Fold 94 issue-named command/module regression files into the canonical test file that owns each subject-under-test, across 52 existing suites (state, config, frontmatter, roadmap-parser, capability-registry, shell-command-projection-dispatch, plan-phase-drift-guard, health-validation, runtime-converters, commands, etc.). Verbatim block-scoped describe wrappers; 881 subtests conserved 1:1. No new test files. Host-env pre-check (per B2): the only GSD_WORKSTREAM/GSD_PROJECT-touching destinations (intel, planning-workspace) clear those vars hermetically, so folded CLI tests are safe. Regenerates regression-name allowlist (222->162), ratchets file-count allowlist across 8 buckets (validate entry removed after dropping <=2), makes 34 relocated allow-test-rule exemptions issue-ref-compliant (ADR-456; prunes 34 stale ids). Repoints CONTEXT.md + ADR-0002/443/1235/3524 test-file references. lint:ci green. Part of epic #1969. Closes #1972. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
984 lines
41 KiB
JavaScript
984 lines
41 KiB
JavaScript
/**
|
|
* Drift guard for gsd:plan-phase workflow (#22)
|
|
*
|
|
* Validates that the plan-phase workflow contains the key structural elements
|
|
* added for issue #22 Change #1:
|
|
*
|
|
* (A) intel.enabled gate — when intel.enabled is true, plan-phase regenerates
|
|
* API-SURFACE.md via `gsd-tools intel api-surface` and injects it into the
|
|
* planner's required reading as a HINT (prefer symbols, may be incomplete,
|
|
* absence = unknown, never exhaustive).
|
|
*
|
|
* (B) "Artifacts this phase produces" section — every PLAN.md must include
|
|
* this section so the plan-review-convergence source-grounding pass can
|
|
* exclude newly-created symbols from drift verification.
|
|
*/
|
|
|
|
// allow-test-rule: source-text-is-the-product
|
|
// The workflow markdown IS the runtime instruction. Testing its text content
|
|
// tests the deployed contract — if the intel gate or Artifacts section
|
|
// requirement is absent, the drift-guard feature is absent from defenses too.
|
|
|
|
const { test, describe } = require('node:test');
|
|
const assert = require('node:assert/strict');
|
|
const fs = require('fs');
|
|
const path = require('path');
|
|
|
|
const WORKFLOW_PATH = path.join(
|
|
__dirname,
|
|
'..',
|
|
'gsd-core',
|
|
'workflows',
|
|
'plan-phase.md'
|
|
);
|
|
|
|
// ─── Fixture ──────────────────────────────────────────────────────────────────
|
|
|
|
const workflow = fs.readFileSync(WORKFLOW_PATH, 'utf8');
|
|
|
|
// ─── (A) intel.enabled gate ───────────────────────────────────────────────────
|
|
|
|
describe('plan-phase workflow: intel.enabled gate for API-SURFACE injection (#22)', () => {
|
|
test('workflow reads intel.enabled config before planner spawn', () => {
|
|
assert.ok(
|
|
workflow.includes('intel.enabled'),
|
|
'workflow must gate API-SURFACE generation on intel.enabled config key'
|
|
);
|
|
});
|
|
|
|
test('workflow runs gsd-tools intel api-surface to regenerate surface', () => {
|
|
assert.ok(
|
|
workflow.includes('intel api-surface'),
|
|
'workflow must call `gsd_run intel api-surface` (or equivalent) to regenerate API-SURFACE.md'
|
|
);
|
|
});
|
|
|
|
test('workflow injects API-SURFACE.md into planner files_to_read when intel.enabled', () => {
|
|
assert.ok(
|
|
workflow.includes('API-SURFACE.md') && workflow.includes('API_SURFACE_PATH'),
|
|
'workflow must pass API_SURFACE_PATH into the planner prompt files_to_read block'
|
|
);
|
|
});
|
|
|
|
test('workflow labels the surface as a HINT (not a hard rule)', () => {
|
|
assert.ok(
|
|
workflow.includes('HINT') || workflow.includes('intel_surface_hint'),
|
|
'API-SURFACE.md must be annotated as a HINT, never a hard rule'
|
|
);
|
|
});
|
|
|
|
test('workflow documents that surface absence means unknown not nonexistent', () => {
|
|
assert.ok(
|
|
workflow.includes("absence means *unknown*, not *nonexistent*") ||
|
|
workflow.includes("absence = unknown") ||
|
|
workflow.includes("absence means unknown"),
|
|
"workflow must state that a symbol's absence from the surface means unknown, not nonexistent"
|
|
);
|
|
});
|
|
|
|
test('workflow states the surface may be incomplete', () => {
|
|
assert.ok(
|
|
workflow.includes('MAY BE INCOMPLETE') || workflow.includes('may be incomplete'),
|
|
'workflow must warn that the API surface may be incomplete'
|
|
);
|
|
});
|
|
|
|
test('workflow skips surface injection when intel.enabled is false', () => {
|
|
assert.ok(
|
|
workflow.includes('no active intel step hook exists') &&
|
|
workflow.includes('API_SURFACE_PATH') &&
|
|
(workflow.includes('when: intel.enabled') || workflow.includes('"when": "intel.enabled"')),
|
|
'workflow must skip the intel step when intel.enabled is false — enforced via capability registry when: gate and explicit no-active-hook skip branch'
|
|
);
|
|
});
|
|
});
|
|
|
|
// ─── (B) "Artifacts this phase produces" requirement ─────────────────────────
|
|
|
|
describe('plan-phase workflow: Artifacts this phase produces section (#22)', () => {
|
|
test('downstream_consumer block requires Artifacts this phase produces section', () => {
|
|
assert.ok(
|
|
workflow.includes('Artifacts this phase produces'),
|
|
'downstream_consumer must list "Artifacts this phase produces" as a required plan section'
|
|
);
|
|
});
|
|
|
|
test('quality_gate checklist includes Artifacts this phase produces item', () => {
|
|
// Find the quality_gate block and confirm the checklist item is there
|
|
const qualityGateMatch = workflow.match(/<quality_gate>([\s\S]*?)<\/quality_gate>/);
|
|
assert.ok(
|
|
qualityGateMatch,
|
|
'workflow must have a <quality_gate> block'
|
|
);
|
|
assert.ok(
|
|
qualityGateMatch[1].includes('Artifacts this phase produces'),
|
|
'<quality_gate> checklist must include an "Artifacts this phase produces" item'
|
|
);
|
|
});
|
|
|
|
test('workflow explains why Artifacts section is needed (source-grounding reviewer)', () => {
|
|
assert.ok(
|
|
workflow.includes('source-grounding') || workflow.includes('plan-review-convergence'),
|
|
'workflow must explain that the Artifacts section is consumed by the source-grounding pass'
|
|
);
|
|
});
|
|
|
|
test('workflow lists symbol kinds for Artifacts section (decorators, classes, functions, CLI flags)', () => {
|
|
// Must enumerate concrete symbol kinds so planner knows what to list
|
|
const hasDecorators = workflow.includes('decorators');
|
|
const hasClasses = workflow.includes('classes');
|
|
const hasFunctions = workflow.includes('functions');
|
|
const hasCliFlags = workflow.includes('CLI flags');
|
|
assert.ok(
|
|
hasDecorators && hasClasses && hasFunctions && hasCliFlags,
|
|
'workflow must enumerate symbol kinds: decorators, classes, functions, CLI flags (needed for Artifacts section guidance)'
|
|
);
|
|
});
|
|
});
|
|
|
|
// ─── (C) Top-level spawn guard (#913) ────────────────────────────────────────
|
|
|
|
describe('plan-phase workflow: top-level spawn guard (#913)', () => {
|
|
// Extract the runtime_compatibility block for targeted assertions
|
|
const rtBlock = (() => {
|
|
const m = workflow.match(/<runtime_compatibility>([\s\S]*?)<\/runtime_compatibility>/);
|
|
return m ? m[1] : '';
|
|
})();
|
|
|
|
test('workflow has a runtime_compatibility block asserting Agent is available at top-level', () => {
|
|
assert.ok(
|
|
rtBlock.length > 0,
|
|
'plan-phase must have a <runtime_compatibility> block — prevents role-collapse regression (#913)'
|
|
);
|
|
assert.ok(
|
|
rtBlock.includes('Agent tool IS available') || rtBlock.includes('Agent IS available'),
|
|
'plan-phase runtime_compatibility must assert that the Agent tool IS available at top-level Claude Code (#913)'
|
|
);
|
|
assert.ok(
|
|
rtBlock.toLowerCase().includes('top-level'),
|
|
'plan-phase runtime_compatibility must scope the IS-available assertion to top-level Claude Code (#913)'
|
|
);
|
|
assert.ok(
|
|
rtBlock.includes('Always spawn') || rtBlock.includes('always spawn'),
|
|
'plan-phase runtime_compatibility must state that plan roles must always be spawned (#913)'
|
|
);
|
|
assert.ok(
|
|
rtBlock.includes('Never absorb') || rtBlock.includes('never absorb'),
|
|
'plan-phase runtime_compatibility must state that roles must never be absorbed inline (#913)'
|
|
);
|
|
});
|
|
|
|
test('workflow states --chain/--auto suppress prompts only, not spawns', () => {
|
|
assert.ok(
|
|
rtBlock.includes('suppress') &&
|
|
(rtBlock.includes('prompts only') || rtBlock.includes('interactive prompts only')),
|
|
'plan-phase runtime_compatibility must document that --chain/--auto suppress prompts only, not spawns (#913)'
|
|
);
|
|
});
|
|
|
|
test('workflow does not contain unscoped CODEX RUNTIME orchestrator rule labels', () => {
|
|
// All "wait for subagent" rules must apply to ALL RUNTIMES, not just Codex
|
|
assert.ok(
|
|
!workflow.includes('ORCHESTRATOR RULE — CODEX RUNTIME'),
|
|
'plan-phase must not label orchestrator wait rules as "CODEX RUNTIME" — they apply to all runtimes including top-level Claude Code (#913)'
|
|
);
|
|
});
|
|
|
|
test('workflow contains ALL RUNTIMES orchestrator rule labels (count preserved)', () => {
|
|
// Must have all 7 agent-spawn wait rules still present (none dropped during rename)
|
|
const allRuntimesCount = (workflow.match(/ORCHESTRATOR RULE — ALL RUNTIMES/g) || []).length;
|
|
assert.ok(
|
|
allRuntimesCount >= 7,
|
|
`plan-phase must have at least 7 "ORCHESTRATOR RULE — ALL RUNTIMES" labels (one per agent spawn site); found ${allRuntimesCount} (#913)`
|
|
);
|
|
});
|
|
});
|
|
|
|
// ─── (D) Attempt-based Agent gate (#922) ─────────────────────────────────────
|
|
|
|
describe('plan-phase workflow: attempt-based Agent availability gate (#922)', () => {
|
|
// Extract the runtime_compatibility block for targeted assertions
|
|
const rtBlock = (() => {
|
|
const m = workflow.match(/<runtime_compatibility>([\s\S]*?)<\/runtime_compatibility>/);
|
|
return m ? m[1] : '';
|
|
})();
|
|
|
|
// Extract the "Other runtimes" clause specifically
|
|
const otherRuntimesClause = (() => {
|
|
const m = rtBlock.match(/\*\*Other runtimes[^*]*\*\*[^\n]*\n([\s\S]*?)(?=\n\*\*|$)/);
|
|
return m ? m[0] : rtBlock;
|
|
})();
|
|
|
|
test('Other runtimes clause does not authorize stopping on a self-assessed absence (#922)', () => {
|
|
// The pre-#922 wording ("if the Agent tool is genuinely absent") let the model
|
|
// self-assess and stop without ever attempting a call. The fixed wording must
|
|
// not contain phrasing that authorizes that pattern.
|
|
const forbiddenPatterns = [
|
|
/if the Agent tool is genuinely absent/i,
|
|
/if.*Agent.*genuinely absent/i,
|
|
];
|
|
for (const pattern of forbiddenPatterns) {
|
|
assert.ok(
|
|
!pattern.test(otherRuntimesClause),
|
|
`plan-phase "Other runtimes" clause must not authorize stopping on a self-assessed Agent absence — ` +
|
|
`use attempt-based gate instead (#922). Found: ${otherRuntimesClause.trim()}`
|
|
);
|
|
}
|
|
});
|
|
|
|
test('Other runtimes clause pins "Always attempt the actual Agent() call" language (#922)', () => {
|
|
// Pin the exact contract phrase so a future edit that changes to "try to determine
|
|
// availability" or "check if Agent is available" does not silently reintroduce introspection.
|
|
assert.ok(
|
|
otherRuntimesClause.includes('Always attempt the actual') ||
|
|
otherRuntimesClause.includes('always attempt the actual'),
|
|
`plan-phase "Other runtimes" clause must pin "Always attempt the actual Agent() call" (or equivalent) (#922). ` +
|
|
`Found: ${otherRuntimesClause.trim()}`
|
|
);
|
|
});
|
|
|
|
test('Other runtimes clause pins "real tool-unavailable error" as the only valid stop signal (#922)', () => {
|
|
// Must tie the stop to a real returned error, not a self-assessed absence.
|
|
assert.ok(
|
|
otherRuntimesClause.includes('real tool-unavailable error') ||
|
|
otherRuntimesClause.includes('tool-unavailable error returned'),
|
|
`plan-phase "Other runtimes" clause must state only a real tool-unavailable error from Agent() authorizes stopping (#922). ` +
|
|
`Found: ${otherRuntimesClause.trim()}`
|
|
);
|
|
});
|
|
|
|
test('Other runtimes clause still prohibits inline role collapse (#922 preserves #913)', () => {
|
|
// Even after the attempt-based rewrite the clause must keep the no-inline-collapse guard.
|
|
const hasNoInline =
|
|
otherRuntimesClause.toLowerCase().includes('do not') &&
|
|
(otherRuntimesClause.toLowerCase().includes('inline') ||
|
|
otherRuntimesClause.toLowerCase().includes('collapse'));
|
|
assert.ok(
|
|
hasNoInline,
|
|
`plan-phase "Other runtimes" clause must still prohibit inline role collapse even with the attempt-based gate (#922). ` +
|
|
`Found: ${otherRuntimesClause.trim()}`
|
|
);
|
|
});
|
|
});
|
|
|
|
|
|
// ────────────────────────────────────────────────────────────────────────
|
|
// Folded from tests/bug-2948-spike-wrap-up-dispatch.test.cjs — consolidation epic #1969 (B3 #1972)
|
|
// ────────────────────────────────────────────────────────────────────────
|
|
{
|
|
const { describe: __foldDescribe } = require('node:test');
|
|
__foldDescribe("folded:bug-2948-spike-wrap-up-dispatch (consolidation epic #1969 B3 #1972)", () => {
|
|
/**
|
|
* Regression test for bug #2948
|
|
*
|
|
* `/gsd:spike --wrap-up` was silently no-oping because:
|
|
* 1. `commands/gsd/spike.md` listed `--wrap-up` as a flag but had no dispatch block.
|
|
* 2. `workflows/spike.md` still referenced the deleted `/gsd-spike-wrap-up` entry-point
|
|
* instead of the correct `/gsd:spike --wrap-up` form.
|
|
*
|
|
* Fix:
|
|
* - `commands/gsd/spike.md` now has a dispatch block that routes `--wrap-up` to
|
|
* spike-wrap-up.md, and spike-wrap-up.md is listed in execution_context so the
|
|
* runtime can find it.
|
|
* - `workflows/spike.md` companion references updated from `/gsd-spike-wrap-up` to
|
|
* `/gsd:spike --wrap-up`.
|
|
*/
|
|
|
|
// allow-test-rule: source-text-is-the-product (see #2948)
|
|
// commands/gsd/*.md files ARE what the runtime loads — testing their
|
|
// frontmatter and section content tests the deployed system-prompt contract.
|
|
|
|
'use strict';
|
|
|
|
const { describe, test } = require('node:test');
|
|
const assert = require('node:assert/strict');
|
|
const fs = require('node:fs');
|
|
const path = require('node:path');
|
|
|
|
const SPIKE_CMD_PATH = path.join(__dirname, '..', 'commands', 'gsd', 'spike.md');
|
|
const SPIKE_WORKFLOW_PATH = path.join(__dirname, '..', 'gsd-core', 'workflows', 'spike.md');
|
|
|
|
/**
|
|
* Parse YAML frontmatter + body from a markdown file.
|
|
* Returns a shallow { key: value } map of frontmatter fields plus `_body`.
|
|
* Mirrors the parseFrontmatter utility used in enh-2792-namespace-skills.test.cjs.
|
|
*/
|
|
function parseFrontmatter(content) {
|
|
const lines = content.split(/\r?\n/);
|
|
|
|
// Frontmatter must start at the very first line; a mid-file '---' is a
|
|
// horizontal rule, not a frontmatter delimiter.
|
|
if (lines[0]?.trim() !== '---') {
|
|
return { _body: content };
|
|
}
|
|
|
|
let closeIdx = -1;
|
|
for (let i = 1; i < lines.length; i += 1) {
|
|
if (lines[i].trim() === '---') {
|
|
closeIdx = i;
|
|
break;
|
|
}
|
|
}
|
|
assert.ok(closeIdx !== -1, 'frontmatter block must be delimited by --- on its own lines');
|
|
const fm = {};
|
|
for (const line of lines.slice(1, closeIdx)) {
|
|
const m = line.match(/^([A-Za-z][A-Za-z0-9_-]*):\s*(.*)$/);
|
|
if (!m) continue;
|
|
const [, key, raw] = m;
|
|
fm[key] = raw.trim().replace(/^["']|["']$/g, '');
|
|
}
|
|
fm._body = lines.slice(closeIdx + 1).join('\n');
|
|
return fm;
|
|
}
|
|
|
|
/**
|
|
* Extract the text content of a named XML-like section from a markdown body.
|
|
* Returns null if the section is absent.
|
|
*/
|
|
function extractSection(body, tag) {
|
|
const open = `<${tag}>`;
|
|
const close = `</${tag}>`;
|
|
const start = body.indexOf(open);
|
|
const end = body.indexOf(close);
|
|
if (start === -1 || end === -1) return null;
|
|
return body.slice(start + open.length, end);
|
|
}
|
|
|
|
/**
|
|
* Parse the @-prefixed workflow references out of an execution_context section.
|
|
* Returns an array of resolved reference strings (@ stripped).
|
|
*/
|
|
function parseExecutionContextRefs(section) {
|
|
return section
|
|
.split(/\r?\n/)
|
|
.map(l => l.trim())
|
|
.filter(l => l.startsWith('@'))
|
|
.map(l => l.slice(1).trim());
|
|
}
|
|
|
|
describe('bug-2948: /gsd:spike --wrap-up dispatch wiring', () => {
|
|
describe('commands/gsd/spike.md — frontmatter and section contract', () => {
|
|
test('spike.md command file exists and has valid frontmatter', () => {
|
|
assert.ok(fs.existsSync(SPIKE_CMD_PATH), 'commands/gsd/spike.md should exist');
|
|
const fm = parseFrontmatter(fs.readFileSync(SPIKE_CMD_PATH, 'utf-8'));
|
|
assert.ok(fm.name, 'frontmatter must have a name field');
|
|
});
|
|
|
|
test('argument-hint frontmatter field advertises --wrap-up flag', () => {
|
|
const fm = parseFrontmatter(fs.readFileSync(SPIKE_CMD_PATH, 'utf-8'));
|
|
assert.ok(
|
|
fm['argument-hint'] && fm['argument-hint'].includes('--wrap-up'),
|
|
`argument-hint must advertise --wrap-up; got: "${fm['argument-hint']}"`
|
|
);
|
|
});
|
|
|
|
test('execution_context section includes spike-wrap-up workflow reference', () => {
|
|
const fm = parseFrontmatter(fs.readFileSync(SPIKE_CMD_PATH, 'utf-8'));
|
|
const execSection = extractSection(fm._body, 'execution_context');
|
|
assert.ok(execSection !== null, 'spike.md must have an <execution_context> section');
|
|
const refs = parseExecutionContextRefs(execSection);
|
|
assert.ok(
|
|
refs.some(r => r.includes('spike-wrap-up')),
|
|
`execution_context must declare a spike-wrap-up reference so the runtime can load the workflow; ` +
|
|
`declared refs: ${JSON.stringify(refs)}`
|
|
);
|
|
});
|
|
|
|
test('process section dispatches first-token --wrap-up to spike-wrap-up workflow', () => {
|
|
const fm = parseFrontmatter(fs.readFileSync(SPIKE_CMD_PATH, 'utf-8'));
|
|
const processSection = extractSection(fm._body, 'process');
|
|
assert.ok(processSection, 'spike.md must have a <process> section');
|
|
|
|
const rules = processSection
|
|
.split(/\r?\n/)
|
|
.map(line => line.trim())
|
|
.filter(Boolean);
|
|
|
|
const wrapUpRule = rules.find(line => line.startsWith('- If it is `--wrap-up`:'));
|
|
const fallbackRule = rules.find(line => line.startsWith('- Otherwise:'));
|
|
|
|
assert.ok(
|
|
wrapUpRule && wrapUpRule.includes('strip the flag') && wrapUpRule.includes('spike-wrap-up'),
|
|
'process must define a --wrap-up branch that strips the flag and routes to spike-wrap-up'
|
|
);
|
|
assert.ok(
|
|
fallbackRule && fallbackRule.includes('spike workflow'),
|
|
'process must define an Otherwise fallback to the normal spike workflow'
|
|
);
|
|
});
|
|
});
|
|
|
|
describe('gsd-core/workflows/spike.md — companion references', () => {
|
|
test('spike workflow file exists', () => {
|
|
assert.ok(fs.existsSync(SPIKE_WORKFLOW_PATH), 'gsd-core/workflows/spike.md should exist');
|
|
});
|
|
|
|
test('does NOT reference the deleted /gsd-spike-wrap-up entry-point', () => {
|
|
const fm = parseFrontmatter(fs.readFileSync(SPIKE_WORKFLOW_PATH, 'utf-8'));
|
|
assert.ok(
|
|
!fm._body.includes('/gsd-spike-wrap-up'),
|
|
'workflows/spike.md must not reference the deleted /gsd-spike-wrap-up command; use /gsd:spike --wrap-up instead'
|
|
);
|
|
});
|
|
|
|
test('references /gsd:spike --wrap-up as the canonical wrap-up invocation', () => {
|
|
const fm = parseFrontmatter(fs.readFileSync(SPIKE_WORKFLOW_PATH, 'utf-8'));
|
|
assert.ok(
|
|
fm._body.includes('/gsd:spike --wrap-up'),
|
|
'workflows/spike.md must reference /gsd:spike --wrap-up as the canonical wrap-up command'
|
|
);
|
|
});
|
|
});
|
|
});
|
|
});
|
|
}
|
|
|
|
|
|
// ────────────────────────────────────────────────────────────────────────
|
|
// Folded from tests/bug-2949-sketch-wrap-up-dispatch.test.cjs — consolidation epic #1969 (B3 #1972)
|
|
// ────────────────────────────────────────────────────────────────────────
|
|
{
|
|
const { describe: __foldDescribe } = require('node:test');
|
|
__foldDescribe("folded:bug-2949-sketch-wrap-up-dispatch (consolidation epic #1969 B3 #1972)", () => {
|
|
// allow-test-rule: source-text-is-the-product (see #2949)
|
|
// 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.
|
|
|
|
/**
|
|
* GSD Tests — /gsd:sketch --wrap-up silently no-ops (#2949)
|
|
*
|
|
* The --wrap-up flag was documented in commands/gsd/sketch.md but never dispatched.
|
|
* The sketch-wrap-up.md micro-skill entry point was deleted in #2790 and the dispatch
|
|
* wiring was never added to the command or workflow.
|
|
*/
|
|
|
|
'use strict';
|
|
|
|
const { describe, test } = require('node:test');
|
|
const assert = require('node:assert/strict');
|
|
const fs = require('fs');
|
|
const path = require('path');
|
|
|
|
const ROOT = path.resolve(__dirname, '..');
|
|
const SKETCH_COMMAND = path.join(ROOT, 'commands/gsd/sketch.md');
|
|
const SKETCH_WORKFLOW = path.join(ROOT, 'gsd-core/workflows/sketch.md');
|
|
|
|
describe('bug-2949: sketch --wrap-up dispatch wiring', () => {
|
|
test('commands/gsd/sketch.md contains --wrap-up dispatch logic', () => {
|
|
const content = fs.readFileSync(SKETCH_COMMAND, 'utf8');
|
|
assert.ok(
|
|
content.includes('--wrap-up'),
|
|
'sketch.md should contain --wrap-up dispatch logic'
|
|
);
|
|
// The dispatch should route to sketch-wrap-up workflow
|
|
assert.ok(
|
|
content.includes('sketch-wrap-up'),
|
|
'sketch.md should reference sketch-wrap-up in dispatch logic'
|
|
);
|
|
});
|
|
|
|
test('commands/gsd/sketch.md has sketch-wrap-up in execution_context section', () => {
|
|
const content = fs.readFileSync(SKETCH_COMMAND, 'utf8');
|
|
// Find execution_context block
|
|
const execCtxMatch = content.match(/<execution_context>([\s\S]*?)<\/execution_context>/);
|
|
assert.ok(execCtxMatch, 'sketch.md must have an <execution_context> block');
|
|
const execCtx = execCtxMatch[1];
|
|
assert.ok(
|
|
execCtx.includes('sketch-wrap-up'),
|
|
`execution_context block should include sketch-wrap-up workflow; got: ${execCtx}`
|
|
);
|
|
});
|
|
|
|
test('workflows/sketch.md does NOT contain old /gsd-sketch-wrap-up form', () => {
|
|
const content = fs.readFileSync(SKETCH_WORKFLOW, 'utf8');
|
|
assert.ok(
|
|
!content.includes('/gsd-sketch-wrap-up'),
|
|
'workflows/sketch.md must not reference the old /gsd-sketch-wrap-up command'
|
|
);
|
|
});
|
|
|
|
test('workflows/sketch.md DOES contain new /gsd:sketch --wrap-up form', () => {
|
|
const content = fs.readFileSync(SKETCH_WORKFLOW, 'utf8');
|
|
assert.ok(
|
|
content.includes('/gsd:sketch --wrap-up'),
|
|
'workflows/sketch.md should reference /gsd:sketch --wrap-up (the new form)'
|
|
);
|
|
});
|
|
});
|
|
});
|
|
}
|
|
|
|
|
|
// ────────────────────────────────────────────────────────────────────────
|
|
// Folded from tests/bug-3156-plan-phase-opencode-dispatch.test.cjs — consolidation epic #1969 (B3 #1972)
|
|
// ────────────────────────────────────────────────────────────────────────
|
|
{
|
|
const { describe: __foldDescribe } = require('node:test');
|
|
__foldDescribe("folded:bug-3156-plan-phase-opencode-dispatch (consolidation epic #1969 B3 #1972)", () => {
|
|
'use strict';
|
|
|
|
// allow-test-rule: source-text-is-the-product (see #3156)
|
|
// commands/gsd/*.md files are the deployed skill surface. Their frontmatter
|
|
// IS the runtime contract. Checking frontmatter fields checks deployed behaviour.
|
|
|
|
/**
|
|
* #3156 — plan-phase auto-dispatches to gsd-planner subagent on OpenCode,
|
|
* losing Task tool access.
|
|
*
|
|
* Root cause: commands/gsd/plan-phase.md had `agent: gsd-planner` in its
|
|
* frontmatter. Per OpenCode docs, `agent: <name>` in a command causes
|
|
* auto-dispatch to a subagent context where the Agent (Task spawner) tool is
|
|
* unavailable. Orchestrator commands that need to spawn subagents via the
|
|
* Agent tool must NOT carry an `agent:` frontmatter directive.
|
|
*
|
|
* This test parses the YAML frontmatter of every commands/gsd/*.md file and
|
|
* asserts:
|
|
* 1. No command file has an `agent:` frontmatter directive at all.
|
|
* (The directive causes OpenCode to auto-dispatch, breaking any command
|
|
* that relies on the Agent tool to spawn subagents.)
|
|
* 2. Any command whose allowed-tools includes `Agent` (an orchestrator) must
|
|
* not have `agent:` in its frontmatter.
|
|
*/
|
|
|
|
const { test, describe } = require('node:test');
|
|
const assert = require('node:assert/strict');
|
|
const fs = require('node:fs');
|
|
const path = require('node:path');
|
|
|
|
const ROOT = path.join(__dirname, '..');
|
|
const COMMANDS_DIR = path.join(ROOT, 'commands', 'gsd');
|
|
|
|
/** Parse the YAML frontmatter block between the first two `---` delimiters. */
|
|
function parseFrontmatter(content) {
|
|
const lines = content.split(/\r?\n/);
|
|
if (lines[0].trim() !== '---') return {};
|
|
const end = lines.findIndex((line, idx) => idx > 0 && line.trim() === '---');
|
|
if (end === -1) return {};
|
|
const fm = {};
|
|
let currentKey = null;
|
|
for (const line of lines.slice(1, end)) {
|
|
const kv = line.match(/^([a-zA-Z0-9_-]+):\s*(.*)/);
|
|
if (kv) {
|
|
currentKey = kv[1];
|
|
fm[currentKey] = kv[2].trim();
|
|
} else if (currentKey && line.match(/^\s+-\s+/)) {
|
|
const val = line.replace(/^\s+-\s+/, '').trim();
|
|
fm[currentKey] = fm[currentKey] ? fm[currentKey] + '\n' + val : val;
|
|
}
|
|
}
|
|
return fm;
|
|
}
|
|
|
|
/** Return the list of tools from the allowed-tools frontmatter block. */
|
|
function allowedTools(fm) {
|
|
const raw = fm['allowed-tools'];
|
|
if (!raw) return [];
|
|
// Multi-line YAML list: each entry on its own line
|
|
if (raw.includes('\n')) {
|
|
return raw.split('\n').map(t => t.trim()).filter(Boolean);
|
|
}
|
|
return raw.split(',').map(t => t.trim()).filter(Boolean);
|
|
}
|
|
|
|
const commandFiles = fs
|
|
.readdirSync(COMMANDS_DIR)
|
|
.filter(f => f.endsWith('.md'))
|
|
.map(f => ({
|
|
name: f,
|
|
full: path.join(COMMANDS_DIR, f),
|
|
content: fs.readFileSync(path.join(COMMANDS_DIR, f), 'utf-8'),
|
|
}));
|
|
|
|
// ─── No command may carry `agent:` ────────────────────────────────────────────
|
|
//
|
|
// OpenCode interprets `agent: <name>` as "auto-dispatch to this subagent",
|
|
// which removes the Agent (subagent-spawner) tool from the command's context.
|
|
// Any orchestrator command is immediately broken. Commands that need to run in
|
|
// the main agent context (i.e., all GSD commands) must omit this directive.
|
|
|
|
describe('#3156 — no command file may have an `agent:` frontmatter directive', () => {
|
|
for (const { name, content } of commandFiles) {
|
|
test(`${name}: no agent: directive in frontmatter`, () => {
|
|
const fm = parseFrontmatter(content);
|
|
assert.ok(
|
|
!Object.prototype.hasOwnProperty.call(fm, 'agent'),
|
|
`${name}: has \`agent: ${fm['agent']}\` in frontmatter — ` +
|
|
'this causes OpenCode to auto-dispatch to a subagent context where the ' +
|
|
'Agent tool is unavailable, breaking orchestrator workflows. ' +
|
|
'Remove the `agent:` directive so the command runs in the main agent context.',
|
|
);
|
|
});
|
|
}
|
|
});
|
|
|
|
// ─── Orchestrator commands must not have `agent:` ────────────────────────────
|
|
//
|
|
// Redundant with the above (belt-and-suspenders), but captures the precise
|
|
// failure mode from #3156: a command whose allowed-tools includes `Agent`
|
|
// relies on spawning subagents. Pairing that with `agent:` is self-defeating.
|
|
|
|
describe('#3156 — orchestrator commands (allowed-tools: Agent) must not have agent:', () => {
|
|
const orchestrators = commandFiles.filter(({ content }) => {
|
|
const fm = parseFrontmatter(content);
|
|
const tools = allowedTools(fm);
|
|
return tools.includes('Agent');
|
|
});
|
|
|
|
for (const { name, content } of orchestrators) {
|
|
test(`${name}: orchestrator must not carry agent: directive`, () => {
|
|
const fm = parseFrontmatter(content);
|
|
assert.ok(
|
|
!Object.prototype.hasOwnProperty.call(fm, 'agent'),
|
|
`${name}: allowed-tools includes Agent (orchestrator) but also has ` +
|
|
`\`agent: ${fm['agent']}\` — OpenCode will auto-dispatch to a subagent ` +
|
|
'where Agent is unavailable, making the orchestrator unable to spawn ' +
|
|
'researcher/planner/checker subagents. Remove the `agent:` directive.',
|
|
);
|
|
});
|
|
}
|
|
});
|
|
});
|
|
}
|
|
|
|
|
|
// ────────────────────────────────────────────────────────────────────────
|
|
// Folded from tests/enh-2310-chunked-plan-phase.test.cjs — consolidation epic #1969 (B3 #1972)
|
|
// ────────────────────────────────────────────────────────────────────────
|
|
{
|
|
const { describe: __foldDescribe } = require('node:test');
|
|
__foldDescribe("folded:enh-2310-chunked-plan-phase (consolidation epic #1969 B3 #1972)", () => {
|
|
// allow-test-rule: source-text-is-the-product (see #2310)
|
|
// 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';
|
|
|
|
|
|
/**
|
|
* Tests for #2310: plan-phase chunked mode + filesystem fallback.
|
|
*
|
|
* Context: on Windows (and occasionally other platforms), gsd-planner's
|
|
* Task() call may never return even though the subagent finished writing all
|
|
* PLAN.md files to disk. The orchestrator hangs indefinitely. Two mitigations:
|
|
*
|
|
* 1. Filesystem fallback (steps 9a, 11a): if the Task() return lacks the
|
|
* expected marker but PLAN.md files exist on disk, surface a recoverable
|
|
* prompt instead of hanging/failing silently.
|
|
*
|
|
* 2. Chunked mode (step 8.5): --chunked flag / workflow.plan_chunked config
|
|
* splits the single long planner Task into (a) a short outline Task and
|
|
* (b) N short single-plan Tasks. Each Task is shorter-lived, the
|
|
* orchestrator can commit work incrementally, and a hang loses only one
|
|
* plan instead of the entire phase.
|
|
*/
|
|
|
|
const { test, describe } = require('node:test');
|
|
const assert = require('node:assert/strict');
|
|
const fs = require('node:fs');
|
|
const path = require('node:path');
|
|
|
|
const PLAN_PHASE = path.join(
|
|
__dirname, '..', 'gsd-core', 'workflows', 'plan-phase.md'
|
|
);
|
|
|
|
const PLANNER_AGENT = path.join(__dirname, '..', 'agents', 'gsd-planner.md');
|
|
const PLANNER_CHUNKED_REF = path.join(__dirname, '..', 'gsd-core', 'references', 'planner-chunked.md');
|
|
const CONFIG_SCHEMA = path.join(__dirname, '..', 'gsd-core', 'bin', 'lib', 'config-schema.cjs');
|
|
const CONFIGURATION_MD = path.join(__dirname, '..', 'docs', 'CONFIGURATION.md');
|
|
|
|
describe('plan-phase.md — filesystem fallback (#2310)', () => {
|
|
const content = fs.readFileSync(PLAN_PHASE, 'utf-8');
|
|
|
|
test('step 9 checks PLAN.md count on disk when planner return lacks completion marker', () => {
|
|
assert.ok(
|
|
content.includes('DISK_PLANS=$(ls "${PHASE_DIR}"/*-PLAN.md'),
|
|
'step 9a must check disk for PLAN.md files via DISK_PLANS variable'
|
|
);
|
|
});
|
|
|
|
test('step 9a fallback section exists', () => {
|
|
assert.ok(
|
|
content.includes('## 9a. Filesystem Fallback'),
|
|
'plan-phase.md must have a ## 9a. Filesystem Fallback section for planner hang recovery'
|
|
);
|
|
});
|
|
|
|
test('step 9a fallback offers Accept plans option', () => {
|
|
assert.ok(
|
|
content.includes('Accept plans'),
|
|
'step 9a must offer "Accept plans" as a recovery option'
|
|
);
|
|
});
|
|
|
|
test('step 9a fallback offers Retry planner option', () => {
|
|
assert.ok(
|
|
content.includes('Retry planner'),
|
|
'step 9a must offer "Retry planner" as a recovery option'
|
|
);
|
|
});
|
|
|
|
test('step 11 has filesystem fallback section', () => {
|
|
assert.ok(
|
|
content.includes('## 11a. Filesystem Fallback'),
|
|
'plan-phase.md must have a ## 11a. Filesystem Fallback section for checker hang recovery'
|
|
);
|
|
});
|
|
|
|
test('step 11a fallback offers Accept verification option', () => {
|
|
assert.ok(
|
|
content.includes('Accept verification'),
|
|
'step 11a must offer "Accept verification" as a recovery option'
|
|
);
|
|
});
|
|
|
|
test('step 11a fallback offers Retry checker option', () => {
|
|
assert.ok(
|
|
content.includes('Retry checker'),
|
|
'step 11a must offer "Retry checker" as a recovery option'
|
|
);
|
|
});
|
|
|
|
test('step 9 routes to step 9a when no recognized marker found', () => {
|
|
assert.ok(
|
|
content.includes('step 9a') || content.includes('9a.'),
|
|
'step 9 handle-return must reference the filesystem fallback path (step 9a)'
|
|
);
|
|
});
|
|
|
|
test('step 11 routes to step 11a when no recognized marker found', () => {
|
|
assert.ok(
|
|
content.includes('step 11a') || content.includes('11a.'),
|
|
'step 11 handle-return must reference the filesystem fallback path (step 11a)'
|
|
);
|
|
});
|
|
});
|
|
|
|
describe('plan-phase.md — chunked mode flag and config (#2310)', () => {
|
|
const content = fs.readFileSync(PLAN_PHASE, 'utf-8');
|
|
|
|
test('step 2 parses --chunked flag', () => {
|
|
assert.ok(
|
|
content.includes('--chunked'),
|
|
'step 2 must parse --chunked flag from $ARGUMENTS'
|
|
);
|
|
});
|
|
|
|
test('step 2 reads workflow.plan_chunked config', () => {
|
|
assert.ok(
|
|
content.includes('workflow.plan_chunked'),
|
|
'step 2 must read workflow.plan_chunked config key'
|
|
);
|
|
});
|
|
|
|
test('step 2 sets CHUNKED_MODE variable', () => {
|
|
assert.ok(
|
|
content.includes('CHUNKED_MODE'),
|
|
'step 2 must set CHUNKED_MODE from flag or config'
|
|
);
|
|
});
|
|
});
|
|
|
|
describe('plan-phase.md — chunked mode implementation (#2310)', () => {
|
|
const content = fs.readFileSync(PLAN_PHASE, 'utf-8');
|
|
|
|
test('step 8.5 chunked planning section exists', () => {
|
|
assert.ok(
|
|
content.includes('## 8.5.'),
|
|
'plan-phase.md must have a step 8.5 section for chunked planning mode'
|
|
);
|
|
});
|
|
|
|
test('chunked mode produces PLAN-OUTLINE.md', () => {
|
|
assert.ok(
|
|
content.includes('PLAN-OUTLINE.md'),
|
|
'chunked mode outline step must produce a *-PLAN-OUTLINE.md file'
|
|
);
|
|
});
|
|
|
|
test('chunked outline step uses outline-only mode', () => {
|
|
assert.ok(
|
|
content.includes('outline-only'),
|
|
'chunked step 8.5.1 must spawn the planner in outline-only mode'
|
|
);
|
|
});
|
|
|
|
test('chunked per-plan step uses single-plan mode', () => {
|
|
assert.ok(
|
|
content.includes('single-plan'),
|
|
'chunked step 8.5.2 must spawn the planner in single-plan mode for each plan'
|
|
);
|
|
});
|
|
|
|
test('chunked mode checks for existing outline to enable resume', () => {
|
|
// The resume check skips the outline Task if PLAN-OUTLINE.md already exists
|
|
assert.ok(
|
|
content.includes('PLAN-OUTLINE.md') && content.includes('already exists'),
|
|
'chunked mode must detect existing PLAN-OUTLINE.md and skip outline generation (resume safety)'
|
|
);
|
|
});
|
|
|
|
test('chunked mode commits each plan individually', () => {
|
|
assert.ok(
|
|
content.includes('chunked'),
|
|
'chunked mode must commit each individual plan for crash resilience'
|
|
);
|
|
});
|
|
|
|
test('step 8 routes to chunked path when CHUNKED_MODE is true', () => {
|
|
assert.ok(
|
|
content.includes('CHUNKED_MODE') && content.includes('8.5'),
|
|
'step 8 must route to step 8.5 when CHUNKED_MODE is true'
|
|
);
|
|
});
|
|
});
|
|
|
|
describe('gsd-planner.md — references planner-chunked.md (#2310)', () => {
|
|
const plannerContent = fs.readFileSync(PLANNER_AGENT, 'utf-8');
|
|
|
|
test('gsd-planner.md references planner-chunked.md for chunked return formats', () => {
|
|
assert.ok(
|
|
plannerContent.includes('planner-chunked.md'),
|
|
'gsd-planner.md must reference planner-chunked.md for ## OUTLINE COMPLETE / ## PLAN COMPLETE formats'
|
|
);
|
|
});
|
|
});
|
|
|
|
describe('planner-chunked.md — chunked return formats (#2310)', () => {
|
|
const content = fs.readFileSync(PLANNER_CHUNKED_REF, 'utf-8');
|
|
|
|
test('planner-chunked.md defines OUTLINE COMPLETE structured return', () => {
|
|
assert.ok(
|
|
content.includes('## OUTLINE COMPLETE'),
|
|
'planner-chunked.md must define ## OUTLINE COMPLETE return format for outline-only mode'
|
|
);
|
|
});
|
|
|
|
test('planner-chunked.md defines PLAN COMPLETE structured return for single-plan mode', () => {
|
|
assert.ok(
|
|
content.includes('## PLAN COMPLETE'),
|
|
'planner-chunked.md must define ## PLAN COMPLETE return format for single-plan mode'
|
|
);
|
|
});
|
|
|
|
test('planner-chunked.md describes resume behaviour', () => {
|
|
assert.ok(
|
|
content.includes('Resume') || content.includes('resume'),
|
|
'planner-chunked.md must describe resume behaviour for interrupted chunked runs'
|
|
);
|
|
});
|
|
});
|
|
|
|
describe('config-schema.cjs — workflow.plan_chunked key (#2310)', () => {
|
|
test('VALID_CONFIG_KEYS includes workflow.plan_chunked', () => {
|
|
const { VALID_CONFIG_KEYS } = require(CONFIG_SCHEMA);
|
|
assert.ok(
|
|
VALID_CONFIG_KEYS.has('workflow.plan_chunked'),
|
|
'config-schema.cjs VALID_CONFIG_KEYS must include workflow.plan_chunked'
|
|
);
|
|
});
|
|
});
|
|
|
|
describe('docs/CONFIGURATION.md — workflow.plan_chunked documented (#2310)', () => {
|
|
const content = fs.readFileSync(CONFIGURATION_MD, 'utf-8');
|
|
|
|
test('CONFIGURATION.md documents workflow.plan_chunked', () => {
|
|
assert.ok(
|
|
content.includes('`workflow.plan_chunked`'),
|
|
'docs/CONFIGURATION.md must document workflow.plan_chunked'
|
|
);
|
|
});
|
|
});
|
|
});
|
|
}
|
|
|
|
|
|
// ────────────────────────────────────────────────────────────────────────
|
|
// Folded from tests/enh-3209-plan-phase-ingest-adr.test.cjs — consolidation epic #1969 (B3 #1972)
|
|
// ────────────────────────────────────────────────────────────────────────
|
|
{
|
|
const { describe: __foldDescribe } = require('node:test');
|
|
__foldDescribe("folded:enh-3209-plan-phase-ingest-adr (consolidation epic #1969 B3 #1972)", () => {
|
|
// allow-test-rule: source-text-is-the-product (see #3209)
|
|
// These assertions validate shipped workflow/command markdown contracts.
|
|
|
|
const { test, describe } = require('node:test');
|
|
const assert = require('node:assert/strict');
|
|
const fs = require('fs');
|
|
const path = require('path');
|
|
|
|
const ROOT = path.join(__dirname, '..');
|
|
const COMMAND_PATH = path.join(ROOT, 'commands', 'gsd', 'plan-phase.md');
|
|
const WORKFLOW_PATH = path.join(ROOT, 'gsd-core', 'workflows', 'plan-phase.md');
|
|
const DOCS_COMMANDS_PATH = path.join(ROOT, 'docs', 'COMMANDS.md');
|
|
|
|
function read(filePath) {
|
|
return fs.readFileSync(filePath, 'utf8');
|
|
}
|
|
|
|
describe('enh #3209: plan-phase ADR ingest express path', () => {
|
|
test('command argument-hint advertises --ingest and --ingest-format', () => {
|
|
const command = read(COMMAND_PATH);
|
|
assert.ok(command.includes('--ingest <path-or-glob>'),
|
|
'plan-phase command argument-hint must include --ingest <path-or-glob>');
|
|
assert.ok(command.includes('--ingest-format <auto|nygard|madr|narrative>'),
|
|
'plan-phase command argument-hint must include --ingest-format selector');
|
|
});
|
|
|
|
test('workflow parses --ingest and --ingest-format flags', () => {
|
|
const workflow = read(WORKFLOW_PATH);
|
|
assert.ok(workflow.includes('--ingest <path-or-glob>'),
|
|
'plan-phase workflow argument parsing must mention --ingest');
|
|
assert.ok(workflow.includes('--ingest-format'),
|
|
'plan-phase workflow argument parsing must mention --ingest-format');
|
|
});
|
|
|
|
test('workflow has explicit mutual exclusion guard for --prd and --ingest', () => {
|
|
const workflow = read(WORKFLOW_PATH);
|
|
assert.ok(
|
|
workflow.includes('cannot combine `--prd` with `--ingest`') ||
|
|
workflow.includes('mutually exclusive'),
|
|
'plan-phase workflow must fail fast when --prd and --ingest are both provided'
|
|
);
|
|
});
|
|
|
|
test('workflow defines an ADR ingest express-path step', () => {
|
|
const workflow = read(WORKFLOW_PATH);
|
|
assert.ok(/##\s*(?:\d+(?:\.\d+)*)?\.?\s*Handle ADR Ingest Express Path/i.test(workflow),
|
|
'plan-phase workflow must include a dedicated ADR ingest express-path step');
|
|
assert.ok(workflow.includes('ADR Ingest Express Path'),
|
|
'workflow must display ADR ingest express-path banner text');
|
|
});
|
|
|
|
test('ADR ingest context template includes scope fence and ADR source attribution', () => {
|
|
const workflow = read(WORKFLOW_PATH);
|
|
assert.ok(workflow.includes('<scope_fence>'),
|
|
'ADR ingest context template must include <scope_fence> for hard out-of-scope exclusions');
|
|
assert.ok(workflow.includes('Source:** ADR Ingest Express Path'),
|
|
'ADR ingest context template must tag source as ADR Ingest Express Path');
|
|
});
|
|
|
|
test('workflow documents status gate and no-decisions fallback', () => {
|
|
const workflow = read(WORKFLOW_PATH);
|
|
assert.ok(
|
|
workflow.includes('Reject `superseded`/`rejected`/`deprecated`') ||
|
|
workflow.includes('reject `superseded`/`rejected`/`deprecated`') ||
|
|
/superseded.*rejected.*deprecated/i.test(workflow),
|
|
'ADR ingest workflow must include status gate for non-active ADRs'
|
|
);
|
|
assert.ok(
|
|
workflow.includes('empty-decisions fallback') ||
|
|
workflow.includes('fall back to discuss-phase'),
|
|
'ADR ingest workflow must document fallback when no locked decisions are present'
|
|
);
|
|
});
|
|
|
|
test('docs COMMANDS advertises --ingest flag for /gsd-plan-phase', () => {
|
|
const commands = read(DOCS_COMMANDS_PATH);
|
|
assert.ok(commands.includes('--ingest <path-or-glob>'),
|
|
'docs/COMMANDS.md must document --ingest for /gsd-plan-phase');
|
|
});
|
|
});
|
|
});
|
|
}
|