Reduces throwing errors when the LLM returns a verbose answer in comm…

…it classification.

Now if there is 'true' or 'false' in the answer string, it is returned as True and False respectively, instead of checking for certain output formats

prospector/llm/llm_service.py

@@ -116,17 +116,9 @@ def classify_commit(
         except Exception as e:
             raise RuntimeError(f"Prompt-model chain could not be invoked: {e}")
 
-        if is_relevant in [
-            "True",
-            "ANSWER:True",
-            "```ANSWER:True```",
-        ]:
+        if "True" in is_relevant:
             return True
-        elif is_relevant in [
-            "False",
-            "ANSWER:False",
-            "```ANSWER:False```",
-        ]:
+        elif "False" in is_relevant:
             return False
         else:
             raise RuntimeError(