Enhance skills tool to have an arg so it is more reliably called, and error handling in agent

- Updated the `skills_categories` function to include a `verbose` parameter, allowing users to request skill counts per category.
- Modified the `handle_skills_function_call` method to pass the `verbose` argument to `skills_categories`.
- Improved error handling in the `AIAgent` class by injecting a recovery message when invalid JSON arguments are detected, guiding users on how to correct their tool calls.
- Enhanced the `GatewayRunner` to return a user-friendly error message if the agent fails to generate a final response, improving overall user experience.

gateway/run.py

@@ -451,7 +451,16 @@ class GatewayRunner:
             # TODO: Implement proper history restoration
             
             result = agent.run_conversation(message)
-            return result.get("final_response", "(No response)")
+            
+            # Return final response, or a message if something went wrong
+            final_response = result.get("final_response")
+            if final_response:
+                return final_response
+            elif result.get("error"):
+                # Agent couldn't recover - show the error
+                return f"⚠️ {result['error']}"
+            else:
+                return "(No response generated)"
         
         # Start progress message sender if enabled
         progress_task = None

model_tools.py

@@ -406,10 +406,15 @@ def get_skills_tool_definitions() -> List[Dict[str, Any]]:
             "type": "function",
             "function": {
                 "name": "skills_categories",
-                "description": "List available skill categories. Call first if you want to discover categories, then use skills_list(category) to filter, or call skills_list if unsure.",
+                "description": "List available skill categories. Call this first to discover what skill categories exist, then use skills_list(category) to see skills in a category.",
                 "parameters": {
                     "type": "object",
-                    "properties": {},
+                    "properties": {
+                        "verbose": {
+                            "type": "boolean",
+                            "description": "If true, include skill counts per category. Default: false."
+                        }
+                    },
                     "required": []
                 }
             }
@@ -907,7 +912,8 @@ def handle_skills_function_call(function_name: str, function_args: Dict[str, Any
         str: Function result as JSON string
     """
     if function_name == "skills_categories":
-        return skills_categories()
+        verbose = function_args.get("verbose", False)
+        return skills_categories(verbose=verbose)
     
     elif function_name == "skills_list":
         category = function_args.get("category")

run_agent.py

@@ -1725,16 +1725,20 @@ class AIAgent:
                             # Don't add anything to messages, just retry the API call
                             continue
                         else:
-                            print(f"{self.log_prefix}❌ Max retries (3) for invalid JSON arguments exceeded. Stopping as partial.")
-                            self._invalid_json_retries = 0  # Reset for next conversation
-                            return {
-                                "final_response": None,
-                                "messages": messages,  # Messages up to last valid point
-                                "api_calls": api_call_count,
-                                "completed": False,
-                                "partial": True,
-                                "error": f"Model generated invalid JSON arguments for tool '{tool_name}': {error_msg}"
-                            }
+                            # Instead of returning partial, inject a helpful message and let model recover
+                            print(f"{self.log_prefix}⚠️  Injecting recovery message for invalid JSON...")
+                            self._invalid_json_retries = 0  # Reset for next attempt
+                            
+                            # Add a user message explaining the issue
+                            recovery_msg = (
+                                f"Your tool call to '{tool_name}' had invalid JSON arguments. "
+                                f"Error: {error_msg}. "
+                                f"For tools with no required parameters, use an empty object: {{}}. "
+                                f"Please either retry the tool call with valid JSON, or respond without using that tool."
+                            )
+                            messages.append({"role": "user", "content": recovery_msg})
+                            # Continue the loop - model will see this message and can recover
+                            continue
                     
                     # Reset retry counter on successful JSON validation
                     self._invalid_json_retries = 0

tools/skills_tool.py

@@ -349,7 +349,7 @@ def _load_category_description(category_dir: Path) -> Optional[str]:
         return None
 
 
-def skills_categories(task_id: str = None) -> str:
+def skills_categories(verbose: bool = False, task_id: str = None) -> str:
     """
     List available skill categories with descriptions (progressive disclosure tier 0).
     
@@ -358,6 +358,7 @@ def skills_categories(task_id: str = None) -> str:
     or first paragraph to explain what skills are in that category.
     
     Args:
+        verbose: If True, include skill counts per category (default: False, but currently always included)
         task_id: Optional task identifier (unused, for API consistency)
         
     Returns: