diff options
Diffstat (limited to 'scripts/tests')
| -rw-r--r-- | scripts/tests/agent-page.bats | 68 | ||||
| -rw-r--r-- | scripts/tests/ai-launcher-runtime.bats | 97 | ||||
| -rw-r--r-- | scripts/tests/install-agents-entry.bats | 51 | ||||
| -rw-r--r-- | scripts/tests/install-ai.bats | 23 | ||||
| -rw-r--r-- | scripts/tests/install-lang-collision.bats | 112 | ||||
| -rw-r--r-- | scripts/tests/pre-commit-secret-scan.bats | 144 |
6 files changed, 495 insertions, 0 deletions
diff --git a/scripts/tests/agent-page.bats b/scripts/tests/agent-page.bats new file mode 100644 index 0000000..071e4b9 --- /dev/null +++ b/scripts/tests/agent-page.bats @@ -0,0 +1,68 @@ +#!/usr/bin/env bats +# agent-page — the runtime-neutral phone pager. Pages Craig over Signal from +# any machine on the tailnet: runs signal-cli directly on velox (where the +# pager identity lives), ssh-relays to velox from everywhere else. These tests +# stub ssh/uname/signal-cli on PATH to verify command construction without a +# network or a phone. + +setup() { + REPO_ROOT="$(cd "$(dirname "$BATS_TEST_FILENAME")/../.." && pwd)" + PAGE="$REPO_ROOT/claude-templates/bin/agent-page" + STUBS="$(mktemp -d)" + LOG="$STUBS/calls.log" + cat > "$STUBS/ssh" <<EOF +#!/bin/bash +echo "ssh \$*" >> "$LOG" +exit 0 +EOF + cat > "$STUBS/signal-cli" <<EOF +#!/bin/bash +echo "signal-cli \$*" >> "$LOG" +exit 0 +EOF + chmod +x "$STUBS/ssh" "$STUBS/signal-cli" +} + +teardown() { + rm -rf "$STUBS" +} + +@test "no message exits 2 with usage" { + run bash "$PAGE" + [ "$status" -eq 2 ] + [[ "$output" == *"usage"* ]] +} + +@test "relays through ssh to velox with the pager account and Craig's UUID" { + PATH="$STUBS:$PATH" run bash "$PAGE" build finished + [ "$status" -eq 0 ] + grep -q "^ssh .*velox" "$LOG" + grep -q "15045173983" "$LOG" + grep -q "b1b5601e-6126-47f8-afaa-0a59f5188fde" "$LOG" + # printf %q escapes the space, so the relayed message reads build\ finished. + grep -qF 'build\ finished' "$LOG" +} + +@test "on velox itself, calls signal-cli directly (no ssh)" { + cat > "$STUBS/uname" <<'EOF' +#!/bin/bash +[ "$1" = "-n" ] && { echo velox; exit 0; } +exec /usr/bin/uname "$@" +EOF + chmod +x "$STUBS/uname" + PATH="$STUBS:$PATH" run bash "$PAGE" hello + [ "$status" -eq 0 ] + grep -q "^signal-cli " "$LOG" + ! grep -q "^ssh " "$LOG" +} + +@test "a failed relay reports the desktop fallback and propagates failure" { + cat > "$STUBS/ssh" <<'EOF' +#!/bin/bash +exit 255 +EOF + chmod +x "$STUBS/ssh" + PATH="$STUBS:$PATH" run bash "$PAGE" urgent thing + [ "$status" -ne 0 ] + [[ "$output" == *"notify"* ]] +} diff --git a/scripts/tests/ai-launcher-runtime.bats b/scripts/tests/ai-launcher-runtime.bats new file mode 100644 index 0000000..3f0ad69 --- /dev/null +++ b/scripts/tests/ai-launcher-runtime.bats @@ -0,0 +1,97 @@ +#!/usr/bin/env bats +# The ai launcher's --runtime flag: pick the agent CLI (claude, codex) that +# a project window launches. Part of the generic-agent-runtime arc — the +# tmux-side counterpart of .emacs.d's ai-term multi-LLM handoff. The +# --print-launch mode exists for exactly these tests: it prints the launch +# command a real run would send to the pane, without touching tmux or fzf. + +setup() { + REPO_ROOT="$(cd "$(dirname "$BATS_TEST_FILENAME")/../.." && pwd)" + AI="$REPO_ROOT/claude-templates/bin/ai" + PROJ="$(mktemp -d)" + mkdir -p "$PROJ/.ai" + touch "$PROJ/.ai/protocols.org" + STUB_BIN="$(mktemp -d)" +} + +teardown() { + rm -rf "$PROJ" "$STUB_BIN" +} + +@test "default runtime launches claude" { + run bash "$AI" --print-launch "$PROJ" + [ "$status" -eq 0 ] + [[ "$output" == claude\ * ]] + [[ "$output" == *"protocols.org"* ]] +} + +@test "--runtime codex launches codex with the same opening line" { + run bash "$AI" --runtime codex --print-launch "$PROJ" + [ "$status" -eq 0 ] + [[ "$output" == codex\ * ]] + [[ "$output" == *"protocols.org"* ]] + [[ "$output" == *"$(basename "$PROJ")"* ]] +} + +@test "AI_RUNTIME env selects the runtime without the flag" { + AI_RUNTIME=codex run bash "$AI" --print-launch "$PROJ" + [ "$status" -eq 0 ] + [[ "$output" == codex\ * ]] +} + +@test "--runtime local launches codex --oss over ollama with the default local model" { + run bash "$AI" --runtime local --print-launch "$PROJ" + [ "$status" -eq 0 ] + [[ "$output" == "codex --oss --local-provider=ollama -m gpt-oss:120b "* ]] + [[ "$output" == *"protocols.org"* ]] +} + +@test "AI_LOCAL_MODEL overrides the local runtime's model" { + AI_LOCAL_MODEL=qwen3-coder:30b run bash "$AI" --runtime local --print-launch "$PROJ" + [ "$status" -eq 0 ] + [[ "$output" == "codex --oss --local-provider=ollama -m qwen3-coder:30b "* ]] +} + +@test "an unknown runtime errors and names the valid ones" { + run bash "$AI" --runtime frobnitz --print-launch "$PROJ" + [ "$status" -eq 2 ] + [[ "$output" == *"claude"* ]] + [[ "$output" == *"codex"* ]] +} + +@test "--print-launch refuses a non-project directory" { + run bash "$AI" --print-launch "$BATS_TEST_TMPDIR" + [ "$status" -eq 1 ] + [[ "$output" == *"protocols.org"* ]] +} + +@test "--print-runtimes lists claude, codex, and one line per ollama model" { + cat > "$STUB_BIN/ollama" <<'STUB' +#!/bin/bash +if [ "$1" = "list" ]; then + printf 'NAME ID SIZE MODIFIED\n' + printf 'gpt-oss:120b aaa 65 GB 1 hour ago\n' + printf 'qwen3-coder:30b bbb 18 GB 1 hour ago\n' +fi +STUB + chmod +x "$STUB_BIN/ollama" + PATH="$STUB_BIN:$PATH" run bash "$AI" --print-runtimes + [ "$status" -eq 0 ] + [ "${lines[0]%% *}" = "claude" ] + [[ "$output" == *"codex"* ]] + [[ "$output" == *"local:gpt-oss:120b"* ]] + [[ "$output" == *"local:qwen3-coder:30b"* ]] +} + +@test "a dead ollama server just drops the local lines" { + cat > "$STUB_BIN/ollama" <<'STUB' +#!/bin/bash +echo "Error: could not connect to a running Ollama instance" >&2 +exit 1 +STUB + chmod +x "$STUB_BIN/ollama" + PATH="$STUB_BIN:$PATH" run bash "$AI" --print-runtimes + [ "$status" -eq 0 ] + [[ "$output" == *"claude"* ]] + [[ "$output" != *"local:"* ]] +} diff --git a/scripts/tests/install-agents-entry.bats b/scripts/tests/install-agents-entry.bats new file mode 100644 index 0000000..03343a6 --- /dev/null +++ b/scripts/tests/install-agents-entry.bats @@ -0,0 +1,51 @@ +#!/usr/bin/env bats +# make install must link the runtime-neutral agent entry file (AGENTS.md) +# into CODEX_DIR so Codex-style harnesses bootstrap from the same +# protocols/rules/skills the Claude side reads. The thin-pointer shape and +# the decision trail live in docs/design/2026-07-13-runtime-portability- +# inventories.org and the generic-agent-runtime task. + +setup() { + REPO_ROOT="$(cd "$(dirname "$BATS_TEST_FILENAME")/../.." && pwd)" + TMPHOME="$(mktemp -d)" +} + +teardown() { + rm -rf "$TMPHOME" +} + +run_install() { + make -C "$REPO_ROOT" install \ + SKILLS_DIR="$TMPHOME/skills" \ + RULES_DIR="$TMPHOME/rules" \ + HOOKS_DIR="$TMPHOME/hooks" \ + CLAUDE_DIR="$TMPHOME/claude" \ + CODEX_DIR="$TMPHOME/codex" \ + LOCAL_BIN="$TMPHOME/bin" +} + +@test "install links AGENTS.md into CODEX_DIR" { + run run_install + [ "$status" -eq 0 ] + [ -L "$TMPHOME/codex/AGENTS.md" ] + grep -q "protocols.org" "$TMPHOME/codex/AGENTS.md" +} + +@test "install is idempotent on the agent entry (second run skips)" { + run run_install + [ "$status" -eq 0 ] + run run_install + [ "$status" -eq 0 ] + [[ "$output" == *"skip AGENTS.md (already linked)"* ]] + [ -L "$TMPHOME/codex/AGENTS.md" ] +} + +@test "install warns on a non-symlink AGENTS.md collision and leaves it alone" { + mkdir -p "$TMPHOME/codex" + echo "hand-written entry" > "$TMPHOME/codex/AGENTS.md" + run run_install + [ "$status" -eq 0 ] + [[ "$output" == *"WARN AGENTS.md exists and is not a symlink"* ]] + [ ! -L "$TMPHOME/codex/AGENTS.md" ] + grep -q "hand-written entry" "$TMPHOME/codex/AGENTS.md" +} diff --git a/scripts/tests/install-ai.bats b/scripts/tests/install-ai.bats index 8e91770..a7eb3c0 100644 --- a/scripts/tests/install-ai.bats +++ b/scripts/tests/install-ai.bats @@ -149,3 +149,26 @@ EOF [ -d "$TEST_HOME/code/pickme/.ai" ] [ ! -d "$TEST_HOME/code/skipme/.ai" ] } + +@test "install-ai: seeds AGENTS.md at the project root" { + mkdir -p "$TEST_HOME/code/fresh" + (cd "$TEST_HOME/code/fresh" && git init -q) + + run bash "$INSTALL_AI" --gitignore "$TEST_HOME/code/fresh" + + [ "$status" -eq 0 ] + [ -f "$TEST_HOME/code/fresh/AGENTS.md" ] + grep -q "protocols.org" "$TEST_HOME/code/fresh/AGENTS.md" +} + +@test "install-ai: never overwrites an existing AGENTS.md" { + mkdir -p "$TEST_HOME/code/fresh" + (cd "$TEST_HOME/code/fresh" && git init -q) + echo "project-owned entry file" > "$TEST_HOME/code/fresh/AGENTS.md" + + run bash "$INSTALL_AI" --gitignore "$TEST_HOME/code/fresh" + + [ "$status" -eq 0 ] + grep -q "project-owned entry file" "$TEST_HOME/code/fresh/AGENTS.md" + ! grep -q "protocols.org" "$TEST_HOME/code/fresh/AGENTS.md" +} diff --git a/scripts/tests/install-lang-collision.bats b/scripts/tests/install-lang-collision.bats new file mode 100644 index 0000000..36abb5b --- /dev/null +++ b/scripts/tests/install-lang-collision.bats @@ -0,0 +1,112 @@ +#!/usr/bin/env bats +# Tests for install-lang's cross-bundle collision guard. +# +# Several bundles ship files at the same path. gitignore-add.txt merges +# (appended, deduped) and CLAUDE.md is seed-only, so both compose across +# bundles. Three do not: +# +# claude/settings.json elisp, bash, go — cp -rT, silently overwritten +# githooks/pre-commit elisp, bash, go — cp -rT, silently overwritten +# coverage-makefile.txt 4 bundles — [skip]ped, fragment dropped +# +# Installing a second bundle used to replace the first's settings.json and +# pre-commit while printing [ok], so a project could lose its paren check or +# secret scan and read the output as success. The guard refuses instead, naming +# what would be replaced. FORCE=1 still overrides. + +INSTALL="${BATS_TEST_DIRNAME}/../install-lang.sh" + +setup() { + PROJ="$(mktemp -d)" + git init -q "$PROJ" +} + +teardown() { + [ -n "${PROJ:-}" ] && rm -rf "$PROJ" +} + +# ---- Normal: single-bundle installs are unaffected ---- + +@test "install-lang: a fresh single-bundle install succeeds" { + run bash "$INSTALL" elisp "$PROJ" + [ "$status" -eq 0 ] + [ -f "$PROJ/.claude/settings.json" ] + grep -q 'validate-el.sh' "$PROJ/.claude/settings.json" +} + +@test "install-lang: reinstalling the SAME bundle is idempotent, not a collision" { + bash "$INSTALL" elisp "$PROJ" + run bash "$INSTALL" elisp "$PROJ" + [ "$status" -eq 0 ] + [[ "$output" != *"collision"* ]] + grep -q 'validate-el.sh' "$PROJ/.claude/settings.json" +} + +# ---- The guard: a second, different bundle must not silently replace ---- + +@test "install-lang: a second bundle sharing settings.json and githooks is refused" { + bash "$INSTALL" elisp "$PROJ" + run bash "$INSTALL" bash "$PROJ" + [ "$status" -ne 0 ] || { echo "second bundle installed without refusal"; return 1; } + [[ "$output" == *"elisp"* ]] || { echo "refusal does not name the existing bundle"; return 1; } +} + +@test "install-lang: the refusal names each file that would be replaced" { + bash "$INSTALL" elisp "$PROJ" + run bash "$INSTALL" bash "$PROJ" + [[ "$output" == *"settings.json"* ]] || { echo "refusal omits settings.json"; return 1; } + [[ "$output" == *"pre-commit"* ]] || { echo "refusal omits githooks/pre-commit"; return 1; } +} + +@test "install-lang: a refused install leaves the first bundle intact" { + bash "$INSTALL" elisp "$PROJ" + bash "$INSTALL" bash "$PROJ" || true + grep -q 'validate-el.sh' "$PROJ/.claude/settings.json" \ + || { echo "elisp settings.json was replaced despite refusal"; return 1; } + grep -q 'check-parens' "$PROJ/githooks/pre-commit" \ + || { echo "elisp pre-commit was replaced despite refusal"; return 1; } +} + +@test "install-lang: bundles colliding only on coverage-makefile.txt are refused too" { + # python and typescript ship no settings.json or githooks, but both ship a + # coverage fragment. The second one's used to be silently dropped. + bash "$INSTALL" python "$PROJ" + run bash "$INSTALL" typescript "$PROJ" + [ "$status" -ne 0 ] || { echo "typescript installed over python's coverage fragment"; return 1; } + [[ "$output" == *"coverage-makefile.txt"* ]] +} + +@test "install-lang: two bundles that share no overwritten file install together" { + # bash ships settings.json + githooks and no coverage fragment; python ships + # only the coverage fragment. Nothing overlaps, so the guard must stay out of + # the way. This is the path where a false refusal would be easiest to + # introduce: the bundle IS detected, and only the empty file-list stops it. + bash "$INSTALL" bash "$PROJ" + run bash "$INSTALL" python "$PROJ" + [ "$status" -eq 0 ] || { echo "guard falsely refused a non-colliding pair: $output"; return 1; } + [ -f "$PROJ/coverage-makefile.txt" ] || { echo "python's coverage fragment did not land"; return 1; } + # bash's config survives untouched. + grep -q 'validate-bash.sh' "$PROJ/.claude/settings.json" + [ -f "$PROJ/.claude/rules/bash.md" ] && [ -f "$PROJ/.claude/rules/python-testing.md" ] +} + +# ---- The escape hatch ---- + +@test "install-lang: FORCE=1 overrides the collision guard" { + bash "$INSTALL" elisp "$PROJ" + run bash "$INSTALL" bash "$PROJ" 1 + [ "$status" -eq 0 ] || { echo "FORCE=1 did not override: $output"; return 1; } + grep -q 'validate-bash.sh' "$PROJ/.claude/settings.json" +} + +@test "install-lang: the refusal points at FORCE=1 and warns it re-seeds CLAUDE.md" { + bash "$INSTALL" elisp "$PROJ" + run bash "$INSTALL" bash "$PROJ" + # Assert the refusal fired first: the pre-existing "[skip] CLAUDE.md already + # exists (use FORCE=1 to overwrite)" line mentions both strings on its own, so + # without this the test passes against an unguarded install. + [ "$status" -ne 0 ] || { echo "no refusal fired"; return 1; } + refusal="$(printf '%s\n' "$output" | grep -v '^ \[skip\]')" + [[ "$refusal" == *"FORCE=1"* ]] || { echo "refusal does not name the override"; return 1; } + [[ "$refusal" == *"CLAUDE.md"* ]] || { echo "refusal does not warn about the CLAUDE.md re-seed"; return 1; } +} diff --git a/scripts/tests/pre-commit-secret-scan.bats b/scripts/tests/pre-commit-secret-scan.bats new file mode 100644 index 0000000..013129e --- /dev/null +++ b/scripts/tests/pre-commit-secret-scan.bats @@ -0,0 +1,144 @@ +#!/usr/bin/env bats +# Tests for the secret-scan block shared by the elisp, bash, and go pre-commit +# hooks. The block greps added lines in the staged diff for credential +# patterns; a hit blocks the commit (exit 1), a clean scan falls through to the +# variant's language check (exit 0). +# +# Every case stages a .txt file, so the language checks that follow the scan +# (check-parens, shellcheck, gofmt) all skip and the scan is what's under test. +# +# The two boundary cases exist because of a live false-positive in a downstream +# project: an embedded PNG sprite data URI blocked a real commit and forced +# --no-verify. Root cause was `grep -iE` applying case-insensitivity to the +# fixed-case AWS token AKIA[0-9A-Z]{16}, so any mixed-case 20-char run inside a +# random base64 blob matched. Measured at ~6% of 100KB blobs; case-sensitive +# matching drops it to 0 across ~10MB. + +VARIANTS="elisp bash go" + +setup() { + REPO="$(mktemp -d)" + cd "$REPO" || return 1 + git init -q . + git config user.email t@example.com + git config user.name Test +} + +teardown() { + cd /tmp || true + [ -n "${REPO:-}" ] && rm -rf "$REPO" +} + +# Stage $2 as the content of file $1 (default staged.txt). +stage() { + local file="${2:-staged.txt}" + printf '%s\n' "$1" > "$file" + git add "$file" +} + +# Run a variant's hook in the temp repo. $1 = variant name. +run_hook() { + bash "${BATS_TEST_DIRNAME}/../../languages/$1/githooks/pre-commit" +} + +# ---- Normal: real secrets still block, clean content still passes ---- + +@test "secret-scan: clean content passes in every variant" { + stage 'const greeting = "hello world";' + for v in $VARIANTS; do + run run_hook "$v" + [ "$status" -eq 0 ] || { echo "$v blocked clean content: $output"; return 1; } + done +} + +@test "secret-scan: a real uppercase AWS access key blocks in every variant" { + stage 'aws_key = "AKIAIOSFODNN7EXAMPLE"' + for v in $VARIANTS; do + run run_hook "$v" + [ "$status" -eq 1 ] || { echo "$v missed an AWS key"; return 1; } + [[ "$output" == *"potential secret"* ]] + done +} + +@test "secret-scan: a keyword=value credential blocks in every variant" { + stage 'api_key: "sk_live_9f3b2a7c1e4d8f0a6b5"' + for v in $VARIANTS; do + run run_hook "$v" + [ "$status" -eq 1 ] || { echo "$v missed an api_key assignment"; return 1; } + done +} + +@test "secret-scan: a PEM private-key header blocks in every variant" { + stage '-----BEGIN RSA PRIVATE KEY-----' + for v in $VARIANTS; do + run run_hook "$v" + [ "$status" -eq 1 ] || { echo "$v missed a PEM header"; return 1; } + done +} + +# ---- Boundary: the case-sensitivity fix ---- + +@test "secret-scan: a lowercase akia-like run does not block (AWS keys are uppercase)" { + # Under `grep -iE` this matched the AKIA token and blocked a legitimate commit. + stage 'const blob = "akiaiosfodnn7examplexyz";' + for v in $VARIANTS; do + run run_hook "$v" + [ "$status" -eq 0 ] || { echo "$v false-positived on a lowercase run: $output"; return 1; } + done +} + +@test "secret-scan: an embedded base64 data URI carrying a mixed-case akia run does not block" { + # The live failure: a sprite blob whose random base64 contained a mixed-case + # 20-char run. Case-sensitive matching is what clears it. + stage 'const SPRITE = "data:image/png;base64,iVBORw0KGgoAkIaIOSFODNN7ExAMPLEqQmCC";' + for v in $VARIANTS; do + run run_hook "$v" + [ "$status" -eq 0 ] || { echo "$v false-positived on a sprite data URI: $output"; return 1; } + done +} + +# ---- Boundary: the scan must not go blind on data-URI lines ---- + +@test "secret-scan: a real credential sharing a line with a base64 data URI still blocks" { + # Minified bundles put a whole file on one line, so a data URI and a real key + # can share it. Skipping any line containing ';base64,' would hide the key. + stage 'const S="data:image/png;base64,iVBORw0KGgoAAAANS";const c={api_key:"sk_live_9f3b2a7c1e4d8f0a6b5"};' + for v in $VARIANTS; do + run run_hook "$v" + [ "$status" -eq 1 ] || { echo "$v went blind on a data-URI line and missed the key"; return 1; } + done +} + +@test "secret-scan: a line matching both passes is reported once, not twice" { + # The scan runs a case-sensitive and a case-insensitive pass. A line carrying + # both an AWS key and a keyword=value credential hits both; reporting it twice + # reads as two separate leaks. + stage 'api_key = "AKIAIOSFODNN7EXAMPLE_padding"' + for v in $VARIANTS; do + run run_hook "$v" + [ "$status" -eq 1 ] + hits="$(printf '%s\n' "$output" | grep -c 'AKIAIOSFODNN7EXAMPLE_padding')" + [ "$hits" -eq 1 ] || { echo "$v reported the line $hits times, want 1"; return 1; } + done +} + +# ---- Error / edge ---- + +@test "secret-scan: an empty staged diff passes" { + for v in $VARIANTS; do + run run_hook "$v" + [ "$status" -eq 0 ] || { echo "$v failed on an empty diff: $output"; return 1; } + done +} + +@test "secret-scan: a secret only on a removed line does not block" { + # The scan reads added lines. Deleting a key should never block the deletion. + stage 'aws_key = "AKIAIOSFODNN7EXAMPLE"' + git commit -qm "seed" --no-verify + printf 'clean\n' > staged.txt + git add staged.txt + for v in $VARIANTS; do + run run_hook "$v" + [ "$status" -eq 0 ] || { echo "$v blocked a removal: $output"; return 1; } + done +} |