Add orch skill forward test evidence

2026-03-19 18:36:31 +08:00
parent d17b5ebfbd
commit e9cbb15c2d
10 changed files with 1036 additions and 0 deletions
@@ -27,6 +27,7 @@ As of now:
 - an inbox skill forward-test plan directory now exists under `docs/tests/inbox-skill/`, with a shared execution template and multiple scenario cases
 - an orch skill forward-test plan directory now exists under `docs/tests/orch-skill/`, with a shared execution contract and initial leader-side workflow scenarios
 - a repo-local replay runner now exists at `scripts/run_orch_skill_forward_tests.sh`, and the five `docs/tests/orch-skill/` cases now include recorded example runs from a bundled-CLI replay captured on `2026-03-19`
+- the five `docs/tests/orch-skill/` cases now also include recorded real subagent-forward runs captured on `2026-03-19`, with spawned leader and worker agents using the packaged `skills/orch/` and `skills/inbox/` bundles
 - a council-review skill forward-test plan directory now exists under `docs/tests/council-review-skill/`, with a shared execution contract and nine council workflow scenarios covering end-to-end flow, unanimous-only defaults, timeout/before-tally errors, explicit minority reporting, invalid report filters, strict tally semantics, malformed reviewer JSON, and target-file inputs
 - an execution-roadmap workflow now exists under `docs/roadmaps/active/` and `docs/roadmaps/archive/` for agent-level work traces and completion archives
 - a repo-local `scripts/package_skill_clis.sh` packaging flow now builds bundled skill CLI assets for `inbox`, `orch`, and `council-review`
@@ -0,0 +1,66 @@
+# Title
+
+Direct Replay For Orch Skill Cases
+
+## Status
+
+- `completed`
+
+## Owner
+
+- codex
+
+## Started At
+
+- `2026-03-19`
+
+## Goal
+
+- Execute the documented `docs/tests/orch-skill/` scenarios against the bundled `skills/orch/assets/orch` and `skills/inbox/assets/inbox` binaries, capture concrete evidence, and sync the repo docs with the observed results.
+
+## Scope
+
+- add a reusable local runner for the five documented orch-skill scenarios
+- run the scenarios and capture per-case evidence
+- update the orch-skill docs with recorded runs and note the execution mode
+- update the implementation roadmap to reflect the new replay coverage
+
+## Checklist
+
+- [x] Review the orch-skill case docs and bundled CLI surfaces.
+- [x] Add a reusable direct replay runner for the five orch-skill scenarios.
+- [x] Execute the runner and collect evidence for all five cases.
+- [x] Update the orch-skill docs with recorded example runs and execution notes.
+- [x] Update the implementation roadmap and archive this execution roadmap.
+
+## Files
+
+- `scripts/run_orch_skill_forward_tests.sh`
+- `docs/tests/orch-skill/README.md`
+- `docs/tests/orch-skill/leader-run-dispatch-reconcile-through-bundled-cli.md`
+- `docs/tests/orch-skill/leader-blocked-answer-resume-through-bundled-cli.md`
+- `docs/tests/orch-skill/strict-worktree-dispatch-to-cleanup-through-bundled-cli.md`
+- `docs/tests/orch-skill/leader-retries-failed-task-through-bundled-cli.md`
+- `docs/tests/orch-skill/leader-reassigns-blocked-task-through-bundled-cli.md`
+- `docs/implementation-roadmap.md`
+- `docs/roadmaps/archive/orch-skill-direct-replay.md`
+
+## Decisions
+
+- Use direct bundled-CLI replay instead of spawning Codex role agents in this turn, because the current session does not permit sub-agent delegation unless the user explicitly asks for it.
+- Keep the replay runner repo-local so the same scenarios can be rerun later without reconstructing the command flow by hand.
+
+## Blockers
+
+- none
+
+## Next Step
+
+- rerun `scripts/run_orch_skill_forward_tests.sh` when the bundled skill binaries or orch-skill case docs change, and add true multi-agent forward coverage later if explicit sub-agent execution is needed
+
+## Completion Summary
+
+- Added `scripts/run_orch_skill_forward_tests.sh` as a reusable direct bundled-CLI replay runner for the five documented orch-skill scenarios.
+- Executed the runner on `2026-03-19`; all five scenarios passed and produced per-case JSON evidence under a temporary output root.
+- Updated `docs/tests/orch-skill/README.md` plus all five case files with recorded example runs and explicit execution-mode notes.
+- Updated `docs/implementation-roadmap.md` to record the new replay runner and captured orch-skill execution evidence.
@@ -0,0 +1,67 @@
+# Title
+
+Real Subagent Forward Tests For Orch Skill
+
+## Status
+
+- `completed`
+
+## Owner
+
+- codex
+
+## Started At
+
+- `2026-03-19`
+
+## Goal
+
+- Execute the documented `docs/tests/orch-skill/` scenarios using real spawned role agents with injected `skills/orch/` and `skills/inbox/`, then record concrete pass/fail evidence and sync the repository docs.
+
+## Scope
+
+- validate subagent skill injection for project-local orch and inbox skills
+- run the five documented orch-skill forward cases with real leader and worker subagents
+- collect main-thread validation evidence and agent summaries
+- update the orch-skill docs and implementation roadmap with the real forward-test results
+
+## Checklist
+
+- [x] Re-read the orch-skill shared execution contract and worker skill constraints.
+- [x] Validate project-local skill injection with a small spawned-agent probe.
+- [x] Execute the five orch-skill cases with real spawned role agents and collect evidence.
+- [x] Update the orch-skill docs and implementation roadmap with the real forward-test results.
+- [x] Archive this execution roadmap with a completion summary.
+
+## Files
+
+- `docs/tests/orch-skill/README.md`
+- `docs/tests/orch-skill/leader-run-dispatch-reconcile-through-bundled-cli.md`
+- `docs/tests/orch-skill/leader-blocked-answer-resume-through-bundled-cli.md`
+- `docs/tests/orch-skill/strict-worktree-dispatch-to-cleanup-through-bundled-cli.md`
+- `docs/tests/orch-skill/leader-retries-failed-task-through-bundled-cli.md`
+- `docs/tests/orch-skill/leader-reassigns-blocked-task-through-bundled-cli.md`
+- `docs/implementation-roadmap.md`
+- `docs/roadmaps/archive/orch-skill-real-forward-test.md`
+
+## Decisions
+
+- Use real spawned role agents per case instead of the direct replay runner, because the user explicitly asked for true tests with subagents.
+- Keep the main thread responsible for DB setup, fixture creation, and independent validation so the final judgment does not rely only on role-agent self-reporting.
+- Fall back from `fork_context: true` to `fork_context: false` for the real case runs after the first wider-context attempt stalled and mis-executed the worker-side contract in this repo.
+- For the longer `retry` and `reassign` cases, keep one leader agent active across staged prompts instead of one long monolithic prompt, because staged execution proved more reliable while still preserving a real agent-owned `orch` flow.
+
+## Blockers
+
+- none
+
+## Next Step
+
+- rerun the same five cases when the packaged skill binaries or case docs change, and consider adding the same real subagent coverage for `council-review` if that surface needs parity
+
+## Completion Summary
+
+- Verified both project-local skill bundles with spawned-agent help-command probes before the real runs.
+- Collected successful real subagent evidence for all five orch-skill cases under `/tmp/orch-skill-subagents.J1XWgs`.
+- Main-thread validation confirmed all five final successful runs reached the expected `orch` and `inbox` states.
+- Updated `docs/tests/orch-skill/README.md`, all five case files, and `docs/implementation-roadmap.md` to record the new real forward-test coverage.
@@ -122,6 +122,26 @@ Use these defaults unless a case file explicitly overrides them:
 - keep the temporary DB, repo fixture, and working directory on failure for debugging
 - cleanup the temporary working directory on success only if the caller does not need replay artifacts

+## Direct CLI Replay
+
+The repository also includes a reusable direct replay runner at `scripts/run_orch_skill_forward_tests.sh`.
+
+This runner executes the bundled `skills/orch/assets/orch` and `skills/inbox/assets/inbox` binaries against temporary SQLite DBs and Git fixtures without spawning Codex role agents.
+
+Use it to validate packaged CLI behavior and record concrete evidence quickly, but do not treat it as a full replacement for the real subagent-forward model described above.
+
+The case files in this directory now include recorded example runs captured through that direct replay path on `2026-03-19`.
+
+## Real Subagent Forward Runs
+
+The five cases in this directory were also executed with real spawned role agents on `2026-03-19`.
+
+That run used injected project-local `skills/orch/` and `skills/inbox/` bundles with a narrow-context fallback (`fork_context: false`) after an earlier wider-context attempt proved unreliable for this repo.
+
+The successful evidence root for those runs was `/tmp/orch-skill-subagents.J1XWgs`.
+
+Some longer cases used staged leader progression while keeping the same leader agent active across phases so the run still exercised real agent-driven `orch` control flow instead of a main-thread direct replay.
+
 ## Per-Case Template

 Each case file should use this structure:
@@ -87,3 +87,30 @@ INBOX_SKILL_PATH/assets/inbox --db TMPDIR/coord.db --json show --thread THREAD_I

 - use the default cleanup policy from [README.md](./README.md)
 - if the run fails, retain `TMPDIR` and `coord.db` for replay and manual inspection
+
+## Recorded Example Run
+
+- recorded on: `2026-03-19`
+- execution mode: `direct_cli_replay` via `scripts/run_orch_skill_forward_tests.sh`
+- result: `pass`
+- observed run id: `run_blog_skill_002`
+- observed thread id: `thr_42ce634f273745e9b95badc14ce52708`
+- evidence summary:
+- `orch wait --for task_blocked` woke on the worker question, and `inbox wait-reply` later woke on the leader answer
+- final `orch status --run run_blog_skill_002 --json` returned `run.status == "done"` and `tasks[0].status == "done"`
+- final `inbox show --thread thr_42ce634f273745e9b95badc14ce52708 --json` contained `question`, `answer`, and `result` messages
+- the recorded `question` payload was `Should logging go to stdout or stderr?`, and the recorded `answer` body was `Use stdout for MVP.`
+- note: this recorded run exercised the packaged binaries directly in a temporary DB and did not spawn separate Codex role agents
+
+## Recorded Real Forward Run
+
+- recorded on: `2026-03-19`
+- execution mode: `real_subagent_forward_test`
+- result: `pass`
+- evidence root: `/tmp/orch-skill-subagents.J1XWgs/leader-blocked-answer-resume-through-bundled-cli`
+- observed run id: `run_blog_skill_002`
+- observed thread id: `thr_fd11536a0b2f4c668f6e78c38090816e`
+- evidence summary:
+- a real leader agent using `skills/orch/` completed `wait --for task_blocked`, `blocked`, `answer`, `wait --for task_done`, `reconcile`, and `status`
+- a real worker agent using `skills/inbox/` completed `claim`, `update --status in_progress`, `update --status blocked`, `wait-reply`, resume `update`, and `done`
+- main-thread validation confirmed `run.status == "done"`, `task.status == "done"`, the blocked question payload `Should logging go to stdout or stderr?`, and the answer body `Use stdout for MVP.`
@@ -96,3 +96,34 @@ INBOX_SKILL_PATH/assets/inbox --db TMPDIR/coord.db --json show --thread THREAD_I

 - use the default cleanup policy from [README.md](./README.md)
 - if the run fails, retain `TMPDIR` and `coord.db` for replay and manual inspection
+
+## Recorded Example Run
+
+- recorded on: `2026-03-19`
+- execution mode: `direct_cli_replay` via `scripts/run_orch_skill_forward_tests.sh`
+- result: `pass`
+- observed run id: `run_blog_skill_reassign_001`
+- observed original thread id: `thr_0a61240412134de3b3d9ab219b6c8f19`
+- observed reassigned thread id: `thr_12fbcf6d89d948548306198d013d77a5`
+- evidence summary:
+- `orch wait --for task_blocked` woke after worker-a posted a blocked question with payload `Proceed with v1 scope?`
+- `orch reassign --run run_blog_skill_reassign_001 --task T1 --to worker-b --json` returned `attempt_no == 2` and assigned the new attempt to `worker-b`
+- final `inbox show` on the original thread returned `thread.status == "cancelled"` and preserved the blocked `question` message
+- final `inbox show` on the reassigned thread returned `thread.status == "done"`
+- final `orch status --run run_blog_skill_reassign_001 --json` returned `run.status == "done"` and `tasks[0].status == "done"`
+- note: this recorded run exercised the packaged binaries directly in a temporary DB and did not spawn separate Codex role agents
+
+## Recorded Real Forward Run
+
+- recorded on: `2026-03-19`
+- execution mode: `real_subagent_forward_test`
+- result: `pass`
+- evidence root: `/tmp/orch-skill-subagents.J1XWgs/leader-reassigns-blocked-task-through-bundled-cli-phased`
+- observed run id: `run_blog_skill_reassign_001`
+- observed original thread id: `thr_7d43af5bc1f7467da98a39adb0de5808`
+- observed reassigned thread id: `thr_eba253db8965423b855d0c784a29702c`
+- evidence summary:
+- the same real leader agent using `skills/orch/` completed the case in three phases: initial `run/task/dispatch`, then `wait --for task_blocked` plus `reassign`, then final `wait --for task_done` plus `status`
+- a real `worker-a` agent using `skills/inbox/` claimed the original thread and posted the blocked question `Proceed with v1 scope?`
+- a real `worker-b` agent using `skills/inbox/` claimed the reassigned thread and completed it
+- main-thread validation confirmed the original thread finished `cancelled`, the reassigned thread finished `done`, and the original blocked question remained visible in thread history
@@ -89,3 +89,33 @@ INBOX_SKILL_PATH/assets/inbox --db TMPDIR/coord.db --json show --thread THREAD_I

 - use the default cleanup policy from [README.md](./README.md)
 - if the run fails, retain `TMPDIR` and `coord.db` for replay and manual inspection
+
+## Recorded Example Run
+
+- recorded on: `2026-03-19`
+- execution mode: `direct_cli_replay` via `scripts/run_orch_skill_forward_tests.sh`
+- result: `pass`
+- observed run id: `run_blog_skill_retry_001`
+- observed first thread id: `thr_8dbf2d2e46d7469891cc1ef604da476f`
+- observed second thread id: `thr_bdd86f4fe08e4ebfb39b8151ac41a3bb`
+- evidence summary:
+- `orch wait --for task_failed` woke after the first worker-owned thread failed
+- `orch retry --run run_blog_skill_retry_001 --task T1 --json` returned `attempt_no == 2` with a distinct replacement thread for the same worker
+- final `inbox show` on the first thread returned `thread.status == "failed"`
+- final `inbox show` on the second thread returned `thread.status == "done"`
+- final `orch status --run run_blog_skill_retry_001 --json` returned `run.status == "done"` and `tasks[0].status == "done"`
+- note: this recorded run exercised the packaged binaries directly in a temporary DB and did not spawn separate Codex role agents
+
+## Recorded Real Forward Run
+
+- recorded on: `2026-03-19`
+- execution mode: `real_subagent_forward_test`
+- result: `pass`
+- evidence root: `/tmp/orch-skill-subagents.J1XWgs/leader-retries-failed-task-through-bundled-cli-phased`
+- observed run id: `run_blog_skill_retry_001`
+- observed first thread id: `thr_1e22121642294b56aae351ddec5180d1`
+- observed second thread id: `thr_f2ab1f1899964007b2447796204e1928`
+- evidence summary:
+- the same real leader agent using `skills/orch/` completed the case in three phases: initial `run/task/dispatch`, then `wait --for task_failed` plus `retry`, then final `wait --for task_done` plus `status`
+- a real worker agent using `skills/inbox/` failed the first thread, polled for the retried pending thread, then claimed and completed the second thread
+- main-thread validation confirmed the two thread ids were distinct, the first thread finished `failed`, the second thread finished `done`, and the run/task both finished `done`
@@ -88,3 +88,29 @@ INBOX_SKILL_PATH/assets/inbox --db TMPDIR/coord.db --json show --thread THREAD_I

 - use the default cleanup policy from [README.md](./README.md)
 - if the run fails, retain `TMPDIR` and `coord.db` for replay and manual inspection
+
+## Recorded Example Run
+
+- recorded on: `2026-03-19`
+- execution mode: `direct_cli_replay` via `scripts/run_orch_skill_forward_tests.sh`
+- result: `pass`
+- observed run id: `run_blog_skill_001`
+- observed thread id: `thr_eced1b8cb1254065a7cd3aaff6dc0bcb`
+- evidence summary:
+- final `orch status --run run_blog_skill_001 --json` returned `run.status == "done"` with a single task `T1` in state `done`
+- final `inbox show --thread thr_eced1b8cb1254065a7cd3aaff6dc0bcb --json` returned thread state `done` and message kinds `task`, `progress`, and `result`
+- the replay also observed `orch wait --for task_done` wake successfully before the final reconcile
+- note: this recorded run exercised the packaged binaries directly in a temporary DB and did not spawn separate Codex role agents
+
+## Recorded Real Forward Run
+
+- recorded on: `2026-03-19`
+- execution mode: `real_subagent_forward_test`
+- result: `pass`
+- evidence root: `/tmp/orch-skill-subagents.J1XWgs/leader-run-dispatch-reconcile-through-bundled-cli`
+- observed run id: `run_blog_skill_001`
+- observed thread id: `thr_7c64e75bbcce4143a7fc425242f7e7d3`
+- evidence summary:
+- a real leader agent using `skills/orch/` completed `run init`, `task add`, `dispatch`, `wait`, `reconcile`, and `status`
+- a real worker agent using `skills/inbox/` completed `fetch`, `claim`, `update --status in_progress`, and `done`
+- main-thread validation confirmed `status.data.run.status == "done"`, `status.data.tasks[0].status == "done"`, and thread history kinds `task`, `progress`, and `result`
@@ -88,3 +88,32 @@ test ! -d WORKTREE_PATH

 - use the default cleanup policy from [README.md](./README.md)
 - if the run fails, retain `TMPDIR`, `coord.db`, and the Git repo fixture for replay and manual inspection
+
+## Recorded Example Run
+
+- recorded on: `2026-03-19`
+- execution mode: `direct_cli_replay` via `scripts/run_orch_skill_forward_tests.sh`
+- result: `pass`
+- observed run id: `run_blog_skill_worktree_001`
+- observed thread id: `thr_5743259fdccb41f9bb33dce0040b27a5`
+- observed worktree suffix: `.orch/worktrees/run-blog-skill-worktree-001/T1/attempt-1`
+- evidence summary:
+- `orch dispatch --strict-worktree` returned `base_ref == "HEAD"`, a concrete `base_commit`, branch `orch/run-blog-skill-worktree-001/T1/attempt-1`, and a non-empty `worktree_path`
+- the task payload stored on the worker thread exposed the same `worktree_path`
+- final `orch status --run run_blog_skill_worktree_001 --json` returned `run.status == "done"` and `tasks[0].status == "done"`
+- final `orch cleanup --run run_blog_skill_worktree_001 --task T1 --json` returned one cleaned attempt and the worktree directory no longer existed afterward
+- note: this recorded run exercised the packaged binaries directly in a temporary DB and Git fixture and did not spawn separate Codex role agents
+
+## Recorded Real Forward Run
+
+- recorded on: `2026-03-19`
+- execution mode: `real_subagent_forward_test`
+- result: `pass`
+- evidence root: `/tmp/orch-skill-subagents.J1XWgs/strict-worktree-dispatch-to-cleanup-through-bundled-cli`
+- observed run id: `run_blog_skill_worktree_001`
+- observed thread id: `thr_089527cd07f74b52a524ba07ed74c2e4`
+- observed worktree path: `/private/tmp/orch-skill-subagents.J1XWgs/strict-worktree-dispatch-to-cleanup-through-bundled-cli/repo/.orch/worktrees/run-blog-skill-worktree-001/T1/attempt-1`
+- evidence summary:
+- a real leader agent using `skills/orch/` completed strict `dispatch`, `wait`, `reconcile`, `cleanup`, and `status`
+- a real worker agent using `skills/inbox/` claimed the thread and finished it with `done`
+- main-thread validation confirmed that the task payload did include the same `worktree_path` even though the worker agent summary failed to notice it, and also confirmed the worktree directory no longer existed after cleanup
@@ -0,0 +1,739 @@
+#!/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 "${run_id}" --task T1 --to worker-a \
+    --body "Implement retry handling for the HTTP client."
+
+  local thread_id
+  thread_id="$(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 --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 strict 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 \
+    --repo-path "${repo_path}" --workspace-root .orch/worktrees --strict-worktree \
+    --body "Implement inside isolated worktree."
+
+  local thread_id
+  local worktree_path
+  thread_id="$(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 strict worktree dispatch, completion, and cleanup."
+}
+
+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 "${run_id}" --task T1 --to worker-a \
+    --body "Initial attempt expected to fail for retry validation."
+
+  local thread_id_1
+  thread_id_1="$(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 "${run_id}" --task T1 --to worker-a \
+    --body "Initial attempt expected to be reassigned."
+
+  local thread_id_1
+  thread_id_1="$(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 "${OUTPUT_ROOT}"
+  fi
+
+  run_case_happy_path
+  run_case_blocked_answer
+  run_case_strict_worktree_cleanup
+  run_case_retry
+  run_case_reassign
+
+  printf '\nResults written to %s\n' "${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" "${OUTPUT_ROOT}/strict-worktree-dispatch-to-cleanup-through-bundled-cli"
+  print_case_summary "leader-retries-failed-task-through-bundled-cli" "${OUTPUT_ROOT}/leader-retries-failed-task-through-bundled-cli"
+  print_case_summary "leader-reassigns-blocked-task-through-bundled-cli" "${OUTPUT_ROOT}/leader-reassigns-blocked-task-through-bundled-cli"
+
+}
+
+main "$@"