# Ansible managed
version: 1

pipeline:
  modules: ['glossary', 'homophones', 'glossary', 'spoken_word', 'grammar']

output:
  schema: audita-v1

llm:
  proposal:
    base_url: https://inference.ai.rakestrawhome.com/v1
    model: google/gemma-4-31b-it
    api_key_env: AUDITA_LLM_API_KEY
    timeout: 900s
    max_retries: 3

  validation:
    base_url: https://inference.ai.rakestrawhome.com/v1
    model: google/gemma-4-31b-it
    api_key_env: AUDITA_VALIDATION_LLM_API_KEY
    timeout: 900s
    max_retries: 3

concurrency:
  total_llm: 4
  proposal_llm: 4
  validation_llm: 4

chunking:
  target_sections: 8
  max_section_tokens: 6144
  min_section_tokens: 2048

normalization:
  max_segment_gap: 3s
  ellipsis_gap: 3s
  max_segment_duration: 240s
  max_segment_tokens: 2048

thresholds:
  glossary: 0.8
  homophones: 0.8
  spoken_word: 0.8
  grammar: 0.8

context:
  description: "The following transcript was recorded during a Dungeons & Dragons game session. It may contain some unrelaed pre-session or post-session banter, in addition to actual D&D gameplay."

diagnostics:
  work_dir: /tmp/audita
  retention: auto