version: 1
pipeline:
  modules: [glossary, homophones, glossary, spoken_word, grammar]
output:
  schema: audita-v1
llm:
  proposal:
    base_url: https://openrouter.ai/api/v1
    model: openrouter/google/gemma-4-31b-it
    api_key_env: AUDITA_LLM_API_KEY
    timeout: 120s
    max_retries: 3
  validation:
    base_url: https://openrouter.ai/api/v1
    model: openrouter/google/gemma-4-31b-it
    api_key_env: AUDITA_VALIDATION_LLM_API_KEY
    timeout: 120
    max_retries: 3
concurrency:
  total_llm: 2
  proposal_llm: 2
  validation_llm: 1
chunking:
  target_sections: 8
  max_section_tokens: 8192
  min_section_tokens: 2048
normalization:
  max_segment_gap: 4s
  ellipsis_gap: 3.5s
  max_segment_duration: 60s
  max_segment_tokens: 2048
thresholds:
  glossary: 0.8
  homophones: 0.8
  spoken_word: 0.8
  grammar: 0.8
context:
  description: "General context for domain vocabulary and speaker names."
diagnostics:
  work_dir: /tmp/audita
  retention: auto