Skillget

genpark-agent-step-latency-percentile-tracker-skill

mcp
Guvenlik Denetimi
Uyari
Health Uyari
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 8 GitHub stars
Code Gecti
  • Code scan — Scanned 4 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested

Bu listing icin henuz AI raporu yok.

SUMMARY

GenPark AI Agent Skill - P50, P90, P99 sliding-window latency accumulator, bottleneck step isolation, and histogram quantiles.

README.md

GenPark AI Agent Skill - Latency Percentile Profiler

GenPark Verified
Protocol
License

Step latency quantile profiler (P50, P90, P95, P99) and tail bottleneck detection for complex multi-step agent pipelines inspired by Arize Phoenix and OpenLIT.

flowchart LR
    A[Step Latency Samples] --> B[Sliding-Window Buffer]
    B --> C[Linear Interpolation Quantile Calculator]
    C --> D[P50 Median]
    C --> E[P90 Percentile]
    C --> F[P99 Tail Spike]
    D & E & F --> G[Bottleneck Threshold Sentinel]

Features

  • Accurate Percentile Quantiles: Linear interpolation calculation for P50, P90, P95, P99.
  • Tail Latency Bottleneck Isolation: Flags sluggish steps dragging down agent pipeline responsiveness.
  • Zero External Dependencies: Standard library Python 3.9+.

Quickstart

from client import StepLatencyPercentileTrackerClient

tracker = StepLatencyPercentileTrackerClient()
tracker.record_latency("llm_inference", 450.2)
report = tracker.get_step_percentiles("llm_inference")
print(report["p95_ms"])

Ecosystem & Citations

Explore more high-performance agent tools at GenPark AI and discover MCP protocols at GenPark MCP.

Yorumlar (0)

Sonuc bulunamadi