feat: Added benchmarks for agent-sdk-go performance and scale testing

[vinodvx]

Description

Adds a config-driven benchmark suite under benchmarks/ to measure agent-sdk-go performance (latency, memory, CPU, tokens, success rate) using real pkg/agent runs with mock LLM and tools.

Highlights

• YAML config for runtime (local/temporal), runs, concurrency, tools, sub-agents, logging, and reports
• Optional external Temporal workers and shared setup for agent/worker fingerprint alignment
• JSON/text reports and optional SDK logs for debugging

Test plan

• go run ./benchmarks/ with default config.yaml (local runtime)
• Run with runtime: temporal and Temporal server up
• Verify reports under benchmarks/reports/ and logs when logger.enabled: true

Type of change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation update
• Refactor / chore

Related issues

Close #20

Checklist

• I have run make lint and make test locally
• I have run make tidy if I added or removed dependencies
• Commit messages follow conventional commits (e.g. feat:, fix:, docs:)
• I have added/updated tests for my changes
• Documentation is updated if needed

[codecov]

Codecov Report

❌ Patch coverage is 0% with 641 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
benchmarks/setup/mock_llm.go	0.00%	95 Missing ⚠️
benchmarks/setup/config.go	0.00%	78 Missing ⚠️
benchmarks/runner.go	0.00%	61 Missing ⚠️
benchmarks/report.go	0.00%	59 Missing ⚠️
benchmarks/metrics.go	0.00%	48 Missing ⚠️
benchmarks/main.go	0.00%	47 Missing ⚠️
benchmarks/setup/tree.go	0.00%	44 Missing ⚠️
benchmarks/worker_manager.go	0.00%	42 Missing ⚠️
benchmarks/setup/opts.go	0.00%	41 Missing ⚠️
benchmarks/worker/main.go	0.00%	40 Missing ⚠️
... and 4 more

📢 Thoughts on this report? Let us know!