ahstn/oceans-llm / .agents/skills/verify-oceans-admin
verify-oceans-admin
VerifiedVerify the Oceans LLM admin control plane and backend gateway against the real local stack, seeded demo data, and bounded live providers when required. Use for user-path checks of sign-in, models, API keys, observability, usage costs, spend controls, batches, agent sessions, request logs, Anthropic Messages thinking and effort compatibility, MCP registry and tool access, OpenRouter routing, guardrails, and Skills storage.
scripts/check-messages.mjs
View on GitHub#!/usr/bin/env node
// Offline Messages regression gate. No gateway stack or upstream credential required.
import { spawnSync } from 'node:child_process'
import { mkdirSync, writeFileSync } from 'node:fs'
import path from 'node:path'
import { fileURLToPath } from 'node:url'
import { assessResults, regressionFingerprint } from './messages-regressions.mjs'
const repoRoot = path.resolve(path.dirname(fileURLToPath(import.meta.url)), '../../../..')
function main(args) {
if (args.length !== 2 || args[0] !== '--output' || !path.isAbsolute(args[1])) {
throw new Error('Usage: mise exec -- node .agents/skills/verify-oceans-admin/scripts/check-messages.mjs --output /absolute/path/messages-regressions.json')
}
const outputFile = args[1]
const source = regressionFingerprint()
mkdirSync(path.dirname(outputFile), { recursive: true })
const save = (result) => writeFileSync(outputFile, `${JSON.stringify({
schemaVersion: 1, generatedAt: new Date().toISOString(), ...source,
scope: 'offline Rust tests and local provider HTTP fixtures; not live native-provider or Claude Code proof',
...result,
}, null, 2)}\n`)
// Never leave an older passing result behind if compilation or execution is interrupted.
save({ verdict: 'fail', checks: [{ id: 'runner-completed', status: 'fail' }] })
const result = spawnSync(process.env.MISE_BIN || 'mise', [
'exec', '--', 'cargo', 'test', '-p', 'gateway-core', '-p', 'gateway-providers',
'-p', 'gateway', '-p', 'gateway-service', '-p', 'gateway-client-config', '--lib', '--', '--color', 'never',
], { cwd: repoRoot, encoding: 'utf8', maxBuffer: 32 * 1024 * 1024 })
const assessment = assessResults(result.stdout || '', result.status)
if (source.sourceHash !== regressionFingerprint().sourceHash) {
assessment.verdict = 'fail'
assessment.checks.push({ id: 'source-unchanged-during-tests', status: 'fail' })
}
save(assessment)
console.log(`${assessment.verdict.toUpperCase()} Messages regressions: ${assessment.passedTests} tests; ${outputFile}`)
if (assessment.verdict !== 'pass') {
console.error(assessment.checks.filter((check) => check.status !== 'pass').map((check) => check.id).join(', '))
console.error('Re-run mise exec -- cargo test -p gateway-core -p gateway-providers -p gateway -p gateway-service -p gateway-client-config --lib for diagnostics.')
process.exitCode = 1
}
}
if (process.argv[1] === fileURLToPath(import.meta.url)) main(process.argv.slice(2))
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |