# Workspace ThothII (esempio). I segreti vivono SOLO in .env (${THT_*}).
# Ogni risorsa dichiara il proprio adapter tramite `type`.

language: it  # descrizioni tabelle/colonne ed evidence sono in italiano (PSD)

dwh:
  type: thoth_rest                  # postgres_direct | thoth_rest
  database:
    database: ${THT_DB_NAME}
    schema: datawarehouse
  endpoint:
    base_url: ${THT_DWH_REST_URL}
    api_key: ${THT_DWH_API_KEY}
    ssl_ca: ${THT_SSL_CA}

roots:
  artifacts: artifacts
  indexes: indexes
  sessions: sessions

examples:
  max_per_column: 10

lsh:
  signature_size: 64
  n_gram: 3
  threshold: 0.5
  max_values_per_column: 1000

eligibility:
  max_declared_len: 128
  max_avg_length: 40
  max_sampled_len: 200
  ignore_columns: [etl_last_update]

evidence:
  source_root: ${THT_DOCS_ROOT}    # es. harness/evidence (cartella curata dentro ThothII)
  evidence_dir: evidence             # cartella curata a mano: unica fonte delle evidence

embeddings:
  base_url: ${THT_OLLAMA_URL}      # es. http://localhost:11434
  model: nomic-embed-text-v2-moe
  dim: 768
  batch_size: 32

vectors:
  type: thoth_vector_http           # pgvector_direct | thoth_vector_http
  reader:
    base_url: ${THT_VEC_REST_URL}
    api_key: ${THT_VEC_API_KEY}
    ssl_ca: ${THT_SSL_CA}
  writer:                           # opzionale: credenziale separata dalla lettura
    base_url: ${THT_VEC_REST_URL}
    api_key: ${THT_VEC_WRITE_API_KEY}
    ssl_ca: ${THT_SSL_CA}
  direct:                           # opzionale: loading server-side diretto
    host: ${THT_VEC_HOST}
    port: ${THT_VEC_PORT}
    database: postgres
    schema: vectors
    user: ${THT_VEC_USER}
    password: ${THT_VEC_PASSWORD}

vector:
  max_chunk_chars: 4000

search:
  rrf_k: 60
  top_schema_tables: 12
  schema_chunk_pool: 150

execution:
  allow: [cte_test, explain, preview, aggregate, export]
  max_preview_rows: 10
  max_export_rows: 100000
  statement_timeout_ms: 30000
  warn_execution_ms: 5000
  max_aggregate_cells: 20