Agentic Loop Fixture

Minimal agentic loop pipeline for inference fixture replay

Category: Test fixture
Task: Minimal agentic loop pipeline for inference fixture replay

Prerequisites: The matching test or replay fixture; this is not a standalone deployment configuration.

This configuration comes from the selected release. The example has not been run here; external services are not bundled.

Download the source file.

# Agentic Loop Fixture
# Requires `--features store-sqlite` because these filters are opt-in.
#
# Minimal agentic loop pipeline for inference fixture replay.
# Exercises parallel_tool_calls preservation without external
# callout filters (no web_search, MCP dispatch, or MCP tool resolve).
#
# This config proves that the openai_agentic_loop filter preserves
# the client's parallel_tool_calls value in the upstream request body.

listeners:
  - name: ai-gateway
    address: "127.0.0.1:8080"
    filter_chains: [agentic-fixture]

filter_chains:
  - name: agentic-fixture
    filters:
      - filter: openai_responses_format
        on_invalid: reject
        headers:
          format: x-praxis-ai-format
          model: x-praxis-ai-model
          stream: x-praxis-ai-stream

      - filter: openai_responses_validate

      - filter: state_owner
        mode: single_tenant
        tenant_id: default

      - filter: openai_response_store
        backend: sqlite
        database_url: "sqlite://responses.db?mode=rwc"
        responses_table: openai_responses
        conversations_table: openai_conversations

      - filter: openai_responses_rehydrate

      - filter: iterative_request_router
        initial_step: inference
        max_iterations: 2
        steps:
          - name: inference
            filters:
              - filter: openai_agentic_loop
                max_infer_iters: 1
              - filter: openai_responses_proxy
              - filter: router
                routes:
                  - path_prefix: "/"
                    cluster: "inference-backend"
              - filter: load_balancer
                clusters:
                  - name: "inference-backend"
                    endpoints:
                      - "127.0.0.1:3001"
            on_result:
              - default: true
                done: true

insecure_options:
  allow_private_endpoints: true # example proxies to local backends