fix(code_execution): handle empty enabled_sandbox_tools in schema description

build_execute_code_schema(set()) produced "from hermes_tools import , ..."
in the code property description — invalid Python syntax shown to the model.

This triggers when a user enables only the code_execution toolset without
any of the sandbox-allowed tools (e.g. `hermes tools code_execution`),
because SANDBOX_ALLOWED_TOOLS & {"execute_code"} = empty set.

Also adds 29 unit tests covering build_execute_code_schema, environment
variable filtering, execute_code edge cases, and interrupt handling.

tools/code_execution_tool.py

@@ -651,7 +651,10 @@ def build_execute_code_schema(enabled_sandbox_tools: set = None) -> dict:
     import_examples = [n for n in ("web_search", "terminal") if n in enabled_sandbox_tools]
     if not import_examples:
         import_examples = sorted(enabled_sandbox_tools)[:2]
-    import_str = ", ".join(import_examples) + ", ..."
+    if import_examples:
+        import_str = ", ".join(import_examples) + ", ..."
+    else:
+        import_str = "..."
 
     description = (
         "Run a Python script that can call Hermes tools programmatically. "