Moderation

Coming soon (Phase 7)

Content safety and policy enforcement for text and images. Not yet callable — returns a gated error today.

Not yet callable

Moderation capabilities are planned for Phase 7 of the platform roadmap. The safety:* namespace is registered but has only placeholder implementations today.

Calling any safety:* slug today returns 403 capability_gated. Do not depend on these endpoints in production code yet.

Intended Capabilities (Phase 7)

SlugWhat it will do
safety:moderate-textDetect toxicity, hate speech, and policy violations in text
safety:moderate-imageDetect adult content, violence, and policy violations in images
safety:brand-safety-checkVerify content is safe for brand association
safety:pii-redactDetect and redact personally identifiable information from text

Intended API Shape

When live, moderation capabilities will follow the standard capability execution pattern.

JavaScript SDK (future)

// NOT callable yet — returns 403 today
const run = await client.capabilities.run('safety:moderate-text', {
  text: 'User-generated content to check',
})

cURL (future)

# NOT callable yet — returns 403 today
curl -X POST https://api.whizur.ai/v1/capabilities/safety:moderate-text/execute \
  -H "X-API-Key: cw_dev_..." \
  -H "Content-Type: application/json" \
  -d '{
    "input": {
      "text": "User-generated content to check"
    }
  }'

Intended input shape — safety:moderate-text

{
  "text": string,            // required — content to evaluate
  "categories"?: string[]    // optional — e.g. ["hate", "violence", "sexual"]
}

Intended output artifact

{
  "flagged": boolean,
  "scores": {
    "hate": number,
    "violence": number,
    "sexual": number,
    "selfHarm": number
  },
  "confidence": number,
  "action": "allow" | "review" | "block"
}

Why Phase 7?

Safety capabilities require production-grade implementations, not the placeholder stubs currently registered. Phase 7 introduces moderation alongside recommendations after the RAG subsystem (Phase 5) and social ingestion (Phase 6) are stable. See context/architecture/launch-scope.md for the full phase plan.

What is Live Now