tpmjs/packages/tools/official/slo-draft/README.md
Ajax Davis 5d2096fb5d feat: add 100+ official TPMJS tools
Implements a comprehensive suite of AI SDK v6 tools across multiple categories:

- Research (5): page-brief, compare-pages, source-credibility, claim-checklist, timeline-from-text
- Web (10): fetch-text, links-catalog, extract-meta, extract-json-ld, redirect-trace, sitemap-read, rss-read, table-extract, robots-policy, url-normalize
- Data (15): csv-parse, csv-stringify, json-repair, json-schema-validate, yaml-parse, yaml-stringify, text-chunk, normalize-whitespace, dedupe-by-key, pivot, rows-filter, rows-sort, rows-group-aggregate, rows-join, schema-infer
- Doc (12): toc-generate, glossary-build, faq-from-text, executive-brief, decision-record-adr, prd-outline, acceptance-criteria, style-rewrite
- Eng (12): diff-text-unified, env-var-docs-generate, dependency-audit-lite, conventional-commit-suggest, markdown-lint-basic, test-case-generate, stacktrace-parse, release-notes, changelog-entry, release-checklist
- Security (7): redact-secrets, secret-scan-text, url-risk-heuristic, csp-compose, hardening-checklist-web, access-control-matrix, data-classification-heuristic
- Stats (9): effect-size-suite, bootstrap-ci, permutation-test, multiple-testing-adjust, linear-regression-ols, logistic-regression, time-series-decompose-lite, anomaly-detect-mad
- Ops (7): slo-draft, runbook-draft, postmortem-draft, postmortem-action-extractor, error-log-triage, coverage-tracker, monitoring-gap-analysis
- Agent (15): prompt-to-workflow-skeleton, workflow-validate-io, workflow-explain, workflow-cost-estimate, tool-call-accuracy-score, eval-fixture-build, guardrail-policy-draft, workflow-auto-repair, tool-selection-plan, novelty-score-workflow, workflow-variant-generate, config-normalize, recipe-*
- Utility (8): base64-encode, base64-decode, hash-text, regex-extract, template-render, date-parse, json-path-query, url-parse
- HTML (3): html-sanitize, html-to-markdown, markdown-to-html

All tools follow AI SDK v6 pattern with tool() and jsonSchema<T>().

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-31 22:55:56 +10:00

2.4 KiB

@tpmjs/tools-slo-draft

Draft Service Level Objective (SLO) definitions for services with comprehensive documentation, error budgets, and alerting strategies.

Installation

npm install @tpmjs/tools-slo-draft

Usage

import { sloDraftTool } from '@tpmjs/tools-slo-draft';

// Use with Vercel AI SDK
const result = await sloDraftTool.execute({
  serviceName: 'Payment API',
  metrics: [
    {
      name: 'Availability',
      target: 99.9,
      window: '30d'
    },
    {
      name: 'API Latency P99',
      target: 95.0,
      window: 'rolling 7 days'
    },
    {
      name: 'Error Rate',
      target: 99.5,
      window: '30d'
    }
  ]
});

console.log(result.slo); // Markdown formatted SLO document
console.log(result.summary); // Brief summary
console.log(result.metrics); // Processed metrics with severity

Input

  • serviceName (string, required): Name of the service
  • metrics (array, required): Array of metric objects with:
    • name (string): Metric name (e.g., "Availability", "Latency P99")
    • target (number): Target percentage (0-100)
    • window (string): Time window (e.g., "30d", "7 days", "rolling 30 days")

Output

Returns an object with:

  • slo (string): Comprehensive SLO document in markdown format
  • metrics (array): Processed metrics with additional metadata:
    • Original name, target, window
    • windowType: 'rolling' or 'calendar'
    • severity: 'critical' (≥99.9%), 'high' (≥99%), or 'medium' (<99%)
  • summary (string): Brief summary of the SLO
  • metadata (object):
    • serviceName: Service name
    • createdAt: ISO timestamp
    • totalMetrics: Total number of metrics
    • criticalMetrics: Number of critical severity metrics

Features

  • Automatic Severity Classification: Metrics are classified as critical, high, or medium based on targets
  • Error Budget Calculation: Calculates allowed downtime for each metric
  • Alerting Strategy: Provides burn rate-based alerting recommendations
  • Window Type Detection: Automatically detects rolling vs calendar windows
  • Comprehensive Documentation: Generates full SLO document with monitoring and review processes

Example Output

The tool generates a markdown document including:

  • SLO definitions with targets and allowed downtime
  • Error budget policies
  • Alerting strategies based on severity
  • Review processes and schedules
  • Links to related documentation

License

MIT