# AI Inference Model Routing
#
# Build:
#   cargo build -p praxis-ai-proxy
#
# Routes LLM API requests to different backends based on the
# "model" field in the JSON request body. Uses the model_to_header
# filter to extract the model name into an X-Model header, then
# the router matches on that header to select the correct cluster.
#
# The model_to_header filter is a convenience wrapper around
# json_body_field that hardcodes the "model" field extraction.
#
# Example request:
#
#   curl -X POST http://localhost:8080/v1/chat/completions \
#     -H "Content-Type: application/json" \
#     -d '{"model": "mistral-7b-instruct", "messages": [...]}'
#
# This request is routed to the mistral cluster. A request with
# "model": "granite-3.1-8b" goes to the granite cluster. Unknown
# models fall through to the default cluster.

listeners:
  - name: inference-gateway
    address: "0.0.0.0:8080" # dev value; binds all interfaces
    filter_chains:
      - extract-model
      - routing

filter_chains:
  # Extract the model field from the JSON body and promote it
  # to the X-AI-Model request header (default is X-Model).
  - name: extract-model
    filters:
      - filter: model_to_header
        header: X-AI-Model

  # Route based on the promoted X-AI-Model header.
  - name: routing
    filters:
      - filter: router
        routes:
          - path_prefix: "/"
            headers:
              x-ai-model: "mistral-7b-instruct"
            cluster: mistral
          - path_prefix: "/"
            headers:
              x-ai-model: "granite-3.1-8b"
            cluster: granite
          - path_prefix: "/"
            cluster: default
      - filter: load_balancer
        clusters:
          - name: mistral
            endpoints:
              - "10.0.1.1:8080"
              - "10.0.1.2:8080"
          - name: granite
            endpoints:
              - "10.0.2.1:8080"
              - "10.0.2.2:8080"
          - name: default
            endpoints:
              - "10.0.3.1:8080"

insecure_options:
  allow_private_endpoints: true # example proxies to local backends