Merge pull request 'fix: signpost partially-suppressed categories (#9)' (#32) from fix/partial-coverage-signposting-9 into main

NEWS.md

@@ -1,5 +1,38 @@
 # uscogdata 0.1.0 (development)
 
+## Signposting now catches partially-suppressed categories
+
+* A coverage suggestion used to fire only when a category returned **no rows
+  at all** in a requested year. That missed the more dangerous case: a
+  category that still returns rows while silently dropping component codes
+  the wide era publishes only as aggregates (#9). `cog_spending(category =
+  "Public Welfare")` for FY2011 returned a plausible figure that omitted
+  `E67`/`E68` entirely -- for Los Angeles County, $2,075,461,000 of a true
+  $5,261,404,000, a 39% understatement, with `provenance$suggestions` empty.
+* Suggestions now also fire on **partial** coverage, and every suggestion
+  carries `trigger` (`"empty_year"` or `"suppressed_component"`),
+  `suppressed_amount`, `suppressed_years` and `suppressed_codes`, so a caller
+  can see how much is missing and decide whether to re-run with the recipe.
+* `cog_revenue()` gets the same fix through the shared verb path. Alaska's
+  FY2011 `Miscellaneous Revenue` reported $943,842,000 while dropping
+  $1,899,995,000 of aggregate-published `U4-` rents and royalties.
+* The trigger stays recipe-driven, so it only fires where a harmonization
+  recipe actually exists to name the fix. `higher_ed_e18_wide` and
+  `general_gov_e89_wide` stay silent in every year measured on the bundled
+  fixture, because their components are ordinary classified leaves even
+  pre-2012.
+* The `suppressed_component` trigger (and any `suppressed_amount`/
+  `suppressed_codes` an `empty_year` fire also carries) is scoped to the
+  calling verb's own flow family: `cog_spending()` only ever measures E/F/G
+  component dollars, `cog_revenue()` only T/A/U/B/C/D. A component from the
+  OTHER flow family reports `suppressed_amount = 0` rather than a fabricated
+  claim. The `empty_year` trigger itself is not flow-scoped -- a category
+  belonging to the other flow (e.g. `cog_spending(category = "IG Local")`)
+  still returns zero rows and can still fire, in any year including modern
+  ones, naming the recipe whose own generic join finds real data for this
+  government. That is a mis-scoped query, not a corpus-format gap, so its
+  `suppressed_amount` is correctly 0.
+
 ## New: `cog_balances()` for cash-and-security holdings
 
 * New `cog_balances()` exposes the 14 cash-and-security holding codes

R/explain.R

@@ -125,8 +125,15 @@ cog_explain <- function(result, format = c("print", "list")) {
   if (length(prov$suggestions) > 0L) {
     cli::cli_h2("Suggestions")
     sugg_lines <- vapply(prov$suggestions, function(s) {
-      sprintf("%s -- %s (years %s-%s): %s", s$recipe_id, s$label,
+      line <- sprintf("%s -- %s (years %s-%s): %s", s$recipe_id, s$label,
               s$available_years[1], s$available_years[2], s$hint)
+      if (isTRUE(s$suppressed_amount > 0)) {
+        line <- paste0(line, sprintf(" [$%s excluded from %s: %s]",
+          formatC(s$suppressed_amount, format = "f", digits = 0, big.mark = ","),
+          paste0("FY", s$suppressed_years, collapse = ", "),
+          paste(s$suppressed_codes, collapse = ", ")))
+      }
+      line
     }, character(1))
     cli::cli_ul(sugg_lines)
   }

R/spending.R

@@ -395,7 +395,8 @@ cog_spending <- function(govid, years, category = NULL,
     }
     suggestions <- .build_suggestions(con, govid, years, category,
                                        direct_leg_result,
-                                       resolved$basis, flow_prefixes)
+                                       resolved$basis, flow_prefixes,
+                                       .select_long_view(view_base, resolved$basis))
   }
 
   # C1(b): when expenditure_concept = "total", flag any row where the IG
@@ -512,6 +513,18 @@ cog_spending <- function(govid, years, category = NULL,
   if (identical(basis, "harmonized")) paste0(view_base, "_harmonized") else view_base
 }
 
+#' The `*_long`/`*_long_harmonized` view behind an annotated view base --
+#' `"spending_annotated"` -> `"spending_long_harmonized"`. `.build_suggestions()`
+#' anti-joins the LONG view rather than the annotated one: they have identical
+#' row membership (the annotated views are the long views plus LEFT JOINs, see
+#' inst/sql/42-spending_annotated_harmonized.sql), but the long view is the
+#' one that actually owns the `NOT is_aggregate` + crosswalk-membership rule
+#' the suppression test is asking about.
+#' @noRd
+.select_long_view <- function(view_base, basis) {
+  .select_view(sub("_annotated$", "_long", view_base), basis)
+}
+
 #' @noRd
 .select_ig_view <- function(basis) {
   if (identical(basis, "harmonized")) "ig_annotated_harmonized" else "ig_annotated"

R/suggestions.R

@@ -1,8 +1,16 @@
 # R/suggestions.R
-# Recipe-component-driven signposting: when a basis = "harmonized" query for
+# Recipe-component-driven signposting. When a basis = "harmonized" query for
-# a category comes back with a coverage gap in some requested years (the
+# a category comes back incomplete in some requested year -- and a
-# result has no rows at all in that year) that a harmonization recipe would
+# harmonization recipe would actually fill it for this government -- surface
-# actually fill for this government, surface that recipe as a suggestion.
+# that recipe as a suggestion. "Incomplete" has two forms, and a recipe
+# qualifies on either:
+#   1. empty_year          -- the result has no rows at all in that year.
+#   2. suppressed_component -- the result HAS rows, but a component code
+#      carries dollars the verb's own long view structurally excludes
+#      (aggregate-published, or absent from summary_categories). This is
+#      uscogdata#9: Public Welfare kept returning E74/E79 rows while dropping
+#      aggregate-only E67/E68, so form 1 never fired and the caller got a
+#      number a third too low with no signpost at all.
 #
 # This is deliberately keyed off the recipe catalog's component codes, not
 # off harmonization_map rows: no live map row carries a non-blank
@@ -48,11 +56,15 @@
 #'   "D")` for `cog_revenue()` -- see `.verb_spendrev()`). Passed through to
 #'   `.attach_ig_counterparts()` to keep the intergovernmental-counterpart
 #'   lookup scoped to the calling verb's own flow family.
+#' @param long_view Name of the verb's own long view (from
+#'   `.select_long_view()`), passed through to `.suppressed_components()` to
+#'   measure the second qualifying path (uscogdata#9).
 #' @return List of `list(recipe_id, label, available_years, hint,
-#'   ig_recipe_id)`, possibly empty.
+#'   ig_recipe_id, trigger, suppressed_amount, suppressed_years,
+#'   suppressed_codes)`, possibly empty.
 #' @noRd
 .build_suggestions <- function(con, govid, years, category, result, basis,
-                                flow_prefixes) {
+                                flow_prefixes, long_view) {
   if (!identical(basis, "harmonized") || is.null(category)) return(list())
 
   # Exclude any recipe that is ITSELF an intergovernmental (M/L) recipe --
@@ -86,7 +98,28 @@
     unique(as.integer(result$year))
   }
   gap_years <- setdiff(as.integer(years), result_years)
-  if (length(gap_years) == 0L) return(list())
+
+  # Path 2 (uscogdata#9): component dollars this government holds that the
+  # verb's own view structurally excludes. Measured across ALL requested
+  # years, not just gap years -- the whole point is that a year with rows can
+  # still be missing dollars. Scoped to the calling verb's own flow_prefixes
+  # (I1) -- see `.suppressed_components()`'s own roxygen for why.
+  #
+  # This runs unconditionally whenever there are candidates -- an earlier
+  # revision of this fix wave tried a free, in-memory pre-check
+  # (`.needs_suppression_query()`) to skip the round trip on an already-
+  # covered path, but a scoped re-review measured it against the fixture and
+  # found it didn't pay for itself (it skipped ~3% of healthy calls, ~0% of
+  # the multi-govid batch shape it was meant to help, at a net cost increase
+  # once its own always-run metadata query was counted) while adding an
+  # untested exactness invariant -- that `result$codes_included` and this
+  # anti-join share the harmonized `item_code` space -- whose silent
+  # violation would kill signposting, the exact failure class uscogdata#9
+  # exists to prevent. Owner's call: keep this simple; a batch-aware
+  # optimization, if one is worth building, is a separate issue.
+  supp <- .suppressed_components(con, candidates, govid, years, long_view, flow_prefixes)
+
+  if (length(gap_years) == 0L && nrow(supp) == 0L) return(list())
 
   meta <- tibble::as_tibble(DBI::dbGetQuery(con, sprintf(
     "SELECT recipe_id, any_value(label) AS label,
@@ -97,35 +130,55 @@
     .sql_lit_chr(candidates)
   )))
 
-  # Which (recipe_id, year) pairs the recipe's own generic join actually
+  # Path 1 (unchanged): (recipe, year) pairs the recipe's own generic join
-  # covers for this government, restricted to the gap years -- the same
+  # covers for this government, restricted to the gap years.
-  # join .run_recipe() uses (component year_min/year_max + gov_type_scope,
+  covered <- if (length(gap_years) == 0L) {
-  # no is_aggregate filter), just checking existence instead of summing.
+    data.frame(recipe_id = character(0), year = integer(0))
-  covered <- DBI::dbGetQuery(con, sprintf(
+  } else {
-    "SELECT DISTINCT r.recipe_id, l.year
+    DBI::dbGetQuery(con, sprintf(
-     FROM long l
+      "SELECT DISTINCT r.recipe_id, l.year
-     JOIN harmonization_recipes r
+       FROM long l
-       ON l.item_code = r.component_code
+       JOIN harmonization_recipes r
-      AND l.year BETWEEN r.year_min AND r.year_max
+         ON l.item_code = r.component_code
-      AND (r.gov_type_scope = 'all'
+        AND l.year BETWEEN r.year_min AND r.year_max
-           OR (r.gov_type_scope = 'state' AND l.type = 0)
+        AND (r.gov_type_scope = 'all'
-           OR (r.gov_type_scope = 'local' AND l.type BETWEEN 1 AND 3))
+             OR (r.gov_type_scope = 'state' AND l.type = 0)
-     WHERE r.recipe_id IN (%s)
+             OR (r.gov_type_scope = 'local' AND l.type BETWEEN 1 AND 3))
-       AND l.canonical_govid IN (%s)
+       WHERE r.recipe_id IN (%s)
-       AND l.year IN (%s)",
+         AND l.canonical_govid IN (%s)
-    .sql_lit_chr(candidates), .sql_lit_chr(govid),
+         AND l.year IN (%s)",
-    paste(gap_years, collapse = ",")
+      .sql_lit_chr(candidates), .sql_lit_chr(govid),
-  ))
+      paste(gap_years, collapse = ",")
+    ))
+  }
 
   suggestions <- list()
   for (rid in candidates) {
-    if (!rid %in% covered$recipe_id) next
+    empty_hit <- rid %in% covered$recipe_id
+    s_rows <- supp[supp$recipe_id == rid, , drop = FALSE]
+    supp_hit <- nrow(s_rows) > 0L
+    if (!empty_hit && !supp_hit) next
     m <- meta[meta$recipe_id == rid, ]
     suggestions[[length(suggestions) + 1L]] <- list(
       recipe_id = rid,
       label = m$label[[1]],
       available_years = c(as.integer(m$year_min), as.integer(m$year_max)),
-      hint = sprintf("re-run with recipe = '%s'", rid)
+      hint = sprintf("re-run with recipe = '%s'", rid),
+      # An empty year is the stronger claim -- the category returned nothing
+      # at all -- so it wins when both paths qualify. The suppressed_* fields
+      # are still populated, so an empty_year fire also reports its dollars.
+      trigger = if (empty_hit) "empty_year" else "suppressed_component",
+      suppressed_amount = if (supp_hit) sum(s_rows$suppressed_amount) else 0,
+      suppressed_years = if (supp_hit) {
+        sort(unique(as.integer(s_rows$year)))
+      } else {
+        integer(0)
+      },
+      suppressed_codes = if (supp_hit) {
+        sort(unique(unlist(strsplit(s_rows$suppressed_codes, ",", fixed = TRUE))))
+      } else {
+        character(0)
+      }
     )
   }
   .attach_ig_counterparts(con, suggestions, flow_prefixes)
@@ -232,12 +285,25 @@
 #' expressions. When a suggestion has an `ig_recipe_id`, one indented
 #' continuation line is appended naming the intergovernmental counterpart
 #' recipe (embedded `\n` renders as a hanging-indent continuation of the
-#' same bullet under cli, not a new bullet).
+#' same bullet under cli, not a new bullet). Same treatment for
+#' `suppressed_amount` (uscogdata#9): only present when dollars were
+#' actually measured as excluded (an `empty_year` fire can carry them too --
+#' see `.build_suggestions()` -- so this keys off the amount, not `trigger`).
 #' @noRd
 .inform_suggestions <- function(suggestions) {
   bullets <- vapply(suggestions, function(s) {
     bullet <- sprintf("%s (%d-%d): %s", s$recipe_id,
             s$available_years[1], s$available_years[2], s$hint)
+    # Only present when dollars were actually measured as excluded. An
+    # empty_year fire can carry them too -- the year had no rows AND the
+    # component was suppressed -- which is strictly more informative.
+    if (isTRUE(s$suppressed_amount > 0)) {
+      bullet <- paste0(bullet, sprintf(
+        "\n  $%s excluded from %s (%s), published as an aggregate or outside the crosswalk",
+        formatC(s$suppressed_amount, format = "f", digits = 0, big.mark = ","),
+        paste0("FY", s$suppressed_years, collapse = ", "),
+        paste(s$suppressed_codes, collapse = ", ")))
+    }
     if (!is.null(s$ig_recipe_id)) {
       bullet <- paste0(bullet, sprintf(
         "\n  intergovernmental counterpart: recipe = '%s'", s$ig_recipe_id))
@@ -245,7 +311,7 @@
     bullet
   }, character(1))
   cli::cli_inform(c(
-    i = "Coverage gap detected for the requested years; a harmonization recipe may fill it:",
+    i = "Incomplete coverage for the requested years; a harmonization recipe may fill it:",
     stats::setNames(bullets, rep("*", length(bullets)))
   ))
 }

R/suppression.R

@@ -0,0 +1,115 @@
+# R/suppression.R
+# Split out of R/suggestions.R (2026-08-05) to keep files under the project's
+# 400-line limit. Owns the second qualifying path for coverage signposting
+# (uscogdata#9): measuring, per government, the component dollars the
+# calling verb's own long view structurally excludes (aggregate-published,
+# or absent from summary_categories). See R/suggestions.R for the
+# orchestrator (`.build_suggestions()`) that calls this and the full
+# uscogdata#9 background.
+
+#' Measure, per (recipe, year), the component dollars this government holds
+#' that the calling verb's own long view structurally excludes.
+#'
+#' This is the second qualifying path for a suggestion (uscogdata#9). The
+#' first -- row absence -- only fires when a category returns NOTHING in a
+#' requested year, which is how Corrections behaves in the wide era. Public
+#' Welfare is the failure mode it misses: E74/E75/E77/E79 still return rows,
+#' so there is no absence to detect, while E67/E68 (aggregate-flagged 1967-
+#' 2011, and absent from `summary_categories` entirely) are dropped. The
+#' caller gets a plausible number a third too low, silently.
+#'
+#' "Structurally excluded" is decided by anti-joining the verb's REAL long
+#' view rather than restating its WHERE clause, so this stays correct if
+#' `spending_long_harmonized` / `revenue_long_harmonized` ever change. That
+#' anti-join is keyed on `item_code`, which is sound only because
+#' harmonization never renames a recipe component -- asserted by the "no
+#' recipe component is ever renamed by harmonization" test in
+#' tests/testthat/test-recipes.R.
+#'
+#' Note what this deliberately does NOT count as suppressed: a component
+#' excluded from the RESULT for scoping reasons -- because it belongs to a
+#' different `category`, or because `expenditure_concept` narrowed the
+#' subtypes -- is still present in the view, so it never fires. Suggesting a
+#' recipe is a coverage fix, not a category redefinition.
+#'
+#' `flow_prefixes` (uscogdata#9 review, finding I1) restricts the measured
+#' components to the CALLING VERB's own flow family (`c("E","F","G")` for
+#' spending, `c("T","A","U","B","C","D")` for revenue). Without this, a
+#' candidate recipe belonging to the OTHER flow family is always absent from
+#' this verb's view (by construction -- `cog_revenue()`'s view never carries
+#' an E-coded row) and so was always reported as "suppressed", fabricating a
+#' dollar claim across flow families (`cog_revenue(category = "Corrections")`
+#' claimed $3.63B excluded that `cog_spending()` reports and fully accounts
+#' for). Filtering on `LEFT(r.component_code, 1)` also drops M/L-prefixed
+#' components from measurement under `cog_spending()` (`flow_prefixes` never
+#' includes "M"/"L") -- harmless today, because a recipe's own M/L components
+#' (e.g. `corrections_ig_local_combined`'s M04/M05) are present in the view
+#' in every year they exist and so never fired as suppressed anyway, but
+#' worth recording since this filter is now the thing relied on to prevent
+#' it.
+#'
+#' @param con Active DuckDB connection.
+#' @param candidates Character vector of recipe ids to measure.
+#' @param govid Character vector of canonical_govid values.
+#' @param years Integer vector of requested years.
+#' @param long_view Name of the verb's long view, from `.select_long_view()`.
+#' @param flow_prefixes The calling verb's own flow-type prefixes (see
+#'   `.build_suggestions()`). Only recipe components whose first character is
+#'   in this set are measured.
+#' @return Tibble of `recipe_id`, `year`, `suppressed_amount` (full US
+#'   dollars), `suppressed_codes` (comma-joined, sorted). Zero rows when
+#'   nothing is suppressed.
+#' @noRd
+.suppressed_components <- function(con, candidates, govid, years, long_view,
+                                    flow_prefixes) {
+  empty <- tibble::tibble(
+    recipe_id = character(0), year = numeric(0),
+    suppressed_amount = numeric(0), suppressed_codes = character(0)
+  )
+  if (length(candidates) == 0L) return(empty)
+
+  # long_view is interpolated as a SQL IDENTIFIER, not a literal, so it can
+  # never be quoted safely. It is always internally derived from a fixed
+  # view_base, so an off-allowlist value is a programming error, not input.
+  if (!long_view %in% c("spending_long", "spending_long_harmonized",
+                        "revenue_long", "revenue_long_harmonized")) {
+    cli::cli_abort(
+      "Internal error: unexpected `long_view` {.val {long_view}}.",
+      class = "uscogdata_internal_error"
+    )
+  }
+
+  sql <- sprintf(
+    "SELECT r.recipe_id,
+            l.year,
+            SUM(l.amt) * 1000.0 AS suppressed_amount,
+            string_agg(DISTINCT l.item_code, ',' ORDER BY l.item_code)
+              AS suppressed_codes
+     FROM long l
+     JOIN harmonization_recipes r
+       ON l.item_code = r.component_code
+      AND l.year BETWEEN r.year_min AND r.year_max
+      AND (r.gov_type_scope = 'all'
+           OR (r.gov_type_scope = 'state' AND l.type = 0)
+           OR (r.gov_type_scope = 'local' AND l.type BETWEEN 1 AND 3))
+     WHERE r.recipe_id IN (%1$s)
+       AND l.canonical_govid IN (%2$s)
+       AND l.year IN (%3$s)
+       AND l.amt <> 0
+       AND LEFT(r.component_code, 1) IN (%5$s)
+       AND NOT EXISTS (
+         SELECT 1 FROM %4$s v
+         WHERE v.canonical_govid = l.canonical_govid
+           AND v.year = l.year
+           AND v.item_code = l.item_code
+           AND v.year IN (%3$s)              -- restated: enables partition pruning (I3a)
+           AND v.canonical_govid IN (%2$s)   -- restated: pushes the govid filter (I3a)
+       )
+     GROUP BY 1, 2
+     ORDER BY 1, 2",
+    .sql_lit_chr(candidates), .sql_lit_chr(govid),
+    paste(as.integer(years), collapse = ","), long_view,
+    .sql_lit_chr(flow_prefixes)
+  )
+  tibble::as_tibble(DBI::dbGetQuery(con, sql))
+}

inst/schemas/provenance-v1.json

@@ -33,7 +33,48 @@
     },
     "harmonization":  { "type": "object" },
     "recipe":         { "type": ["object", "null"] },
-    "suggestions":    { "type": "array" },
+    "suggestions": {
+      "type": "array",
+      "description": "Harmonization recipes that would fill incomplete coverage in the requested years for this government. Empty on a healthy query, on an un-scoped (category = NULL) query, on basis = 'raw', and on a recipe = query (which resolves its own coverage).",
+      "items": {
+        "type": "object",
+        "required": ["recipe_id", "label", "available_years", "hint", "ig_recipe_id",
+                     "trigger", "suppressed_amount", "suppressed_years", "suppressed_codes"],
+        "properties": {
+          "recipe_id": { "type": "string" },
+          "label": { "type": "string" },
+          "available_years": {
+            "type": "array",
+            "items": { "type": "integer" },
+            "description": "[year_min, year_max] of the recipe's component coverage."
+          },
+          "hint": { "type": "string" },
+          "ig_recipe_id": {
+            "type": ["string", "null"],
+            "description": "The intergovernmental (M/L) counterpart recipe covering the same function suffixes, or null. Never set for revenue recipes."
+          },
+          "trigger": {
+            "type": "string",
+            "enum": ["empty_year", "suppressed_component"],
+            "description": "Why this fired. 'empty_year': the result has no rows at all in a requested year. 'suppressed_component': the result HAS rows, but a component code carries dollars this government reports in the requested years that the verb's underlying long view structurally excludes -- aggregate-published, carrying no harmonized code, or absent from summary_categories. This is NOT the same thing as 'excluded from the result': a component present in the view under a different category (a scoping choice, e.g. a different `category` or a narrower `expenditure_concept`) contributes 0 and never fires. 'empty_year' wins when both apply, being the stronger claim; the suppressed_* fields are populated either way, using the same underlying-view measurement, and can be 0 even on an 'empty_year' fire."
+          },
+          "suppressed_amount": {
+            "type": "number",
+            "description": "Full US dollars this government reports, in the recipe's component codes, in the requested years, that the verb's underlying long view structurally excludes (aggregate-published, carrying no harmonized code, or absent from summary_categories) -- summed across those years. This is NOT the same quantity as 'what the result excludes': a component present in the view under a different category or a narrower `expenditure_concept` is scoped out on purpose, counts as 0 here, and is not suppression. 0 does not always mean full coverage -- see 'trigger' and 'empty_year'. May be negative where Census publishes a negative `amt` for the excluded rows."
+          },
+          "suppressed_years": {
+            "type": "array",
+            "items": { "type": "integer" },
+            "description": "The requested years contributing to suppressed_amount."
+          },
+          "suppressed_codes": {
+            "type": "array",
+            "items": { "type": "string" },
+            "description": "The excluded component item codes, sorted."
+          }
+        }
+      }
+    },
     "scope":          { "type": "object" },
     "codes_summed":   { "type": "object" },
     "aggregate_fallback": { "type": ["object", "null"] },

tests/testthat/test-recipes.R

@@ -214,3 +214,255 @@ test_that("no signposting under basis = 'raw'", {
   prov <- attr(r, "provenance")
   expect_length(prov$suggestions, 0L)
 })
+
+# --- uscogdata#9: partial-coverage signposting ------------------------------
+
+test_that("no recipe component is ever renamed by harmonization", {
+  # The suppression trigger anti-joins the verb's long view on item_code.
+  # That is only sound because harmonization never rewrites a recipe
+  # component's code -- every component whose harmonized_code differs has
+  # harmonized_code IS NULL (and is aggregate-flagged). If this ever fails,
+  # .suppressed_components() would report reachable dollars as suppressed.
+  skip_if_no_corpus()
+  con <- uscogdata:::.ensure_session()
+  n <- DBI::dbGetQuery(con,
+    "SELECT COUNT(*) AS renamed FROM long
+     WHERE item_code IN (SELECT DISTINCT component_code FROM harmonization_recipes)
+       AND harmonized_code IS NOT NULL
+       AND harmonized_code <> item_code")$renamed
+  expect_equal(as.integer(n), 0L)
+})
+
+test_that(".select_long_view maps annotated view bases to their long views", {
+  expect_equal(
+    uscogdata:::.select_long_view("spending_annotated", "harmonized"),
+    "spending_long_harmonized")
+  expect_equal(
+    uscogdata:::.select_long_view("revenue_annotated", "harmonized"),
+    "revenue_long_harmonized")
+  expect_equal(
+    uscogdata:::.select_long_view("spending_annotated", "raw"),
+    "spending_long")
+})
+
+test_that(".suppressed_components measures the E67/E68 dollars Public Welfare drops", {
+  skip_if_no_corpus()
+  con <- uscogdata:::.ensure_session()
+  s <- uscogdata:::.suppressed_components(
+    con,
+    candidates = c("welfare_cash_e67_wide", "welfare_cash_e68_wide"),
+    govid = "061037123085", years = 2011L,
+    long_view = "spending_long_harmonized",
+    flow_prefixes = c("E", "F", "G"))
+
+  expect_s3_class(s, "tbl_df")
+  expect_equal(nrow(s), 2L)
+  s <- s[order(s$recipe_id), ]
+  expect_equal(s$recipe_id, c("welfare_cash_e67_wide", "welfare_cash_e68_wide"))
+  expect_equal(s$suppressed_amount, c(1803872000, 271589000))
+  expect_equal(s$suppressed_codes, c("E67", "E68"))
+})
+
+test_that(".suppressed_components finds nothing in a modern year", {
+  skip_if_no_corpus()
+  con <- uscogdata:::.ensure_session()
+  s <- uscogdata:::.suppressed_components(
+    con,
+    candidates = c("welfare_cash_e67_wide", "welfare_cash_e68_wide"),
+    govid = "061037123085", years = 2019L,
+    long_view = "spending_long_harmonized",
+    flow_prefixes = c("E", "F", "G"))
+  expect_equal(nrow(s), 0L)
+})
+
+test_that(".suppressed_components rejects a long_view outside the allowlist", {
+  skip_if_no_corpus()
+  con <- uscogdata:::.ensure_session()
+  expect_error(
+    uscogdata:::.suppressed_components(
+      con, candidates = "welfare_cash_e67_wide", govid = "061037123085",
+      years = 2011L, long_view = "long; DROP TABLE x",
+      flow_prefixes = c("E", "F", "G")),
+    class = "uscogdata_internal_error")
+})
+
+test_that(".suppressed_components never measures a component from the other flow family (I1)", {
+  # uscogdata#9 review, finding I1: without the flow_prefixes filter, a
+  # candidate recipe entirely outside the calling verb's own flow family is
+  # ALWAYS absent from that verb's view (by construction), so it was always
+  # reported as "suppressed" -- fabricating a dollar claim. E67/E68 are
+  # Public Welfare EXPENDITURE codes; scoping the measurement to revenue's
+  # own flow_prefixes must find nothing for them.
+  skip_if_no_corpus()
+  con <- uscogdata:::.ensure_session()
+  s <- uscogdata:::.suppressed_components(
+    con,
+    candidates = c("welfare_cash_e67_wide", "welfare_cash_e68_wide"),
+    govid = "061037123085", years = 2011L,
+    long_view = "revenue_long_harmonized",
+    flow_prefixes = c("T", "A", "U", "B", "C", "D"))
+  expect_equal(nrow(s), 0L)
+})
+
+test_that("uscogdata#9: Public Welfare signposts its suppressed E67/E68 dollars", {
+  # The bug: E74/E79 return rows for FY2011, so there is no row-absence gap,
+  # so nothing fired -- while E67 ($1,803,872,000) and E68 ($271,589,000) were
+  # dropped for being aggregate-published. LA County reports $3,185,943,000
+  # and omits $2,075,461,000, a 39% understatement, silently.
+  skip_if_no_corpus()
+  r <- suppressMessages(
+    cog_spending("061037123085", years = 2011L, category = "Public Welfare"))
+  sugg <- attr(r, "provenance")$suggestions
+
+  expect_length(sugg, 2L)
+  ids <- vapply(sugg, function(s) s$recipe_id, character(1))
+  expect_setequal(ids, c("welfare_cash_e67_wide", "welfare_cash_e68_wide"))
+
+  e67 <- sugg[[which(ids == "welfare_cash_e67_wide")]]
+  expect_equal(e67$trigger, "suppressed_component")
+  expect_equal(e67$suppressed_amount, 1803872000)
+  expect_equal(e67$suppressed_years, 2011L)
+  expect_equal(e67$suppressed_codes, "E67")
+  expect_equal(e67$hint, "re-run with recipe = 'welfare_cash_e67_wide'")
+
+  e68 <- sugg[[which(ids == "welfare_cash_e68_wide")]]
+  expect_equal(e68$trigger, "suppressed_component")
+  expect_equal(e68$suppressed_amount, 271589000)
+  expect_equal(e68$suppressed_codes, "E68")
+})
+
+test_that("uscogdata#9: an empty_year fire keeps its trigger and gains the dollars", {
+  # Corrections is the case that already worked: zero rows in FY2011, so the
+  # row-absence path fires. It must keep firing, keep trigger = "empty_year",
+  # keep its IG counterpart -- and now also report what was suppressed.
+  skip_if_no_corpus()
+  r <- suppressMessages(
+    cog_spending("061037123085", years = 2011L, category = "Corrections"))
+  sugg <- attr(r, "provenance")$suggestions
+
+  expect_length(sugg, 3L)
+  ids <- vapply(sugg, function(s) s$recipe_id, character(1))
+  expect_setequal(ids, c("corrections_combined", "corrections_capital_combined",
+                         "corrections_other_capital_combined"))
+  expect_true(all(vapply(sugg, function(s) s$trigger, character(1)) == "empty_year"))
+
+  cc <- sugg[[which(ids == "corrections_combined")]]
+  expect_equal(cc$suppressed_amount, 1371460000)
+  expect_equal(cc$suppressed_codes, "E05")
+  expect_equal(cc$ig_recipe_id, "corrections_ig_local_combined")
+})
+
+test_that("uscogdata#9: the revenue verb inherits the same trigger", {
+  # Alaska state FY2011 Miscellaneous Revenue reports $943,842,000 from
+  # U11/U20/U30 while dropping $1,899,995,000 of aggregate-published `U4-`
+  # rents and royalties -- the omission is LARGER than the reported figure.
+  skip_if_no_corpus()
+  r <- suppressMessages(
+    cog_revenue("020000227749", years = 2011L,
+                category = "Miscellaneous Revenue"))
+  sugg <- attr(r, "provenance")$suggestions
+
+  expect_length(sugg, 1L)
+  expect_equal(sugg[[1]]$recipe_id, "rents_royalties_u4_wide")
+  expect_equal(sugg[[1]]$trigger, "suppressed_component")
+  expect_equal(sugg[[1]]$suppressed_amount, 1899995000)
+  expect_equal(sugg[[1]]$suppressed_codes, "U4-")
+  # A revenue recipe must never be handed an M/L expenditure counterpart.
+  expect_null(sugg[[1]]$ig_recipe_id)
+})
+
+test_that("I1: cog_revenue never fabricates suppressed dollars for an expenditure-only recipe", {
+  # uscogdata#9 review, finding I1: Corrections is an expenditure-only
+  # category (E04/E05). cog_revenue() naturally returns zero rows for it, so
+  # corrections_combined still fires as an empty_year suggestion (its own
+  # generic join finds real E04/E05 data for this government) -- but before
+  # the flow_prefixes fix, .suppressed_components() measured E04/E05 against
+  # cog_revenue()'s OWN view (which can never contain an E-coded row by
+  # construction) and reported the full $3,631,945,000 as "suppressed",
+  # when cog_spending() for the same gov/years/category actually returns
+  # $3,691,029,000 -- nothing was suppressed at all.
+  skip_if_no_corpus()
+  r <- suppressMessages(
+    cog_revenue("061037123085", years = 2019:2020, category = "Corrections"))
+  sugg <- attr(r, "provenance")$suggestions
+  ids <- vapply(sugg, function(s) s$recipe_id, character(1))
+  expect_true("corrections_combined" %in% ids)
+
+  hit <- sugg[[which(ids == "corrections_combined")]]
+  expect_equal(hit$suppressed_amount, 0)
+  expect_equal(hit$suppressed_years, integer(0))
+  expect_equal(hit$suppressed_codes, character(0))
+
+  # And cog_spending() for the identical gov/years/category is unaffected --
+  # it actually finds the E04/E05 dollars the buggy measurement claimed were
+  # excluded.
+  sp <- suppressMessages(
+    cog_spending("061037123085", years = 2019:2020, category = "Corrections"))
+  expect_equal(sum(sp$amt_nominal), 3691029000)
+})
+
+test_that("uscogdata#9: no partial-coverage fire in a modern year", {
+  skip_if_no_corpus()
+  r <- cog_spending("061037123085", years = 2019L, category = "Public Welfare")
+  expect_length(attr(r, "provenance")$suggestions, 0L)
+})
+
+test_that("uscogdata#9: leaf-and-classified wide-era families never fire", {
+  # higher_ed_e18_wide and general_gov_e89_wide are the control group: their
+  # components (E16/E18, E85/E89) are ordinary classified leaves even in the
+  # wide era, so widening the trigger must leave them silent. This is the
+  # measurement that refutes "it would fire on every category in every legacy
+  # year" -- corpus-wide on the fixture, these two produce zero suppressed rows.
+  skip_if_no_corpus()
+  con <- uscogdata:::.ensure_session()
+  n <- DBI::dbGetQuery(con,
+    "SELECT COUNT(*) AS n
+     FROM long l
+     JOIN harmonization_recipes r
+       ON l.item_code = r.component_code
+      AND l.year BETWEEN r.year_min AND r.year_max
+     WHERE r.recipe_id IN ('higher_ed_e18_wide', 'general_gov_e89_wide')
+       AND l.amt <> 0
+       AND NOT EXISTS (
+         SELECT 1 FROM spending_long_harmonized v
+         WHERE v.canonical_govid = l.canonical_govid
+           AND v.year = l.year AND v.item_code = l.item_code)")$n
+  expect_equal(as.integer(n), 0L)
+})
+
+test_that("uscogdata#9: the cli message reports the suppressed dollars", {
+  skip_if_no_corpus()
+  expect_message(
+    cog_spending("061037123085", years = 2011L, category = "Public Welfare"),
+    "1,803,872,000", fixed = TRUE)
+  expect_message(
+    cog_spending("061037123085", years = 2011L, category = "Public Welfare"),
+    "FY2011", fixed = TRUE)
+  expect_message(
+    cog_spending("061037123085", years = 2011L, category = "Public Welfare"),
+    "E67", fixed = TRUE)
+})
+
+test_that("uscogdata#9: cog_explain() reports the suppressed dollars", {
+  # cog_explain()'s whole "print" output -- including the Suggestions
+  # section built from cli::cli_ul() -- is emitted on the message stream
+  # (verified empirically 2026-08-04: capture.output(..., type = "output")
+  # returns character(0) for this call; testthat::capture_messages() is what
+  # actually carries it), so that is the stream this test captures.
+  skip_if_no_corpus()
+  r <- suppressMessages(
+    cog_spending("061037123085", years = 2011L, category = "Public Welfare"))
+  out <- paste(testthat::capture_messages(cog_explain(r)), collapse = "")
+  expect_match(out, "271,589,000", fixed = TRUE)
+})
+
+test_that("the provenance schema documents the suggestion trigger fields", {
+  sch <- jsonlite::fromJSON(
+    system.file("schemas", "provenance-v1.json", package = "uscogdata"),
+    simplifyVector = FALSE)
+  props <- sch$properties$suggestions$items$properties
+  expect_true(all(c("trigger", "suppressed_amount", "suppressed_years",
+                    "suppressed_codes") %in% names(props)))
+  expect_setequal(unlist(props$trigger$enum),
+                  c("empty_year", "suppressed_component"))
+})