voyage/tests/commands/trekendsession.test.mjs

// tests/commands/trekendsession.test.mjs
// Regression tests for /trekendsession (commands/trekendsession.md).
//
// Bug (2026-07-03): two of the three !`...` eager-exec blocks contained
// unresolved placeholders (<project-dir> etc.). The harness executes
// eager-exec blocks at command LOAD time, so zsh parsed <project-dir> as
// input redirection and the command aborted before the model saw a single
// instruction. Eager-exec is only valid for self-contained commands.
//
// Pattern D (markdown structure) — assertions against command prose.

import { test } from 'node:test';
import { strict as assert } from 'node:assert';
import { existsSync, mkdirSync, mkdtempSync, readFileSync, readdirSync, rmSync, writeFileSync } from 'node:fs';
import { tmpdir } from 'node:os';
import { dirname, join } from 'node:path';
import { spawnSync } from 'node:child_process';
import { fileURLToPath } from 'node:url';
import { childEnv } from '../helpers/child-env.mjs';
import { findSection } from '../../lib/parsers/plan-schema.mjs';

const HERE = dirname(fileURLToPath(import.meta.url));
const ROOT = join(HERE, '..', '..');
const COMMANDS_DIR = join(ROOT, 'commands');
const COMMAND_FILE = join(COMMANDS_DIR, 'trekendsession.md');

function readCommand() {
  return readFileSync(COMMAND_FILE, 'utf8');
}

function extractPhase(commandText, phaseHeader) {
  const startIdx = commandText.indexOf(phaseHeader);
  if (startIdx === -1) return '';
  const rest = commandText.slice(startIdx);
  const nextPhase = rest.search(/\n## (?:Phase |Hard )/);
  if (nextPhase === -1) return rest;
  return rest.slice(0, nextPhase);
}

// Extract all eager-exec blocks (!`...`) from a command/skill file,
// including multi-line blocks. Returns [{ content, line }].
function extractEagerBlocks(text) {
  const blocks = [];
  const re = /!`([^`]+)`/g;
  let m;
  while ((m = re.exec(text)) !== null) {
    const line = text.slice(0, m.index).split('\n').length;
    blocks.push({ content: m[1], line });
  }
  return blocks;
}

// ---------------------------------------------------------------
// Marketplace-wide regression guard: eager-exec blocks must be
// self-contained. An unresolved placeholder (<angle> or {curly}) in an
// eager block is executed verbatim by the shell at load time — <x> is
// parsed as input redirection and aborts the whole command load.
// ---------------------------------------------------------------

test('eager-exec guard — no !`-block in commands/ contains an unresolved placeholder', () => {
  const offenders = [];
  for (const file of readdirSync(COMMANDS_DIR).filter((f) => f.endsWith('.md'))) {
    const text = readFileSync(join(COMMANDS_DIR, file), 'utf8');
    for (const { content, line } of extractEagerBlocks(text)) {
      // Placeholder conventions: <angle-word> or {curly_word}. Curly must
      // contain a separator (- or _) so JS destructuring like {join} in a
      // legitimate self-contained script does not false-positive; angle
      // placeholders are unambiguous (shell would parse them as redirects).
      if (/<[a-z][a-z0-9_-]*>/.test(content) || /\{[a-z][a-z0-9]*([_-][a-z0-9]+)+\}/.test(content)) {
        offenders.push(`${file}:${line}`);
      }
    }
  }
  assert.deepEqual(
    offenders,
    [],
    `eager-exec !\`-blocks run at command LOAD time and must be self-contained; ` +
      `placeholder found in: ${offenders.join(', ')}`,
  );
});

// ---------------------------------------------------------------
// trekendsession-specific: exactly one eager block (Phase 1 project
// discovery — self-contained, legitimate); Phases 3 and 4 are runtime
// Bash-tool commands with model-substituted values, never eager.
// ---------------------------------------------------------------

test('trekendsession — exactly one eager-exec block remains (Phase 1 discovery)', () => {
  const cmd = readCommand();
  const blocks = extractEagerBlocks(cmd);
  assert.equal(
    blocks.length,
    1,
    `expected exactly 1 eager-exec block (Phase 1 discovery), got ${blocks.length} at line(s) ${blocks.map((b) => b.line).join(', ')}`,
  );
  assert.match(
    blocks[0].content,
    /readdirSync\(root\)/,
    'the surviving eager block must be the self-contained Phase 1 discovery script',
  );
});

test('trekendsession Phase 3 — atomic-write block is runtime Bash (no eager prefix) with plugin-root import', () => {
  const phase3 = extractPhase(readCommand(), '## Phase 3 ');
  assert.doesNotMatch(phase3, /!`/, 'Phase 3 must not use eager-exec — values exist only at runtime');
  assert.match(
    phase3,
    /\$\{CLAUDE_PLUGIN_ROOT\}\/lib\/util\/atomic-write\.mjs/,
    'Phase 3 import must use the absolute ${CLAUDE_PLUGIN_ROOT} path — cwd is the user repo, not the plugin root',
  );
  assert.doesNotMatch(
    phase3,
    /['"]\.\/lib\/util\/atomic-write\.mjs['"]/,
    'Phase 3 must not import atomic-write.mjs via a cwd-relative path',
  );
});

test('trekendsession Phase 4 — validator call is runtime Bash (no eager prefix) with plugin-root path', () => {
  const phase4 = extractPhase(readCommand(), '## Phase 4 ');
  assert.doesNotMatch(phase4, /!`/, 'Phase 4 must not use eager-exec — the state-file path exists only at runtime');
  assert.match(
    phase4,
    /\$\{CLAUDE_PLUGIN_ROOT\}\/lib\/validators\/session-state-validator\.mjs/,
    'Phase 4 validator path must use the absolute ${CLAUDE_PLUGIN_ROOT} convention',
  );
  assert.doesNotMatch(
    phase4,
    /<[a-z][a-z0-9_-]*>/,
    'Phase 4 must not use <angle> placeholders in commands — zsh parses <x> as input redirection',
  );
});

// ---------------------------------------------------------------
// DJ5 (fix round 4.5b): Phase 3 splices no label into its shell line.
// The block used to end in '{project_dir}' '{next_brief_path}'
// '{next_label}', filled in by the model: a label holding a ' closed the
// quote and the rest ran as shell. Phase 3 now re-reads $ARGUMENTS through
// the quoted heredoc on stdin, parses it with parseArgs and re-derives the
// project directory itself. The runtime tests run the block as Claude Code
// would after it substitutes ${CLAUDE_PLUGIN_ROOT} and $ARGUMENTS.
// ---------------------------------------------------------------

const ARGS_DELIM = 'VOYAGE_ARGS_EOF_7F3C9E';
const PROJECT_REL = join('.claude', 'projects', '2026-01-01-demo');
const NEXT_BRIEF = '.claude/projects/2026-01-01-demo/next-brief.md';

/** The one runtime ```bash block of Phase 3 (the atomic-write block). */
function phase3Block() {
  const phase3 = extractPhase(readCommand(), '## Phase 3 ');
  const blocks = phase3.split('\n```bash\n').slice(1).map((b) => b.split('\n```')[0])
    .filter((b) => b.includes('atomic-write.mjs'));
  assert.equal(blocks.length, 1, `Phase 3 must hold one \`\`\`bash block that runs atomic-write.mjs; found ${blocks.length}`);
  return blocks[0];
}

/** True when `bin` can be started from PATH. */
function onPath(bin) {
  const r = spawnSync(bin, ['-c', 'exit 0'], { env: childEnv(), encoding: 'utf8' });
  return r.error === undefined && r.status === 0;
}

/**
 * Run the Phase 3 block with `shell` in a fresh fixture project, with
 * `argText` standing where Claude Code puts $ARGUMENTS. Returns the result,
 * what the run wrote, and whether a PWNED file appeared; the fixture is gone
 * on return.
 */
function runPhase3(shell, argText) {
  const block = phase3Block();
  assert.ok(block.includes('$ARGUMENTS'),
    'Phase 3 does not re-read $ARGUMENTS: its values still come from text the model splices into the shell line');
  const script = block.split('${CLAUDE_PLUGIN_ROOT}').join(ROOT).split('$ARGUMENTS').join(argText);
  const fixture = mkdtempSync(join(tmpdir(), 'trekendsession-dj5-'));
  try {
    mkdirSync(join(fixture, PROJECT_REL), { recursive: true });
    writeFileSync(join(fixture, PROJECT_REL, 'brief.md'), '# demo brief\n');
    const r = spawnSync(shell, ['-c', script], { cwd: fixture, env: childEnv(), encoding: 'utf8' });
    const stateFile = join(fixture, PROJECT_REL, '.session-state.local.json');
    const promptFile = join(fixture, PROJECT_REL, 'NEXT-SESSION-PROMPT.local.md');
    return {
      r,
      pwned: ['PWNED', 'PWNED2'].filter((f) => existsSync(join(fixture, f))),
      state: existsSync(stateFile) ? JSON.parse(readFileSync(stateFile, 'utf8')) : null,
      prompt: existsSync(promptFile) ? readFileSync(promptFile, 'utf8') : null,
    };
  } finally {
    rmSync(fixture, { recursive: true, force: true });
  }
}

/** Assert one run wrote `label` whole and ran nothing from it. */
function assertLabelKept(shell, label) {
  const { r, pwned, state, prompt } = runPhase3(shell, `${NEXT_BRIEF} ${label}`);
  const how = `${shell}, label ${JSON.stringify(label)}: exit ${r.status}\n${r.stdout}${r.stderr}`;
  assert.deepEqual(pwned, [], `the label ran as shell under ${how}`);
  assert.equal(r.status, 0, `Phase 3 did not run cleanly under ${how}`);
  assert.ok(state, `no .session-state.local.json was written under ${how}`);
  assert.equal(state.next_session_label, label, `the written label is not the typed one under ${how}`);
  assert.equal(state.next_session_brief_path, NEXT_BRIEF, `the written brief path is not the typed one under ${how}`);
  assert.equal(state.project, PROJECT_REL, `the project directory was not re-derived under ${how}`);
  assert.ok(prompt && prompt.includes(`\n# ${label}\n`), `NEXT-SESSION-PROMPT.local.md does not carry the label under ${how}`);
}

test('[DJ5] Phase 3 has no quoted placeholder for the label, brief or project', () => {
  const block = phase3Block();
  const placeholders = block.match(/\{[a-z][a-z0-9]*(?:[_ -][a-z0-9]+)*\}/g) || [];
  assert.deepEqual(placeholders, [], 'Phase 3 still has the model fill {placeholders} into its shell line');
  assert.doesNotMatch(block, /'\{/, 'Phase 3 still quotes a placeholder as a shell word');
  const lines = block.split('\n');
  const open = lines.findIndex((l) => l.trimEnd().endsWith(`<<'${ARGS_DELIM}'`));
  assert.ok(open !== -1, `Phase 3 does not re-read the arguments through the quoted heredoc <<'${ARGS_DELIM}'`);
  assert.equal(lines[open + 1], '$ARGUMENTS', 'the line inside the Phase 3 heredoc is not $ARGUMENTS alone');
  const filled = lines.filter((l) => l.trim() !== '');
  assert.ok(lines[open + 2] === ARGS_DELIM && filled[filled.length - 1] === ARGS_DELIM,
    `the closing line ${ARGS_DELIM} does not follow $ARGUMENTS as the block's last non-empty line`);
  assert.equal(lines.filter((l, i) => i !== open + 1 && l.includes('$ARGUMENTS')).length, 0,
    'a line outside the Phase 3 heredoc carries $ARGUMENTS');
  assert.match(block, /import \{ parseArgs \} from '\$\{CLAUDE_PLUGIN_ROOT\}\/lib\/parsers\/arg-parser\.mjs'/,
    'Phase 3 does not import parseArgs at runtime from the plugin root');
});

test('[DJ5] Phase 3 run with an injection label creates no file and keeps the label whole', (t) => {
  // The step's label, and the same with a command substitution: under bash,
  // and under zsh (the shell the Bash tool runs) when zsh is on PATH.
  const labels = ["a'; touch PWNED; echo 'b", "a'; touch PWNED; echo 'b $(touch PWNED2)"];
  for (const label of labels) assertLabelKept('bash', label);
  if (onPath('zsh')) {
    for (const label of labels) assertLabelKept('zsh', label);
  } else {
    t.diagnostic('zsh is not on PATH: the zsh half of this test was not run');
  }
});

test("[DJ5] a label with an apostrophe is kept", () => {
  assertLabelKept('bash', "Fix the user's login");
});

// ---------------------------------------------------------------
// Phase 0 runs the arg parser and dispatches only on its exact result, so
// a slug such as "fix-header" never asks for help.
// ---------------------------------------------------------------

/** Whitespace (line breaks too) collapsed to one space. */
const flat = (s) => s.replace(/\s+/g, ' ').trim();

/**
 * The text of a heading's section, up to the next heading of the same or a
 * higher level outside a fence. The heading must exist.
 */
function sectionText(text, heading) {
  const level = heading.match(/^#+/)[0].length;
  const s = findSection(text, heading.replace(/^#+ /, ''), level);
  assert.ok(s, `missing ${heading}`);
  const lines = s.text.split('\n');
  let fenced = false;
  for (let i = 1; i < lines.length; i++) {
    if (/^\s{0,3}(`{3,}|~{3,})/.test(lines[i])) fenced = !fenced;
    const m = !fenced && lines[i].match(/^(#+) /);
    if (m && m[1].length < level) return lines.slice(0, i).join('\n');
  }
  return s.text;
}

/** The single line in `text` that runs `lib/<mod>` (and holds `verb`, when given). */
function libLine(text, mod, verb = '') {
  const esc = mod.replace(/[.*+?^${}()|[\]\\/]/g, '\\$&');
  const re = new RegExp(`^\\s*node \\$\\{CLAUDE_PLUGIN_ROOT\\}/lib/${esc}\\b`);
  const hits = text.split('\n').filter((l) => re.test(l) && l.includes(verb));
  assert.equal(hits.length, 1, `expected exactly one \`${mod}${verb ? ` ${verb}` : ''}\` line; found ${hits.length}`);
  return hits[0].trim();
}

/** The runtime ```bash block of `text` that holds `cmd`, or undefined. */
function bashBlockHolding(text, cmd) {
  return text.split('\n```bash\n').slice(1).map((b) => b.split('\n```')[0]).find((b) => b.includes(cmd));
}

/** A Phase 0 parser block run through bash with the plugin root filled in and `args` in place of $ARGUMENTS. */
function runParser(cmd, args) {
  const filled = cmd.split('$ARGUMENTS').join(args).split('${CLAUDE_PLUGIN_ROOT}').join(ROOT);
  return spawnSync('bash', ['-c', filled], { cwd: ROOT, encoding: 'utf8' });
}

const PHASE0_PARSER_LINE = "node ${CLAUDE_PLUGIN_ROOT}/lib/parsers/arg-parser.mjs --command trekendsession --stdin <<'VOYAGE_ARGS_EOF_7F3C9E'";

test('trekendsession Phase 0 has no "contains --help or -h" check, and its parser line run on fix-header gives no help', () => {
  const phase0 = sectionText(readCommand(), '## Phase 0 — `--help` handling');
  assert.doesNotMatch(flat(phase0), /contains\s+`?--help`?\s+or\s+`?-h`?/i,
    'Phase 0 still prints help when $ARGUMENTS merely contains --help or -h');
  assert.match(flat(phase0), /`flags\['--help'\] === true`/, 'Phase 0 does not dispatch on the parsed --help flag');
  assert.match(flat(phase0), /`positional\[0\] === '-h'`/, 'Phase 0 does not dispatch on a lone -h as the first positional');
  const cmd = libLine(phase0, 'parsers/arg-parser.mjs');
  assert.equal(cmd, PHASE0_PARSER_LINE, 'the Phase 0 parser line is not the trekendsession parser call on $ARGUMENTS');
  const block = bashBlockHolding(phase0, cmd);
  assert.ok(block, 'the parser line is not in a runtime ```bash block');
  assert.equal(block.split('\n')[0], 'setopt nonomatch 2>/dev/null || true', 'the block does not open with setopt nonomatch');
  assert.deepEqual(block.split('\n').slice(-2), ['$ARGUMENTS', 'VOYAGE_ARGS_EOF_7F3C9E'],
    'the block does not end with $ARGUMENTS as the heredoc body and its closing line');
  const plain = runParser(block, 'fix-header');
  assert.equal(plain.status, 0, `the parser line refused fix-header: ${plain.stdout}${plain.stderr}`);
  const r = JSON.parse(plain.stdout);
  assert.equal(r.flags['--help'], undefined, 'fix-header set the --help flag');
  assert.deepEqual(r.positional, ['fix-header']);
  assert.notEqual(r.positional[0], '-h');
  const help = runParser(block, '--help');
  assert.equal(help.status, 0, help.stdout + help.stderr);
  assert.equal(JSON.parse(help.stdout).flags['--help'], true, 'control: --help must set the help flag');
  const two = runParser(block, 'fix-header "Session 2"');
  assert.equal(two.status, 0, two.stdout + two.stderr);
  assert.deepEqual(JSON.parse(two.stdout).positional, ['fix-header', 'Session 2']);
});