fix: extract multi-digit state indices in extract_state_value_from_output

metagpt/utils/repair_llm_raw_output.py

@@ -349,10 +349,9 @@ def extract_state_value_from_output(content: str) -> str:
     """
     content = content.strip()  # deal the output cases like " 0", "0\n" and so on.
     pattern = (
-        r"(?<!-)[0-9]"  # TODO find the number using a more proper method not just extract from content using pattern
+        r"-?\d+"  # extract the first (possibly multi-digit or negative) integer from the output
     )
     matches = re.findall(pattern, content, re.DOTALL)
-    matches = list(set(matches))
     state = matches[0] if len(matches) > 0 else "-1"
     return state
 

tests/metagpt/utils/test_repair_llm_raw_output.py

@@ -386,3 +386,15 @@ class Game{\n       +int score\n       +list<tile> tiles\n       +function move_
     assert output.startswith('{\n"Implementation approach"') and output.endswith(
         '"Anything UNCLEAR": "The requirement is clear to me."\n}'
     )
+
+
+def test_extract_state_value_from_output():
+    from metagpt.utils.repair_llm_raw_output import extract_state_value_from_output
+
+    # single-digit states and the "-1" no-op state are returned as-is
+    assert extract_state_value_from_output("0") == "0"
+    assert extract_state_value_from_output(" 3\n") == "3"
+    assert extract_state_value_from_output("-1") == "-1"
+    # multi-digit state indices (>= 10) must be kept whole, not split into digits
+    assert extract_state_value_from_output("10") == "10"
+    assert extract_state_value_from_output("The next state is 12.") == "12"