stack/tests/llm/golden_lineage.yaml

# Golden longitudinal evaluation set (P49 Task 7, refs #692).
#
# Anchors verified against the corpus in #692. Run with:
#   uv run python dev/scripts/llm_golden.py run --url <chat-url> \
#     --set tests/llm/golden_lineage.yaml --report report.json
#
# Schema per entry:
#   id             unique string
#   question       the question sent to POST /chat
#   mode           "auto" (default), "timeline" or "recent"
#   expect_anchors [{item_key, p_id}]  p_id may be [lo, hi] for a range;
#                  each anchor must appear among the streamed `sources`
#   expect_labels  [regex]  each must be matched somewhere in the
#                  concatenated `token` text (the cited answer prose)
#   forbid         [{pattern, unless_label}]  `pattern` may appear only
#                  in a sentence that also cites a bracketed label
#                  matching `unless_label`
#   expect_events  [{code, kind, year}]  kind may be "a|b" alternatives;
#                  must appear in the `lineage` event payload
#   expect_dockets [docket_id]  must appear among comment-kind sources
#   min_eras       distinct rule years among sources (rule/corpus: the
#                  source's date year; comment: its docket id's year)

- id: ccm-history
  # "CCM" in the CY2027 NPRM also names cardiac contractility modulation
  # (33X01–33X11); a chronic-care-management answer must never drift there.
  forbid:
    - pattern: 'contractility'
      unless_label: '^$'
  question: What is the history of CCM coding and payment?
  mode: timeline
  expect_anchors:
    - item_key: DE2VH9PD
      p_id: [1249, 1251]
    - item_key: YBM4IZUS
      p_id: 1578
  expect_events:
    - code: "99490"
      kind: created
      year: 2015
    - code: G2058
      kind: replaced_by
      year: 2021
  min_eras: 4

- id: g2058-replacement
  question: What replaced G2058, and why?
  mode: timeline
  expect_anchors:
    - item_key: YBM4IZUS
      p_id: 1578
    - item_key: YBM4IZUS
      p_id: 2369
  expect_events:
    - code: G2058
      kind: replaced_by
      year: 2021

- id: apcm-vs-ccm-elements
  question: How do APCM's elements differ from CCM's?
  expect_anchors:
    - item_key: JJ6AM5HJ
      p_id: [1164, 1185]
    - item_key: DE2VH9PD
      p_id: [1245, 1247]

- id: audio-only-em-99441
  question: When were audio-only E/M codes payable, and why did 99441-99443 end?
  mode: timeline
  expect_anchors:
    - item_key: XFGGRBDH
      p_id: 489
  expect_labels:
    # XFGGRBDH is the CY2025 *proposed* rule (91 FR, 2024-07-31); its title
    # carries no "Proposed", so the kind must come from the rule's text.
    - 'CY2025 PFS proposed .*¶489'
  expect_events:
    - code: "99441"
      kind: deleted|disappeared|cpt_deleted
      year: 2025

- id: g2211-commenters-2023-vs-2025
  question: What did commenters say about G2211 in 2023 versus 2025?
  mode: timeline
  expect_dockets:
    - CMS-2023-0121
    - CMS-2025-0304

- id: 99490-telehealth-steps
  question: Does 99490 pass telehealth Steps 1 through 3?
  expect_anchors:
    - item_key: 2KVJ2HKX
      p_id: 394
    - item_key: 2KVJ2HKX
      p_id: 396
    - item_key: 2KVJ2HKX
      p_id: 398

- id: g2064-g2065-to-99424-99426-rate
  question: How did G2064/G2065 becoming 99424/99426 change the RHC/FQHC G0511 rate?
  mode: timeline
  expect_anchors:
    - item_key: JE7KYBW3
      p_id: 1100
    - item_key: JE7KYBW3
      p_id: 1111
    - item_key: MZ24MX5S
      p_id: 1305
  forbid:
    - pattern: '\$[0-9]'
      unless_label: 'Addendum B'