Files
ai-workflow-skill/scripts/run_orch_skill_forward_tests.sh

1060 lines
41 KiB
Bash
Executable File

#!/usr/bin/env bash
set -euo pipefail
readonly SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
readonly REPO_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"
readonly ORCH_BIN="${REPO_ROOT}/skills/orch/assets/orch"
readonly INBOX_BIN="${REPO_ROOT}/skills/inbox/assets/inbox"
OUTPUT_ROOT=""
LAST_BG_PID=""
usage() {
cat <<'EOF'
Usage: scripts/run_orch_skill_forward_tests.sh [--output-root PATH]
Runs the documented orch-skill forward scenarios as direct bundled-CLI replays.
Each case gets its own temporary workspace, SQLite DB, and JSON evidence files.
Options:
--output-root PATH Write results under PATH instead of a temporary directory
-h, --help Show this help text
EOF
}
require_command() {
local cmd="$1"
if ! command -v "${cmd}" >/dev/null 2>&1; then
printf 'missing required command: %s\n' "${cmd}" >&2
exit 1
fi
}
run_json() {
local output_path="$1"
shift
"$@" >"${output_path}"
}
json_get() {
local file_path="$1"
local filter="$2"
jq -r "${filter}" "${file_path}"
}
json_check() {
local file_path="$1"
local filter="$2"
local label="$3"
if jq -e "${filter}" "${file_path}" >/dev/null; then
printf 'PASS: %s\n' "${label}"
else
printf 'FAIL: %s\n' "${label}" >&2
printf ' file: %s\n' "${file_path}" >&2
printf ' jq: %s\n' "${filter}" >&2
exit 1
fi
}
start_wait() {
local output_path="$1"
shift
"$@" >"${output_path}" &
LAST_BG_PID="$!"
}
wait_for_pid() {
local pid="$1"
local label="$2"
if ! wait "${pid}"; then
printf 'background command failed: %s\n' "${label}" >&2
exit 1
fi
}
init_case_dir() {
local case_slug="$1"
local base_dir="${OUTPUT_ROOT}/${case_slug}"
mkdir -p "${base_dir}"
printf '%s\n' "${base_dir}"
}
init_db() {
local db_path="$1"
run_json "${db_path%.db}.init.json" "${INBOX_BIN}" --db "${db_path}" --json init
}
init_git_repo() {
local repo_path="$1"
mkdir -p "${repo_path}"
git -C "${repo_path}" init >/dev/null
git -C "${repo_path}" config user.name "Orch Skill Replay"
git -C "${repo_path}" config user.email "orch-skill-replay@example.com"
printf '# Replay Fixture\n' >"${repo_path}/README.md"
git -C "${repo_path}" add README.md
git -C "${repo_path}" commit -m "Initial commit" >/dev/null
}
join_json_array() {
if [ "$#" -eq 0 ]; then
printf '[]'
return
fi
printf '%s\n' "$@" | jq -R . | jq -s .
}
write_result_json() {
local case_dir="$1"
local case_slug="$2"
local db_path="$3"
local run_id="$4"
local result="$5"
local duration_seconds="$6"
local thread_ids_json="$7"
local worktree_paths_json="$8"
local notes="$9"
jq -n \
--arg case "${case_slug}" \
--arg db_path "${db_path}" \
--arg run_id "${run_id}" \
--arg result "${result}" \
--arg notes "${notes}" \
--arg mode "direct_cli_replay" \
--arg runner_script "scripts/run_orch_skill_forward_tests.sh" \
--argjson duration_seconds "${duration_seconds}" \
--argjson thread_ids "${thread_ids_json}" \
--argjson worktree_paths "${worktree_paths_json}" \
'{
case: $case,
db_path: $db_path,
run_id: $run_id,
thread_ids: $thread_ids,
worktree_paths: $worktree_paths,
result: $result,
duration_seconds: $duration_seconds,
execution_mode: $mode,
runner_script: $runner_script,
notes: $notes
}' >"${case_dir}/result.json"
}
print_case_summary() {
local case_slug="$1"
local case_dir="$2"
printf '%s\t%s\n' "${case_slug}" "$(json_get "${case_dir}/result.json" '.result')"
}
run_case_happy_path() {
local case_slug="leader-run-dispatch-reconcile-through-bundled-cli"
local run_id="run_blog_skill_001"
local case_dir
case_dir="$(init_case_dir "${case_slug}")"
local db_path="${case_dir}/coord.db"
local started_at
started_at="$(date +%s)"
init_db "${db_path}"
run_json "${case_dir}/run.json" \
"${ORCH_BIN}" --db "${db_path}" --json run init \
--run "${run_id}" --goal "Build blog MVP" --summary "Public blog plus admin CRUD"
run_json "${case_dir}/task.json" \
"${ORCH_BIN}" --db "${db_path}" --json task add \
--run "${run_id}" --task T1 --title "Implement retry policy" \
--summary "Add retry policy to HTTP client" --default-to worker-a
run_json "${case_dir}/dispatch.json" \
"${ORCH_BIN}" --db "${db_path}" --json dispatch \
--run "${run_id}" --task T1 --execution-mode analysis --to worker-a \
--body "Implement retry handling for the HTTP client."
local thread_id
thread_id="$(json_get "${case_dir}/dispatch.json" '.data.attempt.thread_id')"
local wait_pid
start_wait "${case_dir}/wait-task-done.json" \
"${ORCH_BIN}" --db "${db_path}" --json wait \
--run "${run_id}" --for task_done --timeout-seconds 15
wait_pid="${LAST_BG_PID}"
sleep 0.2
run_json "${case_dir}/fetch.json" \
"${INBOX_BIN}" --db "${db_path}" --json fetch \
--agent worker-a --limit 1
run_json "${case_dir}/claim.json" \
"${INBOX_BIN}" --db "${db_path}" --json claim \
--agent worker-a --thread "${thread_id}"
run_json "${case_dir}/update.json" \
"${INBOX_BIN}" --db "${db_path}" --json update \
--agent worker-a --thread "${thread_id}" \
--status in_progress --summary "Implementation started"
run_json "${case_dir}/done.json" \
"${INBOX_BIN}" --db "${db_path}" --json done \
--agent worker-a --thread "${thread_id}" \
--summary "Retry policy implemented" \
--body "The HTTP client now retries transient failures."
wait_for_pid "${wait_pid}" "${case_slug}: wait task_done"
run_json "${case_dir}/reconcile.json" \
"${ORCH_BIN}" --db "${db_path}" --json reconcile --run "${run_id}"
run_json "${case_dir}/status.json" \
"${ORCH_BIN}" --db "${db_path}" --json status --run "${run_id}"
run_json "${case_dir}/show.json" \
"${INBOX_BIN}" --db "${db_path}" --json show --thread "${thread_id}"
json_check "${case_dir}/wait-task-done.json" '.data.woke == true' "wait woke on task_done"
json_check "${case_dir}/status.json" '.data.run.status == "done"' "run status done"
json_check "${case_dir}/status.json" '.data.tasks | length == 1 and .[0].task_id == "T1" and .[0].status == "done"' "single done task"
json_check "${case_dir}/show.json" '.data.thread.status == "done"' "thread status done"
json_check "${case_dir}/show.json" '[.data.messages[].kind] | index("task") != null and index("progress") != null and index("result") != null' "thread history includes task progress result"
local duration_seconds
duration_seconds="$(( $(date +%s) - started_at ))"
write_result_json \
"${case_dir}" "${case_slug}" "${db_path}" "${run_id}" pass "${duration_seconds}" \
"$(join_json_array "${thread_id}")" \
"$(join_json_array)" \
"Direct CLI replay of the documented happy path."
}
run_case_blocked_answer() {
local case_slug="leader-blocked-answer-resume-through-bundled-cli"
local run_id="run_blog_skill_002"
local case_dir
case_dir="$(init_case_dir "${case_slug}")"
local db_path="${case_dir}/coord.db"
local started_at
started_at="$(date +%s)"
init_db "${db_path}"
run_json "${case_dir}/run.json" \
"${ORCH_BIN}" --db "${db_path}" --json run init \
--run "${run_id}" --goal "Build dependency-aware workflow" \
--summary "Exercise blocked question handling"
run_json "${case_dir}/task.json" \
"${ORCH_BIN}" --db "${db_path}" --json task add \
--run "${run_id}" --task T1 --title "Build frontend" \
--summary "Implement frontend flow" --default-to worker-a
run_json "${case_dir}/dispatch.json" \
"${ORCH_BIN}" --db "${db_path}" --json dispatch \
--run "${run_id}" --task T1 --execution-mode analysis --to worker-a \
--body "Implement the worker flow and stop if a logging decision is needed."
local thread_id
thread_id="$(json_get "${case_dir}/dispatch.json" '.data.attempt.thread_id')"
local wait_blocked_pid
start_wait "${case_dir}/wait-task-blocked.json" \
"${ORCH_BIN}" --db "${db_path}" --json wait \
--run "${run_id}" --for task_blocked --timeout-seconds 15
wait_blocked_pid="${LAST_BG_PID}"
sleep 0.2
run_json "${case_dir}/claim.json" \
"${INBOX_BIN}" --db "${db_path}" --json claim \
--agent worker-a --thread "${thread_id}"
run_json "${case_dir}/progress.json" \
"${INBOX_BIN}" --db "${db_path}" --json update \
--agent worker-a --thread "${thread_id}" \
--status in_progress --summary "Implementation started"
run_json "${case_dir}/blocked.json" \
"${INBOX_BIN}" --db "${db_path}" --json update \
--agent worker-a --thread "${thread_id}" \
--status blocked --summary "Need logging decision" \
--payload-json '{"question":"Should logging go to stdout or stderr?"}'
wait_for_pid "${wait_blocked_pid}" "${case_slug}: wait task_blocked"
local blocked_message_id
blocked_message_id="$(json_get "${case_dir}/blocked.json" '.data.message.message_id')"
run_json "${case_dir}/orch-blocked.json" \
"${ORCH_BIN}" --db "${db_path}" --json blocked --run "${run_id}"
local wait_reply_pid
start_wait "${case_dir}/wait-reply.json" \
"${INBOX_BIN}" --db "${db_path}" --agent worker-a --json wait-reply \
--thread "${thread_id}" --after-message "${blocked_message_id}" --timeout-seconds 15
wait_reply_pid="${LAST_BG_PID}"
sleep 0.2
run_json "${case_dir}/answer.json" \
"${ORCH_BIN}" --db "${db_path}" --json answer \
--run "${run_id}" --task T1 --body "Use stdout for MVP."
wait_for_pid "${wait_reply_pid}" "${case_slug}: inbox wait-reply"
local wait_done_pid
start_wait "${case_dir}/wait-task-done.json" \
"${ORCH_BIN}" --db "${db_path}" --json wait \
--run "${run_id}" --for task_done --timeout-seconds 15
wait_done_pid="${LAST_BG_PID}"
sleep 0.2
run_json "${case_dir}/resume.json" \
"${INBOX_BIN}" --db "${db_path}" --json update \
--agent worker-a --thread "${thread_id}" \
--status in_progress --summary "Decision applied"
run_json "${case_dir}/done.json" \
"${INBOX_BIN}" --db "${db_path}" --json done \
--agent worker-a --thread "${thread_id}" \
--summary "Frontend complete" \
--body "Worker resumed after the leader answer."
wait_for_pid "${wait_done_pid}" "${case_slug}: wait task_done"
run_json "${case_dir}/reconcile.json" \
"${ORCH_BIN}" --db "${db_path}" --json reconcile --run "${run_id}"
run_json "${case_dir}/status.json" \
"${ORCH_BIN}" --db "${db_path}" --json status --run "${run_id}"
run_json "${case_dir}/show.json" \
"${INBOX_BIN}" --db "${db_path}" --json show --thread "${thread_id}"
json_check "${case_dir}/wait-task-blocked.json" '.data.woke == true and (.data.events | length) >= 1 and .data.events[0].type == "task_blocked"' "wait woke on task_blocked"
json_check "${case_dir}/orch-blocked.json" '.data.blocked | length == 1 and .[0].task.task_id == "T1"' "blocked queue lists task"
json_check "${case_dir}/wait-reply.json" '.data.woke == true and .data.message.kind == "answer"' "wait-reply woke on answer"
json_check "${case_dir}/status.json" '.data.run.status == "done" and .data.tasks[0].status == "done"' "blocked flow run completes"
json_check "${case_dir}/show.json" '[.data.messages[].kind] | index("question") != null and index("answer") != null and index("result") != null' "history includes question answer result"
json_check "${case_dir}/show.json" 'any(.data.messages[]; .kind == "question" and .payload_json.question == "Should logging go to stdout or stderr?")' "question payload matches"
json_check "${case_dir}/show.json" 'any(.data.messages[]; .kind == "answer" and .body == "Use stdout for MVP.")' "answer body matches"
local duration_seconds
duration_seconds="$(( $(date +%s) - started_at ))"
write_result_json \
"${case_dir}" "${case_slug}" "${db_path}" "${run_id}" pass "${duration_seconds}" \
"$(join_json_array "${thread_id}")" \
"$(join_json_array)" \
"Direct CLI replay of the blocked-question workflow, including orch wait and inbox wait-reply."
}
run_case_strict_worktree_cleanup() {
local case_slug="strict-worktree-dispatch-to-cleanup-through-bundled-cli"
local run_id="run_blog_skill_worktree_001"
local case_dir
case_dir="$(init_case_dir "${case_slug}")"
local db_path="${case_dir}/coord.db"
local repo_path="${case_dir}/repo"
local started_at
started_at="$(date +%s)"
init_db "${db_path}"
init_git_repo "${repo_path}"
run_json "${case_dir}/run.json" \
"${ORCH_BIN}" --db "${db_path}" --json run init \
--run "${run_id}" --goal "Validate code-mode worktree dispatch" \
--summary "Exercise worktree allocation and cleanup"
run_json "${case_dir}/task.json" \
"${ORCH_BIN}" --db "${db_path}" --json task add \
--run "${run_id}" --task T1 --title "Implement backend" \
--summary "Implement inside an isolated worktree" --default-to worker-a
run_json "${case_dir}/dispatch.json" \
"${ORCH_BIN}" --db "${db_path}" --json dispatch \
--run "${run_id}" --task T1 --to worker-a \
--execution-mode code --repo-path "${repo_path}" --workspace-root .orch/worktrees \
--body "Implement inside isolated worktree."
local thread_id
local worktree_path
thread_id="$(json_get "${case_dir}/dispatch.json" '.data.attempt.thread_id')"
worktree_path="$(json_get "${case_dir}/dispatch.json" '.data.attempt.worktree_path')"
local wait_pid
start_wait "${case_dir}/wait-task-done.json" \
"${ORCH_BIN}" --db "${db_path}" --json wait \
--run "${run_id}" --for task_done --timeout-seconds 15
wait_pid="${LAST_BG_PID}"
sleep 0.2
run_json "${case_dir}/claim.json" \
"${INBOX_BIN}" --db "${db_path}" --json claim \
--agent worker-a --thread "${thread_id}"
run_json "${case_dir}/thread-before-done.json" \
"${INBOX_BIN}" --db "${db_path}" --json show --thread "${thread_id}"
run_json "${case_dir}/done.json" \
"${INBOX_BIN}" --db "${db_path}" --json done \
--agent worker-a --thread "${thread_id}" \
--summary "Backend complete" \
--body "Confirmed the assigned worktree path from the task payload."
wait_for_pid "${wait_pid}" "${case_slug}: wait task_done"
run_json "${case_dir}/reconcile.json" \
"${ORCH_BIN}" --db "${db_path}" --json reconcile --run "${run_id}"
run_json "${case_dir}/cleanup.json" \
"${ORCH_BIN}" --db "${db_path}" --json cleanup --run "${run_id}" --task T1
run_json "${case_dir}/status.json" \
"${ORCH_BIN}" --db "${db_path}" --json status --run "${run_id}"
run_json "${case_dir}/show.json" \
"${INBOX_BIN}" --db "${db_path}" --json show --thread "${thread_id}"
json_check "${case_dir}/dispatch.json" '.data.attempt.worktree_path != ""' "dispatch returns worktree path"
if jq -e --arg worktree "${worktree_path}" 'any(.data.messages[]; .kind == "task" and .payload_json.worktree_path == $worktree)' "${case_dir}/thread-before-done.json" >/dev/null; then
printf 'PASS: task payload exposes worktree path\n'
else
printf 'FAIL: task payload exposes worktree path\n' >&2
exit 1
fi
json_check "${case_dir}/status.json" '.data.run.status == "done" and .data.tasks[0].status == "done"' "worktree flow run completes"
json_check "${case_dir}/cleanup.json" '.data.cleaned | length == 1' "cleanup removes one attempt"
if [ -d "${worktree_path}" ]; then
printf 'FAIL: worktree path still exists after cleanup: %s\n' "${worktree_path}" >&2
exit 1
fi
printf 'PASS: cleaned worktree removed\n'
local duration_seconds
duration_seconds="$(( $(date +%s) - started_at ))"
write_result_json \
"${case_dir}" "${case_slug}" "${db_path}" "${run_id}" pass "${duration_seconds}" \
"$(join_json_array "${thread_id}")" \
"$(join_json_array "${worktree_path}")" \
"Direct CLI replay of execution-mode code dispatch, completion, and cleanup."
}
run_case_dependency_ready_dispatch() {
local case_slug="leader-dispatches-dependent-task-after-prerequisite-through-bundled-cli"
local run_id="run_blog_skill_deps_001"
local case_dir
case_dir="$(init_case_dir "${case_slug}")"
local db_path="${case_dir}/coord.db"
local started_at
started_at="$(date +%s)"
init_db "${db_path}"
run_json "${case_dir}/run.json" \
"${ORCH_BIN}" --db "${db_path}" --json run init \
--run "${run_id}" --goal "Validate dependency-gated dispatch" \
--summary "Exercise dep add, ready, and staged dispatch"
run_json "${case_dir}/task-1.json" \
"${ORCH_BIN}" --db "${db_path}" --json task add \
--run "${run_id}" --task T1 --title "Implement backend" \
--summary "Prerequisite task" --default-to worker-a
run_json "${case_dir}/task-2.json" \
"${ORCH_BIN}" --db "${db_path}" --json task add \
--run "${run_id}" --task T2 --title "Implement frontend" \
--summary "Dependent task" --default-to worker-b
run_json "${case_dir}/dep.json" \
"${ORCH_BIN}" --db "${db_path}" --json dep add \
--run "${run_id}" --task T2 --depends-on T1
run_json "${case_dir}/ready-initial.json" \
"${ORCH_BIN}" --db "${db_path}" --json ready --run "${run_id}"
run_json "${case_dir}/dispatch-1.json" \
"${ORCH_BIN}" --db "${db_path}" --json dispatch \
--run "${run_id}" --task T1 --execution-mode analysis --to worker-a \
--body "Complete the prerequisite task first."
local thread_id_1
thread_id_1="$(json_get "${case_dir}/dispatch-1.json" '.data.attempt.thread_id')"
local wait_done_pid
start_wait "${case_dir}/wait-task-done-1.json" \
"${ORCH_BIN}" --db "${db_path}" --json wait \
--run "${run_id}" --for task_done --timeout-seconds 15
wait_done_pid="${LAST_BG_PID}"
sleep 0.2
run_json "${case_dir}/claim-1.json" \
"${INBOX_BIN}" --db "${db_path}" --json claim \
--agent worker-a --thread "${thread_id_1}"
run_json "${case_dir}/progress-1.json" \
"${INBOX_BIN}" --db "${db_path}" --json update \
--agent worker-a --thread "${thread_id_1}" \
--status in_progress --summary "Prerequisite started"
run_json "${case_dir}/done-1.json" \
"${INBOX_BIN}" --db "${db_path}" --json done \
--agent worker-a --thread "${thread_id_1}" \
--summary "Prerequisite complete" \
--body "T1 completed so T2 can be dispatched."
wait_for_pid "${wait_done_pid}" "${case_slug}: wait first task_done"
run_json "${case_dir}/reconcile-1.json" \
"${ORCH_BIN}" --db "${db_path}" --json reconcile --run "${run_id}"
run_json "${case_dir}/ready-after-prerequisite.json" \
"${ORCH_BIN}" --db "${db_path}" --json ready --run "${run_id}"
run_json "${case_dir}/dispatch-2.json" \
"${ORCH_BIN}" --db "${db_path}" --json dispatch \
--run "${run_id}" --task T2 --execution-mode analysis --to worker-b \
--body "Dependent task is now ready after T1."
local thread_id_2
thread_id_2="$(json_get "${case_dir}/dispatch-2.json" '.data.attempt.thread_id')"
run_json "${case_dir}/claim-2.json" \
"${INBOX_BIN}" --db "${db_path}" --json claim \
--agent worker-b --thread "${thread_id_2}"
run_json "${case_dir}/done-2.json" \
"${INBOX_BIN}" --db "${db_path}" --json done \
--agent worker-b --thread "${thread_id_2}" \
--summary "Dependent task complete" \
--body "T2 completed after the dependency cleared."
run_json "${case_dir}/reconcile-2.json" \
"${ORCH_BIN}" --db "${db_path}" --json reconcile --run "${run_id}"
run_json "${case_dir}/status.json" \
"${ORCH_BIN}" --db "${db_path}" --json status --run "${run_id}"
run_json "${case_dir}/show-1.json" \
"${INBOX_BIN}" --db "${db_path}" --json show --thread "${thread_id_1}"
run_json "${case_dir}/show-2.json" \
"${INBOX_BIN}" --db "${db_path}" --json show --thread "${thread_id_2}"
json_check "${case_dir}/dep.json" '.data.dependency.task_id == "T2" and .data.dependency.depends_on_task_id == "T1"' "dep add stores T2 -> T1"
json_check "${case_dir}/ready-initial.json" '.data.tasks | length == 1 and .[0].task_id == "T1"' "initial ready lists only prerequisite"
json_check "${case_dir}/wait-task-done-1.json" '.data.woke == true and (.data.events | length) >= 1 and .data.events[0].type == "task_done"' "wait woke on prerequisite completion"
json_check "${case_dir}/ready-after-prerequisite.json" '.data.tasks | length == 1 and .[0].task_id == "T2"' "dependent task becomes ready after reconcile"
json_check "${case_dir}/status.json" '.data.run.status == "done" and ([.data.tasks[] | select(.task_id == "T1")][0].status == "done") and ([.data.tasks[] | select(.task_id == "T2")][0].status == "done")' "dependency-gated run completes with both tasks done"
json_check "${case_dir}/show-1.json" '.data.thread.status == "done"' "prerequisite thread done"
json_check "${case_dir}/show-2.json" '.data.thread.status == "done"' "dependent thread done"
if [ "${thread_id_1}" = "${thread_id_2}" ]; then
printf 'FAIL: dependency flow reused thread ID %s\n' "${thread_id_1}" >&2
exit 1
fi
printf 'PASS: dependency flow created distinct thread IDs\n'
local duration_seconds
duration_seconds="$(( $(date +%s) - started_at ))"
write_result_json \
"${case_dir}" "${case_slug}" "${db_path}" "${run_id}" pass "${duration_seconds}" \
"$(join_json_array "${thread_id_1}" "${thread_id_2}")" \
"$(join_json_array)" \
"Direct CLI replay of dependency-gated ready sequencing from prerequisite completion to dependent dispatch."
}
run_case_cancel_active_task() {
local case_slug="leader-cancels-active-task-through-bundled-cli"
local run_id="run_blog_skill_cancel_001"
local case_dir
case_dir="$(init_case_dir "${case_slug}")"
local db_path="${case_dir}/coord.db"
local started_at
started_at="$(date +%s)"
init_db "${db_path}"
run_json "${case_dir}/run.json" \
"${ORCH_BIN}" --db "${db_path}" --json run init \
--run "${run_id}" --goal "Validate active task cancellation" \
--summary "Exercise direct orch cancel on an active attempt"
run_json "${case_dir}/task-1.json" \
"${ORCH_BIN}" --db "${db_path}" --json task add \
--run "${run_id}" --task T1 --title "Implement backend" \
--summary "Task that will be cancelled mid-flight" --default-to worker-a
run_json "${case_dir}/task-2.json" \
"${ORCH_BIN}" --db "${db_path}" --json task add \
--run "${run_id}" --task T2 --title "Implement frontend" \
--summary "Task that should remain ready" --default-to worker-b
run_json "${case_dir}/dispatch.json" \
"${ORCH_BIN}" --db "${db_path}" --json dispatch \
--run "${run_id}" --task T1 --execution-mode analysis --to worker-a \
--body "Start work so the leader can cancel an active task."
local thread_id
thread_id="$(json_get "${case_dir}/dispatch.json" '.data.attempt.thread_id')"
run_json "${case_dir}/claim.json" \
"${INBOX_BIN}" --db "${db_path}" --json claim \
--agent worker-a --thread "${thread_id}"
run_json "${case_dir}/progress.json" \
"${INBOX_BIN}" --db "${db_path}" --json update \
--agent worker-a --thread "${thread_id}" \
--status in_progress --summary "Active work in progress"
run_json "${case_dir}/cancel.json" \
"${ORCH_BIN}" --db "${db_path}" --json cancel \
--run "${run_id}" --task T1 \
--reason "Task superseded by dependency review."
run_json "${case_dir}/status.json" \
"${ORCH_BIN}" --db "${db_path}" --json status --run "${run_id}"
run_json "${case_dir}/ready.json" \
"${ORCH_BIN}" --db "${db_path}" --json ready --run "${run_id}"
run_json "${case_dir}/show.json" \
"${INBOX_BIN}" --db "${db_path}" --json show --thread "${thread_id}"
json_check "${case_dir}/cancel.json" '.data.cancelled_tasks | length == 1 and .[0].task_id == "T1" and .[0].status == "cancelled"' "cancel returns cancelled T1"
json_check "${case_dir}/status.json" '.data.run.status == "ready"' "run remains ready after cancelling one active task"
json_check "${case_dir}/status.json" '([.data.tasks[] | select(.task_id == "T1")][0].status == "cancelled") and ([.data.tasks[] | select(.task_id == "T2")][0].status == "ready")' "status keeps T2 ready while T1 is cancelled"
json_check "${case_dir}/ready.json" '.data.tasks | length == 1 and .[0].task_id == "T2"' "ready queue still exposes untouched T2"
json_check "${case_dir}/show.json" '.data.thread.status == "cancelled"' "cancelled thread reaches terminal state"
json_check "${case_dir}/show.json" 'any(.data.messages[]; .kind == "progress")' "cancelled thread preserves worker progress history"
local duration_seconds
duration_seconds="$(( $(date +%s) - started_at ))"
write_result_json \
"${case_dir}" "${case_slug}" "${db_path}" "${run_id}" pass "${duration_seconds}" \
"$(join_json_array "${thread_id}")" \
"$(join_json_array)" \
"Direct CLI replay of cancelling an active task while leaving unrelated ready work untouched."
}
run_case_payload_only_answer() {
local case_slug="leader-answers-blocked-task-with-payload-json-through-bundled-cli"
local run_id="run_blog_skill_payload_answer_001"
local case_dir
case_dir="$(init_case_dir "${case_slug}")"
local db_path="${case_dir}/coord.db"
local started_at
started_at="$(date +%s)"
init_db "${db_path}"
run_json "${case_dir}/run.json" \
"${ORCH_BIN}" --db "${db_path}" --json run init \
--run "${run_id}" --goal "Validate payload-only answers" \
--summary "Exercise answer --payload-json on a blocked task"
run_json "${case_dir}/task.json" \
"${ORCH_BIN}" --db "${db_path}" --json task add \
--run "${run_id}" --task T1 --title "Build frontend" \
--summary "Resume after structured leader decision" --default-to worker-a
run_json "${case_dir}/dispatch.json" \
"${ORCH_BIN}" --db "${db_path}" --json dispatch \
--run "${run_id}" --task T1 --execution-mode analysis --to worker-a \
--body "Pause if a structured logging decision is needed."
local thread_id
thread_id="$(json_get "${case_dir}/dispatch.json" '.data.attempt.thread_id')"
local wait_blocked_pid
start_wait "${case_dir}/wait-task-blocked.json" \
"${ORCH_BIN}" --db "${db_path}" --json wait \
--run "${run_id}" --for task_blocked --timeout-seconds 15
wait_blocked_pid="${LAST_BG_PID}"
sleep 0.2
run_json "${case_dir}/claim.json" \
"${INBOX_BIN}" --db "${db_path}" --json claim \
--agent worker-a --thread "${thread_id}"
run_json "${case_dir}/blocked.json" \
"${INBOX_BIN}" --db "${db_path}" --json update \
--agent worker-a --thread "${thread_id}" \
--status blocked --summary "Need structured logging decision" \
--payload-json '{"question":"Use stdout or stderr for structured logs?"}'
wait_for_pid "${wait_blocked_pid}" "${case_slug}: wait task_blocked"
local blocked_message_id
blocked_message_id="$(json_get "${case_dir}/blocked.json" '.data.message.message_id')"
run_json "${case_dir}/orch-blocked.json" \
"${ORCH_BIN}" --db "${db_path}" --json blocked --run "${run_id}"
local wait_reply_pid
start_wait "${case_dir}/wait-reply.json" \
"${INBOX_BIN}" --db "${db_path}" --agent worker-a --json wait-reply \
--thread "${thread_id}" --after-message "${blocked_message_id}" --timeout-seconds 15
wait_reply_pid="${LAST_BG_PID}"
sleep 0.2
run_json "${case_dir}/answer.json" \
"${ORCH_BIN}" --db "${db_path}" --json answer \
--run "${run_id}" --task T1 \
--payload-json '{"decision":"stdout","source":"leader","format":"structured"}'
wait_for_pid "${wait_reply_pid}" "${case_slug}: inbox wait-reply"
local wait_done_pid
start_wait "${case_dir}/wait-task-done.json" \
"${ORCH_BIN}" --db "${db_path}" --json wait \
--run "${run_id}" --for task_done --timeout-seconds 15
wait_done_pid="${LAST_BG_PID}"
sleep 0.2
run_json "${case_dir}/resume.json" \
"${INBOX_BIN}" --db "${db_path}" --json update \
--agent worker-a --thread "${thread_id}" \
--status in_progress --summary "Structured decision applied"
run_json "${case_dir}/done.json" \
"${INBOX_BIN}" --db "${db_path}" --json done \
--agent worker-a --thread "${thread_id}" \
--summary "Frontend complete" \
--body "Worker resumed after reading the structured leader decision."
wait_for_pid "${wait_done_pid}" "${case_slug}: wait task_done"
run_json "${case_dir}/reconcile.json" \
"${ORCH_BIN}" --db "${db_path}" --json reconcile --run "${run_id}"
run_json "${case_dir}/status.json" \
"${ORCH_BIN}" --db "${db_path}" --json status --run "${run_id}"
run_json "${case_dir}/show.json" \
"${INBOX_BIN}" --db "${db_path}" --json show --thread "${thread_id}"
json_check "${case_dir}/wait-task-blocked.json" '.data.woke == true and (.data.events | length) >= 1 and .data.events[0].type == "task_blocked"' "payload-answer flow woke on task_blocked"
json_check "${case_dir}/orch-blocked.json" '.data.blocked | length == 1 and .[0].task.task_id == "T1"' "blocked queue lists payload-answer task"
json_check "${case_dir}/answer.json" '.data.message.kind == "answer" and .data.message.payload_json.decision == "stdout" and .data.message.payload_json.source == "leader" and .data.message.payload_json.format == "structured"' "answer writes payload-json without body"
json_check "${case_dir}/wait-reply.json" '.data.woke == true and .data.message.kind == "answer" and .data.message.payload_json.decision == "stdout"' "wait-reply exposes structured answer payload"
json_check "${case_dir}/status.json" '.data.run.status == "done" and .data.tasks[0].status == "done"' "payload-answer flow run completes"
json_check "${case_dir}/show.json" 'any(.data.messages[]; .kind == "question" and .payload_json.question == "Use stdout or stderr for structured logs?")' "payload-answer question recorded"
json_check "${case_dir}/show.json" 'any(.data.messages[]; .kind == "answer" and .payload_json.decision == "stdout" and .payload_json.source == "leader" and .payload_json.format == "structured")' "payload-answer message preserved in history"
local duration_seconds
duration_seconds="$(( $(date +%s) - started_at ))"
write_result_json \
"${case_dir}" "${case_slug}" "${db_path}" "${run_id}" pass "${duration_seconds}" \
"$(join_json_array "${thread_id}")" \
"$(join_json_array)" \
"Direct CLI replay of answering a blocked task with payload-json only."
}
run_case_retry() {
local case_slug="leader-retries-failed-task-through-bundled-cli"
local run_id="run_blog_skill_retry_001"
local case_dir
case_dir="$(init_case_dir "${case_slug}")"
local db_path="${case_dir}/coord.db"
local started_at
started_at="$(date +%s)"
init_db "${db_path}"
run_json "${case_dir}/run.json" \
"${ORCH_BIN}" --db "${db_path}" --json run init \
--run "${run_id}" --goal "Validate retry behavior" \
--summary "Exercise failed attempt retry"
run_json "${case_dir}/task.json" \
"${ORCH_BIN}" --db "${db_path}" --json task add \
--run "${run_id}" --task T1 --title "Implement backend" \
--summary "Retry after a simulated failure" --default-to worker-a
run_json "${case_dir}/dispatch.json" \
"${ORCH_BIN}" --db "${db_path}" --json dispatch \
--run "${run_id}" --task T1 --execution-mode analysis --to worker-a \
--body "Initial attempt expected to fail for retry validation."
local thread_id_1
thread_id_1="$(json_get "${case_dir}/dispatch.json" '.data.attempt.thread_id')"
local wait_failed_pid
start_wait "${case_dir}/wait-task-failed.json" \
"${ORCH_BIN}" --db "${db_path}" --json wait \
--run "${run_id}" --for task_failed --timeout-seconds 15
wait_failed_pid="${LAST_BG_PID}"
sleep 0.2
run_json "${case_dir}/claim-1.json" \
"${INBOX_BIN}" --db "${db_path}" --json claim \
--agent worker-a --thread "${thread_id_1}"
run_json "${case_dir}/fail.json" \
"${INBOX_BIN}" --db "${db_path}" --json fail \
--agent worker-a --thread "${thread_id_1}" \
--summary "Build failed" --body "Simulated first-attempt failure."
wait_for_pid "${wait_failed_pid}" "${case_slug}: wait task_failed"
run_json "${case_dir}/reconcile-failed.json" \
"${ORCH_BIN}" --db "${db_path}" --json reconcile --run "${run_id}"
run_json "${case_dir}/retry.json" \
"${ORCH_BIN}" --db "${db_path}" --json retry \
--run "${run_id}" --task T1 --to worker-a \
--body "Retry after fixing the failure."
local thread_id_2
thread_id_2="$(json_get "${case_dir}/retry.json" '.data.attempt.thread_id')"
local wait_done_pid
start_wait "${case_dir}/wait-task-done.json" \
"${ORCH_BIN}" --db "${db_path}" --json wait \
--run "${run_id}" --for task_done --timeout-seconds 15
wait_done_pid="${LAST_BG_PID}"
sleep 0.2
run_json "${case_dir}/fetch-retry.json" \
"${INBOX_BIN}" --db "${db_path}" --json fetch \
--agent worker-a --status pending --limit 5
run_json "${case_dir}/claim-2.json" \
"${INBOX_BIN}" --db "${db_path}" --json claim \
--agent worker-a --thread "${thread_id_2}"
run_json "${case_dir}/done-2.json" \
"${INBOX_BIN}" --db "${db_path}" --json done \
--agent worker-a --thread "${thread_id_2}" \
--summary "Retry completed" --body "Second attempt succeeded."
wait_for_pid "${wait_done_pid}" "${case_slug}: wait task_done"
run_json "${case_dir}/reconcile-done.json" \
"${ORCH_BIN}" --db "${db_path}" --json reconcile --run "${run_id}"
run_json "${case_dir}/status.json" \
"${ORCH_BIN}" --db "${db_path}" --json status --run "${run_id}"
run_json "${case_dir}/show-1.json" \
"${INBOX_BIN}" --db "${db_path}" --json show --thread "${thread_id_1}"
run_json "${case_dir}/show-2.json" \
"${INBOX_BIN}" --db "${db_path}" --json show --thread "${thread_id_2}"
json_check "${case_dir}/wait-task-failed.json" '.data.woke == true and (.data.events | length) >= 1 and .data.events[0].type == "task_failed"' "wait woke on task_failed"
json_check "${case_dir}/retry.json" '.data.attempt.attempt_no == 2 and .data.task.status == "dispatched"' "retry creates second dispatched attempt"
json_check "${case_dir}/status.json" '.data.run.status == "done" and .data.tasks[0].status == "done"' "retry flow run completes"
json_check "${case_dir}/show-1.json" '.data.thread.status == "failed"' "first thread failed"
json_check "${case_dir}/show-2.json" '.data.thread.status == "done"' "second thread done"
if [ "${thread_id_1}" = "${thread_id_2}" ]; then
printf 'FAIL: retry reused thread ID %s\n' "${thread_id_1}" >&2
exit 1
fi
printf 'PASS: retry created distinct thread IDs\n'
local duration_seconds
duration_seconds="$(( $(date +%s) - started_at ))"
write_result_json \
"${case_dir}" "${case_slug}" "${db_path}" "${run_id}" pass "${duration_seconds}" \
"$(join_json_array "${thread_id_1}" "${thread_id_2}")" \
"$(join_json_array)" \
"Direct CLI replay of failed attempt reconciliation followed by retry."
}
run_case_reassign() {
local case_slug="leader-reassigns-blocked-task-through-bundled-cli"
local run_id="run_blog_skill_reassign_001"
local case_dir
case_dir="$(init_case_dir "${case_slug}")"
local db_path="${case_dir}/coord.db"
local started_at
started_at="$(date +%s)"
init_db "${db_path}"
run_json "${case_dir}/run.json" \
"${ORCH_BIN}" --db "${db_path}" --json run init \
--run "${run_id}" --goal "Validate reassign behavior" \
--summary "Exercise blocked-task reassignment"
run_json "${case_dir}/task.json" \
"${ORCH_BIN}" --db "${db_path}" --json task add \
--run "${run_id}" --task T1 --title "Implement backend" \
--summary "Reassign after worker-a blocks" --default-to worker-a
run_json "${case_dir}/dispatch.json" \
"${ORCH_BIN}" --db "${db_path}" --json dispatch \
--run "${run_id}" --task T1 --execution-mode analysis --to worker-a \
--body "Initial attempt expected to be reassigned."
local thread_id_1
thread_id_1="$(json_get "${case_dir}/dispatch.json" '.data.attempt.thread_id')"
local wait_blocked_pid
start_wait "${case_dir}/wait-task-blocked.json" \
"${ORCH_BIN}" --db "${db_path}" --json wait \
--run "${run_id}" --for task_blocked --timeout-seconds 15
wait_blocked_pid="${LAST_BG_PID}"
sleep 0.2
run_json "${case_dir}/claim-1.json" \
"${INBOX_BIN}" --db "${db_path}" --json claim \
--agent worker-a --thread "${thread_id_1}"
run_json "${case_dir}/blocked.json" \
"${INBOX_BIN}" --db "${db_path}" --json update \
--agent worker-a --thread "${thread_id_1}" \
--status blocked --summary "Need product decision" \
--payload-json '{"question":"Proceed with v1 scope?"}'
wait_for_pid "${wait_blocked_pid}" "${case_slug}: wait task_blocked"
run_json "${case_dir}/reconcile-blocked.json" \
"${ORCH_BIN}" --db "${db_path}" --json reconcile --run "${run_id}"
run_json "${case_dir}/orch-blocked.json" \
"${ORCH_BIN}" --db "${db_path}" --json blocked --run "${run_id}"
run_json "${case_dir}/reassign.json" \
"${ORCH_BIN}" --db "${db_path}" --json reassign \
--run "${run_id}" --task T1 --to worker-b \
--reason "Try another worker with clearer ownership."
local thread_id_2
thread_id_2="$(json_get "${case_dir}/reassign.json" '.data.attempt.thread_id')"
local wait_done_pid
start_wait "${case_dir}/wait-task-done.json" \
"${ORCH_BIN}" --db "${db_path}" --json wait \
--run "${run_id}" --for task_done --timeout-seconds 15
wait_done_pid="${LAST_BG_PID}"
sleep 0.2
run_json "${case_dir}/fetch-worker-b.json" \
"${INBOX_BIN}" --db "${db_path}" --json fetch \
--agent worker-b --status pending --limit 5
run_json "${case_dir}/claim-2.json" \
"${INBOX_BIN}" --db "${db_path}" --json claim \
--agent worker-b --thread "${thread_id_2}"
run_json "${case_dir}/done-2.json" \
"${INBOX_BIN}" --db "${db_path}" --json done \
--agent worker-b --thread "${thread_id_2}" \
--summary "Reassigned work complete" --body "Worker-b completed the reassigned attempt."
wait_for_pid "${wait_done_pid}" "${case_slug}: wait task_done"
run_json "${case_dir}/reconcile-done.json" \
"${ORCH_BIN}" --db "${db_path}" --json reconcile --run "${run_id}"
run_json "${case_dir}/status.json" \
"${ORCH_BIN}" --db "${db_path}" --json status --run "${run_id}"
run_json "${case_dir}/show-1.json" \
"${INBOX_BIN}" --db "${db_path}" --json show --thread "${thread_id_1}"
run_json "${case_dir}/show-2.json" \
"${INBOX_BIN}" --db "${db_path}" --json show --thread "${thread_id_2}"
json_check "${case_dir}/wait-task-blocked.json" '.data.woke == true and (.data.events | length) >= 1 and .data.events[0].type == "task_blocked"' "wait woke on blocked event for reassign"
json_check "${case_dir}/orch-blocked.json" '.data.blocked | length == 1 and .[0].task.task_id == "T1"' "blocked queue lists reassigned task"
json_check "${case_dir}/reassign.json" '.data.attempt.attempt_no == 2 and .data.attempt.assigned_to == "worker-b"' "reassign creates attempt 2 for worker-b"
json_check "${case_dir}/status.json" '.data.run.status == "done" and .data.tasks[0].status == "done"' "reassign flow run completes"
json_check "${case_dir}/show-1.json" '.data.thread.status == "cancelled"' "original thread cancelled"
json_check "${case_dir}/show-2.json" '.data.thread.status == "done"' "new thread done"
json_check "${case_dir}/show-1.json" 'any(.data.messages[]; .kind == "question" and .payload_json.question == "Proceed with v1 scope?")' "original blocked question preserved"
if [ "${thread_id_1}" = "${thread_id_2}" ]; then
printf 'FAIL: reassign reused thread ID %s\n' "${thread_id_1}" >&2
exit 1
fi
printf 'PASS: reassign created distinct thread IDs\n'
local duration_seconds
duration_seconds="$(( $(date +%s) - started_at ))"
write_result_json \
"${case_dir}" "${case_slug}" "${db_path}" "${run_id}" pass "${duration_seconds}" \
"$(join_json_array "${thread_id_1}" "${thread_id_2}")" \
"$(join_json_array)" \
"Direct CLI replay of blocked-task reassignment from worker-a to worker-b."
}
main() {
while [ "$#" -gt 0 ]; do
case "$1" in
--output-root)
OUTPUT_ROOT="$2"
shift 2
;;
-h|--help)
usage
exit 0
;;
*)
printf 'unknown argument: %s\n' "$1" >&2
usage >&2
exit 1
;;
esac
done
require_command jq
require_command git
require_command mktemp
if [ ! -x "${ORCH_BIN}" ]; then
printf 'orch skill binary is not executable: %s\n' "${ORCH_BIN}" >&2
exit 1
fi
if [ ! -x "${INBOX_BIN}" ]; then
printf 'inbox skill binary is not executable: %s\n' "${INBOX_BIN}" >&2
exit 1
fi
if [ -z "${OUTPUT_ROOT}" ]; then
OUTPUT_ROOT="$(mktemp -d "${TMPDIR:-/tmp}/orch-skill-forward.XXXXXX")"
else
mkdir -p "${OUTPUT_ROOT}"
fi
run_case_happy_path
run_case_blocked_answer
run_case_strict_worktree_cleanup
run_case_dependency_ready_dispatch
run_case_cancel_active_task
run_case_payload_only_answer
run_case_retry
run_case_reassign
printf '\nResults written to %s\n' "${OUTPUT_ROOT}"
printf 'case\tresult\n'
print_case_summary "leader-run-dispatch-reconcile-through-bundled-cli" "${OUTPUT_ROOT}/leader-run-dispatch-reconcile-through-bundled-cli"
print_case_summary "leader-blocked-answer-resume-through-bundled-cli" "${OUTPUT_ROOT}/leader-blocked-answer-resume-through-bundled-cli"
print_case_summary "strict-worktree-dispatch-to-cleanup-through-bundled-cli" "${OUTPUT_ROOT}/strict-worktree-dispatch-to-cleanup-through-bundled-cli"
print_case_summary "leader-dispatches-dependent-task-after-prerequisite-through-bundled-cli" "${OUTPUT_ROOT}/leader-dispatches-dependent-task-after-prerequisite-through-bundled-cli"
print_case_summary "leader-cancels-active-task-through-bundled-cli" "${OUTPUT_ROOT}/leader-cancels-active-task-through-bundled-cli"
print_case_summary "leader-answers-blocked-task-with-payload-json-through-bundled-cli" "${OUTPUT_ROOT}/leader-answers-blocked-task-with-payload-json-through-bundled-cli"
print_case_summary "leader-retries-failed-task-through-bundled-cli" "${OUTPUT_ROOT}/leader-retries-failed-task-through-bundled-cli"
print_case_summary "leader-reassigns-blocked-task-through-bundled-cli" "${OUTPUT_ROOT}/leader-reassigns-blocked-task-through-bundled-cli"
}
main "$@"