# llms.txt — Viva City Mall
# Purpose: Declare permissions for Large Language Model (LLM) crawlers and AI agents.
# Domain: https://vivacitymall.in
# Owner: Viva City Mall (Jaipur, Rajasthan, IN)
# Last-Updated: 2025-11-10
# Contact: info@vivacitymall.in
# Sitemap: https://vivacitymall.in/sitemap.xml

# ---- Global Policy ---------------------------------------------------------
# Summary:
# - Allow AI crawlers to fetch public content for search, snippet generation,
#   and real-time answers.
# - Disallow using the content to train foundation models without prior written consent.
# - Respect robots.txt, this llms.txt, and standard rate limits.

Policy: fetch=allow; indexing=allow; summarization=allow
Policy: training=disallow; fine-tuning=disallow; embedding-store=allow-cache-30d
Attribution: required
Commercial-Use: allow-nontraining
Rate-Limit: 1 rps
Crawl-Delay: 1
Cache-Retention: 30d
Respect-Robots-Txt: true
Honor-If-Modified-Since: true
Honor-ETag: true

# ---- Path Rules (similar to robots.txt syntax) -----------------------------
# Public content allowed
Allow: /

# Sensitive/system paths blocked (adjust as needed)
Disallow: /admin/
Disallow: /login/
Disallow: /api/
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /search
Disallow: /cart/
Disallow: /checkout/
Disallow: /user/
Disallow: /private/
Disallow: /*?*  # avoid query-only pages if they create duplicates

# ---- Media Guidance --------------------------------------------------------
# Images and videos may be displayed in summaries/previews with attribution.
# Do not use media to train vision models without permission.
Media-Use: preview-with-attribution
Media-Training: disallow

# ---- Required Headers for Crawlers ----------------------------------------
# Provide a contact and purpose for accountability.
Required-Header: User-Agent
Required-Header: From
Required-Header: Purpose

# ---- Per-Agent Directives --------------------------------------------------
# OpenAI GPTBot
User-Agent: GPTBot
Allow: /
Disallow: /admin/ /login/ /private/
Policy: training=disallow

# Google Extended (for generative features)
User-Agent: Google-Extended
Allow: /
Disallow: /admin/ /login/ /private/
Policy: training=disallow

# Anthropic ClaudeBot / CCBot
User-Agent: ClaudeBot
Allow: /
Disallow: /admin/ /login/ /private/
Policy: training=disallow

# Perplexity Bot
User-Agent: PerplexityBot
Allow: /
Disallow: /admin/ /login/ /private/
Policy: training=disallow

# Common AI crawlers (update as needed)
User-Agent: FacebookBot
User-Agent: Applebot-Extended
User-Agent: OAI-SearchBot
Allow: /
Disallow: /admin/ /login/ /private/
Policy: training=disallow

# ---- Legal / Licensing -----------------------------------------------------
# Unless explicitly licensed otherwise in writing:
Copyright: © Viva City Mall. All rights reserved.
License: Non-exclusive license for indexing/summarization only.
Contact-For-Licensing: info@vivacitymall.in

# ---- Fallback --------------------------------------------------------------
# If a crawler cannot parse this file, it must default to the most restrictive
# interpretation: no training, follow robots.txt, rate-limit 1 rps, and honor
# cache-retention of 30 days.