Update core/evolution_engine.py

core/evolution_engine.py

@@ -1,28 +1,33 @@
 # algoforge_prime/core/evolution_engine.py
 from .llm_clients import call_huggingface_api, call_gemini_api, LLMResponse
 from ..prompts.system_prompts import get_system_prompt
+# from ..prompts.prompt_templates import format_evolution_user_prompt # If you create one
 
 def evolve_solution(
-    original_solution_text,
-    original_critique_text, # This now includes test results if any
-    original_score,
-    problem_description,
-    problem_type,
-    llm_client_config # Dict: {"type": ..., "model_id": ..., "temp": ..., "max_tokens": ...}
-):
-    system_p_evolve = get_system_prompt("evolution_general", problem_type)
+    original_solution_text: str,
+    comprehensive_critique_text: str, # This includes LLM critique + test summary
+    original_combined_score: int,
+    problem_description: str,
+    problem_type: str,
+    llm_client_config: dict # {"type": ..., "model_id": ..., "temp": ..., "max_tokens": ...}
+) -> str: # Returns evolved solution text or an error string
+    """
+    Attempts to evolve a solution based on its critique and score.
+    """
+    system_p_evolve = get_system_prompt("evolution_general") # problem_type can be used for specialization
     
-    # Construct a more detailed user prompt for evolution
     user_p_evolve = (
-        f"Original Problem (for context): \"{problem_description}\"\n\n"
-        f"The current leading solution (which had a score of {original_score}/10) is:\n```\n{original_solution_text}\n```\n"
-        f"The comprehensive critique for this solution was:\n'''\n{original_critique_text}\n'''\n\n"
-        f"Your mission: Evolve this solution. Make it demonstrably superior based on the critique and any test failures mentioned. "
-        "If the original solution was just a sketch, flesh it out. If it had flaws (especially those highlighted by tests), fix them. "
-        "If it was good, make it great. Explain the key improvements you've made as part of your response."
+        f"Original Problem Context: \"{problem_description}\"\n\n"
+        f"The solution to be evolved achieved a score of {original_combined_score}/10.\n"
+        f"Here is the solution text:\n```python\n{original_solution_text}\n```\n\n"
+        f"Here is the comprehensive evaluation and critique it received (including any automated test feedback):\n'''\n{comprehensive_critique_text}\n'''\n\n"
+        f"Your Task: Based on the above, evolve the provided solution to make it demonstrably superior. "
+        f"Address any flaws, incompleteness, or inefficiencies mentioned in the critique or highlighted by test failures. "
+        f"If the solution was good, make it even better (e.g., more robust, more efficient, clearer). "
+        f"Clearly explain the key improvements you've made as an integral part of your evolved response (e.g., in comments or a concluding summary)."
     )
 
-    llm_response_obj = None
+    llm_response_obj = None # type: LLMResponse
     if llm_client_config["type"] == "hf":
         llm_response_obj = call_huggingface_api(
             user_p_evolve, llm_client_config["model_id"],
@@ -35,10 +40,10 @@ def evolve_solution(
             temperature=llm_client_config["temp"], max_new_tokens=llm_client_config["max_tokens"],
             system_prompt_text=system_p_evolve
         )
+    else:
+        return f"ERROR (Evolution): Unknown LLM client type '{llm_client_config['type']}'"
 
-    if llm_response_obj and llm_response_obj.success:
+    if llm_response_obj.success:
         return llm_response_obj.text
-    elif llm_response_obj:
-        return f"ERROR (Evolution): {llm_response_obj.error}"
     else:
-        return "ERROR (Evolution): Unknown error during LLM call."
+        return f"ERROR (Evolution with {llm_response_obj.model_id_used}): {llm_response_obj.error}"