# Token Usage Response Headers
#
# Inject Praxis-Token-Input, Praxis-Token-Output, and
# Praxis-Token-Total headers into downstream responses when
# token counts are available in filter metadata.
#
# Usage:
#   cargo run -p praxis-ai-proxy -- -c examples/configs/token-usage-headers.yaml
#   curl -v http://localhost:8080/v1/chat/completions
#
# The filter reads token.input, token.output, and token.total from
# filter metadata and injects them as response headers. When no token
# data is present the filter is a no-op.
#
# NOTE: response hooks run in reverse declared order (the last filter's
# on_response fires first), so a token-counting filter (or any filter
# that calls set_token_usage()) must be declared AFTER token_usage_headers
# in the pipeline for headers to appear. Without it the filter is always
# a no-op. See token-counting.yaml for a filter that populates
# token.input/token.output/token.total.

listeners:
  - name: default
    address: "127.0.0.1:8080"
    filter_chains:
      - main

filter_chains:
  - name: main
    filters:
      - filter: router
        routes:
          - path_prefix: "/"
            cluster: backend

      - filter: token_usage_headers

      - filter: load_balancer
        clusters:
          - name: backend
            endpoints:
              - "127.0.0.1:3000"

insecure_options:
  allow_private_endpoints: true # example proxies to local backends