Pass a docket ID like 'FAR Case 2023-008' (or a FAC number like
'FAC 2025-06'). Runs BOTH a docket-id search and a quoted full-text
search, then merges the two result sets (deduped by document number)
in chronological order to show the full rulemaking progression:
ANPRM -> proposed rule -> final rule -> corrections. The dual query
matters: FAC introduction and companion documents often carry only
internal docket numbers, so a docket-only search returns a partial set.

Docket matching is token-based, not substring: 'FAR Case 2023' matches
all 2023 cases (token '2023' matches '2023-008'), but a partial token
like 'FAR Case 20' matches nothing. Be specific to avoid false positives.

Each document carries matched_by: 'docket' or 'docket+text' when its
docket ids name the case, 'text' when it only mentions the case in its
text (regulatory agendas, related or companion cases, FAC
introductions, public meetings). Read 'text' matches with care.

Each underlying search returns at most 100 documents. truncated=True
flags that one of the searches hit that cap (docket_matches and
term_matches carry the API's full counts); narrow the docket_id if so.

Minimum docket_id length is 3 characters to prevent token matches that
return unrelated documents (e.g. 'x' matched 65 random dockets in 0.1.x).