Fix max_tokens calculation to respect model context window

src/llm_router.py

@@ -54,7 +54,7 @@ class LLMRouter:
             logger.info(f"✓ Novita AI API client initialized")
             logger.info(f"  Base URL: {self.settings.novita_base_url}")
             logger.info(f"  Model: {self.settings.novita_model}")
-        except Exception as e:
+            except Exception as e:
             logger.error(f"Failed to initialize Novita AI client: {e}")
             raise RuntimeError(f"Could not initialize Novita AI API client: {e}") from e
     
@@ -162,8 +162,8 @@ class LLMRouter:
                 
         except Exception as e:
             logger.error(f"Error calling Novita AI API: {e}", exc_info=True)
-            raise
-    
+                        raise
+            
     def _format_deepseek_r1_prompt(self, prompt: str, task_type: str, model_config: dict) -> str:
         """
         Format prompt according to DeepSeek-R1 best practices:
@@ -318,7 +318,7 @@ class LLMRouter:
                 continue
             
             # Estimate tokens (simple: 1 token ≈ 4 chars)
-            tokens = len(content) // 4
+                tokens = len(content) // 4
             
             if total_tokens + tokens <= max_tokens:
                 formatted_context.append(f"=== {element.upper()} ===\n{content}")
@@ -337,7 +337,7 @@ class LLMRouter:
     def _truncate_to_tokens(self, content: str, max_tokens: int) -> str:
         """Truncate content to fit within token limit"""
         # Simple character-based truncation (1 token ≈ 4 chars)
-        max_chars = max_tokens * 4
-        if len(content) <= max_chars:
-            return content
+            max_chars = max_tokens * 4
+            if len(content) <= max_chars:
+                return content
         return content[:max_chars - 3] + "..."