voyage/lib/review/findings-schema.mjs
Kjell Tore Guttormsen 255b6b4bf8
feat(trekplan): Regression and On failure step rules, and trial 2's minor fixes
The minor points (B8-B12, C13, C14, C16, C17) of the second voyage-lekerepo
trial (2026-10-08), each verified against the code and started with a test
that failed first.

- K10: optional step field `Regression:` - one command the criteria runner
  allows, unpiped; plan-validator refuses one that can never run
  (PLAN_STEP_REGRESSION_NOT_RUNNABLE). Any plan_version, no bump.
- K11: `On failure:` opens with revert | retry | skip | escalate, or the
  validator warns (PLAN_STEP_ON_FAILURE_UNKNOWN); onFailureAction in
  plan-schema.
- B8 (operator decision 2026-10-08): minors open after the last critic round
  are listed numbered in the Phase 10 summary; the ones the operator picks are
  fixed and get one more round (--extra-round when the 3 are spent).
- B11: plan-review dedup merges two reviewers' findings on the same file:line
  with the same content (trial pair: Jaccard 0.44, overlap 0.83); the Jaccard
  threshold for every other pair is unchanged.
- B12: /trekbrief Step 4c says the reviewer runs in the background and is
  waited for, not "foreground, blocking".
- C13: the Phase 4 size count includes .mjs, .cjs, .mts, .cts.
- C14: --evidence shows the first output line on PASS rows.
- C16: findings-schema checks path:line citations in finding prose (error) and
  in the prose around the block (warning) against the file.
- C17: git-historian gets the brief, never proposes changing a frozen file,
  and names the remote from `git remote -v`.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-08 21:42:21 +02:00

287 lines
12 KiB
JavaScript
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

// lib/review/findings-schema.mjs
// Reviewer-output JSON schema contract for /trekreview Phase 5 (NW1).
//
// brief-conformance-reviewer and code-correctness-reviewer each emit a trailing
// fenced `json` block of shape:
//
// { "reviewer": "<name>", "findings": [ { id, severity, rule_key, file, line,
// brief_ref, title, detail,
// recommended_action }, ... ] }
//
// This module codifies that contract so main can VALIDATE each reviewer's JSON
// (not merely JSON.parse it) and re-ask on *schema* failure as well as parse
// failure, replacing the fragile "parse the last json block" contract that used
// to live in commands/trekreview.md (the :202–204 prose).
//
// Load-bearing fields (the downstream dedup triplet + verdict severity) are hard
// errors: file, rule_key, severity, line. Unknown rule_keys are errors too — the
// catalogue is the contract. Descriptive fields (title/detail/recommended_action/
// brief_ref) and unknown top-level keys are tolerated (forward-compat, mirroring
// review-validator.mjs).
//
// 3-layer pattern (Content → Raw-text → CLI shim) mirroring the other validators.
import { readFileSync, existsSync, realpathSync, statSync } from 'node:fs';
import { fileURLToPath } from 'node:url';
import { resolve, sep } from 'node:path';
import { issue, fail } from '../util/result.mjs';
import { RULE_KEYS, SEVERITY_VALUES } from './rule-catalogue.mjs';
// The fields main + the coordinator depend on. Descriptive fields are not here
// on purpose: a missing recommended_action should not trigger a re-ask.
export const FINDING_REQUIRED_FIELDS = Object.freeze([
'severity',
'rule_key',
'file',
'line',
]);
// Last fenced ```json … ``` block in a reviewer's output. The contract pins the
// JSON block as the LAST fence so prose above it never confuses the parser.
const JSON_FENCE_GLOBAL = /```json[ \t]*\r?\n([\s\S]*?)```/gi;
/**
* Extract the inner body of the LAST fenced `json` block in `text`.
* @param {string} text
* @returns {string|null} the JSON source, or null if no json fence is present.
*/
export function extractFindingsBlock(text) {
if (typeof text !== 'string') return null;
JSON_FENCE_GLOBAL.lastIndex = 0;
let last = null;
let m;
while ((m = JSON_FENCE_GLOBAL.exec(text)) !== null) {
last = m[1];
}
return last;
}
function validateFinding(finding, index, errors) {
const loc = `findings[${index}]`;
if (finding === null || typeof finding !== 'object' || Array.isArray(finding)) {
errors.push(issue('FINDING_NOT_OBJECT', `${loc} is not an object`, undefined, loc));
return;
}
if (typeof finding.file !== 'string' || finding.file.length === 0) {
errors.push(issue('FINDING_MISSING_FILE', `${loc}.file must be a non-empty string`, undefined, loc));
}
if (typeof finding.rule_key !== 'string' || finding.rule_key.length === 0) {
errors.push(issue('FINDING_MISSING_RULE_KEY', `${loc}.rule_key must be a non-empty string`, undefined, loc));
} else if (!RULE_KEYS.has(finding.rule_key)) {
errors.push(issue(
'FINDING_UNKNOWN_RULE_KEY',
`${loc}.rule_key "${finding.rule_key}" is not in the rule catalogue`,
'Use a rule_key from lib/review/rule-catalogue.mjs',
loc,
));
}
if (typeof finding.severity !== 'string' || !SEVERITY_VALUES.includes(finding.severity)) {
errors.push(issue(
'FINDING_BAD_SEVERITY',
`${loc}.severity must be one of ${SEVERITY_VALUES.join('|')}, got ${JSON.stringify(finding.severity)}`,
undefined,
loc,
));
}
if (typeof finding.line !== 'number' || !Number.isInteger(finding.line) || finding.line < 0) {
errors.push(issue(
'FINDING_BAD_LINE',
`${loc}.line must be an integer ≥ 0, got ${JSON.stringify(finding.line)}`,
'Use 0 for file-scoped findings without a specific line.',
loc,
));
}
}
/**
* Validate an already-parsed reviewer-output payload against the schema.
* Accumulates every error (so a re-ask can name all problems at once).
* @param {unknown} payload
* @returns {import('../util/result.mjs').Result}
*/
// A reviewer that reads the diff cites the line in the PATCH, not in the file:
// the voyage-lekerepo trial (2026-10-06) cited tests/cli.test.mjs:194 for a
// 124-line file, the coordinator then set the only brief-anchored MAJOR aside,
// and the claim itself was right. With a repo root, a line past the end of a
// file that exists is an error, so Phase 5's bounded re-ask fixes it before the
// coordinator ever sees it. A file absent from the tree is not judged here.
function lineCount(repoRoot, file) {
const root = resolve(repoRoot);
const abs = resolve(root, file);
if (abs !== root && !abs.startsWith(root + sep)) return null;
try {
if (!statSync(abs).isFile()) return null;
const text = readFileSync(abs, 'utf-8');
if (text === '') return 0;
return text.endsWith('\n') ? text.split('\n').length - 1 : text.split('\n').length;
} catch {
return null;
}
}
function checkLineRange(finding, index, repoRoot, errors) {
if (!finding || typeof finding.file !== 'string' || !Number.isInteger(finding.line) || finding.line <= 0) return;
const n = lineCount(repoRoot, finding.file);
if (n === null || finding.line <= n) return;
errors.push(issue(
'FINDING_LINE_OUT_OF_RANGE',
`findings[${index}] cites ${finding.file}:${finding.line}, but the file has ${n} lines`,
'Cite the line number in the file itself (Read it), not the line in the diff or patch.',
));
}
// The same check for a `path:line` (or `path:a-b`) a reviewer writes in prose:
// a finding's title/detail/recommended_action/brief_ref, and the text around
// the JSON block. code-correctness-reviewer wrote "`tests/contract.sh:119`
// relies on git" about a 33-line file, and nothing looked (voyage-lekerepo
// trial 2, 2026-10-08). In a finding's fields a line past the end of a file
// that exists is an error (the re-ask can fix the block); in the prose around
// the block it is a warning (see validateReviewerOutput). A path absent from
// the tree is not judged. The path needs an extension, so `localhost:8080` and
// `host.example:443` are no citation of anything in the tree; a path glued to
// a `\` or `:` (a Windows path) is not read as one relative to the root.
const PROSE_CITE = /(?<![\w./\\:-])((?:\.{0,2}\/)?[\w.-]+(?:\/[\w.-]+)*\.[A-Za-z0-9]+):(\d+)(?:[-–—](\d+))?(?![\w])/g;
const PROSE_FIELDS = Object.freeze(['title', 'detail', 'recommended_action', 'brief_ref']);
function checkProseCitations(text, where, repoRoot, errors, seen) {
if (typeof text !== 'string' || text === '') return;
PROSE_CITE.lastIndex = 0;
let m;
while ((m = PROSE_CITE.exec(text)) !== null) {
const line = Math.max(Number(m[2]), m[3] === undefined ? 0 : Number(m[3]));
if (line <= 0) continue;
const n = lineCount(repoRoot, m[1]);
if (n === null || line <= n) continue;
const key = `${where}\u0000${m[0]}`;
if (seen.has(key)) continue;
seen.add(key);
errors.push(issue(
'FINDING_PROSE_LINE_OUT_OF_RANGE',
`${where} cites ${m[0]}, but ${m[1]} has ${n} lines`,
'Cite the line number in the file itself (Read it), not the line in the diff or patch, or drop the line number.',
));
}
}
function checkFindingProse(finding, index, repoRoot, errors, seen) {
if (!finding || typeof finding !== 'object') return;
for (const field of PROSE_FIELDS) {
checkProseCitations(finding[field], `findings[${index}].${field}`, repoRoot, errors, seen);
}
}
/**
* @param {unknown} payload
* @param {{ repoRoot?: string }} [opts] - with a repo root, cited lines are checked against the files:
* each finding's `file:line`, and every `path:line` in its prose fields
*/
export function validateFindings(payload, opts = {}) {
if (payload === null || typeof payload !== 'object' || Array.isArray(payload)) {
return fail(issue('FINDINGS_NOT_OBJECT', `Reviewer output must be a JSON object, got ${Array.isArray(payload) ? 'array' : typeof payload}`));
}
const errors = [];
const warnings = [];
if (typeof payload.reviewer !== 'string' || payload.reviewer.length === 0) {
warnings.push(issue('FINDINGS_MISSING_REVIEWER', 'Reviewer output should carry a non-empty "reviewer" name'));
}
if (!Array.isArray(payload.findings)) {
errors.push(issue('FINDINGS_NOT_ARRAY', `Field "findings" must be an array, got ${typeof payload.findings}`));
return { valid: false, errors, warnings, parsed: payload };
}
const seen = new Set();
for (let i = 0; i < payload.findings.length; i++) {
validateFinding(payload.findings[i], i, errors);
if (opts.repoRoot) {
checkLineRange(payload.findings[i], i, opts.repoRoot, errors);
checkFindingProse(payload.findings[i], i, opts.repoRoot, errors, seen);
}
}
return { valid: errors.length === 0, errors, warnings, parsed: payload };
}
/**
* Validate a reviewer's raw output text: extract the last json fence, parse it,
* then schema-validate. Parse-stage failures get stable codes so they flow
* through the same bounded re-ask path as schema failures.
* @param {string} rawText
* @returns {import('../util/result.mjs').Result}
*/
export function validateReviewerOutput(rawText, opts = {}) {
const block = extractFindingsBlock(rawText);
if (block === null) {
return fail(issue(
'FINDINGS_NO_JSON_BLOCK',
'No trailing fenced ```json block found in reviewer output',
'Reviewers must end their output with a single ```json findings block.',
));
}
let parsed;
try {
parsed = JSON.parse(block);
} catch (e) {
return fail(issue('FINDINGS_PARSE_ERROR', `Reviewer JSON block did not parse: ${e.message}`));
}
const r = validateFindings(parsed, opts);
if (!opts.repoRoot) return r;
// The prose around the block (the text outside the LAST json fence; the
// block itself was checked field by field above) is a WARNING, not an error:
// the bounded re-ask asks for the JSON block only, which cannot correct that
// prose, and nothing downstream reads it — an error there could only stop a
// review over text no one uses (independent review, 2026-10-08).
const at = rawText.lastIndexOf(block);
const found = [];
checkProseCitations(rawText.slice(0, at) + rawText.slice(at + block.length), 'reviewer prose', opts.repoRoot, found, new Set());
return found.length === 0 ? r : { ...r, warnings: [...r.warnings, ...found] };
}
// ---- CLI shim ----------------------------------------------------------------
function isDir(p) {
try { return statSync(p).isDirectory(); } catch { return false; }
}
function isMain() {
try {
return realpathSync(process.argv[1]) === realpathSync(fileURLToPath(import.meta.url));
} catch {
return false;
}
}
if (isMain()) {
const args = process.argv.slice(2);
const rootIdx = args.indexOf('--repo-root');
const repoRoot = rootIdx >= 0 ? args[rootIdx + 1] : undefined;
// Without the flag nothing is skipped (rootIdx + 1 would be 0: the file).
const skipIdx = rootIdx >= 0 ? rootIdx + 1 : -1;
const filePath = args.find((a, i) => !a.startsWith('--') && i !== skipIdx);
// A missing value, a flag in its place, or a root that is not a directory
// would switch the line check off without a word: a usage error instead.
const badRoot = rootIdx >= 0 && (!repoRoot || repoRoot.startsWith('--') || !isDir(repoRoot));
if (!filePath || badRoot) {
process.stderr.write('Usage: findings-schema.mjs [--json] [--repo-root <dir>] <reviewer-output.txt|.md>\n');
process.exit(2);
}
if (!existsSync(filePath)) {
process.stderr.write(`findings-schema: file not found: ${filePath}\n`);
process.exit(2);
}
const r = validateReviewerOutput(readFileSync(filePath, 'utf-8'), { repoRoot });
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(`findings-schema: ${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);
}