6eb4f2cb8b
Some checks failed
CI / lint (push) Successful in 40s
CI / notebooks-smoke (push) Successful in 1m52s
Deploy / notebooks (push) Has been skipped
Deploy / zotero (push) Has been skipped
Deploy / docs (push) Has been skipped
Deploy / api (push) Has been skipped
Deploy / llm (push) Has been skipped
Deploy / mc (push) Has been skipped
CI / test (push) Failing after 3m8s
Infra CI / zotero (push) Successful in 31s
Infra CI / notebooks (push) Successful in 1m4s
Infra CI / api (push) Successful in 1m29s
Infra CI / docs (push) Successful in 1m55s
Infra CI / mc (push) Failing after 58s
Infra CI / llm (push) Successful in 1m20s
Deploy / report (push) Successful in 22s
Every Federal Register rule item was indexed twice: as anchored FR paragraphs in the rules collection (67k chunks, federalregister.gov links) and again from its PDF attachment into corpus (161k chunks, kind 'corpus', item-URL links). The PDF copies outnumbered the anchored ones 2:1 in retrieval, so proposed rules and corrections came back as 'corpus' citations. iter_corpus_refs now skips rule-typed and fr_anchors-bearing items; stack llm prune-rules deletes the corpus copies (and their index_state rows) and stamps rule_kind (proposed/final/correction, bib.frlink.rule_kind) on the rules chunks; new rule docs carry rule_kind from the start. as_source exposes it, the prompt's source line reads '(proposed rule, 2026-07-16)', and the chat and search badges show it instead of 'rule'. CMS Internet-Only Manual chapters: llm.manuals.sectionize turns each body section heading (the ones followed by their '(Rev.' line; the table of contents stays plain) into a markdown heading, so chunks split at section boundaries and carry section / iom_section / iom_title plus the chapter's publication number and chapter; enrich_pdf_pages lets chunks under a sub-heading inherit the enclosing file so they keep their page. Manual citations read 'IOM 100-04 ch.18 §10.1.2' and link to the chapter PDF page; /search takes doctype, manual, chapter and section filters.
260 lines
8.1 KiB
Python
260 lines
8.1 KiB
Python
"""llm.links — kind-specific evidence deep links (pure)."""
|
|
|
|
from llm.links import for_source
|
|
|
|
|
|
class TestComment:
|
|
def test_plain_comment_links_to_comment_page(self):
|
|
url, label = for_source(
|
|
{"kind": "comment", "comment_id": "CMS-2026-2377-3438"}, "snippet"
|
|
)
|
|
assert url == "https://www.regulations.gov/comment/CMS-2026-2377-3438"
|
|
assert label == "CMS-2026-2377-3438"
|
|
|
|
def test_pdf_attachment_chunk_links_to_page(self):
|
|
url, label = for_source(
|
|
{
|
|
"kind": "comment",
|
|
"comment_id": "CMS-2026-2377-3438",
|
|
"attachment": "attachment_2.pdf",
|
|
"page": "4",
|
|
},
|
|
"s",
|
|
)
|
|
assert url == (
|
|
"https://downloads.regulations.gov/CMS-2026-2377-3438/attachment_2.pdf#page=4"
|
|
)
|
|
assert label == "CMS-2026-2377-3438 p.4"
|
|
|
|
def test_non_pdf_attachment_no_page(self):
|
|
url, label = for_source(
|
|
{"kind": "comment", "comment_id": "C-1", "attachment": "attachment_1.docx"},
|
|
"s",
|
|
)
|
|
assert url == "https://downloads.regulations.gov/C-1/attachment_1.docx"
|
|
assert label == "C-1"
|
|
|
|
def test_missing_comment_id_falls_back_to_item_key(self):
|
|
url, label = for_source({"kind": "comment", "item_key": "ABCD1234"}, "s")
|
|
assert label == "ABCD1234"
|
|
assert url == ""
|
|
|
|
|
|
class TestRule:
|
|
MD = {
|
|
"kind": "rule",
|
|
"html_url": "https://www.federalregister.gov/documents/2026/07/16/2026-14327/x",
|
|
"p_id": "938",
|
|
"page": "43949",
|
|
"ordinal": "4",
|
|
"fr_volume": "91",
|
|
}
|
|
|
|
def test_paragraph_link_with_highlight(self):
|
|
url, label = for_source(
|
|
self.MD,
|
|
"In the FY 2027 Hospice proposed rule, CMS solicited comment. More.",
|
|
)
|
|
assert url == (
|
|
"https://www.federalregister.gov/documents/2026/07/16/2026-14327/x#p-938"
|
|
":~:text=In%20the%20FY%202027%20Hospice%20proposed%20rule%2C%20CMS%20solicited%20comment."
|
|
)
|
|
assert label == "91 FR 43949 ¶4"
|
|
|
|
def test_no_p_id_degrades_to_page_link(self):
|
|
md = {**self.MD, "p_id": "", "ordinal": ""}
|
|
url, label = for_source(md, "s")
|
|
assert url.endswith("/x#page-43949")
|
|
assert label == "91 FR 43949"
|
|
|
|
def test_no_page_degrades_to_document(self):
|
|
md = {
|
|
"kind": "rule",
|
|
"html_url": "https://fr.test/doc",
|
|
"title": "CY2027 PFS NPRM",
|
|
}
|
|
url, label = for_source(md, "s")
|
|
assert url == "https://fr.test/doc"
|
|
assert label == "CY2027 PFS NPRM"
|
|
|
|
|
|
class TestCorpus:
|
|
def test_item_url_and_short_title_with_year(self):
|
|
url, label = for_source(
|
|
{
|
|
"kind": "corpus",
|
|
"url": "https://pubmed.ncbi.nlm.nih.gov/19922199/",
|
|
"title": "A consensus on palliative care quality metrics for hospital programs",
|
|
"year": "2009",
|
|
},
|
|
"s",
|
|
)
|
|
assert url == "https://pubmed.ncbi.nlm.nih.gov/19922199/"
|
|
assert (
|
|
label
|
|
== "A consensus on palliative care quality metrics for hospital… (2009)"
|
|
)
|
|
|
|
def test_pdf_url_gets_page(self):
|
|
url, _ = for_source(
|
|
{
|
|
"kind": "corpus",
|
|
"url": "https://x.test/report.pdf",
|
|
"title": "R",
|
|
"page": "7",
|
|
},
|
|
"s",
|
|
)
|
|
assert url == "https://x.test/report.pdf#page=7"
|
|
|
|
def test_non_pdf_url_ignores_page(self):
|
|
url, _ = for_source(
|
|
{
|
|
"kind": "corpus",
|
|
"url": "https://x.test/report",
|
|
"title": "R",
|
|
"page": "7",
|
|
},
|
|
"s",
|
|
)
|
|
assert url == "https://x.test/report"
|
|
|
|
def test_untitled_falls_back_to_item_key(self):
|
|
_, label = for_source({"kind": "corpus", "item_key": "K1", "url": ""}, "s")
|
|
assert label == "K1"
|
|
|
|
|
|
def test_unknown_kind_treated_as_corpus():
|
|
url, label = for_source({"url": "https://u.test", "title": "T"}, "s")
|
|
assert (url, label) == ("https://u.test", "T")
|
|
|
|
|
|
class TestAsSource:
|
|
def test_shape_matches_rag_source(self):
|
|
from llm.links import as_source
|
|
|
|
s = as_source(
|
|
{
|
|
"kind": "comment",
|
|
"comment_id": "CMS-2026-2377-1",
|
|
"date": "2026-08-19",
|
|
"title": "t",
|
|
"docket": "CMS-2026-2377",
|
|
"item_key": "ABCD1234",
|
|
"seq": "3",
|
|
"section": "Some Heading",
|
|
},
|
|
"body " * 200,
|
|
0.123456,
|
|
)
|
|
assert set(s) == {
|
|
"attachment",
|
|
"page",
|
|
"rule_kind",
|
|
"doctype",
|
|
"manual",
|
|
"chapter",
|
|
"iom_section",
|
|
"id",
|
|
"label",
|
|
"kind",
|
|
"url",
|
|
"title",
|
|
"date",
|
|
"docket",
|
|
"comment_id",
|
|
"snippet",
|
|
"score",
|
|
"item_key",
|
|
"p_id",
|
|
"seq",
|
|
"section",
|
|
}
|
|
assert s["label"] == "CMS-2026-2377-1" and s["kind"] == "comment"
|
|
assert len(s["snippet"]) <= 500 and s["score"] == 0.1235
|
|
# non-rule kind: seq/section carried through, p_id blanked
|
|
assert s["item_key"] == "ABCD1234" and s["seq"] == "3"
|
|
assert s["section"] == "Some Heading" and s["p_id"] == ""
|
|
|
|
def test_rule_kind_carries_p_id_not_seq(self):
|
|
from llm.links import as_source
|
|
|
|
s = as_source({**TestRule.MD, "item_key": "WXYZ5678", "seq": "9"}, "text", 0.0)
|
|
assert s["item_key"] == "WXYZ5678"
|
|
assert s["p_id"] == "938" and s["seq"] == ""
|
|
|
|
def test_missing_keys_default_to_empty(self):
|
|
from llm.links import as_source
|
|
|
|
s = as_source({"kind": "corpus"}, "text", 0.0)
|
|
assert s["item_key"] == "" and s["p_id"] == ""
|
|
assert s["seq"] == "" and s["section"] == ""
|
|
|
|
|
|
class TestRuleKindAndManual:
|
|
def test_rule_source_carries_rule_kind(self):
|
|
from llm.links import as_source
|
|
|
|
s = as_source(
|
|
{
|
|
"kind": "rule",
|
|
"item_key": "R1",
|
|
"p_id": "12",
|
|
"page": "43949",
|
|
"ordinal": "4",
|
|
"fr_volume": "91",
|
|
"html_url": "https://www.federalregister.gov/d/2026-14327",
|
|
"rule_kind": "proposed",
|
|
"title": "t",
|
|
},
|
|
"text",
|
|
0.5,
|
|
)
|
|
assert s["rule_kind"] == "proposed" and s["label"] == "91 FR 43949 ¶4"
|
|
assert s["url"].startswith("https://www.federalregister.gov/d/2026-14327#p-12")
|
|
assert (
|
|
as_source({"kind": "corpus", "rule_kind": "final"}, "t", 0.1)["rule_kind"]
|
|
== ""
|
|
)
|
|
|
|
def test_manual_section_label_and_link(self):
|
|
from llm.links import as_source
|
|
|
|
s = as_source(
|
|
{
|
|
"kind": "corpus",
|
|
"doctype": "manual",
|
|
"manual": "100-04",
|
|
"chapter": "18",
|
|
"iom_section": "10.1.2",
|
|
"iom_title": "Influenza Virus Vaccine",
|
|
"page": "7",
|
|
"title": "Medicare Claims Processing Manual — Chapter 18",
|
|
"url": "https://www.cms.gov/x/clm104c18.pdf",
|
|
},
|
|
"text",
|
|
0.5,
|
|
)
|
|
assert s["label"] == "IOM 100-04 ch.18 §10.1.2"
|
|
assert s["url"] == "https://www.cms.gov/x/clm104c18.pdf#page=7"
|
|
assert (s["doctype"], s["manual"], s["chapter"], s["iom_section"]) == (
|
|
"manual",
|
|
"100-04",
|
|
"18",
|
|
"10.1.2",
|
|
)
|
|
# a manual chunk before the first section (front matter) keeps the title label
|
|
s2 = as_source(
|
|
{
|
|
"kind": "corpus",
|
|
"doctype": "manual",
|
|
"manual": "",
|
|
"chapter": "",
|
|
"title": "Chapter 18",
|
|
"year": "2024",
|
|
},
|
|
"t",
|
|
0.5,
|
|
)
|
|
assert s2["label"] == "Chapter 18 (2024)"
|