updated temperature, max_tokens -> dream_mode

dream_agent.py

@@ -66,11 +66,17 @@ def execute_dream_reflection(target_file="core_logic.py"):
     </proposed_patch>
     """
 
+    """
+    Note on max_tokens -> When making an API call to Groq without a max_tokens parameter, the server does not leave the window wide open. Instead, it applies a provider-side default cap. For most execution endpoints running Llama 3.1 models, if no parameter is specified, the engine typically cuts off or caps the generation token pool automatically (often default-limited at around 1024 or 2048 tokens).
+    """
+
     try:
         completion = client.chat.completions.create(
             model="llama-3.1-8b-instant",
             messages=[{"role": "user", "content": simulation_prompt}],
-            temperature=0.1  # Low temperature to preserve structural discipline
+            temperature=0.0,       # Force absolute deterministic logic pathing
+            max_tokens=4096,       # Allots enough context space to prevent truncation loops
+            top_p=1.0              # Works alongside temp=0.0 to focus token selection tightly
         )
         
         proposal_payload = completion.choices[0].message.content