Files
stack/scripts/verify.sh
T
jason.woltje 0734b1f3a5 fix(launcher): detach stdin on agent container run (#5)
pi print mode reads piped stdin until EOF; an attached terminal stdin
blocked the one-shot run forever. Automated contexts (closed stdin)
never exposed it. Request text comes from the compose command.

Proven: tail -f /dev/null | scripts/hello.sh now returns MOSAIC_HELLO_OK
in ~4s (previously timed out at 30s); verify.sh remains green.

Closes #5
2026-09-02 19:50:07 -05:00

61 lines
1.8 KiB
Bash
Executable File

#!/usr/bin/env bash
# Complete verification test:
# 1. Build or confirm the image is built.
# 2. Run the agent request.
# 3. Remove surrounding whitespace from the response.
# 4. Compare with the expected marker (default MOSAIC_HELLO_OK).
# 5. Exit 0 only on exact match; nonzero otherwise.
#
# EXPECTED_MARKER may be overridden to prove the failure path
# (acceptance criterion 9), e.g.:
# EXPECTED_MARKER=MOSAIC_NOT_OK scripts/verify.sh
set -euo pipefail
cd "$(dirname "$0")/.."
# shellcheck source=common.sh
source scripts/common.sh
IMAGE="mosaic-poc-agent:0.84.4"
EXPECTED="${EXPECTED_MARKER:-MOSAIC_HELLO_OK}"
load_config
# Ensure the configured data root exists (host-owned) before the mount,
# otherwise Docker would auto-create a root-owned directory.
bootstrap_runtime_dir
# 1. Build the image only if it is not already present.
if ! docker image inspect "$IMAGE" >/dev/null 2>&1; then
echo "verify: image $IMAGE not found, building..." >&2
bootstrap_runtime_dir
docker compose build
fi
# 2. Run the agent request (stdout only = model response).
# stdin detached: see hello.sh — print mode would block on a terminal.
set +e
RESPONSE="$(docker compose run --rm -T mosaic-agent </dev/null 2>/tmp/mosaic-poc-stderr.$$)"
RC=$?
set -e
STDERR_FILE="/tmp/mosaic-poc-stderr.$$"
if [ $RC -ne 0 ]; then
echo "verify: agent run failed (exit $RC):" >&2
cat "$STDERR_FILE" >&2
rm -f "$STDERR_FILE"
exit 1
fi
rm -f "$STDERR_FILE"
# 3. Remove surrounding whitespace.
TRIMMED="$(printf '%s' "$RESPONSE" | sed -e 's/^[[:space:]]*//' -e 's/[[:space:]]*$//')"
# 4-6. Exact comparison gate.
if [ "$TRIMMED" = "$EXPECTED" ]; then
echo "PASS: response matches expected marker"
exit 0
fi
echo "FAIL: response does not match expected marker" >&2
printf 'expected: %s\n' "$EXPECTED" >&2
printf 'actual : %s\n' "$TRIMMED" >&2
exit 1