* test(#1960): add failing-first RCA-branching contract + schema-invariant tests Epic #1957 Phase 2A. Source-text-is-the-product contract tests (fishbone >=2 categories, AND-gate, multi-cause root_cause, backward compat, reasoning checkpoint candidate_causes+and_gate fields, debugger-philosophy single-cause note, DEBUG template) plus behavioral schema-invariant checks on two fixtures: two contributing causes (AND-gate yes) -> both recorded; single-cause (AND-gate no) -> one root_cause, identical to today. Failing-first: reference, agent edits, and template note do not yet exist. * feat(#1960): add RCA branching (fishbone + AND-gate) to gsd-debugger Epic #1957 Phase 2A. Guards against 5-Whys single-cause bias: before committing root_cause, the debugger enumerates candidate causes across >=2 Ishikawa categories (code/config/environment/data) and explicitly answers an AND-gate question. When the AND-gate fires, every contributing cause is recorded, so a multi-cause fix no longer recurs via the unaddressed second cause. Resolution.root_cause may hold one OR a small set (additive; single-cause sessions are byte-identical to today). The Structured Reasoning Checkpoint gains candidate_causes + and_gate fields; debugger-philosophy.md adds the single-cause-bias trap. Full rules extracted to gsd-core/references/debugger-rca-branching.md (slim Phase 2 routing + 2 checkpoint fields kept in the agent). INVENTORY + manifest + agent-size baseline + install-parity goldens + AGENTS.md + DEBUG template updated. * fix(#1960): address orthogonal review (AND-gate self-consistency, parity guard, narrowed claim, ripples) - Reference: the collapse rule now enforces AND-gate self-consistency — and_gate=yes with a single confirmed cause is flagged as incomplete (return to Phase 3); a race/timing note clarifies such bugs bridge categories; the 'byte-identical' backward-compat claim narrowed to 'root_cause shape unchanged; reasoning_checkpoint gains 2 fields in every session'. - DEBUG.md: stale 'five-field' mirror prose -> seven-field (parallel-surface drift the reviewer flagged); new debug-session-management parity test pins the field-count claim to the gsd-debugger.md YAML keys (CRLF-safe). - Scalar-assuming consumers of set-valued root_cause updated: session-manager compact summaries (319/332), diagnose-only return (1062), archive entry (1216), ROOT CAUSE FOUND return (1322). - Test: added the AND-gate-yes/single-cause invariant + fixture; rephrased the fixture describe block honestly as a schema-invariant specification. - Phase 2 bullet phrasing clarified ('at hypothesis formation, before the Phase 4 commit'). * test(#1960): parity regex accepts word-form count ('seven-field' or '7-field') * test(#1960): parity regex counts array-valued YAML keys (no inline value) * chore(#1960): backfill changeset pr number (PR #2405)
224 lines
10 KiB
JavaScript
224 lines
10 KiB
JavaScript
// allow-test-rule: source-text-is-the-product
|
|
// Workflow .md / agent .md / command .md / reference .md files — their text
|
|
// IS what the runtime loads. Testing text content tests the deployed contract.
|
|
// Per CONTRIBUTING.md exception matrix.
|
|
'use strict';
|
|
|
|
|
|
const { describe, test } = require('node:test');
|
|
const assert = require('node:assert/strict');
|
|
const fs = require('node:fs');
|
|
const path = require('node:path');
|
|
|
|
describe('debug session management implementation', () => {
|
|
test('DEBUG.md template contains reasoning_checkpoint field', () => {
|
|
const content = fs.readFileSync(
|
|
path.join(process.cwd(), 'gsd-core/templates/DEBUG.md'),
|
|
'utf8'
|
|
);
|
|
assert.ok(content.includes('reasoning_checkpoint'), 'DEBUG.md must contain reasoning_checkpoint field');
|
|
});
|
|
|
|
test('DEBUG.md template contains tdd_checkpoint field', () => {
|
|
const content = fs.readFileSync(
|
|
path.join(process.cwd(), 'gsd-core/templates/DEBUG.md'),
|
|
'utf8'
|
|
);
|
|
assert.ok(content.includes('tdd_checkpoint'), 'DEBUG.md must contain tdd_checkpoint field');
|
|
});
|
|
|
|
test('debug command contains list subcommand logic', () => {
|
|
const content = fs.readFileSync(
|
|
path.join(process.cwd(), 'gsd-core/workflows/debug.md'),
|
|
'utf8'
|
|
);
|
|
assert.ok(
|
|
content.includes('SUBCMD=list') || content.includes('"list"'),
|
|
'debug.md must contain list subcommand logic'
|
|
);
|
|
});
|
|
|
|
test('debug command contains continue subcommand logic', () => {
|
|
const content = fs.readFileSync(
|
|
path.join(process.cwd(), 'gsd-core/workflows/debug.md'),
|
|
'utf8'
|
|
);
|
|
assert.ok(
|
|
content.includes('SUBCMD=continue') || content.includes('"continue"'),
|
|
'debug.md must contain continue subcommand logic'
|
|
);
|
|
});
|
|
|
|
test('debug command contains status subcommand logic', () => {
|
|
const content = fs.readFileSync(
|
|
path.join(process.cwd(), 'gsd-core/workflows/debug.md'),
|
|
'utf8'
|
|
);
|
|
assert.ok(
|
|
content.includes('SUBCMD=status') || content.includes('"status"'),
|
|
'debug.md must contain status subcommand logic'
|
|
);
|
|
});
|
|
|
|
test('debug command contains TDD gate logic', () => {
|
|
const content = fs.readFileSync(
|
|
path.join(process.cwd(), 'gsd-core/workflows/debug.md'),
|
|
'utf8'
|
|
);
|
|
assert.ok(
|
|
content.includes('TDD_MODE') || content.includes('tdd_mode'),
|
|
'debug.md must contain TDD gate logic'
|
|
);
|
|
});
|
|
|
|
test('debug.md reads tdd_mode via workflow.tdd_mode key (not bare tdd_mode)', () => {
|
|
const content = fs.readFileSync(
|
|
path.join(process.cwd(), 'gsd-core/workflows/debug.md'),
|
|
'utf8'
|
|
);
|
|
assert.ok(
|
|
!content.includes('config-get tdd_mode'),
|
|
'debug.md must not use bare "tdd_mode" key — use "workflow.tdd_mode" to match every other consumer'
|
|
);
|
|
assert.ok(
|
|
content.includes('config-get workflow.tdd_mode'),
|
|
'debug.md must read tdd_mode via the "workflow.tdd_mode" key'
|
|
);
|
|
});
|
|
|
|
test('debug command contains security hardening', () => {
|
|
const content = fs.readFileSync(
|
|
path.join(process.cwd(), 'gsd-core/workflows/debug.md'),
|
|
'utf8'
|
|
);
|
|
assert.ok(content.includes('DATA_START'), 'debug.md must contain DATA_START injection boundary marker');
|
|
});
|
|
|
|
test('debug command surfaces next_action before spawn', () => {
|
|
const content = fs.readFileSync(
|
|
path.join(process.cwd(), 'gsd-core/workflows/debug.md'),
|
|
'utf8'
|
|
);
|
|
assert.ok(
|
|
content.includes('[debug] Next:') || content.includes('next_action'),
|
|
'debug.md must surface next_action before agent spawn'
|
|
);
|
|
});
|
|
|
|
test('gsd-debugger contains structured reasoning checkpoint', () => {
|
|
const content = fs.readFileSync(
|
|
path.join(process.cwd(), 'agents/gsd-debugger.md'),
|
|
'utf8'
|
|
);
|
|
assert.ok(content.includes('reasoning_checkpoint'), 'gsd-debugger.md must contain reasoning_checkpoint');
|
|
});
|
|
|
|
test('gsd-debugger contains TDD checkpoint mode', () => {
|
|
const content = fs.readFileSync(
|
|
path.join(process.cwd(), 'agents/gsd-debugger.md'),
|
|
'utf8'
|
|
);
|
|
assert.ok(content.includes('tdd_mode'), 'gsd-debugger.md must contain tdd_mode');
|
|
assert.ok(content.includes('TDD CHECKPOINT'), 'gsd-debugger.md must contain TDD CHECKPOINT return format');
|
|
});
|
|
|
|
test('gsd-debugger contains delta debugging technique', () => {
|
|
const content = fs.readFileSync(
|
|
path.join(process.cwd(), 'agents/gsd-debugger.md'),
|
|
'utf8'
|
|
);
|
|
assert.ok(content.includes('Delta Debugging'), 'gsd-debugger.md must contain Delta Debugging technique');
|
|
});
|
|
|
|
test('gsd-debugger contains security note about DATA_START', () => {
|
|
const content = fs.readFileSync(
|
|
path.join(process.cwd(), 'agents/gsd-debugger.md'),
|
|
'utf8'
|
|
);
|
|
assert.ok(content.includes('DATA_START'), 'gsd-debugger.md must contain DATA_START security reference');
|
|
});
|
|
});
|
|
|
|
// Tests for #2148 and #2151
|
|
describe('debug skill dispatch and sub-orchestrator (#2148, #2151)', () => {
|
|
test('gsd-debugger ROOT CAUSE FOUND format includes specialist_hint field', () => {
|
|
const content = fs.readFileSync(path.join(process.cwd(), 'agents', 'gsd-debugger.md'), 'utf8');
|
|
assert.ok(content.includes('specialist_hint'), 'gsd-debugger missing specialist_hint in ROOT CAUSE FOUND');
|
|
assert.ok(content.includes('swift_concurrency'), 'gsd-debugger missing specialist_hint derivation guidance');
|
|
});
|
|
|
|
test('debug.md orchestrator has specialist skill dispatch step', () => {
|
|
const content = fs.readFileSync(path.join(process.cwd(), 'gsd-core/workflows/debug.md'), 'utf8');
|
|
assert.ok(content.includes('specialist_hint'), 'debug.md missing specialist dispatch logic');
|
|
assert.ok(content.includes('typescript-expert'), 'debug.md missing skill dispatch mapping');
|
|
});
|
|
|
|
test('debug.md specialist dispatch prompt uses DATA_START/DATA_END boundaries', () => {
|
|
const content = fs.readFileSync(path.join(process.cwd(), 'gsd-core/workflows/debug.md'), 'utf8');
|
|
assert.ok(content.includes('DATA_START') && content.includes('DATA_END'),
|
|
'debug.md specialist dispatch prompt missing security boundaries');
|
|
});
|
|
|
|
test('gsd-debug-session-manager agent exists with correct tools', () => {
|
|
const content = fs.readFileSync(path.join(process.cwd(), 'agents', 'gsd-debug-session-manager.md'), 'utf8');
|
|
assert.ok(content.includes('Agent'), 'gsd-debug-session-manager missing Agent tool');
|
|
assert.ok(content.includes('AskUserQuestion'), 'gsd-debug-session-manager missing AskUserQuestion tool');
|
|
});
|
|
|
|
test('gsd-debug-session-manager spawns debugger with Agent() dispatcher', () => {
|
|
const content = fs.readFileSync(path.join(process.cwd(), 'agents', 'gsd-debug-session-manager.md'), 'utf8');
|
|
assert.ok(content.includes('\nAgent('), 'session manager must dispatch debugger with Agent(');
|
|
});
|
|
|
|
test('gsd-debug-session-manager uses DATA_START/DATA_END for checkpoint responses', () => {
|
|
const content = fs.readFileSync(path.join(process.cwd(), 'agents', 'gsd-debug-session-manager.md'), 'utf8');
|
|
assert.ok(content.includes('DATA_START') && content.includes('DATA_END'),
|
|
'gsd-debug-session-manager missing security boundaries on checkpoint responses');
|
|
});
|
|
|
|
test('gsd-debug-session-manager has compact summary output format', () => {
|
|
const content = fs.readFileSync(path.join(process.cwd(), 'agents', 'gsd-debug-session-manager.md'), 'utf8');
|
|
assert.ok(content.includes('DEBUG SESSION COMPLETE'), 'session manager missing compact summary format');
|
|
});
|
|
|
|
test('gsd-debug-session-manager includes anti-heredoc rule', () => {
|
|
const content = fs.readFileSync(path.join(process.cwd(), 'agents', 'gsd-debug-session-manager.md'), 'utf8');
|
|
assert.ok(content.includes('heredoc'), 'session manager missing anti-heredoc rule');
|
|
});
|
|
|
|
test('debug.md delegates to gsd-debug-session-manager', () => {
|
|
const content = fs.readFileSync(path.join(process.cwd(), 'gsd-core', 'workflows', 'debug.md'), 'utf8');
|
|
assert.ok(content.includes('gsd-debug-session-manager'),
|
|
'debug.md does not delegate to session manager');
|
|
});
|
|
|
|
test('DEBUG.md reasoning_checkpoint field-count claim matches gsd-debugger.md YAML keys (parity)', () => {
|
|
// Parallel-surface drift guard (DEFECT.GENERATIVE-FIX): the field-count
|
|
// claim in the DEBUG.md section_rules prose must equal the number of keys
|
|
// enumerated in the gsd-debugger.md reasoning_checkpoint YAML block.
|
|
// CRLF-safe regex/split per DEFECT.WINDOWS-TEST-PORTABILITY. Accepts either
|
|
// digit ("7-field") or word ("seven-field") count form.
|
|
const NUMWORDS = { one: 1, two: 2, three: 3, four: 4, five: 5, six: 6, seven: 7, eight: 8, nine: 9, ten: 10 };
|
|
const debugContent = fs.readFileSync(path.join(process.cwd(), 'gsd-core', 'templates', 'DEBUG.md'), 'utf8');
|
|
const agentContent = fs.readFileSync(path.join(process.cwd(), 'agents', 'gsd-debugger.md'), 'utf8');
|
|
const debugMatch = debugContent.match(/reasoning_checkpoint[^.\r\n]*?(\d+|one|two|three|four|five|six|seven|eight|nine|ten)-field structured reasoning record/i);
|
|
assert.ok(debugMatch, 'DEBUG.md must state a "N-field structured reasoning record" claim for reasoning_checkpoint');
|
|
const claimedCount = /^\d+$/.test(debugMatch[1]) ? parseInt(debugMatch[1], 10) : NUMWORDS[debugMatch[1].toLowerCase()];
|
|
assert.ok(typeof claimedCount === 'number', `unrecognized field-count token: ${debugMatch[1]}`);
|
|
const yamlBlock = agentContent.match(/reasoning_checkpoint:\s*\r?\n([\s\S]*?)```/);
|
|
assert.ok(yamlBlock, 'gsd-debugger.md must define a fenced reasoning_checkpoint YAML block');
|
|
const keys = new Set();
|
|
for (const line of yamlBlock[1].split(/\r?\n/)) {
|
|
// Match 2-space-indented YAML keys (with OR without an inline value —
|
|
// array-valued keys like confirming_evidence: have no trailing space).
|
|
const m = line.match(/^ {2}([a-z_]+):/);
|
|
if (m) keys.add(m[1]);
|
|
}
|
|
assert.strictEqual(
|
|
keys.size,
|
|
claimedCount,
|
|
`parity drift: DEBUG.md claims ${claimedCount}-field but gsd-debugger.md enumerates ${keys.size} keys (${[...keys].join(', ')}). Update BOTH surfaces together.`
|
|
);
|
|
});
|
|
});
|