voyage/lib/validators/progress-validator.mjs
Kjell Tore Guttormsen 29b4ac91b3
fix: round 7 of the release review of 6.3.0, for 6.3.1
Round 7 (516dffa..45aa9e1, WARN: 12 MAJOR, 0 BLOCKER) and the fence defect
found while writing its review.md. Each fix began with a test that failed on
0f400d3 (v6.3.0); suite 2208 (2206/0/2), 14 tests more.

- Tests-only (operator 2026-10-11): the plan's Files: alone decides, and the
  text says so (red-proof, trekexecute Sub-step B, step-implementer,
  HANDOVER-CONTRACTS). red-proof no longer reads the step's diff, so a change
  already in the tree when the step began no longer counts against it, and a
  plan placed outside .claude/ reads the same. The round-6 test that had the
  diff overrule the plan is rewritten to the new rule.
- The Files: reader keeps a plain file beside a backticked path
  (", Dockerfile", "the CLI entry src/cli.mjs", "and Makefile"). Measured on
  the 520 Files: fields in 182 plans: no field reads differently.
- Red proof reports a command its timeout killed as killed after the timeout,
  not "could not start"; the release check tells a timeout from output past
  its buffer and from another signal. One reading of a stop
  (criteria-runner stoppedBy) for red proof, the criteria runner and the
  release check.
- A trailing `# comment` is dropped in a backticked check too, and in a
  command passed as written, so the words screened are the words run.
- The release check reads a relative --review in --repo.
- The 15-minute timeout is defined once (criteria-runner.mjs).
- The findings check reads each cited file once per validation.
- One isMain helper (lib/util/is-main.mjs) for every CLI: the 31 copies of
  the realpath guard and the 20 modules still on the file:// guard, which
  exited 0 having done nothing under a symlink or a path with a space.
- The Bash guard writes its no-one-to-ask refusal once, on a direct condition.
- The findings check ends a ```json block only at a fence on its own line, so
  three backticks inside a JSON string no longer end it (also in 6.2.0).
- Brief-conformance notes: a test for test-lock green on exit 127 (it
  passed at once; it fails when 127 is read as could-not-run); the prose now
  names the git revision `@~1` as the one leading-@ exception.

Not changed: the example plan's steps 1-2 keep their tests-only warning
(operator decision 2026-10-09; the r5 test records it). Brief note 4 (a
Regression: whose runner is not installed goes to the fix rounds) is a
routing question for the operator.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 09:11:57 +02:00

231 lines
12 KiB
JavaScript

// lib/validators/progress-validator.mjs
// Validate progress.json shape + resume-readiness.
// Forward-compat: unknown keys are tolerated silently, so additive-optional fields land
// WITHOUT a schema_version bump. `iterations_remaining` (trekexecute's recovery/retry budget
// signal) is shape-checked here only when present (non-negative integer); it is NOT in
// PROGRESS_REQUIRED_TOP, so legacy progress.json without it still validates. The field's
// liveness (never-decremented) is enforced deterministically by the Phase 7.5 completion-gate
// cross-check in trekexecute, not by this per-validation shape check.
// The same holds for the wave-1 step-loop fields (per step: start_sha, report_path,
// red_proof, test_lock, fix_rounds 0..5; per run: decisions): shape-checked when
// present, never required. So are the wave-2 coupling fields (per step: step_check
// from K9, regression from K10; per run: plan_approval, arch_rules, scope_sweep,
// simplify, review) and the key of plan_verification.failed_criteria: the runner
// says `exitCode`, progress says `exit_code`, and only `exit_code` is accepted (C15).
import { readFileSync, existsSync } from 'node:fs';
import { issue, fail } from '../util/result.mjs';
import { isMain } from '../util/is-main.mjs';
export const PROGRESS_REQUIRED_TOP = ['schema_version', 'plan', 'plan_version', 'mode', 'status', 'total_steps', 'current_step', 'steps'];
export const PROGRESS_VALID_STATUSES = ['pending', 'in_progress', 'completed', 'failed', 'partial', 'stopped'];
// Step statuses /trekexecute stores. `blocked` is the Step 0 sandbox sentinel; `stopped` above
// is the escalation / dirty-tree / entry-condition stop. Both are states other readers already
// know (lib/util/session-orders.mjs ENDED_BAD).
export const PROGRESS_STEP_STATUSES = ['completed', 'in_progress', 'failed', 'pending', 'deferred', 'skipped', 'blocked'];
// Wave 1 (P8/P9) per-step fields, all optional on read so an older progress.json
// still resumes; `null` means "not set yet". fix_rounds is the step's place on
// the upward ladder: 0 = passed its first control, 1-3 = fix rounds, 4 = sent up
// to the plan, 5 = sent up to the operator. There is no sixth round.
export const PROGRESS_MAX_FIX_ROUNDS = 5;
export const PROGRESS_RED_PROOF_VALUES = ['proven', 'rejected', 'not-run'];
export const PROGRESS_TEST_LOCK_VALUES = ['locked', 'released', 'not-locked'];
// Wave 2 (order 6) coupling fields. Each value is the exit of a contract CLI said
// in words; "not-measured" / "not-run" are never green, and "absent" means the plan
// declared nothing (no `Regression:` field), so nothing new happened.
export const PROGRESS_STEP_CHECK_VALUES = ['clean', 'findings', 'not-measured']; // K9 exit 0 / 1 / 2
export const PROGRESS_REGRESSION_VALUES = ['passed', 'failed', 'unrunnable', 'not-run', 'absent']; // K10
export const PROGRESS_PLAN_APPROVAL_VALUES = ['approved', 'not-checked']; // K2; not-checked = a session spec
export const PROGRESS_ARCH_RULES_VALUES = ['pass', 'violation', 'not-measured']; // K5 exit 0 / 1 / 2
export const PROGRESS_SCOPE_SWEEP_VALUES = ['pass', 'deviation', 'not-measured']; // K6 exit 0 / 1 / 2
export const PROGRESS_SIMPLIFY_VALUES = ['applied', 'clean', 'reverted', 'revert-refused', 'not-run'];
export const PROGRESS_REVIEW_GATE_EXITS = [0, 1, 2]; // K7: ALLOW/WARN, BLOCK, could not decide
function checkStepFields(k, s, errors) {
const set = (v) => v !== undefined && v !== null;
if (s.fix_rounds !== undefined &&
!(Number.isInteger(s.fix_rounds) && s.fix_rounds >= 0 && s.fix_rounds <= PROGRESS_MAX_FIX_ROUNDS)) {
errors.push(issue('PROGRESS_FIX_ROUNDS_INVALID',
`steps["${k}"].fix_rounds=${JSON.stringify(s.fix_rounds)} must be an integer 0..${PROGRESS_MAX_FIX_ROUNDS}`));
}
if (set(s.start_sha) && !(typeof s.start_sha === 'string' && /^[0-9a-f]{7,64}$/.test(s.start_sha))) {
errors.push(issue('PROGRESS_START_SHA_INVALID', `steps["${k}"].start_sha must be a git sha, got ${JSON.stringify(s.start_sha)}`));
}
if (set(s.report_path) && !(typeof s.report_path === 'string' && s.report_path.trim() !== '')) {
errors.push(issue('PROGRESS_REPORT_PATH_INVALID', `steps["${k}"].report_path must be a non-empty path`));
}
if (set(s.red_proof) && !PROGRESS_RED_PROOF_VALUES.includes(s.red_proof)) {
errors.push(issue('PROGRESS_RED_PROOF_INVALID', `steps["${k}"].red_proof "${s.red_proof}" not in [${PROGRESS_RED_PROOF_VALUES.join(', ')}]`));
}
if (set(s.test_lock) && !PROGRESS_TEST_LOCK_VALUES.includes(s.test_lock)) {
errors.push(issue('PROGRESS_TEST_LOCK_INVALID', `steps["${k}"].test_lock "${s.test_lock}" not in [${PROGRESS_TEST_LOCK_VALUES.join(', ')}]`));
}
if (set(s.step_check) && !PROGRESS_STEP_CHECK_VALUES.includes(s.step_check)) {
errors.push(issue('PROGRESS_STEP_CHECK_INVALID', `steps["${k}"].step_check ${JSON.stringify(s.step_check)} not in [${PROGRESS_STEP_CHECK_VALUES.join(', ')}]`));
}
if (set(s.regression) && !PROGRESS_REGRESSION_VALUES.includes(s.regression)) {
errors.push(issue('PROGRESS_REGRESSION_INVALID', `steps["${k}"].regression ${JSON.stringify(s.regression)} not in [${PROGRESS_REGRESSION_VALUES.join(', ')}]`));
}
}
const isStr = (v) => typeof v === 'string' && v.trim() !== '';
// Wave 2 (order 6) run-level fields; all optional, shape-checked when set.
function checkCouplingFields(p, errors) {
const set = (v) => v !== undefined && v !== null;
const oneOf = (field, values, code) => {
if (set(p[field]) && !values.includes(p[field])) {
errors.push(issue(code, `${field} ${JSON.stringify(p[field])} not in [${values.join(', ')}]`));
}
};
oneOf('plan_approval', PROGRESS_PLAN_APPROVAL_VALUES, 'PROGRESS_PLAN_APPROVAL_INVALID');
oneOf('arch_rules', PROGRESS_ARCH_RULES_VALUES, 'PROGRESS_ARCH_RULES_INVALID');
oneOf('simplify', PROGRESS_SIMPLIFY_VALUES, 'PROGRESS_SIMPLIFY_INVALID');
const sw = p.scope_sweep;
if (set(sw) && !(typeof sw === 'object' && PROGRESS_SCOPE_SWEEP_VALUES.includes(sw.status) &&
Array.isArray(sw.outside) && sw.outside.every(isStr))) {
errors.push(issue('PROGRESS_SCOPE_SWEEP_INVALID',
`scope_sweep must be {status: ${PROGRESS_SCOPE_SWEEP_VALUES.join('|')}, outside: [paths]}`));
}
const rv = p.review;
if (set(rv) && !(typeof rv === 'object' && Number.isInteger(rv.round) && rv.round >= 1 &&
PROGRESS_REVIEW_GATE_EXITS.includes(rv.gate_exit))) {
errors.push(issue('PROGRESS_REVIEW_INVALID', 'review must be {round: integer >= 1, gate_exit: 0|1|2, ...}'));
}
// C15: the criteria runner reports `exitCode`; progress.json carries `exit_code`
// (an integer, or null when the criterion never ran). The executor translates;
// the runner's key here means the translation was skipped.
const fc = p.plan_verification?.failed_criteria;
if (fc !== undefined && fc !== null) {
const ok = Array.isArray(fc) && fc.every((c) => c && typeof c === 'object' && !('exitCode' in c) &&
'exit_code' in c && (c.exit_code === null || Number.isInteger(c.exit_code)));
if (!ok) {
errors.push(issue('PROGRESS_FAILED_CRITERIA_KEY',
'plan_verification.failed_criteria entries carry exit_code (integer or null), never the runner key exitCode'));
}
}
}
// The run-level decision log (P4): every decision the executor took on its own,
// with what it costs if it is wrong. Optional; when present, every entry carries both.
function checkDecisions(decisions, errors) {
if (decisions === undefined) return;
const ok = Array.isArray(decisions) && decisions.every((d) => d && typeof d === 'object' &&
typeof d.decision === 'string' && d.decision.trim() !== '' &&
typeof d.cost_if_wrong === 'string' && d.cost_if_wrong.trim() !== '');
if (!ok) errors.push(issue('PROGRESS_DECISION_INVALID', 'decisions must be an array of {decision, cost_if_wrong} with both non-empty'));
}
export function validateProgressContent(jsonText, opts = {}) {
let parsed;
try { parsed = JSON.parse(jsonText); }
catch (e) {
return fail(issue('PROGRESS_PARSE_ERROR', `Cannot parse JSON: ${e.message}`));
}
return validateProgressObject(parsed, opts);
}
export function validateProgressObject(parsed, opts = {}) {
const errors = [];
const warnings = [];
if (typeof parsed !== 'object' || parsed === null) {
return fail(issue('PROGRESS_NOT_OBJECT', 'Progress payload is not an object'));
}
for (const k of PROGRESS_REQUIRED_TOP) {
if (!(k in parsed)) {
errors.push(issue('PROGRESS_MISSING_FIELD', `Required field missing: ${k}`));
}
}
if (parsed.schema_version !== undefined && parsed.schema_version !== '1') {
errors.push(issue('PROGRESS_SCHEMA_MISMATCH', `schema_version "${parsed.schema_version}" not supported (expected "1")`));
}
if (parsed.status !== undefined && !PROGRESS_VALID_STATUSES.includes(parsed.status)) {
errors.push(issue('PROGRESS_BAD_STATUS', `status "${parsed.status}" not in [${PROGRESS_VALID_STATUSES.join(', ')}]`));
}
if (typeof parsed.total_steps === 'number' && typeof parsed.current_step === 'number') {
if (parsed.current_step < 0 || parsed.current_step > parsed.total_steps) {
errors.push(issue('PROGRESS_STEP_RANGE', `current_step=${parsed.current_step} outside [0, ${parsed.total_steps}]`));
}
}
// Additive-optional: iterations_remaining is trekexecute's recovery/retry budget signal.
// When present it must be a non-negative integer; absence is valid (backward-compat).
if (parsed.iterations_remaining !== undefined &&
!(Number.isInteger(parsed.iterations_remaining) && parsed.iterations_remaining >= 0)) {
errors.push(issue(
'PROGRESS_ITERATIONS_REMAINING_INVALID',
`iterations_remaining=${parsed.iterations_remaining} must be a non-negative integer`,
));
}
if (parsed.steps && typeof parsed.steps === 'object') {
const stepKeys = Object.keys(parsed.steps);
if (typeof parsed.total_steps === 'number' && stepKeys.length !== parsed.total_steps) {
warnings.push(issue(
'PROGRESS_STEP_COUNT_MISMATCH',
`total_steps=${parsed.total_steps} but steps map has ${stepKeys.length} entries`,
));
}
for (const k of stepKeys) {
const s = parsed.steps[k];
if (s === null || typeof s !== 'object') {
errors.push(issue('PROGRESS_STEP_SHAPE', `steps["${k}"] is not an object`));
continue;
}
if (s.status !== undefined && !PROGRESS_STEP_STATUSES.includes(s.status)) {
warnings.push(issue('PROGRESS_STEP_BAD_STATUS', `steps["${k}"].status "${s.status}" unrecognized`));
}
checkStepFields(k, s, errors);
}
}
checkDecisions(parsed.decisions, errors);
checkCouplingFields(parsed, errors);
return { valid: errors.length === 0, errors, warnings, parsed };
}
export function checkResumeReadiness(progressObj) {
const errors = [];
if (progressObj.status === 'completed') {
return { valid: false, errors: [issue('PROGRESS_ALREADY_DONE', 'Run is already completed; nothing to resume')], warnings: [], parsed: progressObj };
}
if (typeof progressObj.current_step !== 'number') {
errors.push(issue('PROGRESS_NO_CURRENT', 'No current_step in progress.json'));
}
return { valid: errors.length === 0, errors, warnings: [], parsed: progressObj };
}
export function validateProgress(filePath, opts = {}) {
if (!existsSync(filePath)) return fail(issue('PROGRESS_NOT_FOUND', `File not found: ${filePath}`));
let text;
try { text = readFileSync(filePath, 'utf-8'); }
catch (e) { return fail(issue('PROGRESS_READ_ERROR', `Cannot read ${filePath}: ${e.message}`)); }
return validateProgressContent(text, opts);
}
if (isMain(import.meta.url)) {
const args = process.argv.slice(2);
const filePath = args.find(a => !a.startsWith('--'));
if (!filePath) {
process.stderr.write('Usage: progress-validator.mjs [--quick] <progress.json>\n');
process.exit(2);
}
const r = validateProgress(filePath);
if (args.includes('--json')) {
process.stdout.write(JSON.stringify({ valid: r.valid, errors: r.errors, warnings: r.warnings }, null, 2) + '\n');
} else {
process.stdout.write(`progress-validator: ${r.valid ? 'PASS' : 'FAIL'} ${filePath}\n`);
for (const e of r.errors) process.stderr.write(` ERROR [${e.code}] ${e.message}\n`);
for (const w of r.warnings) process.stderr.write(` WARN [${w.code}] ${w.message}\n`);
}
process.exit(r.valid ? 0 : 1);
}