From 4d61692f056353c7e5302e02e4f680744eb2a5d8 Mon Sep 17 00:00:00 2001
From: Jared Knowles <jared@civilytics.com>
Date: Sat, 18 Jul 2026 13:40:54 -0400
Subject: [PATCH] feat: export cog_manifest() accessor + pin CPI coverage
 1967-present

---
 NAMESPACE                      |  1 +
 R/manifest.R                   | 15 +++++++++++++++
 man/cog_manifest.Rd            | 18 ++++++++++++++++++
 tests/testthat/test-adjust.R   |  7 +++++++
 tests/testthat/test-manifest.R | 11 +++++++++++
 5 files changed, 52 insertions(+)
 create mode 100644 man/cog_manifest.Rd

diff --git a/NAMESPACE b/NAMESPACE
index 518e06d..19baa13 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -7,6 +7,7 @@ export(cog_explain)
 export(cog_find_peers)
 export(cog_geographic_rollup)
 export(cog_gov_search)
+export(cog_manifest)
 export(cog_mirror)
 export(cog_peer_compare)
 export(cog_revenue)
diff --git a/R/manifest.R b/R/manifest.R
index bc7eb70..c248ec6 100644
--- a/R/manifest.R
+++ b/R/manifest.R
@@ -146,3 +146,18 @@
 }
 
 `%||%` <- function(a, b) if (is.null(a) || (length(a) == 1 && is.na(a))) b else a
+
+#' Return the parsed corpus manifest for the active session.
+#'
+#' Opens a session (connecting to the configured corpus) if none is active,
+#' then returns the manifest exactly as parsed from `manifest.json`. Useful
+#' for consumers that need the published year range (`years` block, schema
+#' v5+) or the partition list without issuing a data query.
+#'
+#' @return Named list: `schema_version`, `built_at`, `pipeline_commit`,
+#'   `data_vintage`, `scope`, `years` (schema v5+), `schema`, `files`.
+#' @export
+cog_manifest <- function() {
+  .ensure_session()
+  .uscogdata_env$manifest
+}
diff --git a/man/cog_manifest.Rd b/man/cog_manifest.Rd
new file mode 100644
index 0000000..a04718f
--- /dev/null
+++ b/man/cog_manifest.Rd
@@ -0,0 +1,18 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/manifest.R
+\name{cog_manifest}
+\alias{cog_manifest}
+\title{Return the parsed corpus manifest for the active session.}
+\usage{
+cog_manifest()
+}
+\value{
+Named list: `schema_version`, `built_at`, `pipeline_commit`,
+  `data_vintage`, `scope`, `years` (schema v5+), `schema`, `files`.
+}
+\description{
+Opens a session (connecting to the configured corpus) if none is active,
+then returns the manifest exactly as parsed from `manifest.json`. Useful
+for consumers that need the published year range (`years` block, schema
+v5+) or the partition list without issuing a data query.
+}
diff --git a/tests/testthat/test-adjust.R b/tests/testthat/test-adjust.R
index b10e3e6..57f19a2 100644
--- a/tests/testthat/test-adjust.R
+++ b/tests/testthat/test-adjust.R
@@ -41,3 +41,10 @@ test_that(".inflate preserves NA amounts", {
   expect_true(is.na(result[2]))
   expect_false(any(is.na(result[c(1, 3)])))
 })
+
+test_that("bundled CPI covers the full 1967+ corpus era through this year", {
+  cpi <- .cpi_table()
+  expect_lte(min(cpi$year), 1967L)
+  expect_gte(max(cpi$year), as.integer(format(Sys.Date(), "%Y")))
+  expect_false(any(is.na(cpi$cpi)))
+})
diff --git a/tests/testthat/test-manifest.R b/tests/testthat/test-manifest.R
index 0c4a20c..c8e5f54 100644
--- a/tests/testthat/test-manifest.R
+++ b/tests/testthat/test-manifest.R
@@ -99,3 +99,14 @@ test_that("remote manifest fetch does not poison cache when response is HTML", {
     0L
   )
 })
+
+test_that("cog_manifest returns the active session's parsed manifest", {
+  with_fixture_corpus({
+    m <- cog_manifest()
+    expect_type(m, "list")
+    expect_true(m$schema_version >= 4L)
+    yrs <- vapply(m$files$long_partitions, function(p) as.integer(p$year),
+                  integer(1))
+    expect_setequal(yrs, c(2019L, 2020L))
+  })
+})
-- 
2.54.0