Validate shell commands against an allow-list without HITL interrupts.
When the agent invokes a shell tool (any tool in SHELL_TOOL_NAMES),
this middleware checks the command against the configured allow-list
before execution. Rejected commands are returned as error ToolMessage
objects — the graph never pauses, so LangSmith traces stay as a single
continuous run.
Use this middleware in non-interactive mode to avoid the interrupt/resume cycle that fragments traces.
