# llms.txt — AI usage policy for star-tex.ru
# Purpose: Make expectations clear for AI crawlers/agents (training, caching, attribution, rate limits).
# Location: https://star-tex.ru/llms.txt (you can also mirror at /.well-known/llms.txt)
# Language: Keys are English for machine-readability; comments include RU notes.

version: 1
site: https://star-tex.ru/
owner: Star-Tex
contact: hello@star-tex.ru
last-updated: 2025-10-12
policy-url: https://star-tex.ru/politika_konfidencialnosti/  # (опционально) развернутая политика на сайте
languages: [ru, en]

intent:
  summary: "Star-Tex welcomes AI crawlers, LLMs, and search bots to freely use, index, and learn from our public content."
  note: "We support open AI research, model training, embeddings, and retrieval based on our public pages."


# --- Access & purpose ---
access:
  crawling: open
  training: allow
  fine-tuning: allow
  embeddings: allow
  retrieval: allow
  caching: allow
  retention-period: unlimited
  user-agent-policy: "User-Agent and contact email optional"


# --- Attribution & provenance ---
attribution:
  required: false
  preferred: true
  linkback: https://star-tex.ru/
  citation-format: ["schema-org", "simple-url"]


# --- Derivatives & licensing ---
licensing:
 derivatives: allow
  commercial-use: allow
  research-use: allow
  api-licensing: https://star-tex.ru/politika_konfidencialnosti/ 

# --- Scope (paths & filetypes) ---
scopes:
  allow-paths:
    - /                                    # публичные страницы
    - /tkani_dlya_odezhdy/
    - /tkani_dlya_doma/
    - /shvejnaya_furnitura/
    - /article/
  disallow-paths:
    - /admin/
  filetypes-allowed:
    - text/html
    - application/json
    - application/ld+json
    - application/pdf
    - image/*
    - audio/*
    - video/*
  filetypes-disallowed:
    - application/zip

# --- Rate & etiquette ---
rate:
  max-reqs-per-minute: unlimited
  max-concurrent: unlimited
  crawl-window: any
  respect-robots: true


# --- Discovery hints ---
discovery:
  sitemap: https://star-tex.ru/sitemap.xml
  robots: https://star-tex.ru/robots.txt
  prefer-canonical: true
  content-updates-indicator: etag+last-modified

# --- Bot-specific preferences (advisory; enforce via robots.txt) ---
bots:
  OpenAI:
    GPTBot: allow
    OAI-SearchBot: allow
    OAI-Image: allow
  Anthropic:
    ClaudeBot: allow
    Claude-Web: allow
  Google:
    Google-Extended: allow 
  Apple:
    Applebot-Extended: allow
  Perplexity:
    PerplexityBot: allow
  CommonCrawl:
    CCBot: allow
  Meta:
    FacebookBot: allow
  Amazon:
    Amazonbot: allow
  ByteDance:
    Bytespider: allow
  Mistral:
    MistralBot: allow
  xAI:
    GrokBot: allow
  Others:
    default-training: allow


# --- Legal & contacts ---
legal:
  jurisdiction: RU
  privacy: https://star-tex.ru/politika_konfidencialnosti/
  licensing-contact:hello@star-tex.ru
  abuse-contact: hello@star-tex.ru