# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content


User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# Regla por defecto: todo abierto. Cubre los buscadores clasicos y, a
# proposito, tambien los agentes de busqueda y recuperacion de las IA
# (OAI-SearchBot, PerplexityBot) y los que actuan en nombre de una persona que
# pide la pagina (ChatGPT-User, Claude-User). Esos son los que citan y enlazan:
# para un sitio educativo publico, esa es la distribucion que importa.
#
# La unica excepcion es /static/*.html$: esas rutas servian copias de las
# paginas del sitio y no deben indexarse por separado.
User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /
Disallow: /static/*.html$

# Rastreadores cuyo unico destino es entrenar modelos: no aportan trafico ni
# cita, asi que se declaran fuera. Van con su propio grupo porque en robots.txt
# manda el grupo mas especifico: al nombrarlos, dejan de seguir la regla por
# defecto de arriba.
#
# Google-Extended y Applebot-Extended no afectan a sus buscadores: son solo la
# senal de entrenamiento de Gemini y de Apple Intelligence.
#
# Aviso honesto: esto es una declaracion, no una defensa. Los rastreadores que
# la respetan la respetan; los que no, entran igual. La posicion se mantiene
# porque no cuesta visibilidad —todo lo que cita sigue permitido— y deja la
# puerta abierta a un acuerdo de licencia en el futuro.
User-agent: GPTBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: meta-externalagent
Disallow: /

# Alineados con el bloqueo de bots de IA de Cloudflare, que ya los para en el
# borde (comunicacion-exterior-2026-10.md, H15): que robots.txt diga lo mismo.
User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Amazonbot
Disallow: /

Sitemap: https://constituchat.com/sitemap.xml

# Catalogo de lo que el sitio publica para agentes (ARD): servidor MCP, agente
# A2A, skills y catalogo de la API.
Agentmap: https://constituchat.com/.well-known/ai-catalog.json