apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
  name: ${NAME}-llm-ai-proxy-advanced
  namespace: ${NAMESPACE}
plugin: ai-proxy-advanced
config:
  # The plugin's own ceiling on what it will introspect, distinct from nginx's
  # client_body_buffer_size — both have to clear 30 KB prompts or the payload
  # and usage logging stay empty. Raised together; neither alone is enough.
  max_request_body_size: 262144
  targets:
    - route_type: llm/v1/chat
      auth:
        header_name: Authorization
        header_value: ${OPENROUTER_BEARER}
      # dev only, like the rest of this gateway's audit trail: log_payloads
      # puts the prompt and the completion in the log stream, and -- because
      # OpenTelemetry instrumentation is on here -- in the spans as well.
      #
      # This is what the pre-function/post-function capture in
      # observability.yaml stood in for on this route. Kong's own
      # implementation reassembles a streamed SSE answer; accumulating raw
      # chunks does not.
      logging:
        log_payloads: true
        # Model usage and token counts in the log records. With this off Kong
        # counted nothing of its own, which is half of why usage was missing.
        log_statistics: true
      model:
        provider: openai
        # name deliberately unset: the client's own `model` field is passed
        # through to OpenRouter.
        options:
          upstream_url: ${OPENROUTER_UPSTREAM_URL}
          # Cost per 1M tokens, in the provider's currency. Kong multiplies
          # these by the token counts to produce kong_ai_llm_cost_total, so a
          # stale figure yields confidently wrong money rather than an error.
          # Re-check them whenever the model or the contract changes.
          input_cost: ${LLM_INPUT_COST}
          output_cost: ${LLM_OUTPUT_COST}