fix: use resolved tool_obj for fallback tool execution

When the LLM returns a short tool name that doesn't match the deduped
key in tool_map, the fallback scan correctly resolves tool_obj via
schema.name. However the execution branch still checked
`tool_name not in tool_map` and passed `tool_map[tool_name]`, so
fallback-resolved tools were never executed.

Change the condition to check `tool_obj is None` and pass `tool_obj`
directly to _execute_tool_call.

Closes #15

Made-with: Cursor

openspace/llm/client.py

@@ -754,7 +754,7 @@ class LLMClient:
                 except:
                     pass
                 
-                if tool_name not in tool_map:
+                if tool_obj is None:
                     result = ToolResult(
                         status=ToolStatus.ERROR,
                         error=f"Tool '{tool_name}' not found"
@@ -762,7 +762,7 @@ class LLMClient:
                 else:
                     try:
                         result = await _execute_tool_call(
-                            tool=tool_map[tool_name],
+                            tool=tool_obj,
                             openai_tool_call={
                                 "id": tool_call.id,
                                 "type": "function",