feat: System tick performance metrics

[Doglightning]

https://www.loom.com/share/bd3c9f6293ad488b83d2b9fce3d8d9a4

TL;DR

Added performance monitoring and profiling capabilities to Cardinal's debug module to track system execution times and tick performance.

What changed?

This PR adds comprehensive performance monitoring to Cardinal's debug module:

1. Added a new performance package with:
   • Ring buffer data structures for storing tick timing samples and system execution spans
   • Statistics collection for tick durations, overruns, and system-level execution times
   • Freshness tracking to monitor tick recency
2. Enhanced the ECS scheduler to:
   • Track execution time of individual systems
   • Pass tick timestamps through the execution chain
   • Support optional performance callbacks for instrumentation
3. Added new debug service endpoints:
   • PerfOverview - Returns aggregated tick timing statistics (avg, p95, max durations)
   • PerfSchedule - Returns detailed per-system execution spans for visualizing the tick timeline
4. Modified the World's tick flow to:
   • Record tick start/end times
   • Track system execution spans
   • Maintain performance metrics with minimal overhead when debug mode is disabled

How to test?

1. Enable debug mode when creating a Cardinal world
2. Use the debug service endpoints to query performance data:
   • Call PerfOverview with a window of 10, 60, or 300 seconds to get tick timing statistics
   • Call PerfSchedule with a window of 10 or 60 seconds to get system execution spans
3. Observe the performance metrics in high-load scenarios to identify bottlenecks

Why make this change?

Performance monitoring is critical for game development to:

1. Identify systems that are taking too long to execute
2. Detect when ticks are exceeding their time budget (overruns)
3. Visualize the execution timeline to optimize system scheduling
4. Provide developers with insights to maintain consistent tick rates
5. Help diagnose performance issues in production environments

This change enables developers to profile their Cardinal worlds with minimal overhead, making it easier to build performant games that maintain consistent frame rates.

[Doglightning]

• feat: System tick performance metrics #870 👈 (View in Graphite)
• feat: debugger mvp #868 : 2 other dependent PRs (#869 , #871 )
• refactor: cardinal #865 : 2 other dependent PRs (#863 , #867 )
• main

---

How to use the Graphite Merge Queue

Add the label graphite/merge to this PR to add it to the merge queue.

You must have a Graphite account in order to use the merge queue. Sign up using this link.

An organization admin has enabled the Graphite Merge Queue in this repository.

Please do not merge from GitHub as this will restart CI on PRs being processed by the merge queue.

This stack of pull requests is managed by Graphite. Learn more about stacking.

[rmrt1n]

Here's an amp thread I used to help w my review if you're interested. It's a bit unstructured though.