211 lines
11 KiB
Bash
Executable File
211 lines
11 KiB
Bash
Executable File
#!/usr/bin/env bash
|
||
# test-send-message-verdict.sh — locks the fail-loud verdict logic of the patched
|
||
# send-message.sh against three real tmux-pane fixtures on a throwaway socket:
|
||
#
|
||
# 1. DELIVERED — a REPL that renders a `❯ ` input box and submits on Enter
|
||
# (text scrolls to history, box clears) => exit 0 "✓ delivered".
|
||
# 2. DELIVERED — a pane with NO prompt glyph that DOES submit => exit 0. A pi
|
||
# seat is this fixture (U+2500 rule, no glyph). Reshaped for
|
||
# #1257; see the note at the fixture for why the old exit-2
|
||
# assertion was wrong.
|
||
# 2b. UNCONFIRMED— a glyphless pane that never submits (raw/no-echo hung TUI)
|
||
# => must fail loud. This carries the historical
|
||
# false-positive guard that fixture 2 used to be credited with.
|
||
# 3. DRAFT — a `❯ `-prompt pane that never submits (message stays on the
|
||
# input line) => exit 2, stderr "unsubmitted draft".
|
||
# 4. DELIVERED — a pane whose input box is two `─` rules with NO prompt glyph
|
||
# (box shape) anywhere (pi's shape) and which submits => exit 0. Pre-#1362
|
||
# the glyph probe could not see this box at all, so EVERY send
|
||
# to such a pane reported "may be UNDELIVERED" while landing.
|
||
# 5. DRAFT — the same glyphless box, holding our tail across every flush
|
||
# (box shape) Enter => exit 2, stderr "unsubmitted draft". Pre-#1362 this
|
||
# also reported unconfirmed, so the true state was invisible.
|
||
# 6. DELIVERED — a SHAPELESS REPL (no glyph, no box) that submits => exit 0.
|
||
# The 2026-09-04 scratch probe regression: shape probing alone reports "may
|
||
# be UNDELIVERED" on this pane while the message is consumed; the cursor-row
|
||
# draft transition is the authoritative runtime-agnostic verdict.
|
||
# 6b. UNCONFIRMED— a shapeless pane in raw/no-echo mode that never reads stdin
|
||
# (shapeless) => exit 2 "could not confirm submission" (never delivered).
|
||
set -uo pipefail
|
||
|
||
HERE=$(cd -- "$(dirname -- "$0")" && pwd)
|
||
SEND="${SEND:-$HERE/send-message.sh}"
|
||
SOCKET="verdict-test-$RANDOM-$$"
|
||
TMP=$(mktemp -d)
|
||
trap 'tmux -L "$SOCKET" kill-server >/dev/null 2>&1 || true; rm -rf "$TMP"' EXIT
|
||
|
||
PASS=0; FAIL=0
|
||
ok() { PASS=$((PASS+1)); printf ' ok %s\n' "$1"; }
|
||
no() { FAIL=$((FAIL+1)); printf ' FAIL %s\n %s\n' "$1" "$2"; }
|
||
|
||
command -v tmux >/dev/null 2>&1 || { echo "tmux required" >&2; exit 1; }
|
||
|
||
# --- Fixture 1: a submitting REPL with a ❯ prompt box (interactive bash, glyph PS1).
|
||
# readline strips bracketed-paste markers just like a real agent REPL; Enter
|
||
# executes (text -> scrollback), leaving a fresh empty `❯ ` box.
|
||
tmux -L "$SOCKET" new-session -d -s repl -c "$TMP" \
|
||
'PS1="❯ " exec bash --noprofile --norc -i'
|
||
sleep 0.3
|
||
out=$("$SEND" -L "$SOCKET" -t "=repl" -m "verdict fixture one delivered ok" 2>"$TMP/e1"); rc=$?
|
||
if [ "$rc" -eq 0 ] && grep -qF "✓ delivered" <<<"$out"; then
|
||
ok "delivered: ❯-prompt REPL that submits => exit 0 ✓ delivered"
|
||
else
|
||
no "delivered: ❯-prompt REPL that submits => exit 0 ✓ delivered" "rc=$rc out=[$out] err=[$(cat "$TMP/e1")]"
|
||
fi
|
||
|
||
# --- Fixture 2: NO prompt glyph, and the pane DOES submit (interactive bash).
|
||
# RESHAPED 2026-08-16 (#1257), deliberately. This fixture previously asserted
|
||
# exit 2 here and was labelled "false-positive FIXED". That assertion was wrong,
|
||
# and locking it in is what kept E7 alive: the pane submits, so "delivered" is
|
||
# the truth, and a pi seat — whose input box is a bare U+2500 rule with no glyph
|
||
# — IS this fixture. Reporting exit 2 for it told operators a delivered message
|
||
# may be undelivered, and the retry that advice invites is the duplicate.
|
||
#
|
||
# The guard this fixture was reaching for is real and is NOT dropped: "never
|
||
# infer delivered from absence" is now enforced positively by fixture 2b below
|
||
# (glyphless AND not submitting => must fail) and by fixture 3 (locatable box
|
||
# still carrying our tail => draft). Absence alone decides nothing either way.
|
||
tmux -L "$SOCKET" new-session -d -s noglyph -c "$TMP" \
|
||
'PS1="sh-noglyph$ " exec bash --noprofile --norc -i'
|
||
sleep 0.3
|
||
out=$("$SEND" -L "$SOCKET" -t "=noglyph" -m "verdict fixture two must fail loud" 2>"$TMP/e2"); rc=$?
|
||
if [ "$rc" -eq 0 ] && grep -qF "✓ delivered" <<<"$out"; then
|
||
ok "delivered: glyphless pane that submits => exit 0 (runtime-agnostic, E7 FIXED)"
|
||
else
|
||
no "delivered: glyphless pane that submits => exit 0" "rc=$rc out=[$out] err=[$(cat "$TMP/e2")]"
|
||
fi
|
||
|
||
# --- Fixture 2b: NO prompt glyph AND never submits — a hung managed TUI holding the
|
||
# terminal in raw/no-echo, which is what a stuck agent seat actually is (measured
|
||
# on live pi: stty -echo -icanon). Nothing is echoed, nothing is consumed, so
|
||
# there is no positive evidence of submission and the tool MUST fail loud. This
|
||
# is the historical false-positive guard, kept as a positive test.
|
||
tmux -L "$SOCKET" new-session -d -s rawstuck -c "$TMP" \
|
||
'bash --noprofile --norc -c "stty -echo -icanon min 1 time 0 2>/dev/null; exec sleep infinity"'
|
||
sleep 0.3
|
||
if out=$("$SEND" -L "$SOCKET" -t "=rawstuck" -r 1 -m "verdict fixture two-b never submitted" 2>"$TMP/e2b"); then
|
||
no "unconfirmed: glyphless hung TUI must NOT report success" "expected non-zero, got 0 (out=[$out])"
|
||
else
|
||
rc=$?
|
||
if [ "$rc" -ne 0 ] && grep -qF "could not confirm submission" "$TMP/e2b"; then
|
||
ok "unconfirmed: glyphless hung TUI (raw/no-echo) => non-zero + 'could not confirm submission'"
|
||
else
|
||
no "unconfirmed: glyphless hung TUI => non-zero + stderr" "rc=$rc err=[$(cat "$TMP/e2b")]"
|
||
fi
|
||
fi
|
||
|
||
# --- Fixture 3: a ❯ box that never submits (sleep ignores stdin; TTY echo keeps the
|
||
# pasted tail sitting on the ❯ line) => draft => exit 2.
|
||
tmux -L "$SOCKET" new-session -d -s draft -c "$TMP" \
|
||
'printf "❯ "; exec sleep infinity'
|
||
sleep 0.3
|
||
if out=$("$SEND" -L "$SOCKET" -t "=draft" -r 1 -m "verdict fixture three stuck unsubmitted draft" 2>"$TMP/e3"); then
|
||
no "draft: unsubmitted message must NOT report success" "expected exit 2, got 0 (out=[$out])"
|
||
else
|
||
rc=$?
|
||
if [ "$rc" -eq 2 ] && grep -qF "unsubmitted draft" "$TMP/e3"; then
|
||
ok "draft: stuck ❯-line message => exit 2 + 'unsubmitted draft'"
|
||
else
|
||
no "draft: stuck ❯-line message => exit 2 + stderr" "rc=$rc err=[$(cat "$TMP/e3")]"
|
||
fi
|
||
fi
|
||
|
||
# --- Fixtures 4 and 5: a pi-shaped pane. The input box is two `─` rules with the
|
||
# text between them and NO prompt glyph anywhere, so the glyph probe alone can
|
||
# never locate it and every send reports "may be UNDELIVERED" (#1362). The
|
||
# renderer below is the shape, not the runtime: MODE=clear submits (box empties),
|
||
# MODE=keep leaves the text sitting in the box.
|
||
cat > "$TMP/pibox.sh" <<'PIBOX'
|
||
#!/usr/bin/env bash
|
||
MODE=${1:-clear}
|
||
RULE=$(printf '─%.0s' $(seq 1 60))
|
||
buf=""
|
||
draw() {
|
||
printf '\033[H\033[2J'
|
||
printf 'fixture output line\n\n'
|
||
printf '%s\n' "$RULE"
|
||
printf '%s\n' "$buf"
|
||
printf '%s\n' "$RULE"
|
||
printf '~/fixture (main)\n'
|
||
printf 'tok 0 model fixture\n'
|
||
}
|
||
draw
|
||
while IFS= read -r line; do
|
||
# keep: hold the tail across every flush Enter, which is what a stuck draft does.
|
||
if [ "$MODE" = keep ]; then [ -n "$line" ] && buf=$line; else buf=""; fi
|
||
draw
|
||
done
|
||
PIBOX
|
||
chmod +x "$TMP/pibox.sh"
|
||
|
||
tmux -L "$SOCKET" new-session -d -s pibox -c "$TMP" "exec bash '$TMP/pibox.sh' clear"
|
||
sleep 0.3
|
||
out=$("$SEND" -L "$SOCKET" -t "=pibox" -m "pi fixture four delivered ok" 2>"$TMP/e4"); rc=$?
|
||
if [ "$rc" -eq 0 ] && grep -qF "✓ delivered" <<<"$out"; then
|
||
ok "delivered: glyphless box-drawn REPL that submits => exit 0 ✓ delivered"
|
||
else
|
||
no "delivered: glyphless box-drawn REPL that submits => exit 0 ✓ delivered" "rc=$rc out=[$out] err=[$(cat "$TMP/e4")]"
|
||
fi
|
||
|
||
tmux -L "$SOCKET" new-session -d -s piboxdraft -c "$TMP" "exec bash '$TMP/pibox.sh' keep"
|
||
sleep 0.3
|
||
if out=$("$SEND" -L "$SOCKET" -t "=piboxdraft" -r 1 -m "pi fixture five stuck in the box" 2>"$TMP/e5"); then
|
||
no "draft: glyphless box-drawn pane holding our tail must NOT report success" "expected exit 2, got 0 (out=[$out])"
|
||
else
|
||
rc=$?
|
||
if [ "$rc" -eq 2 ] && grep -qF "unsubmitted draft" "$TMP/e5"; then
|
||
ok "draft: message left in a glyphless box => exit 2 + 'unsubmitted draft'"
|
||
else
|
||
no "draft: message left in a glyphless box => exit 2 + stderr" "rc=$rc err=[$(cat "$TMP/e5")]"
|
||
fi
|
||
fi
|
||
|
||
# --- Fixtures 6 and 6b: a SHAPELESS REPL. The pane renders nothing at all: no
|
||
# prompt glyph and no rule box, so locate_input_box() alone can never see it
|
||
# and shape-probing alone reports "may be UNDELIVERED" on a delivered message
|
||
# (measured live 2026-09-04, scratch probe: a shapeless consumer CONSUMED the
|
||
# message while the shipped shape probe exited 2 with retry advice - the exact
|
||
# #1257 regression). The cursor-row draft transition is the authoritative,
|
||
# runtime-agnostic delivered verdict: fixture 6's consumer submits => exit 0.
|
||
# Fixture 6b is the guard arm: a shapeless pane whose foreground never reads
|
||
# stdin keeps the echoed paste on the cursor line across every flush Enter =>
|
||
# DRAFT => exit 2, never delivered.
|
||
cat > "$TMP/shapeless.py" <<'SHAPELESS'
|
||
import sys
|
||
for line in sys.stdin:
|
||
pass # consume and render nothing
|
||
SHAPELESS
|
||
tmux -L "$SOCKET" new-session -d -s shapeless -c "$TMP" "exec python3 -u '$TMP/shapeless.py'"
|
||
sleep 0.3
|
||
out=$("$SEND" -L "$SOCKET" -t "=shapeless" -m "fixture six shapeless consumed ok" 2>"$TMP/e6"); rc=$?
|
||
if [ "$rc" -eq 0 ] && grep -qF "✓ delivered" <<<"$out"; then
|
||
ok "delivered: shapeless REPL that submits => exit 0 ✓ delivered (probe regression)"
|
||
else
|
||
no "delivered: shapeless REPL that submits => exit 0 ✓ delivered" "rc=$rc out=[$out] err=[$(cat "$TMP/e6")]"
|
||
fi
|
||
|
||
# MEASURED LIMIT (2026-09-04, this suite's development): a shapeless pane in
|
||
# COOKED mode whose foreground never reads stdin (e.g. 'sleep infinity') scrolls
|
||
# its kernel echo off the cursor row on the flush Enter, so no runtime-agnostic
|
||
# signal available to the sender distinguishes it from a delivering pane. The
|
||
# non-reading guard therefore requires either a locatable box still carrying the
|
||
# tail (fixture 3) or raw/no-echo mode (fixture 2b). Real REPL seats read stdin,
|
||
# which is why this limit is not reachable against agent seats; recorded here so
|
||
# nobody rediscovers it as a silent gap.
|
||
tmux -L "$SOCKET" new-session -d -s shapelessraw -c "$TMP" 'stty raw -echo; exec sleep infinity'
|
||
sleep 0.3
|
||
if out=$("$SEND" -L "$SOCKET" -t "=shapelessraw" -r 1 -m "fixture six b shapeless raw never consumed" 2>"$TMP/e6b"); then
|
||
no "unconfirmed: shapeless raw non-reading pane must NOT report success" "expected exit 2, got 0 (out=[$out])"
|
||
else
|
||
rc=$?
|
||
if [ "$rc" -eq 2 ] && grep -qF "could not confirm submission" "$TMP/e6b"; then
|
||
ok "unconfirmed: shapeless raw non-reading pane => exit 2 + 'could not confirm submission'"
|
||
else
|
||
no "unconfirmed: shapeless raw non-reading pane => exit 2 + stderr" "rc=$rc err=[$(cat "$TMP/e6b")]"
|
||
fi
|
||
fi
|
||
|
||
echo "---"
|
||
echo "PASS=$PASS FAIL=$FAIL"
|
||
[ "$FAIL" -eq 0 ]
|