feat: add agent runtime reliability report

[hyeokjun32]

Summary

• Added a Lab-owned Agent Runtime Reliability Report path.
• Bundles Orchestrator orchestration_summary and AIGuard runtime reliability guard_analysis into an agent deployment decision context.
• Added CLI support via agent-runtime-report with text/json/markdown output.
• Added lightweight fixtures and portfolio documentation for the 3-agent runtime reliability demo.

Validation

• poetry run python3 -m pytest tests/test_agent_runtime_report.py -q
• poetry run inferedgelab agent-runtime-report --orchestration-summary examples/agent_runtime/agent_3_orchestration_summary.json --guard-analysis examples/agent_runtime/aiguard_runtime_guard_analysis.json
• poetry run inferedgelab portfolio-demo-check
• poetry run python3 -m pytest -q
• git diff --check

Impact

• Connects Forge -> Runtime -> Orchestrator -> AIGuard evidence into a Lab-owned report surface.
• Keeps existing Runtime result, compare output, and classic deployment decision contracts unchanged.

Notes

• This is local-first report evidence, not a production cloud orchestration dashboard.
• Lab remains the final deployment decision owner.