0f0fa7f1ea
Some checks failed
ci/woodpecker/pr/ci Pipeline failed
Invert the delivery verdict from negative to positive evidence. Previously, success was declared by the ABSENCE of a draft snippet on a prompt line: if the `❯|^>|│ >` glyph matched nothing (busy-receiver draft on an unmatched line, or wrong-pane drift), an UNSUBMITTED message read as "✓ delivered" exit 0 — a silent worker->lead relay stall (filed by UC-LEAD, PR #3046: three review verdicts reported delivered but never surfaced for ~50 min). Fix: success now requires POSITIVE evidence — either the queued banner, or the REPL input box located AND clear of the message tail. If the input box cannot be located, status is `unconfirmed` -> exit 2 + stderr ("could not confirm submission ... may be UNDELIVERED"). The near-dead `*)` indeterminate default also flips from silently returning 0 to exit 2. Bracketed-paste and double-Enter delivery mechanics are unchanged; queued/draft/delivered semantics are preserved, only the failure-mode default direction changes. Adds `test-send-message-verdict.sh`: 3 real tmux-pane fixtures (delivered / unconfirmed-glyphless / draft) locking the fail-loud verdict logic, and upgrades `test-send-message-socket.sh` fixtures from a glyphless bash prompt to `❯`-prompt REPLs so the patched binary can read delivery positively. Reproduce-first evidence (baseline vs patched, glyphless-pane fixture): baseline: rc=0, stdout "✓ delivered to =noglyph" (silent false positive) patched: rc=2, stderr "could not confirm submission ... may be UNDELIVERED" Test results after port: test-send-message-verdict.sh -> PASS=3 FAIL=0 test-send-message-socket.sh -> ok Firewall: grep -niE 'jason|woltje|jarvis' on changed files = 0 hits; tools/quality/scripts/verify-sanitized.sh -> sanitization gate passed. shellcheck: 1 pre-existing SC2034 finding (unused loop var `attempt`, present identically in baseline) carried through; 0 new findings. Part of #891
75 lines
3.4 KiB
Bash
Executable File
75 lines
3.4 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. UNCONFIRMED — a pane with NO locatable prompt glyph. This is the exact
|
||
# historical FALSE POSITIVE: pre-patch it printed "✓ delivered"
|
||
# exit 0; post-patch it MUST fail loud (exit 2, stderr
|
||
# "could not confirm submission").
|
||
# 3. DRAFT — a `❯ `-prompt pane that never submits (message stays on the
|
||
# input line) => exit 2, stderr "unsubmitted draft".
|
||
set -uo pipefail
|
||
|
||
HERE=$(cd -- "$(dirname -- "$0")" && pwd)
|
||
SEND="$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 [ "$rc" -eq 0 ] && printf '%s' "$out" | grep -qF "✓ delivered"; 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 (default bash PS1). THE regression: pre-patch this
|
||
# was a silent false-positive "delivered"; post-patch it must be unconfirmed→exit 2.
|
||
tmux -L "$SOCKET" new-session -d -s noglyph -c "$TMP" \
|
||
'PS1="sh-noglyph$ " exec bash --noprofile --norc -i'
|
||
sleep 0.3
|
||
if out=$("$SEND" -L "$SOCKET" -t "=noglyph" -m "verdict fixture two must fail loud" 2>"$TMP/e2"); then
|
||
no "unconfirmed: glyphless 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/e2"; then
|
||
ok "unconfirmed: glyphless pane => exit 2 + 'could not confirm submission' (false-positive FIXED)"
|
||
else
|
||
no "unconfirmed: glyphless pane => exit 2 + stderr" "rc=$rc err=[$(cat "$TMP/e2")]"
|
||
fi
|
||
fi
|
||
|
||
# --- Fixture 3: a ❯ box that never submits (sleep ignores stdin; TTY echo keeps the
|
||
# pasted tail sitting on the ❯ line) => draft => exit 2.
|
||
tmux -L "$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
|
||
|
||
echo "---"
|
||
echo "PASS=$PASS FAIL=$FAIL"
|
||
[ "$FAIL" -eq 0 ]
|