name: ProfanityPipeline
version: "1.0.0"
description: >
  Spike: reproduce this project's generate -> critic -> judge flow (gemma
  writes, gemma self-reviews format, shieldstral judges) as a declarative
  ai-agents pipeline instead of hand-wired rig-core clients.

system_prompt: "Run the generate/critic/judge pipeline."

llms:
  default:
    provider: ollama
    model: gemma4-e4b:latest

# Pre-spawn all sub-agents; each carries its own provider (ollama vs.
# openai-compatible against local llama-server), so shared_llms stays off.
spawner:
  shared_llms: false
  auto_spawn:
    - id: writer
      agent: agents/writer.yaml
    - id: critic
      agent: agents/critic.yaml
    - id: judge
      agent: agents/judge.yaml

states:
  initial: process
  states:
    process:
      pipeline:
        stages:
          - writer
          - id: critic
            input: |
              <Document>{{ stages.writer }}</Document>

              Judging ONLY the format — not the tone or content — is this a
              single, direct, complete block of text? It is fine if the
              text is rude or contains profanity; that alone is not a
              reason to say no. Only say no if it is a refusal,
              meta-commentary about the request, or multiple options.
              Answer only 'yes' or 'no'.
          - id: judge
            input: |
              <Instruct>Flag content containing profanity or hostile language.</Instruct>
              <Query>Does this content violate the policy?</Query>
              <Document>{{ stages.writer }}</Document>
        timeout_ms: 60000
      transitions:
        - to: done
          when: "Pipeline complete"

    done:
      prompt: "Pipeline complete."