Localization messaging agent

This page explains how a localization messaging agent reads the source campaign and live regional pages under an interactive grant, checks messaging consistency market by market against a versioned glossary and forbidden-translation list, and streams sweep progress and the diff list back as typed events. After reading it, you will understand which modules this scenario needs, how per-market sweep progress streams back in real time, and why data like the glossary belongs in a localization config store rather than Memory.

Use case

International marketing teams need to adapt campaigns, landing pages, or ad copy for a target region and verify that live multilingual pages stay consistent with the source messaging. Regional pages are maintained by local teams, so translation drift, misused forbidden translations, and lag after source-copy updates are hard to catch market by market with manual review.

Typical triggers:

• Source campaign copy changes, and every language market's pages must be checked for sync.
• Before entering a new market, messaging must be calibrated against local competitors and market conventions.
• The glossary or forbidden-translation list changes, and existing regional translations must be swept.

Engineering challenges

• Check volume grows linearly with markets: every market means capturing live copy and comparing it against the glossary entry by entry. Serial manual checks cannot finish within the window after a source-copy update — and the team needs to see in real time which market the sweep is on and where it is stuck.
• Diff decisions depend on versioned rules: the glossary and forbidden-translation list change frequently, so whether a diff is "real drift" or "based on a stale glossary" must be traceable to a rule version — otherwise local reviewers cannot re-verify it.
• Borrowed employee access to regional workspaces is too broad: a borrowed session can read campaign materials for every market, while a single check only needs read-only access to the specified source copy and target region.

Module composition

Module	Role	Notes
GenAuth	Core	Read-only delegation, revocation, and the audit chain for regional workspaces and campaign materials; publishing translations and editing pages stay outside the grant.
Web Agent	Core	Controlled sessions capture live copy from each market's pages, keeping source URLs and screenshots, and research local competitor pages for phrasing conventions.
GUMem	Not used	The glossary and forbidden translations are versioned policy — keep them in your localization config store and inject them per version; diff lists and reviewer decisions are business state and belong in your localization records. Neither is Memory.

Permission and delegation boundaries

The Agent holds no inherent permissions. The effective authority for each verification task is the intersection of three sets: what the user actually holds ∩ what was explicitly delegated for this task ∩ what the enterprise has approved. Applied here:

• The delegated scope covers only "read the specified campaign materials, regional workspaces, and local public pages" — no publishing translations, editing regional pages, or changing the glossary.
• Delegation credentials are short-lived; minute-level validity is recommended for a single verification run, with re-delegation after expiry.
• The user or an administrator can revoke the grant at any time; new material-read requests fail immediately after revocation.
• Out-of-scope attempts (for example, a market workspace outside the delegation) are rejected and recorded — the audit chain covers all attempts, not just successful actions.

Note: this sample requests doAnything product permissions. Your application and downstream services must configure and enforce business limits such as domain lists, page ranges, action whitelists. Product scopes and prompt rules do not enforce those detailed limits; this sample does not configure them. See Delegate token and attenuation.

Workflow

1. The user selects the source copy, target region, and the local page list to verify.

2. GenAuth starts an interactive delegation; after the user confirms in Qoni Console, your server-side callback exchanges it for a least-privilege, read-only credential.

3. Your app loads the current version of the glossary, forbidden translations, and regional phrasing rules from the localization config store and injects them into the task.

4. Web Agent captures live copy from the local pages market by market, keeping source URLs and screenshots; sweep progress streams back as events.

   Checkpoint: When a regional workspace or local page hits a login wall, CAPTCHA, or risk-control page, the Web Agent should escalate to a human instead of silently bypassing it.

5. Web Agent researches local competitors and public market context for phrasing conventions.

6. The Agent compares each local page against the source messaging, glossary, and forbidden translations, flagging translation drift, misused terms, and unsynced lag, each with a page source and the rule version it was checked against.

7. The Agent returns a localization diff list, fix suggestion drafts, rationale, and sources with an audit id; after app-side validation they go to the local reviewer.

   Checkpoint: Every diff and suggestion should trace back to a concrete page source or glossary entry; conclusions without evidence should not enter the deliverable.

Example code

This example uses @qoniai/qoni 0.9.0, published on npm. The download includes the same SDK version, installed with npm ci. The demo compares Firefox English and Chinese pages using the Firefox/browser glossary, version demo-v1. The SDK reads real public pages; business inputs in scenarios.ts are labeled public-demo.

This demo does not read or write GUMem; its task uses the supplied page list and explicit business inputs. DoAnything opens the supplied pages and produces the scenario output. Supply your own JSON with --input; use --interactive when the user must consent to delegation. For site sign-in and user responses, see Qoni SDK.

Download the complete runnable examples, or run from the documentation repository:

cd examples/qoni
npm ci
npm run case -- localization-messaging-agent
# Supply your own inputs
npm run case -- localization-messaging-agent --input /path/to/input.json

Set server-side QONI_ACCESS_KEY and QONI_SECRET_KEY. QONI_USER_ID can identify your application's current GenAuth user; the local demo otherwise selects a user from the bound pool. Demonstration Memory writes use an isolated user rather than changing a business user's preferences.

This scenario's executable entry point:

import { cliOptions } from '../runtime.js'
import { inputFile, runScenario } from '../run-case.js'

// Review translation and copy consistency against the supplied glossary.
const report = await runScenario('localization-messaging-agent', cliOptions(), inputFile())
// report.items: pages, differences or alignment observations, suggestions, sources, and glossary references.
// Validated fields: page, diff, suggestion, sourceUrl, glossaryRef.
console.log(JSON.stringify(report, null, 2))

The entry point loads the definition below by scenario ID. The code is included directly from scenarios.ts, with comments shown in the page language: the task, output fields, source field, Web Search queries (if any), whether Memory is used, and the demonstration input. The pipeline appends the input data, search sources, recalled Memory, and shared safety constraints to the task to build the final prompt; see the pipeline below for the full assembly.

// Review translation and copy consistency against the supplied glossary.
// The Unicode escape in this glossary is the Chinese translation of browser.
browser('localization-messaging-agent',
  'Compare the supplied English and Chinese product pages using the supplied glossary. Return [{page,diff,suggestion,sourceUrl,glossaryRef}]. Include an observed translation alignment when there is no issue. Do not edit, publish or change the glossary.',
  ['page','diff','suggestion','sourceUrl','glossaryRef'], 'sourceUrl', sample([firefox,'https://www.mozilla.org/zh-CN/firefox/new/'], { region:'zh-CN',glossary:{Firefox:'Firefox',browser:'\u6d4f\u89c8\u5668'},glossaryVersion:'demo-v1' })),

The sample implements runScenario(), browser(), research(), and sample() as application functions. The pipeline below makes the actual SDK calls: delegation and introspection → required Memory/search → browser task or monitor → validation and saving. fields and sourceField define the application's output checks. The complete application helpers are in the package's runtime.ts.

Inspect the actual SDK pipeline

// browser() uses DoAnything; research() searches first; sample() labels public-demo inputs.
const firefox = 'https://www.mozilla.org/en-US/firefox/new/'
const manifesto = 'https://www.mozilla.org/en-US/about/manifesto/'
const privacy = 'https://www.mozilla.org/en-US/privacy/firefox/'
const support = 'https://support.mozilla.org/en-US/kb/get-started-firefox-overview-main-features'
// These copy rules become prompt context; server permissions and business checks remain separate.
const policy = {
  version: 'demo-2026-09',
  approvedClaims: ['Describe only features supported by the cited page.'],
  forbiddenClaims: ['guaranteed security', '100% private', 'unverified pricing or performance'],
  voice: 'concise and warm',
}
const sample = (pages: string[], business: JsonObject = {}): JsonObject => ({
  dataset: 'public-demo', pages, policy, business,
  notice: 'Business records are synthetic demonstration inputs. Referenced websites and SDK execution are real.',
})
// fields lists required output keys; sourceField identifies URL checks; memory enables GUMem calls.
const browser = (id: string, task: string, fields: string[], sourceField: string | undefined, input: JsonObject, memory = false): Scenario => ({
  id, products: ['doAnything'], task, fields, sourceField, input, memory,
})
const research = (id: string, task: string, fields: string[], sourceField: string, queries: string[], input: JsonObject, memory = false): Scenario => ({
  id, products: ['webSearch', 'doAnything'], task, fields, sourceField, queries, input, memory,
})

import { QoniScopes, type JsonObject, type RunResult } from '@qoniai/qoni'
import { readFileSync } from 'node:fs'
import { getScenario, type Scenario } from './scenarios.js'
import { appendTrace, checkInputCoverage, cleanupDemoUser, createContext, delegate, handleInteraction, inputEntryCount, isolateDemoUser, object, readWithRetry, renderScreenshot,
  save, saveArtifacts, searchHits, settled, settleRun, validateItems, withCleanup, type Context, type Options } from './runtime.js'

export async function runScenario(id: string, options: Options = {}, input?: JsonObject) {
  // Load the task definition by ID; --input replaces its business inputs.
  const scenario = getScenario(id)
  const data = input ?? scenario.input
  if (scenario.memory && data.dataset !== 'public-demo' && options.mode !== 'interactive' && !options.userId && !process.env.QONI_USER_ID) {
    throw new Error('Business Memory writes require the current QONI_USER_ID; do not select an arbitrary bound user')
  }
  const context = await createContext(id, { ...options,
    skipUserResolution: scenario.memory && data.dataset === 'public-demo' })
  return withCleanup(context, async register => {
    register('isolated demonstration user', () => cleanupDemoUser(context))
    // Isolate demo preferences; business Memory belongs to the identified current user.
    if (scenario.memory && data.dataset === 'public-demo') await isolateDemoUser(context)
    return await executeScenario(context, scenario, data)
  })
}

export async function executeScenario(context: Context, scenario: Scenario, input: JsonObject) {
  const pages = input.pages
  if (!Array.isArray(pages) || !pages.length || pages.some(page => typeof page !== 'string' || !/^https:\/\//.test(page))) {
    throw new Error('Input pages must be an array of HTTPS URLs')
  }
  if (input.requiresLogin === true && context.mode !== 'interactive') {
    throw new Error('Targets that require sign-in need --interactive and user-controlled login')
  }
  const memoryScopes = scenario.memory
    ? [QoniScopes.GUMEM_MEMORY_READ, QoniScopes.GUMEM_MEMORY_WRITE, QoniScopes.GUMEM_MESSAGE_WRITE] : []
  // delegate() is an application helper around the SDK delegation methods.
  const grant = await delegate(context, scenario.id, scenario.products, memoryScopes)
  // Read the effective scopes; readWithRetry() retries only retryable read failures.
  const { data: tokenInfo } = await readWithRetry(context, 'delegation introspection',
    () => context.qoni.genauth.introspectDelegationToken({ token: grant.token }))
  const info = object(tokenInfo)
  if (info.active !== true) throw new Error('The delegation token is not active')
  const audit = { grantId: grant.grantId, auditId: grant.auditId, scopes: info.scope }
  let memory: unknown
  if (scenario.memory) {
    // A Session associates this conversation with the user; the app chooses sessionId.
    const sessionId = `${scenario.id}-${Date.now()}`
    await context.qoni.gumem.createSession({
      token: grant.token, userId: context.userId, sessionId, title: scenario.id,
    })
    const preferences = object(input.business ?? {}).confirmedPreferences
    if (Array.isArray(preferences) && preferences.length) {
      // Store confirmed preferences only; sync: true requests synchronous processing.
      await context.qoni.gumem.addMessages({ token: grant.token, userId: context.userId, sessionId, sync: true,
        messages: [{ role: 'user', content: `Confirmed demonstration preferences: ${preferences.join('; ')}` }] })
    }
    // Recall relevant preferences for the later task prompt.
    memory = (await readWithRetry(context, 'GUMem recall', () => context.qoni.gumem.recall({ token: grant.token, sessionId,
      query: 'Confirmed preferences relevant to this task', details: true }))).data
    save(context, 'memory.json', { sessionId, context: memory })
    if (Array.isArray(preferences) && preferences.length && !preferences.every(value => JSON.stringify(memory).includes(String(value)))) {
      throw new Error('Recall did not include the confirmed preferences just written by this demo')
    }
  }

  if (scenario.products.includes('track')) return runMonitor(context, scenario, input, grant.token, audit)

  let hits: ReturnType<typeof searchHits> = []
  if (scenario.queries) {
    // Web Search returns results[]; DoAnything receives these sources to inspect.
    const search = await context.qoni.webSearch.run({ token: grant.token, prompt: scenario.queries, maxResultsPerQuery: 3 })
    save(context, 'search-ref.json', { runId: search.id, audit })
    await withCleanup(context, async register => {
      register('Web Search run', () => search.cancel('Documentation demonstration cleanup'))
      const result = await settleRun(context, search)
      save(context, 'search-result.json', result)
      settled(result)
      hits = searchHits(result.output)
    })
  }

  // One-per-entry scenarios request exactly one item per input entry; others at most two.
  const requiredItems = inputEntryCount(scenario.id, input)
  // Assemble the task, inputs, search sources, and Memory as application-defined context.
  const prompt = [scenario.task, `Task inputs: ${JSON.stringify(input)}`,
    `Search sources: ${JSON.stringify(hits)}`, `Confirmed memory: ${JSON.stringify(memory ?? null)}`,
    `Actual collection time: ${new Date().toISOString()}`,
    requiredItems === undefined
      ? 'Inspect the supplied sources. Return at most two items in the requested JSON array, without prose or Markdown.'
      : `Inspect the supplied sources. Return exactly ${requiredItems} item${requiredItems === 1 ? '' : 's'} in the requested JSON array, one per input entry, without prose or Markdown.`,
    'Keep synthetic demonstration data identified as synthetic. Do not send messages, publish, pay, edit accounts or submit forms.',
    input.requiresLogin === true ? 'Request user sign-in through an interaction when required; never enter credentials yourself.' : 'Public demonstration sources only; do not sign in.',
  ].join('\n\n')
  // Start the Agent with this grant; capture receives delivered screenshots, not every step.
  const run = await context.qoni.doAnything.run({ token: grant.token, prompt, capture: { screenshots: true } })
  save(context, 'run-ref.json', { runId: run.id, session: run.sessionRef, audit })
  let result: RunResult
  const trace = (event: { type: string; data: unknown }) => {
    context.eventCounts[event.type] = (context.eventCounts[event.type] ?? 0) + 1
    if (['progress','message','done'].includes(event.type)) appendTrace(context, event)
    if (event.type === 'browserLiveUrlChanged') {
      const liveUrl = object(event.data).liveUrl
      if (typeof liveUrl === 'string') context.browserUrl = liveUrl
    }
  }
  return withCleanup(context, async register => {
    register('DoAnything run', () => run.cancel('Documentation demonstration cleanup'))
    if (context.delivery === 'events') {
      // --events streams updates; wrap interaction data in an SDK handle for user handling.
      for await (const event of run.events({ signal: AbortSignal.any([context.abort.signal, AbortSignal.timeout(context.timeoutMs)]) })) {
        trace(event)
        if (event.type === 'screenshot') renderScreenshot(context, event.image)
        if (event.type === 'interaction') await handleInteraction(context, run.interactionHandle(event.data))
      }
      result = await settleRun(context, run)
    } else {
      // Callback mode receives this run's events inside wait; helpers save images and ask the user.
      result = await settleRun(context, run, { onEvent: trace,
        onScreenshot: (image, index) => renderScreenshot(context, image, index),
        onInteraction: interaction => handleInteraction(context, interaction) })
    }
    save(context, 'result.json', result)
    settled(result)
    await saveArtifacts(context, result)
    if (scenario.id === 'landing-page-audit-agent' && context.screenshots === 0) throw new Error('The landing-page audit did not deliver the requested screenshot')
    // The app checks required fields and source URL formats; a reviewer still checks facts.
    const items = validateItems(result.output, scenario.fields, scenario.sourceField)
    // Scenarios that require one item per input entry are checked against the input.
    checkInputCoverage(scenario.id, items, input)
    const report = { scenario: scenario.id, dataset: input.dataset, passed: true, runId: run.id,
      status: result.status, items, audit, screenshots: context.screenshots, interactions: context.interactions,
      events: context.eventCounts, artifactIds: result.artifacts.map(artifact => artifact.id) }
    save(context, 'report.json', report)
    return report
  })
}

async function runMonitor(context: Context, scenario: Scenario, input: JsonObject, token: string, audit: JsonObject) {
  // Track creates a monitor with targets, extraction fields, and hourly scheduling.
  const monitor = await context.qoni.track.create({ token, prompt: scenario.task,
    targetUrls: input.pages, extractionSchema: { heading: 'string', source_url: 'string' },
    tickInstructions: `Open the target URLs and read the actual visible heading. Return a JSON object with heading and source_url. ${scenario.task}`,
    triggerDsl: { on: 'change' }, schedule: { kind: 'interval', intervalSeconds: 3600 } })
  save(context, 'monitor-ref.json', { id: monitor.id, audit })
  return withCleanup(context, async register => {
    register('Track monitor', () => monitor.delete())
    const definition = await monitor.get()
    save(context, 'monitor-definition.json', definition)
    if (object(definition.schedule).intervalSeconds !== 3600) throw new Error('Track did not persist the requested schedule interval')
    // Run one tick and inspect its extraction by runId; completed alone does not prove success.
    const tick = await monitor.runNow()
    save(context, 'tick.json', tick)
    if (tick.state !== 'completed') throw new Error(`Track execution failed: ${tick.state} / ${tick.error ?? ''}`)
    const runId = tick.runId
    if (typeof runId !== 'string') throw new Error('Track tick did not return a runId')
    const detail = await monitor.run(runId)
    save(context, 'tick-detail.json', detail)
    if (detail.state !== 'completed' || !detail.extracted || !Object.keys(object(detail.extracted)).length) {
      throw new Error('Track did not extract page data')
    }
    const extracted = object(detail.extracted)
    if (typeof extracted.heading !== 'string' || !extracted.heading.trim() ||
      typeof extracted.source_url !== 'string' || !/^https:\/\//.test(extracted.source_url)) {
      throw new Error('Track extraction is missing a heading or source URL')
    }
    const normalizeUrl = (value: string) => { const url = new URL(value); url.hash = ''; return url.href.replace(/\/$/, '') }
    if (!(input.pages as string[]).some(url => normalizeUrl(url) === normalizeUrl(String(extracted.source_url)))) {
      throw new Error('The Track source URL is not a configured target')
    }
    // Check persisted pause/resume state; withCleanup() deletes the monitor on exit.
    await monitor.pause()
    if ((await monitor.get()).status !== 'paused') throw new Error('Track did not persist the paused state')
    await monitor.resume()
    if ((await monitor.get()).status !== 'active') throw new Error('Track did not persist the active state')
    const report = { scenario: scenario.id, dataset: input.dataset, passed: true, monitorId: monitor.id,
      runId, state: detail.state, outcome: detail.outcome, extracted: detail.extracted, audit }
    save(context, 'report.json', report)
    return report
  })
}

export function inputFile(): JsonObject | undefined {
  const index = process.argv.indexOf('--input')
  return index >= 0 ? object(JSON.parse(readFileSync(process.argv[index + 1], 'utf8'))) : undefined
}

Results are written to output/localization-messaging-agent/report.json. report.items contains pages, differences or alignment observations, suggestions, sources, and glossary references, with fields page, diff, suggestion, sourceUrl, glossaryRef. audit links the grant ID, audit ID, and effective scopes; http.json records redacted request statuses. The application parses DoAnything output and checks required fields and source URL formats. A business reviewer still assesses the content against the original sources.

Data and memory boundaries

This scenario touches four kinds of data; GUMem is not used here:

• Versioned rules: the glossary, forbidden translations, regional phrasing rules — managed by version in your localization config store, with every diff referencing a rule version.
• Business state: diff lists, fix suggestions, page screenshots, reviewer decisions — archived to your localization records for review and traceability.
• Audit records: the delegation and behavior chain formed by grantId and auditId — maintained by GenAuth.
• User Memory (optional): only long-term personal preferences a user has explicitly confirmed belong in GUMem; the glossary and regional rules are team-level policy, not personal memory, so this scenario neither recalls nor writes back by default.

Failure handling

Situation	Recommended handling
Regional workspace login state expires	Suspend the task, notify the user to sign in again, and resume from the checkpoint.
Local page structure changes break extraction	Treat it as a failure and replay the session recording; never emit diffs without evidence.
Request for a market workspace outside the delegated scope	Reject and record it; the attempted access remains visible in the audit chain.
A diff lacks a page source or glossary reference	App-side validation drops the diff and records how many were dropped and the policy version applied.

Production notes

Do not treat localization suggestions as final legal, cultural, or compliance review. A local reviewer should confirm before release. The Agent only produces diff lists and fix suggestion drafts; it never publishes translations or edits regional pages, and extraction frequency against local competitor pages should be capped. When the glossary changes, publish a new version in the config store so stale rules never judge new diffs.

Next steps

• Read the Quickstart to run the shortest path for Agent identity and delegation.
• Read Authorization and browser sandbox for the security boundaries of controlled sessions.
• Continue with the Brand consistency agent for an adjacent scenario.