An allow-test-rule annotation citing a category that does not apply is worse than no annotation, because it reads as reviewed. Eight were confirmed by reading the assertions each one covered, and auditing the rest found five more plus one refutation — a converter test whose wording described the wrong mechanism while the covered assertion genuinely was deployed-text. The instructive one used the CANONICAL string for the same mistake: STATE.md command output labelled as a deployed artifact. A canonical string is not evidence the category fits, which is why normalising strings alone would have laundered the problem rather than fixed it. Every mapping the audit had inferred rather than code-verified was spot-checked before rewriting, and the ones that turned out not to fit were re-annotated rather than relabelled. Fourteen STATE.md assertions had a typed extractor available all along and now use it; their annotations came out because nothing needs exempting. Eight assertions genuinely need a production change first — CLI stdout and stderr with no structured mode — and are tagged pending-migration-to-typed-ir citing #3090, which is what that category is for. It had zero real uses before this, while one file carried a real citation to migration issue #2974 under a non-canonical tag. Six annotations covered assertions that do no text matching at all. An exemption for a violation that does not exist is noise that makes the real ones harder to audit; those are removed. atomic-write-coverage gains the annotation it always warranted — its own docstring describes a structural-regression-guard while the file carried none. Fifty-nine non-canonical strings across roughly thirty files are normalised, and the allow-test-rule allowlist is regenerated to match. 472 annotations became 463: every one now uses a canonical category, and the two remaining non-canonical strings are ESLint RuleTester fixtures, not annotations. Refs #3057 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
243 lines
10 KiB
JavaScript
243 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.
|
|
|
|
/**
|
|
* Tests for modular decomposition of agents/gsd-planner.md
|
|
*
|
|
* Verifies that:
|
|
* 1. gsd-planner.md stays under the 100K agent file threshold
|
|
* 2. gsd-planner.md is under 45K chars (proving the three mode sections were extracted)
|
|
* 3. The three reference files exist
|
|
* 4. gsd-planner.md contains reference pointers to each extracted file
|
|
* 5. Each reference file contains key content from the original mode section
|
|
*/
|
|
'use strict';
|
|
|
|
const { describe, test } = require('node:test');
|
|
const assert = require('node:assert/strict');
|
|
const fs = require('fs');
|
|
const path = require('path');
|
|
|
|
const PROJECT_ROOT = path.join(__dirname, '..');
|
|
|
|
// ─── Size thresholds ─────────────────────────────────────────────────────────
|
|
|
|
const AGENT_FILE_SIZE_LIMIT = 100 * 1024; // 100K — appropriate for version-controlled source
|
|
const PLANNER_EXTRACTED_LIMIT = 48 * 1024; // 48K — proves extraction happened
|
|
|
|
// ─── File paths ──────────────────────────────────────────────────────────────
|
|
|
|
const PLANNER_PATH = path.join(PROJECT_ROOT, 'agents', 'gsd-planner.md');
|
|
const GAP_CLOSURE_REF = path.join(PROJECT_ROOT, 'gsd-core', 'references', 'planner-gap-closure.md');
|
|
const REVISION_REF = path.join(PROJECT_ROOT, 'gsd-core', 'references', 'planner-revision.md');
|
|
const REVIEWS_REF = path.join(PROJECT_ROOT, 'gsd-core', 'references', 'planner-reviews.md');
|
|
|
|
// ─── gsd-planner.md size ─────────────────────────────────────────────────────
|
|
|
|
describe('gsd-planner.md size constraints', () => {
|
|
test('planner file exists', () => {
|
|
assert.ok(fs.existsSync(PLANNER_PATH), `Missing: ${PLANNER_PATH}`);
|
|
});
|
|
|
|
test('planner is under 100K chars (agent file threshold)', () => {
|
|
const raw = fs.readFileSync(PLANNER_PATH, 'utf-8');
|
|
// Normalize CRLF → LF before measuring — Windows checkouts inflate length by ~1 char/line
|
|
const content = raw.replace(/\r\n/g, '\n').replace(/\r/g, '\n');
|
|
assert.ok(
|
|
content.length < AGENT_FILE_SIZE_LIMIT,
|
|
`gsd-planner.md is ${content.length} chars, exceeds 100K agent threshold`
|
|
);
|
|
});
|
|
|
|
test('planner is under 45K chars (proves mode sections were extracted)', () => {
|
|
const raw = fs.readFileSync(PLANNER_PATH, 'utf-8');
|
|
// Normalize CRLF → LF before measuring — Windows checkouts inflate length by ~1 char/line
|
|
const content = raw.replace(/\r\n/g, '\n').replace(/\r/g, '\n');
|
|
assert.ok(
|
|
content.length < PLANNER_EXTRACTED_LIMIT,
|
|
`gsd-planner.md is ${content.length} chars, expected < 45K after extracting mode sections`
|
|
);
|
|
});
|
|
});
|
|
|
|
// ─── Reference files exist ───────────────────────────────────────────────────
|
|
|
|
describe('extracted reference files exist', () => {
|
|
test('planner-gap-closure.md exists', () => {
|
|
assert.ok(fs.existsSync(GAP_CLOSURE_REF), `Missing: ${GAP_CLOSURE_REF}`);
|
|
});
|
|
|
|
test('planner-revision.md exists', () => {
|
|
assert.ok(fs.existsSync(REVISION_REF), `Missing: ${REVISION_REF}`);
|
|
});
|
|
|
|
test('planner-reviews.md exists', () => {
|
|
assert.ok(fs.existsSync(REVIEWS_REF), `Missing: ${REVIEWS_REF}`);
|
|
});
|
|
});
|
|
|
|
// ─── gsd-planner.md contains reference pointers ──────────────────────────────
|
|
|
|
describe('gsd-planner.md contains reference pointers to extracted files', () => {
|
|
let plannerContent;
|
|
|
|
test('planner references planner-gap-closure.md', () => {
|
|
plannerContent = plannerContent || fs.readFileSync(PLANNER_PATH, 'utf-8');
|
|
assert.ok(
|
|
plannerContent.includes('planner-gap-closure.md'),
|
|
'gsd-planner.md must reference planner-gap-closure.md'
|
|
);
|
|
});
|
|
|
|
test('planner references planner-revision.md', () => {
|
|
plannerContent = plannerContent || fs.readFileSync(PLANNER_PATH, 'utf-8');
|
|
assert.ok(
|
|
plannerContent.includes('planner-revision.md'),
|
|
'gsd-planner.md must reference planner-revision.md'
|
|
);
|
|
});
|
|
|
|
test('planner references planner-reviews.md', () => {
|
|
plannerContent = plannerContent || fs.readFileSync(PLANNER_PATH, 'utf-8');
|
|
assert.ok(
|
|
plannerContent.includes('planner-reviews.md'),
|
|
'gsd-planner.md must reference planner-reviews.md'
|
|
);
|
|
});
|
|
});
|
|
|
|
// ─── Reference files contain key content ────────────────────────────────────
|
|
|
|
describe('reference files contain key content from original mode sections', () => {
|
|
test('planner-gap-closure.md contains gap closure content', () => {
|
|
const content = fs.readFileSync(GAP_CLOSURE_REF, 'utf-8');
|
|
const hasGapContent = content.toLowerCase().includes('gap_closure') ||
|
|
content.toLowerCase().includes('gap closure') ||
|
|
content.includes('GAP CLOSURE') ||
|
|
content.includes('--gaps');
|
|
assert.ok(hasGapContent, 'planner-gap-closure.md must contain gap closure mode content');
|
|
});
|
|
|
|
test('planner-revision.md contains revision content', () => {
|
|
const content = fs.readFileSync(REVISION_REF, 'utf-8');
|
|
const hasRevisionContent = content.includes('revision') ||
|
|
content.includes('Revision') ||
|
|
content.includes('REVISION') ||
|
|
content.includes('revision_context');
|
|
assert.ok(hasRevisionContent, 'planner-revision.md must contain revision mode content');
|
|
});
|
|
|
|
test('planner-reviews.md contains reviews content', () => {
|
|
const content = fs.readFileSync(REVIEWS_REF, 'utf-8');
|
|
const hasReviewsContent = content.includes('reviews') ||
|
|
content.includes('Reviews') ||
|
|
content.includes('REVIEWS') ||
|
|
content.includes('REVIEWS.md');
|
|
assert.ok(hasReviewsContent, 'planner-reviews.md must contain reviews mode content');
|
|
});
|
|
});
|
|
|
|
|
|
// ────────────────────────────────────────────────────────────────────────
|
|
// Folded from tests/bug-3320-planner-deep-work-rules.test.cjs — consolidation epic #1969 (B4 #1973)
|
|
// ────────────────────────────────────────────────────────────────────────
|
|
{
|
|
const { describe: __foldDescribe } = require('node:test');
|
|
__foldDescribe("folded:bug-3320-planner-deep-work-rules (consolidation epic #1969 B4 #1973)", () => {
|
|
'use strict';
|
|
|
|
// allow-test-rule: source-text-is-the-product [#3320]
|
|
// The bug is a contradiction in prompt/workflow source text. These assertions
|
|
// intentionally pin the contract words that planner agents consume.
|
|
|
|
const { describe, test } = require('node:test');
|
|
const assert = require('node:assert/strict');
|
|
const fs = require('fs');
|
|
const path = require('path');
|
|
|
|
const ROOT = path.join(__dirname, '..');
|
|
const PLANNER_AGENT = path.join(ROOT, 'agents', 'gsd-planner.md');
|
|
const PLAN_PHASE_WORKFLOW = path.join(ROOT, 'gsd-core', 'workflows', 'plan-phase.md');
|
|
|
|
function read(relativePath) {
|
|
return fs.readFileSync(path.join(ROOT, relativePath), 'utf8');
|
|
}
|
|
|
|
function extractDeepWorkRules() {
|
|
const workflow = fs.readFileSync(PLAN_PHASE_WORKFLOW, 'utf8');
|
|
const match = workflow.match(/<deep_work_rules>[\s\S]*?<\/deep_work_rules>/);
|
|
assert.ok(match, 'plan-phase.md must contain a deep_work_rules block');
|
|
return match[0];
|
|
}
|
|
|
|
describe('bug #3320 planner action contract', () => {
|
|
test('planner agent explicitly keeps implementation code out of action blocks', () => {
|
|
const planner = fs.readFileSync(PLANNER_AGENT, 'utf8');
|
|
|
|
assert.match(
|
|
planner,
|
|
/NEVER place fenced code blocks \(```\) inside `<action>`/,
|
|
'gsd-planner.md must explicitly forbid fenced implementation code in <action>'
|
|
);
|
|
assert.match(
|
|
planner,
|
|
/Code excerpts belong in `<read_first>` source files or referenced context/,
|
|
'gsd-planner.md must route code excerpts to context/read-first material'
|
|
);
|
|
});
|
|
|
|
test('plan-phase deep_work_rules no longer requires self-sufficient code dumps', () => {
|
|
const deepWorkRules = extractDeepWorkRules();
|
|
|
|
assert.doesNotMatch(
|
|
deepWorkRules,
|
|
/copy them into the action verbatim/,
|
|
'deep_work_rules must not tell planners to copy source material verbatim into <action>'
|
|
);
|
|
assert.doesNotMatch(
|
|
deepWorkRules,
|
|
/complete the task from the action text alone/,
|
|
'deep_work_rules must not make <action> self-sufficient without read_first/context'
|
|
);
|
|
assert.match(
|
|
deepWorkRules,
|
|
/Do not include full file contents, fenced code blocks, or complete implementations in `<action>`/,
|
|
'deep_work_rules must explicitly bound concrete values to avoid code dumping'
|
|
);
|
|
});
|
|
|
|
test('plan-phase acceptance criteria allow behavior and test assertions', () => {
|
|
const deepWorkRules = extractDeepWorkRules();
|
|
|
|
assert.match(
|
|
deepWorkRules,
|
|
/behavior assertion/,
|
|
'acceptance criteria must allow behavior assertions, not just grep checks'
|
|
);
|
|
assert.match(
|
|
deepWorkRules,
|
|
/test command/,
|
|
'acceptance criteria must allow test-command assertions'
|
|
);
|
|
});
|
|
|
|
test('quality gate matches the reconciled planner contract', () => {
|
|
const workflow = read('gsd-core/workflows/plan-phase.md');
|
|
|
|
assert.match(
|
|
workflow,
|
|
/Every task has `<acceptance_criteria>` with behavior, test-command, CLI, or source assertions/,
|
|
'quality gate must not narrow acceptance criteria back to grep-only checks'
|
|
);
|
|
assert.match(
|
|
workflow,
|
|
/Every `<action>` contains concrete identifiers without fenced code blocks or full implementations/,
|
|
'quality gate must enforce concrete prose without implementation dumps'
|
|
);
|
|
});
|
|
});
|
|
});
|
|
}
|