Curated results include units, history start, access needs, supported fetch tool,
    and caveat count so the next call can select the right concept. When the catalog has
    no match, uncurated candidates from the source's own search are returned under
    uncurated_upstream. BEA inventory candidates intentionally omit reviewed history,
    units, and verified_on. For keyless discovery across the Z.1 package data dictionary,
    pass family="z1".
    

    Prefer ids from find_series. Uncataloged FRED and BLS series are also served as
    fred.<SERIES_ID> / bls.<SERIES_ID>. Their source unit metadata is labeled when
    available; otherwise annualization is explicitly unknown. These passthroughs carry
    interpretation warnings instead of curated review. Returns a compact preview,
    binding caveats, provenance, and an artifact descriptor. Read full bytes through
    fiscus-cache://artifact/<cache_key>. Set refresh only for a new source retrieval.
    For a FRED/ALFRED snapshot, set vintage_as_of to a closed past ISO date; start and
    end remain observation-date bounds, and FRED_API_KEY is required. Vintage failures
    distinguish an unset key, a rejected credential, no ALFRED history, a request before
    the first ALFRED vintage, and a source identifier that does not exist. A failed BOGZ1
    identifier is not auto-corrected because its two-letter prefix encodes the concept.
    

    table_id is BEA's canonical TableName (for example T10106). frequency must be
    A, Q, or M and must be advertised for that table in BEA's source inventory.
    The route is NIPA-only, sends an explicit Year list rather than Year=X, and
    returns source-observed metric labels plus per-line coverage. Uncurated tables
    omit reviewed units, history, and verified_on claims; exact curated pairs add
    a separate catalog overlay. BEA_API_KEY is required for a source retrieval.
    

    Use official FiscalData query keys such as fields, filter, sort, and page[size].
    Narrow large requests with a filter instead of raising max_pages indiscriminately.
    

    Serves sources published as direct files (workbooks, delimited text, archives).
    Parseable csv/tsv files return a row preview; binary formats return provenance and
    an artifact descriptor. Read exact bytes at fiscus-cache://artifact/<cache_key>.
    

    Supply a date range to evaluate history seams and unit_classes when checking a planned
    combination of differently scaled, adjusted, or annualized series.