fix: round 2 of the release review of 6.3.0

Round 2 (v6.2.0..0d044f6, BLOCK: 2 BLOCKER, 11 MAJOR, 1 MINOR), each fixed
behind a test that failed first.

- The git runner checks only words /bin/sh passes through unchanged (no
  quote, backslash, $, glob or brace) and refuses --output and its
  abbreviations: round 1's --output refusal was bypassed by quoting.
- fieldPaths: backticked paths are kept as written, parentheses and all; in
  plain text every path-like word counts, and a parenthesised note does not.
- plan-validator --steps-from reads the plan's ## Verification for an
  appended End-to-end step, and warns instead of failing under --soft.
- regression-check prints progress_status, the value progress.json takes;
  /trekexecute copies it.
- release-check: a plugin in a subdirectory is checked in its own directory,
  the suite is not run when a cheaper check already makes the answer exit 2,
  and a bad argument or a crash is exit 2.
- Skill routing looks a skill up among skills only, and builds the corpus
  vectors once.
- /trekexecute Phase 7.2 says plainly that remediation steps in the review
  template's own form stop with a re-plan; making them runnable is a later
  order (operator 2026-10-10).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-10-10 22:43:38 +02:00
commit ed87cc668d
Signed by: ktg
SSH key fingerprint: SHA256:JakMjO6FTBBzN0Bhfj9saOoEjaFxlSdYuZQQpM/lF9Q
10 changed files with 263 additions and 70 deletions

View file

@ -10,8 +10,11 @@
// (no command, or a command outside the test-runner allowlist): the
// step is not done, and that is a finding for the fix rounds
// 2 = could not run: bad usage, a plan that cannot be read, no step N
// JSON on stdout: {step, status, command, exit_code, output}
// JSON on stdout: {step, status, progress_status, command, exit_code, output}
// status: passed | failed | blocked | unrunnable | absent | error
// progress_status: the value progress.json takes for steps.N.regression
// (blocked counts as unrunnable, error as not-run), so the executor
// copies one field and never translates
//
// The command is the field's first backticked span — the same reading as the
// runner's `## Verification` bullets — and it goes through the same two
@ -44,6 +47,8 @@ function exec(command, { cwd, timeoutMs }) {
export const REGRESSION_FIELD = 'Regression';
const EXIT = Object.freeze({ passed: 0, absent: 0, failed: 1, blocked: 1, unrunnable: 1, error: 2 });
const PROGRESS = Object.freeze({ passed: 'passed', absent: 'absent', failed: 'failed', blocked: 'unrunnable', unrunnable: 'unrunnable', error: 'not-run' });
const withProgress = (r) => ({ ...r, progress_status: PROGRESS[r.status] ?? 'not-run' });
/**
* @param {{ planText: string, step: number, cwd?: string, run?: Function }} o
@ -52,19 +57,19 @@ const EXIT = Object.freeze({ passed: 0, absent: 0, failed: 1, blocked: 1, unrunn
export function checkRegression({ planText, step, cwd = process.cwd(), run = (c, o) => runCriteria(c, { ...o, exec }) }) {
const base = { step, command: null, exit_code: null, output: '' };
const found = sliceSteps(planText).find((s) => Number(s.n) === step);
if (!found) return { ...base, status: 'error', output: `no "### Step ${step}:" in the plan`, exit: EXIT.error };
if (!found) return withProgress({ ...base, status: 'error', output: `no "### Step ${step}:" in the plan`, exit: EXIT.error });
const field = parseStepFields(found.body).get(REGRESSION_FIELD);
if (!field) return { ...base, status: 'absent', output: 'no Regression: field — nothing to run', exit: EXIT.absent };
if (!field) return withProgress({ ...base, status: 'absent', output: 'no Regression: field — nothing to run', exit: EXIT.absent });
const { command, reason } = firstCommand(field.text);
const [r] = run([{ label: `R${step}`, text: field.text, command, reason }], { cwd });
return {
return withProgress({
step,
status: r.status,
command: r.command ?? null,
exit_code: r.exitCode ?? null,
output: r.output ?? '',
exit: EXIT[r.status] ?? EXIT.error,
};
});
}
export function main(argv) {
@ -92,7 +97,7 @@ export function main(argv) {
}
let planText;
try { planText = readFileSync(plan, 'utf8'); } catch (e) {
return say({ step, status: 'error', command: null, exit_code: null, output: `cannot read ${plan}: ${e.message}`, exit: 2 });
return say(withProgress({ step, status: 'error', command: null, exit_code: null, output: `cannot read ${plan}: ${e.message}`, exit: 2 }));
}
return say(checkRegression({ planText, step, cwd }));
}