Merge pull request 'labels-sweep — pass bootstrap through the workflow_call boundary it was lost at (#215)' (#218) from build/215-bootstrap-bridge into main

Reviewed-on: #218
Reviewed-by: kimi-reviewer-andresmgsl <andres+4@heavyduty.builders>
Reviewed-by: glm-reviewer-andresmgsl <andres+5@heavyduty.builders>
Reviewed-by: codex-reviewer-andresmgsl <andres+2@heavyduty.builders>

.github/workflows/labels-sweep.yml

@@ -34,6 +34,20 @@ name: labels-sweep
 on:
   workflow_call:
     inputs:
+      bootstrap:
+        description: >-
+          Bootstrap the label taxonomy before sweeping. The CALLER passes
+          this through from its own workflow_dispatch input. The measured
+          invariant (ceremony#215): the value must be DECLARED here and
+          EXPLICITLY passed — on this instance the called workflow did not
+          see the caller's event inputs as an implicit substitute (runs
+          459/523 bootstrapped on a bootstrap=no dispatch) while the
+          top-level caller received the value in both contexts (probe runs
+          6/7). Absent means "no": an event- or cron-woken sweep must never
+          re-upsert ~20 labels.
+        type: string
+        required: false
+        default: "no"
       pr_workflow_name:
         description: >-
           The `name:` of the consumer's PR-facing labels caller, exported
@@ -86,18 +100,21 @@ jobs:
       # papers over for `run:` steps, which composite `uses:` has no
       # equivalent of.
       #
-      # bootstrap: every trigger-driven wake arrives as workflow_dispatch
+      # bootstrap: read from the DECLARED workflow_call input and nothing
-      # too (that is how the trigger's dispatch wakes the caller), so the event
+      # else. The old gate read `github.event.inputs.bootstrap` from inside
-      # name alone no longer separates the operator's manual full-board
+      # this called workflow, and on this instance that context arrived
-      # bootstrap from an event-woken sweep — the caller's `bootstrap`
+      # empty (runs 459/523: every dispatch-woken sweep bootstrapped on a
-      # dispatch input does: the trigger passes "no", a bare manual
+      # bootstrap=no body) while the top-level caller received the value in
-      # dispatch defaults to "yes". A caller reached on any other event
+      # both contexts (probe runs 6/7) — ceremony#215. The reliable channel
-      # (the cron) has no input and stays "no".
+      # is declare-and-pass, so that is the only one used. The caller passes
+      # the value through `with.bootstrap`; anything not exactly yes|no is
+      # fed through for labels-reconcile's own validation to judge, so a
+      # typo refuses loudly instead of silently bootstrapping.
       - name: reconcile state + stale
         if: github.repository != 'heavy-duty/ceremony'
         uses: ./.ceremony-src/actions/labels-reconcile
         with:
-          bootstrap: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.bootstrap != 'no' && 'yes' || 'no' }}
+          bootstrap: ${{ inputs.bootstrap }}
         env:
           GH_TOKEN: ${{ github.token }}
           REPO: ${{ github.repository }}
@@ -106,7 +123,7 @@ jobs:
         if: github.repository == 'heavy-duty/ceremony'
         uses: ./actions/labels-reconcile
         with:
-          bootstrap: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.bootstrap != 'no' && 'yes' || 'no' }}
+          bootstrap: ${{ inputs.bootstrap }}
         env:
           GH_TOKEN: ${{ github.token }}
           REPO: ${{ github.repository }}

.github/workflows/self-labels-sweep.yml

@@ -44,3 +44,11 @@ jobs:
     # pr_workflow_name keeps its default: ceremony's PR-facing caller is
     # named `labels` (self-labels.yml).
     uses: ./.github/workflows/labels-sweep.yml
+    with:
+      # The dispatch input crosses the workflow_call boundary HERE, or not
+      # at all: on this instance the called workflow did not see this
+      # caller's event inputs implicitly (ceremony#215), so declare-and-pass
+      # is the only channel used. On `schedule` the top-level context is
+      # empty, and empty maps to "no" EXPLICITLY — a cron that bootstraps is
+      # the failure kimi named before it could exist.
+      bootstrap: ${{ inputs.bootstrap || 'no' }}

actions/labels-reconcile/action.yml

@@ -23,7 +23,8 @@ runs:
         BOOTSTRAP: ${{ inputs.bootstrap }}
         LABELS_CONF: ${{ github.workspace }}/.github/labels.conf
       run: |
-        if [ "$BOOTSTRAP" = yes ]; then
+        # BOOTSTRAP passes through as-is: the script gates on the input. The
-          export GITHUB_EVENT_NAME=workflow_dispatch
+        # export-the-event-name hack that lived here died with ceremony#215 —
-        fi
+        # the script keyed on GITHUB_EVENT_NAME, which #209 made true for
+        # every machine wake, so "no" could never mean no.
         bash "$GITHUB_ACTION_PATH/labels-reconcile.sh"

actions/labels-reconcile/labels-reconcile.sh

@@ -28,8 +28,9 @@ fi
 # stale approval must never promote unreviewed code to the human.
 #
 # DRY_RUN=1 narrates every mutation instead of performing it (how this script
-# is rehearsed against the live repo). A workflow_dispatch run also bootstraps
+# is rehearsed against the live repo). A run with BOOTSTRAP=yes also
-# the taxonomy (label create --force) — that heal is dispatch-only; the cron
+# bootstraps the taxonomy (label create --force) — the operator's manual
+# dispatch defaults the input to yes; every machine wake passes no. The cron
 # sweep tolerates a missing label rather than recreating it.
 #
 # The state machine below is pure (globals in, state out) and covered by
@@ -1021,8 +1022,15 @@ main() {
   load_config "$LABELS_CONF"
   NOW="$(date +%s)"
 
-  if [ "${GITHUB_EVENT_NAME:-}" = workflow_dispatch ]; then
+  # The bootstrap keys on the INPUT, never the event name. It used to test
-    log "workflow_dispatch: bootstrapping the taxonomy"
+  # GITHUB_EVENT_NAME = workflow_dispatch — correct while an operator's manual
+  # dispatch was the only dispatch there was, and wrong from #209 on, when the
+  # trigger job made EVERY event-woken sweep a workflow_dispatch run: the
+  # bootstrap=no input became inert by construction, and every board event
+  # re-upserted the taxonomy (ceremony#215 — runs 459/523, then venue drill
+  # runs 16/17, which bootstrapped on a delivered "no" and caught this).
+  if [ "${BOOTSTRAP:-no}" = yes ]; then
+    log "bootstrap=yes: bootstrapping the taxonomy"
     bootstrap_labels
   fi
 

changelog.d/215.md

@@ -0,0 +1,47 @@
+### Fixed
+
+- The sweep's `bootstrap` value crosses the `workflow_call` boundary as a
+  declared input, explicitly passed by the caller — the one channel measured
+  to work; the called workflow did not see the caller's event inputs as an
+  implicit substitute on this instance (#215).
+
+- Before the bridge, `github.event.inputs` was empty inside the called
+  workflow, so every dispatch-woken sweep bootstrapped: ~20 label upserts on
+  each board event (#215).
+
+- The caller maps an empty top-level value to `no` explicitly, so a
+  cron-woken sweep can never bootstrap; the declared input also defaults to
+  `no`, so a consumer that passes nothing gets the safe path (#215).
+
+- The gate feeds the declared input to `labels-reconcile` unchanged, so an
+  invalid value meets the action's own `yes|no` refusal instead of being
+  silently coerced (#215).
+
+- `docs/CONSUMERS.md`'s published sweep stub carries the same pass-through —
+  without it every consumer inherits the defect ceremony fixed for
+  itself (#215).
+
+### Added
+
+- `test/labels-bootstrap.test.sh` pins the bridge at every hop: the declared
+  boundary, both gate sites as the identity, no expression reading
+  `github.event.inputs`, and the caller and stub pass-throughs
+  byte-exact (#215).
+
+- The same test drives the four value paths — schedule-empty, `no`, `yes`,
+  invalid — through the shipped expressions into the action's real
+  validator (#215).
+
+- The taxonomy bootstrap keys on the `BOOTSTRAP` input, never the event name.
+  It tested `GITHUB_EVENT_NAME = workflow_dispatch` — correct while an
+  operator's manual dispatch was the only dispatch there was, inert-by-
+  construction from #209 on, when every machine wake became a dispatch
+  event (#215).
+
+- The venue drill caught that: with the bridge delivering `no` perfectly,
+  drill runs 16/17 still bootstrapped, because the script never read the
+  input the whole chain existed to deliver (#215).
+
+- `test/labels-reconcile.test.sh` pins the regression pair exactly: a
+  `workflow_dispatch` event with `BOOTSTRAP=no` (or unset) creates and
+  deletes nothing; only `BOOTSTRAP=yes` bootstraps (#215).

docs/CONSUMERS.md

@@ -458,8 +458,15 @@ permissions:
 jobs:
   sweep:
     uses: heavy-duty/ceremony/.github/workflows/labels-sweep.yml@<pinned-tag>
+    with:
+      # Pass the dispatch input through the workflow_call boundary
+      # explicitly — a called workflow must not rely on reading the caller's
+      # event inputs (ceremony#215 measured that failing). Empty (schedule)
+      # maps to "no" explicitly, so a cron-woken sweep never re-upserts the
+      # taxonomy.
+      bootstrap: ${{ inputs.bootstrap || 'no' }}
     # If this repo's PR-facing labels caller is named anything but `labels`,
-    # pass that name: `with: { pr_workflow_name: <name> }`. The sweep exports
+    # pass that name alongside: `pr_workflow_name: <name>`. The sweep exports
     # it as SELF_WORKFLOW so the label machinery's own check entries (scope,
     # trigger) never count toward blocker:ci-red — a red trigger means "fix
     # the caller", which no PR edit can do (#208 reads it).

test/labels-bootstrap.test.sh

@@ -0,0 +1,93 @@
+#!/usr/bin/env bash
+# The bootstrap bridge across the workflow_call boundary (#215).
+#
+# The defect: a called workflow cannot read the caller's dispatch inputs on
+# this forge — `github.event.inputs.*` is empty inside `workflow_call` even
+# though the top-level caller receives the value in both contexts (probe runs
+# 6/7). The old gate read exactly that, so every dispatch-woken sweep
+# bootstrapped (runs 459/523). The fix moves the value through a DECLARED
+# `workflow_call` input, passed by the caller, with empty mapped to "no" at
+# the caller so a cron can never bootstrap.
+#
+# These cases pin the wiring at every hop and drive the four value paths
+# through the semantics of the exact expressions shipped — extracted from the
+# YAML, never retyped, so an edited expression is an edited test input.
+set -uo pipefail
+
+ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+# shellcheck source=test/harness.sh
+. "$ROOT/test/harness.sh"
+
+REUSABLE="$ROOT/.github/workflows/labels-sweep.yml"
+CALLER="$ROOT/.github/workflows/self-labels-sweep.yml"
+CONSUMERS="$ROOT/docs/CONSUMERS.md"
+
+# --- the declared boundary ---------------------------------------------------
+decl() { yq -r ".on.workflow_call.inputs.bootstrap.$1 // \"\"" "$REUSABLE"; }
+declares_boundary() { [ -n "$(yq -r '.on.workflow_call.inputs.bootstrap // ""' "$REUSABLE")" ]; }
+check "labels-sweep.yml declares bootstrap as a workflow_call input" 0 "" declares_boundary
+check "...typed string" 0 "string" decl type
+check "...defaulting to no — an absent pass-through must never bootstrap" 0 "no" \
+  decl default
+
+# --- the gate reads the declared input, and nothing else ---------------------
+gate_exprs() { yq -r '.jobs[].steps[] | select(.with.bootstrap != null) | .with.bootstrap' "$REUSABLE"; }
+gates_are_identity() {
+  [ "$(gate_exprs | sort -u)" = "\${{ inputs.bootstrap }}" ] \
+    && [ "$(gate_exprs | wc -l)" -eq 2 ]
+}
+check "both gate sites feed the DECLARED input, unchanged" 0 "" gates_are_identity
+# The forbidden context is only live inside an expression: the file NAMES it
+# in comments and in the declared input's description to explain the defect,
+# and both are prose. Matching raw text asserted on the explanation — the
+# adjacent-assertion trap this suite keeps re-learning — so the predicate is
+# scoped to `${{ … }}` bodies.
+reads_event_inputs() { grep -qE '\$\{\{[^}]*github\.event\.inputs' "$REUSABLE"; }
+check "no expression in the reusable reads github.event.inputs — the context this forge empties" 1 "" \
+  reads_event_inputs
+
+# --- the caller passes it through, empty mapped to no ------------------------
+CALLER_EXPR="$(yq -r '.jobs.sweep.with.bootstrap // ""' "$CALLER")"
+check "self-labels-sweep.yml passes with.bootstrap through the boundary" 0 "" \
+  test -n "$CALLER_EXPR"
+check "...with the exact empty-guard expression" 0 "" \
+  test "$CALLER_EXPR" = "\${{ inputs.bootstrap || 'no' }}"
+
+# The published stub must carry the same bridge, or every consumer inherits
+# the defect ceremony just fixed for itself.
+check "the CONSUMERS.md sweep stub passes bootstrap through the boundary" 0 \
+  "bootstrap: \${{ inputs.bootstrap || 'no' }}" \
+  grep -F "bootstrap: \${{ inputs.bootstrap || 'no' }}" "$CONSUMERS"
+
+# --- the four value paths, through the shipped expressions -------------------
+# Evaluate the caller expression's semantics for a given top-level value. The
+# expression is asserted byte-exact above, so modelling `x || 'no'` here is
+# modelling the string the tree actually ships, not a hope about it.
+caller_pass() { [ -n "$1" ] && printf '%s' "$1" || printf 'no'; }
+# The reusable's gate is asserted to be the identity; the value then meets
+# actions/labels-reconcile's REAL validate step, extracted and executed.
+VALIDATE="$(mktemp)"
+trap 'rm -f "$VALIDATE"' EXIT
+{
+  printf '%s\n' '#!/usr/bin/env bash'
+  yq -r '.runs.steps[] | select(.name == "validate bootstrap input") | .run' \
+    "$ROOT/actions/labels-reconcile/action.yml"
+} >"$VALIDATE"
+chmod +x "$VALIDATE"
+path() { BOOTSTRAP="$(caller_pass "$1")" bash "$VALIDATE"; }
+
+check "schedule (empty top-level context) validates as a non-bootstrap sweep" 0 "" path ""
+check "a REST event wake passing no validates as a non-bootstrap sweep" 0 "" path no
+check "a manual dispatch passing yes validates as a bootstrap" 0 "" path yes
+invalid_path() { BOOTSTRAP="maybe" bash "$VALIDATE"; }
+check "an invalid value reaches the validator UNSANITIZED and refuses" 2 \
+  "bootstrap must be 'yes' or 'no'" invalid_path
+
+# ...and the non-bootstrap/bootstrap split is what the validator's callers
+# act on: prove the two accepted values are distinguished, not merely both
+# accepted, by pinning what each resolves to after the caller pass.
+check "empty and no resolve identically — the cron can never bootstrap" 0 "" \
+  test "$(caller_pass "")" = "$(caller_pass no)"
+check "...and yes stays yes through the pass" 0 "" test "$(caller_pass yes)" = yes
+
+summary

test/labels-reconcile.test.sh

@@ -883,7 +883,6 @@ expect "attention diagnosis caused no PR mutation" "$attention_mutations_before"
 # -- the sweep wiring observes the existing per-PR skip without writing -------
 blind_main_probe() {
   (
-    GITHUB_EVENT_NAME=schedule
     REPO=owner/repo
     LABELS_CONF=.github/labels.conf
     # This probe IS a GitHub board — say so at the forge boundary rather
@@ -942,7 +941,6 @@ expect "exactly the blind PRs match the counted shape whole-line — no more, no
 #    shape, where the probes could not reach the per-PR path at all.
 unrequested_main_probe() { # $1 = read | denied, the head-commit read's outcome
   (
-    GITHUB_EVENT_NAME=schedule
     REPO=owner/repo
     LABELS_CONF=.github/labels.conf
     # main() preflights the forge before it reads anything, so a probe that
@@ -1148,17 +1146,18 @@ EOF
 chmod +x "$EXEC/stub/gh"
 printf 'panel=bot-a bot-b bot-c\n' >"$EXEC/labels.conf"
 
-exec_env() { # $1 = event name → the real script, executed under the PATH stub
+exec_env() { # $1 = event name, $2 = BOOTSTRAP value ("" = unset)
   : >"$EXEC/record"
   env PATH="$EXEC/stub:$PATH" GH_RECORD="$EXEC/record" \
     CEREMONY_FORGE=github \
     REPO=owner/repo LABELS_CONF="$EXEC/labels.conf" GITHUB_EVENT_NAME="$1" \
+    ${2:+BOOTSTRAP="$2"} \
     bash actions/labels-reconcile/labels-reconcile.sh
 }
 
 exec_rc=0
-exec_out="$(exec_env workflow_dispatch 2>&1)" || exec_rc=$?
+exec_out="$(exec_env workflow_dispatch yes 2>&1)" || exec_rc=$?
-expect "an executed dispatch with all six absent completes green" 0 "$exec_rc"
+expect "an executed bootstrap=yes with all six absent completes green" 0 "$exec_rc"
 expect "...reaching the end of the sweep" \
   yes "$(grep -q 'reconciled.' <<<"$exec_out" && echo yes || echo no)"
 expect "...having attempted all six deletions" \
@@ -1167,12 +1166,18 @@ expect "...and created the full taxonomy" \
   "$(core_label_rows | cut -d'|' -f1)" \
   "$(sed -n 's/^create //p' "$EXEC/record")"
 
-# -- bootstrap is dispatch-only, deletes included: the cron and
+# -- the bootstrap keys on the INPUT, never the event (ceremony#215): from
-#    pull_request_target paths touch no label
+#    #209 on, EVERY machine wake is a workflow_dispatch event, so an event
-for ev in schedule pull_request_target; do
+#    gate made bootstrap=no inert — runs 459/523 and venue drill runs 16/17
+#    bootstrapped on a delivered "no". The regression case is exactly that
+#    pair: dispatch event, no.
+for pair in "workflow_dispatch:no" "workflow_dispatch:" "schedule:no" "schedule:" "pull_request_target:"; do
+  ev="${pair%%:*}"; bs="${pair#*:}"
   ev_rc=0
-  exec_env "$ev" >/dev/null 2>&1 || ev_rc=$?
+  exec_env "$ev" "$bs" >/dev/null 2>&1 || ev_rc=$?
-  expect "the $ev path completes green" 0 "$ev_rc"
+  expect "the $ev event with BOOTSTRAP='${bs:-unset}' completes green" 0 "$ev_rc"
+  expect "...and creates nothing" \
+    no "$(grep -q '^create ' "$EXEC/record" && echo yes || echo no)"
   expect "...and deletes nothing" \
     no "$(grep -q '^delete ' "$EXEC/record" && echo yes || echo no)"
 done
@@ -1471,7 +1476,6 @@ expect "...and a malformed panel= line in that same file is refused, not passed"
 # ---------------------------------------------------------------------------
 write_fail_probe() { # $1 = ok | fail — whether the label edit write succeeds
   (
-    GITHUB_EVENT_NAME=schedule
     REPO=owner/repo
     LABELS_CONF=.github/labels.conf
     CEREMONY_FORGE=github
@@ -1541,7 +1545,9 @@ expect "...and does print reconciled." \
 # exited 0 (@codex-reviewer-andresmgsl, #192 review).
 stale_fail_probe() {
   (
-    GITHUB_EVENT_NAME=schedule
+    # No event name: the script stopped reading GITHUB_EVENT_NAME when the
+    # bootstrap moved to the BOOTSTRAP input (#215); default no is the
+    # non-bootstrap sweep this probe simulates.
     REPO=owner/repo
     LABELS_CONF=.github/labels.conf
     CEREMONY_FORGE=github