changelog.d/200.md

@@ -32,6 +32,10 @@
   so a composite `action.yml` or a `.yaml` workflow is seen without anyone
   remembering to add a glob (#200).
 
+- Discovery is git's, not the filesystem's: `ls-files`, so the tarballs `ci.yml`
+  extracts into the checkout and any developer cache are not parsed as source
+  (#200).
+
 - It refuses when the recorded commit is missing, absent from the object store,
   or not an ancestor — three distinct refusals, none of them a skip. `ci.yml`
   fetches that exact object so the test reads local evidence without CI

test/upstream-delta.test.sh

@@ -122,7 +122,6 @@ scan_root() { printf '%s' "${SCAN_ROOT:-$ROOT}"; }
 # rest. Excluding is safer than including because a new file type arrives
 # scanned rather than invisible.
 #
-#   .git/         not source
 #   test/         the harness stubs and asserts these tokens by design
 #   changelog.d/  prose fragments
 #   *.md          prose. `drills/` stays in the INVENTORY because its records
@@ -130,14 +129,21 @@ scan_root() { printf '%s' "${SCAN_ROOT:-$ROOT}"; }
 #                 selector verb in prose is not a decision, and scanning prose
 #                 for decisions is the mistake this guard's own comment
 #                 handling exists to avoid.
+#
+# DISCOVERY IS GIT'S, NOT THE FILESYSTEM'S. An earlier head said "tracked" and
+# used `find`, which walks the working directory and knows nothing about the
+# index. That is not pedantry: `ci.yml` extracts shellcheck and actionlint
+# tarballs INTO the checkout before the suite runs, and any developer cache
+# sits there too. @codex-reviewer-andresmgsl reproduced a false red with one
+# untracked file. `git ls-files -z` makes "tracked" executable rather than
+# prose.
 scanned_paths() {
   local root; root="$(scan_root)"
-  find "$root" -type f \
+  git -C "$root" ls-files -z 2>/dev/null \
-    -not -path "$root/.git/*" \
+    | tr '\0' '\n' \
-    -not -path "$root/test/*" \
+    | grep -vE '^(test/|changelog\.d/)' \
-    -not -path "$root/changelog.d/*" \
+    | grep -vE '\.md$' \
-    -not -name '*.md' \
+    | sort
-    2>/dev/null | sed "s|^$root/||" | sort
 }
 
 forge_specific_files() {
@@ -203,15 +209,20 @@ check "every forge-deciding file is named in the inventory" 0 "" no_unlisted
 TMP="$(mktemp -d)"
 trap 'rm -rf "$TMP"' EXIT
 
-fixture_tree() { # -> a tree the scan walks, with no forge-deciding files
+# A tiny GIT repository, because discovery is git's now: a fixture that is only
+# a directory would be invisible to `ls-files` and every must-fail below would
+# pass vacuously.
+fixture_tree() { # -> a tracked tree with no forge-deciding files
   local t="$TMP/tree"
   rm -rf "$t"
-  mkdir -p "$t/lib" "$t/actions/x" "$t/bin" "$t/.github/scripts" \
+  mkdir -p "$t/lib" "$t/.github/workflows"
-           "$t/.github/workflows" "$t/drills"
   printf '#!/usr/bin/env bash\necho hello\n' >"$t/lib/plain.sh"
   printf 'name: ci\non: [push]\n' >"$t/.github/workflows/plain.yml"
+  git -C "$t" init -q 2>/dev/null
+  git -C "$t" add -A 2>/dev/null
   printf '%s' "$t"
 }
+track() { git -C "$root" add -A 2>/dev/null; }
 
 root="$(fixture_tree)"
 clean_tree_passes() { SCAN_ROOT="$root" no_unlisted; }
@@ -221,10 +232,10 @@ check "the guard is green on a tree with no forge decisions" 0 "" clean_tree_pas
 # shellcheck disable=SC2016 # fixture CONTENT: the literal text a scanned file would hold
 printf '%s\n' '#!/usr/bin/env bash' 'case "$(forge_detect)" in forgejo) : ;; esac' \
   >"$root/lib/scattered.sh"
-scattered_shell() { SCAN_ROOT="$root" no_unlisted; }
+track; scattered_shell() { SCAN_ROOT="$root" no_unlisted; }
 check "a new SHELL file deciding the forge fails the real guard" 1 "" scattered_shell
 check "...and the failure names the file" 1 "lib/scattered.sh" scattered_shell
-rm -f "$root/lib/scattered.sh"
+rm -f "$root/lib/scattered.sh"; track
 
 # MUST FAIL on a NON-SHELL surface too, so coverage cannot regress to the old
 # shell-only glob: a workflow deciding on the server URL.
@@ -232,10 +243,10 @@ rm -f "$root/lib/scattered.sh"
 printf '%s\n' 'name: x' 'on: [push]' 'jobs:' '  j:' '    steps:' \
   '      - run: [ "$GITHUB_SERVER_URL" = https://github.com ] || exit 0' \
   >"$root/.github/workflows/scattered.yml"
-scattered_workflow() { SCAN_ROOT="$root" no_unlisted; }
+track; scattered_workflow() { SCAN_ROOT="$root" no_unlisted; }
 check "a new WORKFLOW deciding the forge fails it too" 1 "" scattered_workflow
 check "...naming that file" 1 ".github/workflows/scattered.yml" scattered_workflow
-rm -f "$root/.github/workflows/scattered.yml"
+rm -f "$root/.github/workflows/scattered.yml"; track
 
 # @codex-reviewer-andresmgsl's two reproductions, verbatim as fixtures. Both
 # passed the hand-picked-glob version 21/21, which is why discovery is derived
@@ -244,10 +255,10 @@ mkdir -p "$root/actions/unlisted-forge-decision"
 printf '%s\n' 'name: x' 'runs:' '  using: composite' '  steps:' \
   '    - shell: bash' '      env:' '        CEREMONY_FORGE_CLIENT: gh' \
   '      run: true' >"$root/actions/unlisted-forge-decision/action.yml"
-composite_action_seen() { SCAN_ROOT="$root" no_unlisted; }
+track; composite_action_seen() { SCAN_ROOT="$root" no_unlisted; }
 check "a forge declaration in actions/*/action.yml fails the guard" 1 \
   "actions/unlisted-forge-decision/action.yml" composite_action_seen
-rm -rf "$root/actions/unlisted-forge-decision"
+rm -rf "$root/actions/unlisted-forge-decision"; track
 
 # ...and a workflow written .yaml rather than .yml — `*.yml` was never a
 # complete workflow surface.
@@ -255,22 +266,37 @@ rm -rf "$root/actions/unlisted-forge-decision"
 printf '%s\n' 'name: x' 'on: [push]' 'jobs:' '  j:' \
   "    if: github.server_url == 'https://github.com'" '    steps: []' \
   >"$root/.github/workflows/unlisted-forge-decision.yaml"
-yaml_workflow_seen() { SCAN_ROOT="$root" no_unlisted; }
+track; yaml_workflow_seen() { SCAN_ROOT="$root" no_unlisted; }
 check "...and one in a .yaml workflow does too" 1 \
   ".github/workflows/unlisted-forge-decision.yaml" yaml_workflow_seen
-rm -f "$root/.github/workflows/unlisted-forge-decision.yaml"
+rm -f "$root/.github/workflows/unlisted-forge-decision.yaml"; track
 check "...leaving the fixture tree green again" 0 "" clean_tree_passes
 
 # A declaration is a delta location even in a file that would otherwise read as
 # a shim consumer, so the consumer allow-list cannot hide one.
 mkdir -p "$root/lib"
 printf '%s\n' '#!/usr/bin/env bash' 'CEREMONY_FORGE_CLIENT=gh' >"$root/lib/facts.sh"
-declared_not_exempt() { SCAN_ROOT="$root" no_unlisted; }
+track; declared_not_exempt() { SCAN_ROOT="$root" no_unlisted; }
 check "a shim consumer that DECLARES a client is not exempt" 1 "lib/facts.sh" \
   declared_not_exempt
-rm -f "$root/lib/facts.sh"
+rm -f "$root/lib/facts.sh"; track
+track
 check "...and the tree is green again once it is gone" 0 "" clean_tree_passes
 
+# UNTRACKED input is not source. ci.yml extracts shellcheck and actionlint
+# tarballs into the checkout before the suite runs, and a developer cache sits
+# there too; parsing either is a false red on something outside the repository
+# property (@codex-reviewer-andresmgsl, #200 review — reproduced with one file).
+printf 'CEREMONY_FORGE_CLIENT=gh\n' >"$root/local-tool-cache.txt"
+check "an UNTRACKED marker-bearing file is ignored" 0 "" clean_tree_passes
+check "...and is still ignored once it carries a decision" 0 "" clean_tree_passes
+track
+check "...but the moment it is TRACKED the guard sees it" 1 "local-tool-cache.txt" \
+  clean_tree_passes
+git -C "$root" rm -q --cached local-tool-cache.txt 2>/dev/null
+rm -f "$root/local-tool-cache.txt"
+check "...and removing it restores green" 0 "" clean_tree_passes
+
 # Path matching, both boundaries.
 check "a directory entry does not match a sibling with the same prefix" 1 "" \
   in_inventory drills-old/0.4.1.md