Merge pull request #1404 from MemPalace/fix/1155-call-llm-retry-on-json-decode

fix(closet_llm): retry _call_llm on JSONDecodeError (#1155)

mempalace/closet_llm.py

@@ -169,6 +169,9 @@ def _call_llm(cfg: LLMConfig, source_file: str, wing: str, room: str, content: s
             parsed = json.loads(text)
             return parsed, payload.get("usage")
         except json.JSONDecodeError:
+            if attempt < 2:
+                time.sleep(2**attempt)
+                continue
             return None, None
         except urllib.error.HTTPError as e:
             # 429 / 503 = retry with backoff

tests/test_closet_llm.py

@@ -196,10 +196,34 @@ class TestCallLLM:
                 }
             )
 
-        with patch("urllib.request.urlopen", side_effect=fake_urlopen):
+        with (
-            parsed, usage = _call_llm(cfg, "/tmp/x", "w", "r", "c")
+            patch("urllib.request.urlopen", side_effect=fake_urlopen),
+            patch("mempalace.closet_llm.time.sleep"),
+        ):
+            parsed, _ = _call_llm(cfg, "/tmp/x", "w", "r", "c")
         assert parsed is None
 
+    def test_retries_on_json_decode_error(self):
+        cfg = self._make_cfg()
+        call_count = {"n": 0}
+
+        def fake_urlopen(req, timeout=None):
+            call_count["n"] += 1
+            return _FakeResp(
+                {
+                    "choices": [{"message": {"content": "not json at all"}}],
+                    "usage": {"prompt_tokens": 1, "completion_tokens": 1},
+                }
+            )
+
+        with (
+            patch("urllib.request.urlopen", side_effect=fake_urlopen),
+            patch("mempalace.closet_llm.time.sleep"),
+        ):
+            parsed, _ = _call_llm(cfg, "/tmp/x", "w", "r", "c")
+        assert parsed is None
+        assert call_count["n"] == 3
+
 
 # ── regenerate_closets error paths ───────────────────────────────────────