fix(#1257): confirm delivery by draft transition, not prompt detection (adopts #1262) (#1332)

Co-authored-by: code-infra-01 <[email protected]>
2026-09-04 22:25:13 +00:00
parent d6302f8e6f
commit 5d27700026
5 changed files with 268 additions and 50 deletions
@@ -0,0 +1,97 @@
+#!/usr/bin/env bash
+# Red-first regression test for E7 (#1017 task 2): the confirm-check must bind
+# "delivered" to WHETHER THE MESSAGE WAS SUBMITTED, not to which runtime's prompt
+# glyph is present. A pi seat renders a U+2500 rule input box with no ❯/^>/│ >
+# glyph; send-message.sh:118 locates the box only by glyph, so a genuinely
+# delivered message on a glyphless REPL falsely reports exit 2 "may be UNDELIVERED",
+# and the operator's rc=2-driven retry duplicates it.
+#
+# Parameterized on $SEND: RED against the shipping blob (B and D fail), GREEN
+# against a candidate patch. No pi; no fake HOME; hermetic throwaway socket.
+#
+# Submission counting is EXACT and terminal-echo-independent: the fixture message
+# is `echo <tok> >>SINK`; each real submission appends one line. wc -l SINK ==
+# number of times the REPL actually executed the send. This does not depend on how
+# many times the marker string is painted on screen.
+set -u
+SEND="${SEND:?set SEND=/path/to/send-message.sh}"
+SOCKET="glyphagnostic-$$"
+TMP="$(mktemp -d)"
+tmux() { command tmux -L "$SOCKET" "$@"; }
+cleanup() { command tmux -L "$SOCKET" kill-server 2>/dev/null; rm -rf "$TMP"; }
+trap cleanup EXIT
+pass=0; fail=0
+ok() { printf 'ok   %s\n' "$1"; pass=$((pass+1)); }
+no() { printf 'FAIL %s -- %s\n' "$1" "$2"; fail=$((fail+1)); }
+
+mk() { tmux new-session -d -s "$1" -x 120 -y 40 -c "$TMP" "PS1='$2' exec bash --noprofile --norc -i"; sleep 0.5; }
+subs() { [ -f "$1" ] && wc -l <"$1" | tr -d ' ' || echo 0; }  # exact submission count
+
+echo "SEND=$SEND    tmux $(command tmux -V | awk '{print $2}')"
+
+# --- A (control): glyph box (❯) that submits => exit 0, exactly one submission.
+mk ctl '❯ '
+SINK="$TMP/sink.ctl"
+out=$("$SEND" -L "$SOCKET" -t ctl -m "echo x >>'$SINK'" 2>"$TMP/e.ctl"); rc=$?; sleep 0.4
+if [ "$rc" = 0 ] && [ "$(subs "$SINK")" = 1 ]; then
+  ok "control: ❯-box submits => exit 0, exactly one submission"
+else no "control: ❯-box submits => exit 0, one submission" "rc=$rc subs=$(subs "$SINK") err=[$(cat "$TMP/e.ctl")]"; fi
+
+# --- B (THE false-rc regression): glyphless U+2500 box that SUBMITS. Message lands
+#     (subs==1) yet shipping reports exit 2. Must be exit 0.
+mk sub $'──────── \n'
+SINK="$TMP/sink.sub"
+out=$("$SEND" -L "$SOCKET" -t sub -m "echo x >>'$SINK'" 2>"$TMP/e.sub"); rc=$?; sleep 0.4
+if [ "$rc" = 0 ] && [ "$(subs "$SINK")" = 1 ]; then
+  ok "glyphless: U+2500 box that submits => exit 0 (delivered, not 'UNDELIVERED')"
+else no "glyphless: U+2500 box that submits => exit 0" \
+        "rc=$rc subs=$(subs "$SINK")(delivered=$([ "$(subs "$SINK")" -ge 1 ] && echo yes||echo no)) err=[$(cat "$TMP/e.sub")]"; fi
+
+# --- D (duplicate arm): operator follows the rc=2 stderr and retries once. On the
+#     glyphless box, shipping => two submissions (the reported duplicate). The
+#     property: one logical send => exactly one submission. Same fix closes it.
+mk dup $'──────── \n'
+SINK="$TMP/sink.dup"
+tries=0
+for attempt in 1 2; do
+  tries=$((tries+1))
+  out=$("$SEND" -L "$SOCKET" -t dup -m "echo x >>'$SINK'" 2>/dev/null); rc=$?
+  sleep 0.4
+  [ "$rc" = 0 ] && break   # operator stops retrying only when told delivered
+done
+if [ "$(subs "$SINK")" = 1 ]; then
+  ok "duplicate: one logical send (rc-driven retry) => exactly one submission (tries=$tries)"
+else no "duplicate: one logical send => exactly one submission" "submissions=$(subs "$SINK") tries=$tries"; fi
+
+# --- E (faithful hung managed TUI, NOT a cooked shell): raw/no-echo, paints nothing.
+#     A cooked `sleep infinity` echoes the paste via the kernel line discipline and
+#     false-passes a cursor-row fix that is correct on real seats (measured). So: raw.
+mk_rawstuck() { tmux new-session -d -s "$1" -x 120 -y 40 -c "$TMP" \
+  "bash --noprofile --norc -c 'stty -echo -icanon min 1 time 0 2>/dev/null; exec sleep infinity'"; sleep 0.5; }
+mk_rawstuck estuck
+SINK="$TMP/sink.estuck"
+out=$("$SEND" -L "$SOCKET" -t estuck -r 1 -m "this stuck draft was never submitted" 2>/dev/null); rc=$?
+sleep 0.3
+if [ "$rc" != 0 ] && [ "$(subs "$SINK")" = 0 ]; then
+  ok "raw/no-echo stuck TUI (not submitted) => non-zero (no false delivered)"
+else no "raw stuck TUI must NOT report delivered" "rc=$rc subs=$(subs "$SINK")"; fi
+
+# --- F (busy/queued branch, your BUSY-not-runtime finding): glyphless pane rendering the
+#     queued banner, never consuming. QUEUED_RE :113 fires before the glyph grep => rc=0.
+mk_busy() { tmux new-session -d -s "$1" -x 120 -y 40 -c "$TMP" \
+  "bash --noprofile --norc -c 'printf \"Press up to edit queued messages\n\"; exec sleep infinity'"; sleep 0.5; }
+mk_busy ebusy
+SINK="$TMP/sink.ebusy"
+out=$("$SEND" -L "$SOCKET" -t ebusy -m "echo x >>'$SINK'" 2>/dev/null); rc=$?; sleep 0.3
+if [ "$rc" = 0 ]; then
+  ok "busy/queued-banner glyphless => exit 0 (queued is delivery; runtime owns custody)"
+else no "busy/queued-banner must report delivered" "rc=$rc"; fi
+
+# --- C (historical-bug guard): unresolvable target. No pane ever carried our draft
+#     => must fail, never infer delivered from absence of a glyph/snippet.
+if out=$("$SEND" -L "$SOCKET" -t "nonexistent-$$" -m "echo x >>'$TMP/sink.wrong'" 2>/dev/null); then
+  no "wrong-pane: unresolvable target must NOT report success" "expected non-zero, got 0"
+else ok "wrong-pane: unresolvable target => non-zero (no false delivered)"; fi
+
+echo "---"; echo "pass=$pass fail=$fail"
+[ "$fail" = 0 ]