Kjell Tore Guttormsen
2ee8137e7c
Wave-1 order 4 (P7, P12, the P9 test lock, the P3 plan-approval guard). All command hooks; none runs a model. - P12: pre-bash-executor answers permissionDecision "ask" before merge into main, push, tag/publish and destructive git (holds in auto mode). post-approval-log writes exactly what the person was asked to the K2 approval log: merge/push to main as `merge`, tag/publish as `release`, with a one-hour expiry; nothing when no person was asked. - P3: pre-plan-gate runs the K3 plan gate on a Voyage plan leaving plan mode and sends a refused plan back; "not measured" asks, never passes. - P9: lib/util/test-lock.mjs (K8). pre-write-executor refuses edits to locked test files; stop-test-lock refuses "done" for the locking session (stop_hook_active guarded). - P7: post-edit-check runs the target repo's own formatter/linter per edit, only during a Voyage plan run or after opt-in (.claude/voyage-guards.json); lib/verification/step-check.mjs (K9) fails the step on findings; no tool reads "not measured", never green. - STORM cap matcher also names `Agent` (the tool's name since 2.1.63). - Mod precondition stated in README, SECURITY.md and every PreToolUse stop guard: Voyage's guards are deterministic only when no installed mod handles `tool.check`. K2, K3 and K5 are stubbed in tests until orders 2 and 3 are merged. Two independent review rounds; every finding has a regression test. Suite 1600 (1598 pass / 0 fail / 2 skipped). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
26 lines
1.3 KiB
JavaScript
26 lines
1.3 KiB
JavaScript
// tests/hooks/storm-matcher.test.mjs
|
|
// The STORM cap (pre-agent-cap.mjs) must see subagent spawns. The tool was
|
|
// renamed Task -> Agent in Claude Code 2.1.63; the docs state the old name
|
|
// still works as an alias «in settings and agent definitions»
|
|
// (code.claude.com/docs/en/sub-agents, the rename note) and say nothing about
|
|
// hook matchers, which compare against the tool name the hook input carries.
|
|
// So the matcher must name `Agent` itself. Resolved with Claude Code's matcher
|
|
// rules (hooks § Matcher patterns), as write-guard-coverage.test.mjs does.
|
|
|
|
import { test } from 'node:test';
|
|
import { strict as assert } from 'node:assert';
|
|
import { scriptsFor } from './guard-helpers.mjs';
|
|
|
|
const fires = (tool) => scriptsFor('PreToolUse', tool).some((p) => p.endsWith('pre-agent-cap.mjs'));
|
|
|
|
test('STORM cap fires on Agent (the tool name since 2.1.63)', () => {
|
|
assert.ok(fires('Agent'), 'pre-agent-cap.mjs must fire for tool_name "Agent"');
|
|
});
|
|
|
|
test('STORM cap still fires on WebSearch, WebFetch and the old Task name', () => {
|
|
for (const t of ['WebSearch', 'WebFetch', 'Task']) assert.ok(fires(t), t);
|
|
});
|
|
|
|
test('STORM cap does not fire on unrelated tools', () => {
|
|
for (const t of ['Bash', 'Edit', 'Write', 'Read', 'AgentOutput', 'ExitPlanMode']) assert.ok(!fires(t), t);
|
|
});
|