_response = " ".join(ai_lines)
             content = f"{user_turn}\n{ai_response}" if ai_response else user_turn
 
             if len(content.strip()) > MIN_CHUNK_SIZE:

tests/test_convo_miner_unit.py

@@ -47,6 +47,17 @@ def test_short_content_skipped(self):
         # Too short to produce chunks (below MIN_CHUNK_SIZE)
         assert isinstance(chunks, list)
 
+    def test_long_ai_response_not_truncated(self):
+        """AI responses longer than 8 lines must be stored in full (verbatim principle)."""
+        lines = [f"Step {i}: important detail that must be stored" for i in range(1, 14)]
+        content = "> How do I implement authentication?\n" + "\n".join(lines)
+        chunks = chunk_exchanges(content)
+        assert len(chunks) >= 1
+        stored = chunks[0]["content"]
+        # All 13 lines must be present — none silently dropped
+        for i in range(1, 14):
+            assert f"Step {i}:" in stored, f"Step {i} was truncated and not stored"
+
 
 class TestDetectConvoRoom:
     def test_technical_room(self):