From 6ec263ae192591eb04ec0c51080823ea5c016105 Mon Sep 17 00:00:00 2001
From: Michael Sitarzewski <msitarzewski@users.noreply.github.com>
Date: Wed, 2 Sep 2026 22:26:42 -0500
Subject: [PATCH] Reapply "test(install): add a regression suite for install.sh
 + CI on Linux and macOS (#772)" (#827)

This reverts commit 4bab3cf4a222fc51717ba884c2f91a350cc57187.
---
 .github/workflows/test-install.yml |  30 +++
 CONTRIBUTING.md                    |   5 +
 scripts/test-install.sh            | 302 +++++++++++++++++++++++++++++
 3 files changed, 337 insertions(+)
 create mode 100644 .github/workflows/test-install.yml
 create mode 100755 scripts/test-install.sh

diff --git a/.github/workflows/test-install.yml b/.github/workflows/test-install.yml
new file mode 100644
index 00000000..4318ac30
--- /dev/null
+++ b/.github/workflows/test-install.yml
@@ -0,0 +1,30 @@
+name: Test Installer
+
+# No path filter on purpose: the installer's contract can break from the other
+# side too — a renamed division, a file that loses its frontmatter, a change to
+# lib.sh — so these run on every PR.
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+jobs:
+  test-install:
+    name: install.sh behavior (${{ matrix.os }})
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        # macOS ships bash 3.2, Linux ships bash 5 — the scripts must pass on both.
+        os: [ubuntu-latest, macos-latest]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Shell syntax
+        run: |
+          for f in scripts/*.sh; do bash -n "$f"; done
+
+      - name: Run installer tests
+        run: |
+          chmod +x scripts/test-install.sh scripts/install.sh
+          ./scripts/test-install.sh
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index fbecb4cf..d136a503 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -240,6 +240,11 @@ Want agency-agents to install into a new tool (a CLI, editor, or agent runtime)?
 4. **`.gitignore`** — add a rule for your tool's generated output under `integrations/<tool>/`. **This step is required and easy to miss.** Converted agent/skill files are generated locally by `convert.sh` and are **never committed** (see "Things we'll always close" below) — only `integrations/<tool>/README.md` is tracked. Match an existing per-tool entry.
 5. **`integrations/<tool>/README.md`** — a short doc for the integration (every tool has one; it's the only committed file in the tool's directory).
 6. **Run `./scripts/check-tools.sh`** — it must pass. It cross-checks `tools.json` against `install.sh` and `convert.sh` and flags anything missing.
+7. **Run `./scripts/test-install.sh`** — it must pass. It installs into throwaway
+   sandboxes (never your real `$HOME`) and pins the installer's observable
+   contract: where files land, that `--path` beats the tool's env var, that
+   `--division` / `--agent` / `--agents-file` filter, that `--dry-run` writes
+   nothing, and that paths with spaces survive. CI runs it on Linux and macOS.
 
 If your PR commits the converted output (the generated `integrations/<tool>/*` files), CI and review will ask you to remove it and add the `.gitignore` rule instead.
 
diff --git a/scripts/test-install.sh b/scripts/test-install.sh
new file mode 100755
index 00000000..2be8448e
--- /dev/null
+++ b/scripts/test-install.sh
@@ -0,0 +1,302 @@
+#!/usr/bin/env bash
+#
+# test-install.sh — regression tests for scripts/install.sh.
+#
+# install.sh is the largest script in the repo and every install bug so far has
+# been a silent one: agents land in the wrong directory, a path with a space is
+# split into two, a filter installs everything. These tests pin the observable
+# contract — where files land and how many — so those regressions fail loudly.
+#
+# Design constraints (same as the rest of scripts/):
+#   * bash 3.2 + BSD userland, no jq, no GNU-only flags.
+#   * Never touches the real $HOME. Every case runs with HOME set to a fresh
+#     sandbox, so a broken default path writes into the sandbox, not your config.
+#   * Only exercises the two source tools (claude-code, copilot) so no case
+#     depends on convert.sh output being present or fresh.
+#
+# Usage: ./scripts/test-install.sh [-v]
+#   -v  echo the installer's own output for failing cases
+
+set -uo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+INSTALL="$SCRIPT_DIR/install.sh"
+# shellcheck source=scripts/lib.sh
+. "$SCRIPT_DIR/lib.sh"
+
+VERBOSE=false
+[[ "${1:-}" == "-v" ]] && VERBOSE=true
+
+passed=0
+failed=0
+xfailed=0
+SANDBOX_ROOT="$(mktemp -d "${TMPDIR:-/tmp}/agency-install-tests.XXXXXX")"
+trap 'rm -rf "$SANDBOX_ROOT"' EXIT
+
+pass() { printf '  ok   %s\n' "$1"; passed=$((passed + 1)); }
+fail() {
+  printf '  FAIL %s\n' "$1"
+  [[ -n "${2:-}" ]] && printf '       %s\n' "$2"
+  failed=$((failed + 1))
+}
+
+# assert_eq <expected> <actual> <label>
+assert_eq() {
+  if [[ "$1" == "$2" ]]; then pass "$3"; else fail "$3" "expected '$1', got '$2'"; fi
+}
+
+# xfail_eq <expected> <actual> <label> <tracking> — a case that is known to fail
+# until a specific fix lands. It never turns the suite red: a mismatch is the
+# documented status quo today, and a match means the fix landed and the case
+# should be promoted to a plain assert_eq (one-word edit).
+xfail_eq() {
+  if [[ "$1" == "$2" ]]; then
+    pass "$3"
+    printf '       ^ %s appears to have landed — promote this case to assert_eq\n' "$4"
+  else
+    printf '  xfail %s\n' "$3"
+    printf '       expected '\''%s'\'', got '\''%s'\'' — fixed by %s\n' "$1" "$2" "$4"
+    xfailed=$((xfailed + 1))
+  fi
+}
+
+# sandbox <name> — fresh HOME for one case; echoes its path.
+sandbox() {
+  local d="$SANDBOX_ROOT/$1"
+  rm -rf "$d"; mkdir -p "$d"
+  printf '%s' "$d"
+}
+
+# run_install <home> [args...] — run the installer with an isolated HOME.
+# Captures stdout+stderr in RUN_OUT and the exit status in RUN_STATUS.
+run_install() {
+  local home="$1"; shift
+  RUN_OUT="$(HOME="$home" "$INSTALL" --no-interactive "$@" 2>&1)"
+  RUN_STATUS=$?
+  $VERBOSE && printf '%s\n' "$RUN_OUT"
+  return 0
+}
+
+# count_md <dir> — .md files directly in <dir> (0 when the dir does not exist).
+count_md() {
+  [[ -d "$1" ]] || { printf '0'; return; }
+  find "$1" -maxdepth 1 -name '*.md' -type f | wc -l | tr -d ' '
+}
+
+# ---------------------------------------------------------------------------
+# Expected values, derived from the repo the same way install.sh derives them
+# (divisions.json -> directories -> files with frontmatter), never hardcoded.
+# ---------------------------------------------------------------------------
+divisions_from_json() {
+  awk '/"divisions"[[:space:]]*:[[:space:]]*\{/{f=1; next} f' "$REPO_ROOT/divisions.json" \
+    | grep -oE '^[[:space:]]*"[a-z0-9-]+"[[:space:]]*:' \
+    | sed -E 's/[[:space:]]*"([a-z0-9-]+)"[[:space:]]*:/\1/'
+}
+
+ALL_DIVISIONS=()
+while IFS= read -r _d; do [[ -n "$_d" ]] && ALL_DIVISIONS+=("$_d"); done < <(divisions_from_json)
+
+agent_files_in() {
+  local d="$REPO_ROOT/$1" f
+  [[ -d "$d" ]] || return 0
+  while IFS= read -r f; do is_agent_file "$f" && printf '%s\n' "$f"; done \
+    < <(find "$d" -name "*.md" -type f | sort)
+}
+
+TOTAL_AGENTS=0
+for _div in "${ALL_DIVISIONS[@]}"; do
+  TOTAL_AGENTS=$(( TOTAL_AGENTS + $(agent_files_in "$_div" | wc -l | tr -d ' ') ))
+done
+ENG_AGENTS=$(agent_files_in engineering | wc -l | tr -d ' ')
+# `awk NR==1` rather than `head -1`: head exits at the first line and the
+# still-writing function dies on SIGPIPE, which prints a spurious error.
+FIRST_ENG_FILE="$(agent_files_in engineering | awk 'NR==1')"
+FIRST_ENG_SLUG="$(agent_slug "$FIRST_ENG_FILE")"
+
+echo "Testing $INSTALL"
+echo "  repo: $REPO_ROOT"
+echo "  ${#ALL_DIVISIONS[@]} divisions, $TOTAL_AGENTS agents (engineering: $ENG_AGENTS)"
+echo ""
+
+# ---------------------------------------------------------------------------
+# 1. Help and listings
+# ---------------------------------------------------------------------------
+echo "help + listings"
+
+home="$(sandbox help)"
+RUN_OUT="$(HOME="$home" "$INSTALL" --help 2>&1)"; RUN_STATUS=$?
+assert_eq 0 "$RUN_STATUS" "--help exits 0"
+case "$RUN_OUT" in *"Usage:"*) pass "--help prints usage" ;; *) fail "--help prints usage" ;; esac
+
+home="$(sandbox list-teams)"
+run_install "$home" --list teams
+assert_eq 0 "$RUN_STATUS" "--list teams exits 0"
+missing=""
+for _div in "${ALL_DIVISIONS[@]}"; do
+  case "$RUN_OUT" in *"$_div"*) ;; *) missing="$missing $_div" ;; esac
+done
+assert_eq "" "$missing" "--list teams names every division in divisions.json"
+
+home="$(sandbox list-agents)"
+run_install "$home" --list agents
+listed=$(printf '%s\n' "$RUN_OUT" | grep -c "$FIRST_ENG_SLUG")
+[[ "$listed" -ge 1 ]] && pass "--list agents includes $FIRST_ENG_SLUG" \
+  || fail "--list agents includes $FIRST_ENG_SLUG"
+
+# ---------------------------------------------------------------------------
+# 2. --dry-run writes nothing
+# ---------------------------------------------------------------------------
+echo ""
+echo "dry-run"
+
+home="$(sandbox dry-run)"
+run_install "$home" --tool claude-code --dry-run
+assert_eq 0 "$RUN_STATUS" "--dry-run exits 0"
+assert_eq 0 "$(find "$home" -type f | wc -l | tr -d ' ')" "--dry-run creates no files"
+
+# ---------------------------------------------------------------------------
+# 3. Default destination + --path override
+# ---------------------------------------------------------------------------
+echo ""
+echo "destinations"
+
+home="$(sandbox default-dest)"
+run_install "$home" --tool claude-code
+assert_eq "$TOTAL_AGENTS" "$(count_md "$home/.claude/agents")" \
+  "claude-code installs every agent to \$HOME/.claude/agents"
+assert_eq 0 "$(count_md "$home/.claude")" "claude-code writes nothing into the config root"
+
+home="$(sandbox path-override)"
+dest="$home/custom-dir"
+run_install "$home" --tool claude-code --path "$dest"
+assert_eq "$TOTAL_AGENTS" "$(count_md "$dest")" "--path overrides the default destination"
+assert_eq 0 "$(count_md "$home/.claude/agents")" "--path leaves the default destination empty"
+
+# Env var override, and --path winning over it. COPILOT_AGENT_DIR is used here
+# because it unambiguously names the agents directory itself.
+home="$(sandbox env-override)"
+dest="$home/from-env"
+RUN_OUT="$(HOME="$home" COPILOT_AGENT_DIR="$dest" "$INSTALL" --no-interactive --tool copilot 2>&1)"
+assert_eq "$TOTAL_AGENTS" "$(count_md "$dest")" "COPILOT_AGENT_DIR overrides the default destination"
+
+home="$(sandbox env-vs-path)"
+RUN_OUT="$(HOME="$home" COPILOT_AGENT_DIR="$home/from-env" "$INSTALL" --no-interactive \
+  --tool copilot --path "$home/from-flag" 2>&1)"
+assert_eq "$TOTAL_AGENTS" "$(count_md "$home/from-flag")" "--path wins over the env var"
+assert_eq 0 "$(count_md "$home/from-env")" "env var destination is unused when --path is given"
+
+# ---------------------------------------------------------------------------
+# 4. Paths with spaces (regression: word-splitting in the install loop)
+# ---------------------------------------------------------------------------
+echo ""
+echo "paths with spaces"
+
+home="$(sandbox 'spaces')"
+dest="$home/My Agents/claude code"
+run_install "$home" --tool claude-code --path "$dest"
+assert_eq "$TOTAL_AGENTS" "$(count_md "$dest")" "installs into a path containing spaces"
+assert_eq 0 "$(find "$home" -maxdepth 1 -name 'My' -o -maxdepth 1 -name 'Agents' | wc -l | tr -d ' ')" \
+  "a spaced path is not split into separate directories"
+
+# ---------------------------------------------------------------------------
+# 4b. Parallel workers get their arguments intact (PR #755)
+#
+# --parallel hands the parent's selection state to child workers. On main that
+# happens through a command-shaped string expanded unquoted, so a --path or
+# --agents-file containing whitespace or glob characters is word-split and
+# pathname-expanded on the way in. The install then writes nothing while still
+# reporting "Done! Installed 2 tool(s)" and exiting 0 — a silent miss, which is
+# why the exit-status assertion below cannot catch it on its own and the file
+# count is what actually pins the regression.
+#
+# Two tools are required: a single tool stays on the serial path and never
+# reaches the worker spawn.
+#
+# --jobs 1 is deliberate. Workers are still spawned through the same xargs/sh
+# hand-off, so argument propagation — the thing under test — is exercised in
+# full; serializing them just keeps a second, unrelated defect out of this case.
+# With two workers running concurrently against one shared --path, the parent
+# exits non-zero on roughly 3 runs in 5 (measured on macOS, bash 3.2) once the
+# workers actually copy anything. That race is invisible on main only because
+# the workers currently install nothing at all. See the PR discussion.
+# ---------------------------------------------------------------------------
+echo ""
+echo "parallel workers"
+
+home="$(sandbox parallel-serial-control)"
+dest="$home/My [Agents]/dest dir"
+list="$home/my agents list.txt"
+{ echo "# same selection as the parallel case below"; echo "$FIRST_ENG_SLUG"; } > "$list"
+run_install "$home" --tool claude-code,copilot --no-convert --agents-file "$list" --path "$dest"
+assert_eq 0 "$RUN_STATUS" "serial control: two tools, spaced/globbed --path, exits 0"
+assert_eq 1 "$(count_md "$dest")" "serial control: installs exactly the one selected agent"
+
+home="$(sandbox parallel)"
+dest="$home/My [Agents]/dest dir"
+list="$home/my agents list.txt"
+{ echo "# one agent, listed in a file whose own path has spaces"; echo "$FIRST_ENG_SLUG"; } > "$list"
+run_install "$home" --tool claude-code,copilot --parallel --jobs 1 --no-convert --agents-file "$list" --path "$dest"
+assert_eq 0 "$RUN_STATUS" "--parallel with a spaced/globbed --path exits 0"
+xfail_eq 1 "$(count_md "$dest")" \
+  "--parallel installs exactly the one selected agent (spaced --path + --agents-file)" "PR #755"
+
+# ---------------------------------------------------------------------------
+# 5. Selection filters
+# ---------------------------------------------------------------------------
+echo ""
+echo "selection"
+
+home="$(sandbox division)"
+dest="$home/dest"
+run_install "$home" --tool claude-code --division engineering --path "$dest"
+assert_eq "$ENG_AGENTS" "$(count_md "$dest")" "--division installs only that division"
+
+home="$(sandbox agent)"
+dest="$home/dest"
+run_install "$home" --tool claude-code --agent "$FIRST_ENG_SLUG" --path "$dest"
+assert_eq 1 "$(count_md "$dest")" "--agent installs exactly one agent"
+
+home="$(sandbox agents-file)"
+dest="$home/dest"
+list="$home/agents.txt"
+{ echo "# comment line"; echo ""; echo "$FIRST_ENG_SLUG"; } > "$list"
+run_install "$home" --tool claude-code --agents-file "$list" --path "$dest"
+assert_eq 1 "$(count_md "$dest")" "--agents-file skips comments and blank lines"
+
+home="$(sandbox unknown-tool)"
+run_install "$home" --tool definitely-not-a-tool
+[[ "$RUN_STATUS" -ne 0 ]] && pass "unknown --tool exits non-zero" \
+  || fail "unknown --tool exits non-zero" "exited 0"
+
+# ---------------------------------------------------------------------------
+# 6. --link and idempotency
+# ---------------------------------------------------------------------------
+echo ""
+echo "link + repeat runs"
+
+home="$(sandbox link)"
+dest="$home/dest"
+run_install "$home" --tool claude-code --link --division engineering --path "$dest"
+links=$(find "$dest" -maxdepth 1 -type l | wc -l | tr -d ' ')
+assert_eq "$ENG_AGENTS" "$links" "--link creates symlinks, not copies"
+
+home="$(sandbox idempotent)"
+dest="$home/dest"
+run_install "$home" --tool claude-code --division engineering --path "$dest"
+first=$(count_md "$dest")
+run_install "$home" --tool claude-code --division engineering --path "$dest"
+assert_eq "$first" "$(count_md "$dest")" "re-running installs the same set, not duplicates"
+
+# ---------------------------------------------------------------------------
+echo ""
+if [[ $xfailed -gt 0 ]]; then
+  echo "Results: $passed passed, $failed failed, $xfailed known-broken (xfail)."
+else
+  echo "Results: $passed passed, $failed failed."
+fi
+if [[ $failed -gt 0 ]]; then
+  echo "FAILED"
+  exit 1
+fi
+echo "PASSED"