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>
2.8 KiB
2.8 KiB
@tpmjs/tools-postmortem-draft
Draft postmortem documents from incident details with timeline and action items.
Installation
npm install @tpmjs/tools-postmortem-draft
Usage
import { postmortemDraftTool } from '@tpmjs/tools-postmortem-draft';
const result = await postmortemDraftTool.execute({
title: 'Database Connection Pool Exhaustion',
timeline: [
{
time: '2025-01-15T14:23:00Z',
event: 'First alerts for elevated error rates',
},
{
time: '2025-01-15T14:25:00Z',
event: 'Connection pool exhaustion confirmed',
},
{
time: '2025-01-15T14:30:00Z',
event: 'Emergency pool size increase deployed',
},
{
time: '2025-01-15T14:35:00Z',
event: 'Service restored, errors subsiding',
},
{
time: '2025-01-15T14:45:00Z',
event: 'Incident resolved, monitoring continues',
},
],
rootCause:
'Database connection pool size was set to 10 connections, which was insufficient for peak traffic. A code deployment earlier that day introduced a connection leak that slowly exhausted the pool.',
actionItems: [
'Increase connection pool size from 10 to 50',
'Add connection pool monitoring and alerting',
'Review code for connection leaks and add tests',
'Implement circuit breaker pattern for database calls',
],
});
console.log(result.postmortem);
// Markdown-formatted postmortem document
console.log(`Severity: ${result.severity}`);
console.log(`Duration: ${result.duration}`);
Features
- Generates structured markdown postmortem documents
- Automatically calculates incident duration from timeline
- Assesses severity based on incident characteristics
- Includes timeline, root cause, and action items
- Follows SRE postmortem best practices
- Adds placeholder sections for team review
Input
PostmortemDraftInput
title(string, required): Title of the incidenttimeline(array, required): Array of timeline eventsrootCause(string, required): Root cause analysisactionItems(array, required): Array of action items
TimelineEvent
time(string, required): Timestamp of the event (ISO 8601 recommended)event(string, required): Description of what happened
Output
PostmortemDraft
postmortem(string): Markdown-formatted postmortem documentseverity(string): Assessed severity ('low' | 'medium' | 'high' | 'critical')duration(string | null): Calculated incident duration
Severity Assessment
The tool automatically assesses severity based on keywords and timeline:
- Critical: Complete outage, data loss, security breach
- High: Major outage, service down, significant customer impact
- Medium: Degraded performance, partial outage
- Low: Minor issues, minimal impact
License
MIT