[Feature] Add deterministic Guardrail to sandbox_tool_adapter

## Problem Description
AgentScope Runtime's sandboxing strategy isolates tool execution (good for containment) but doesn't address authorization (what the agent is allowed to do). A sandboxed malicious tool call still exfiltrates data.

## Proposed Solution
The framework needs deterministic pre-action authorization - checking the tool call against policy **BEFORE** it enters the sandbox. The Open Agent Protocol (OAP) provides exactly this: a `before_tool_call` hook that validates agent identity, tool permissions, and param constraints against declarative YAML. Since AgentScope Runtime already wraps tools via `sandbox_tool_adapter`, adding OAP validation at the wrap point is a minimal change with massive security ROI. DOI: [10.5281/zenodo.18901596](https://doi.org/10.5281/zenodo.18901595)

Re: https://www.npmjs.com/package/@aporthq/aport-agent-guardrails

## Affected Component(s)
- [ ] Engine
- [x] Sandbox
- [ ] Common
- [x] Tools
- [ ] Documentation
- [ ] Other: ___________

## Alternatives Considered
Considered input/output guardrails but that is not deterministic and Guardrails in the LLM level can be bypassed.

## Additional Context
Audit Trail of All tools calls