mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-03 15:27:56 +01:00
v1.93.21.0 fix(ship): native FIXABLE collects at its own Severity outside gate and risk reviews (GST-987) (#3869)
* fix(review-ledger): a finding's Severity field sets its label, body severity words never raise it (GST-976) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review-ledger): Severity counts only in field position, locus-first and emoji-led labels lead, an inline field floors the next (GST-976 review) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review-ledger): linear lead-label prefix, all-caps leads before a space, fields after a parenthesis or without a colon at the line start (GST-976 review) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review-ledger): a lead's file:line has no runaway backtracking and may be a range; a mid-line Severity field must close its clause (GST-976 review) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review-ledger): a field at the line's start needs no closing clause; mid-line fields accept : / and → after the label (GST-976 fix-check) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: changelog fragment and review-policy collect step for GST-976 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review-ledger): a Severity field's label chain (High/Critical) takes its strongest label; mid-line fields keep the clause-closing set (GST-976 scoped check) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(review-ledger): never weaker than main invariant over pinned inputs, fixtures and generated field shapes; a multi-label Severity field counts as none, lowercase fields keep their label (GST-976) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: GST-976 re-audit, multi-label and lowercase Severity fields Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: native FIXABLE raises only on gate and risk review classes (GST-987) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: collect records fixable_raises:false so a later re-derive uses the same class (GST-987) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: GST-987 review fixes: history/floor reasons and FIXABLE-only fields keep v2; manifest must name this ledger Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: GST-987 round-2 fixes: FIXABLE relaxes only beside Blocks: no; raw FIXABLE heading; unreadable manifest keeps v2 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: GST-987 fix-check: items under a FIXABLE heading need Blocks: no; Blocks: no-op is not Blocks: no; wrong-tree collect with an unreadable manifest Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: GST-987 docs audit: depth section notes the native FIXABLE exception Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: a paragraph under a numbered finding heading joins it, so its fields attach (gstack-evals #149, GST-987) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: verify re-derives native labels with the collect's class (GST-987, after #3717) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: #149 join stops at a labeled or located paragraph and after the fields (GST-987) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: GST-987 #149 sibling shapes as named never-weaker invariant fixtures Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: drop the released GST-976 changelog fragment carried by the stack Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
This commit is contained in:
Garry Tanandcapy-ai[bot] authored and GitHub committed
1 parent
16e4d2f4f0
commit
e0531db793
11 files changed
+165
-25
No files matched your search
@@ -1,5 +1,13 @@
|
||||
# Changelog
|
||||
|
||||
## [1.93.21.0] - 2026-11-02
|
||||
|
||||
**/ship's finding collector lets the native reviewer's own Severity field decide outside gate and risk reviews.**
|
||||
|
||||
### Fixed
|
||||
|
||||
- On a code or docs review with no risk reason (security, secrets, auth, money, user data), no depth error and no history or floor escalation, a native adversarial finding marked FIXABLE that states its own `Severity: Medium` or `Severity: Low` and `Blocks: no` now collects at that severity instead of CRITICAL. Gate and risk reviews, and any collect without this pass's manifest, keep collecting FIXABLE as CRITICAL, and so does a FIXABLE finding without `Blocks: no` or without a Severity field. (GST-987)
|
||||
|
||||
## [1.93.20.0] - 2026-11-02
|
||||
|
||||
### Changed
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# gstack digest v1.93.20.0 — regenerate/re-copy after upgrading gstack
|
||||
# gstack digest v1.93.21.0 — regenerate/re-copy after upgrading gstack
|
||||
|
||||
Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed
|
||||
for agent hosts without a full skill install. The full skills add workflows,
|
||||
|
||||
@@ -20,7 +20,7 @@ import * as fs from 'node:fs';
|
||||
import * as path from 'node:path';
|
||||
import { EXIT, exitTableHelp } from '../lib/headless-artifacts';
|
||||
import { BRIEF_ROLES, BriefError, briefFile, checkReviewedTree, checkoutRoot, checkoutTree, promptHash, renderBrief, sectionTexts, withWorkspace, type BriefRole, type Slots, type TreeCheck } from '../lib/review-brief';
|
||||
import { cleanMarkers, collect, mayBeUnavailable, parseFindings, readJsonl, readLedger, readerKey, recordJudgment, recordSent, appendEvent, verify, type JudgedLine, type MergedLine, type VerifyRow } from '../lib/review-ledger';
|
||||
import { cleanMarkers, collect, fixableRaises, mayBeUnavailable, parseFindings, readJsonl, readLedger, readerKey, recordJudgment, recordSent, appendEvent, verify, type JudgedLine, type MergedLine, type VerifyRow } from '../lib/review-ledger';
|
||||
import { buildManifest, chunkCount, chunkOf, manifestPath, markReader, readManifest, renderStage, writeManifest, STAGES, type Extra, type Manifest, type PassReader, type ReaderState, type Stage } from '../lib/review-pass';
|
||||
import type { Dispatch } from '../lib/review-depth';
|
||||
import { runScriptSync } from '../lib/script-invocation';
|
||||
@@ -329,10 +329,12 @@ function main(): number {
|
||||
process.stdout.write(`COLLECT_UNAVAILABLE: reader=${reader} sha256=${r.sha} reason=${JSON.stringify(why)} (missing outside coverage: unavailable, never clean)\n`);
|
||||
return EXIT.ok;
|
||||
}
|
||||
const r = collect(ledger, reader, output, merged, path.resolve(outFile!), unavailable, tree);
|
||||
const mf = flag('--manifest');
|
||||
let plan: ReturnType<typeof readManifest> | undefined;
|
||||
try { plan = mf ? readManifest(mf) : undefined; } catch (e) { process.stderr.write(`gstack-review-dispatch collect: ${(e as Error).message}; native FIXABLE collects as CRITICAL\n`); }
|
||||
const r = collect(ledger, reader, output, merged, path.resolve(outFile!), unavailable, tree, fixableRaises(plan && path.resolve(plan.ledger) === path.resolve(ledger) ? plan.plan_lines : undefined));
|
||||
if (tree && !tree.ok) {
|
||||
const mf = flag('--manifest');
|
||||
if (mf) { const m = readManifest(mf); markReader(m, reader, 'failed', { output: outFile, error: `reviewed another tree: ${tree.reported}` }); writeManifest(mf, m); }
|
||||
if (mf && plan) { markReader(plan, reader, 'failed', { output: outFile, error: `reviewed another tree: ${tree.reported}` }); writeManifest(mf, plan); }
|
||||
process.stdout.write(wrongTree(reader, tree));
|
||||
return EXIT.fail;
|
||||
}
|
||||
|
||||
@@ -326,7 +326,8 @@ fix-checks run at `full` effort (the lane's reasoning); specialists run at
|
||||
batched specialist, which carries the Red Team prompt and stays `full`. The
|
||||
outside voice and the native adversarial pass carry the floor sentence and end
|
||||
each finding with `Severity:` and `Blocks: yes|no`; a finding is CRITICAL when
|
||||
its label rule says so (native FIXABLE, outside Critical or High) or it says
|
||||
its label rule says so (native FIXABLE, except as the collect step below
|
||||
relaxes it on a runtime-only code or docs plan; outside Critical or High) or it says
|
||||
`Blocks: yes`, and `Blocks: no` never lowers one (`gstack-review-dispatch collect`). Work that cannot block (the Step 7 coverage audit, the Step 8
|
||||
plan-completion audit, the Step 14.5 docs audit, decision-trail reviewers,
|
||||
watchers) runs at `light`: the same model at a lower reasoning effort, never a
|
||||
@@ -564,7 +565,11 @@ ones, and the arm lost blockers. `bin/gstack-review-dispatch` closes both ends:
|
||||
second line for the same field starts another: `Severity` sets its label (a label leading the finding stays its floor),
|
||||
`Blocks: yes` makes it CRITICAL and `Blocks: no` never lowers it; an inline
|
||||
`Blocks: yes` is CRITICAL too, and with no finding above it is one. The native
|
||||
adversarial voice's FIXABLE collects as CRITICAL (normalizer v2, GSTA-167). An unnumbered, unlabeled bullet with no file:line
|
||||
adversarial voice's FIXABLE collects as CRITICAL (normalizer v2, GSTA-167) unless collect `--manifest` names this
|
||||
ledger's pass and its plan is the code or docs class with only `runtime=<n>` depth reasons (no `risk:`, `error:`,
|
||||
`history:` or `floor:` reason). On such a plan a native finding's own `Severity` field decides and FIXABLE beside it
|
||||
raises nothing once it also states `Blocks: no`; a native FIXABLE finding without `Blocks: no`, with no `Severity` field,
|
||||
or whose field names only FIXABLE or INVESTIGATE still collects as CRITICAL (GST-987). An unnumbered, unlabeled bullet with no file:line
|
||||
under a paragraph finding whose Severity or Blocks line has not come yet is that finding's detail, so the field line after it
|
||||
lands on the finding; a numbered item is its own finding.
|
||||
A negated severity word still collects at its label ("found nothing CRITICAL", "No P0/P1 issues"), so a reader's
|
||||
|
||||
+36
-11
@@ -55,9 +55,11 @@ const ANY_LABEL = new RegExp(`(?<![A-Za-z0-9])(${LABELS})(?![A-Za-z0-9])`);
|
||||
const LABEL_HEADING = new RegExp(`^(?:#{1,6}\\s*|\\*\\*)(${LABELS})(?:\\s+(?:findings?|severity|issues?))?\\s*:?\\**\\s*$`);
|
||||
const HEADING = /^(?:#{1,6}\s|\*\*[^*]+\*\*:?$)/;
|
||||
const LIST_ITEM = /^(?:[-*+]|\d+[.)])\s+\S/;
|
||||
const NUMBERED_HEAD = /^(?:#{1,6}\s+|\*\*\s*)\d+[.)]\s/;
|
||||
const stronger = (a: string, b: string) => ((rank(a) ?? 0) >= (rank(b) ?? 0) ? a : b);
|
||||
/** A prose voice's `Blocks: yes` (GSTA-167 normalizer v2): the finding is CRITICAL whatever its label; `Blocks: no` never lowers one. */
|
||||
const BLOCKS_YES = /(?<![A-Za-z0-9])Blocks:?\**:?\s*\**\s*yes(?![A-Za-z0-9])/i;
|
||||
const BLOCKS_NO = /(?<![A-Za-z0-9])Blocks:?\**:?\s*\**\s*no(?![A-Za-z0-9-])/i;
|
||||
const ALL_LABELS = new RegExp(ANY_LABEL.source, 'g');
|
||||
/** A file:line locus ("auth.ts:9"): prose naming one after a finding's fields starts the next finding. */
|
||||
const LOCUS = /[\w./-]+\.\w+:\d+/;
|
||||
@@ -102,9 +104,11 @@ export interface MergedLine { id: string; reader: string; label: string; stated?
|
||||
* starts the next finding, except an unlabeled, unnumbered bullet with no file:line under a paragraph finding whose fields have not
|
||||
* come yet, which is its detail and joins its text (GSTA-196: 4 findings with detail bullets collected as 8). An inline
|
||||
* `Blocks: yes` is CRITICAL too. The native voice's FIXABLE collects as CRITICAL; other labels stay as written for lead judgment. When in doubt the parser merges rather than drops: a lost blocker costs the gate.
|
||||
* With fixableRaises false (a code or docs review with no risk, error, history or floor reason, GST-987) a native FIXABLE finding that
|
||||
* states `Blocks: no` collects at its own Severity field; one with no Blocks: no, no Severity field or only a FIXABLE field stays CRITICAL.
|
||||
*/
|
||||
export function parseFindings(reader: string, output: string): Array<{ label: string; raw: string }> {
|
||||
type Finding = { label: string; raw: string; fields: Set<string>; list: boolean; lead?: string };
|
||||
export function parseFindings(reader: string, output: string, fixableRaises = true): Array<{ label: string; raw: string }> {
|
||||
type Finding = { label: string; raw: string; fields: Set<string>; list: boolean; lead?: string; fixable?: boolean; heading?: boolean };
|
||||
const out: Finding[] = [];
|
||||
let section: string | null = null;
|
||||
let current: Finding | null = null;
|
||||
@@ -115,9 +119,9 @@ export function parseFindings(reader: string, output: string): Array<{ label: st
|
||||
const named = (l: string) => (role === 'adversarial-native' && l.toUpperCase() === 'FIXABLE' ? 'CRITICAL' : l);
|
||||
const strongestOf = (labels: Array<string | undefined>) => labels.reduce<string | undefined>((a, b) => (a === undefined ? b : b === undefined ? a : stronger(a, b)), undefined);
|
||||
const strongest = (t: string) => strongestOf([...t.matchAll(ALL_LABELS)].map(m => named(m[1]!)));
|
||||
const fieldOf = (t: string) => { const ls = [...t.matchAll(SEVERITY_FIELD)].flatMap(m => (m[1] ?? m[2]!).match(FIELD_LABELS)!); return ls.length === 1 ? ls[0] : undefined; };
|
||||
const critical = (t: string) => BLOCKS_YES.test(t) || (role === 'adversarial-native' && /(?<![A-Za-z0-9])FIXABLE(?![A-Za-z0-9])/.test(t));
|
||||
const leadOf = (t: string) => { const l = LEAD_LABEL.exec(t)?.[1]; return l === undefined ? undefined : named(l); };
|
||||
const fieldOf = (t: string) => { const ls = [...t.matchAll(SEVERITY_FIELD)].flatMap(m => (m[1] ?? m[2]!).match(FIELD_LABELS)!); return ls.length === 1 && (fixableRaises || role !== 'adversarial-native' || rank(ls[0]!)) ? ls[0] : undefined; };
|
||||
const critical = (t: string) => BLOCKS_YES.test(t) || (fixableRaises && role === 'adversarial-native' && /(?<![A-Za-z0-9])FIXABLE(?![A-Za-z0-9])/.test(t));
|
||||
const leadOf = (t: string) => { const l = LEAD_LABEL.exec(t)?.[1]; return l === undefined || !fixableRaises ? l : named(l); };
|
||||
const labelOf = (t: string) => {
|
||||
const field = fieldOf(t);
|
||||
if (field === undefined) return strongest(t);
|
||||
@@ -150,7 +154,7 @@ export function parseFindings(reader: string, output: string): Array<{ label: st
|
||||
continue;
|
||||
}
|
||||
const heading = LABEL_HEADING.exec(t);
|
||||
if (heading) { section = named(heading[1]!); current = null; head = ''; continue; }
|
||||
if (heading) { section = fixableRaises ? named(heading[1]!) : heading[1]!; current = null; head = ''; continue; }
|
||||
if (!indented && HEADING.test(t)) { section = null; current = null; }
|
||||
if (t.startsWith('{')) {
|
||||
try {
|
||||
@@ -160,12 +164,20 @@ export function parseFindings(reader: string, output: string): Array<{ label: st
|
||||
}
|
||||
const detail = listItem && /^[-*+]\s/.test(t) && !locus && !label && !section && !!current && !current.list && !current.fields.size;
|
||||
if (detail && !blocks) { current!.raw += ` | ${t}`; continue; }
|
||||
if (afterGap && current?.heading && !current.fields.size && !LIST_ITEM.test(t) && !HEADING.test(t) && !NUMBERED_HEAD.test(t) && !LEAD_LABEL.test(t) && !LOCUS.test(t)) {
|
||||
current.raw += ` | ${t}`;
|
||||
if (blocks) current.label = 'CRITICAL';
|
||||
else if (label) current.label = stronger(current.label, label);
|
||||
continue;
|
||||
}
|
||||
const fresh = (listItem && !detail) || (!indented && !detail && (t.startsWith('**') || afterGap)) || (!!current?.fields.size && locus);
|
||||
if (fresh) { current = null; head = t; }
|
||||
const inherited = section && listItem ? section : undefined;
|
||||
const found = label && inherited ? stronger(inherited, label) : label ?? inherited;
|
||||
if (found) {
|
||||
current = push(blocks ? 'CRITICAL' : found, t, [], strongestOf([leadOf(t), inherited, fieldOf(t)]));
|
||||
current.fixable = inherited?.toUpperCase() === 'FIXABLE';
|
||||
current.heading = !indented && NUMBERED_HEAD.test(t);
|
||||
if (!indented) head = t;
|
||||
continue;
|
||||
}
|
||||
@@ -176,7 +188,20 @@ export function parseFindings(reader: string, output: string): Array<{ label: st
|
||||
}
|
||||
if (!fresh && !current && (!LIST_ITEM.test(head) || locus)) head = t;
|
||||
}
|
||||
return out.map(({ label, raw }) => ({ label, raw }));
|
||||
const unblocked = (f: Finding) => fixableRaises || role !== 'adversarial-native' || !(f.fixable || f.label.toUpperCase() === 'FIXABLE' || /(?<![A-Za-z0-9])FIXABLE(?![A-Za-z0-9])/.test(f.raw)) || BLOCKS_NO.test(f.raw);
|
||||
return out.map(f => ({ label: unblocked(f) ? f.label : 'CRITICAL', raw: f.raw }));
|
||||
}
|
||||
|
||||
/**
|
||||
* Whether the native voice's FIXABLE raises a finding with its own Severity field to CRITICAL (GST-987): true on the gate class, on any
|
||||
* risk reason (security, secret, auth, money, user data), a depth error, a history or floor escalation, and whenever the plan's
|
||||
* REVIEW_CLASS or REVIEW_DEPTH reasons cannot be read: only a code or docs plan whose every reason is `runtime=<n>` relaxes it.
|
||||
*/
|
||||
export function fixableRaises(planLines?: readonly string[]): boolean {
|
||||
const cls = planLines?.map(l => /^REVIEW_CLASS: (\S+)/.exec(l)?.[1]).find(Boolean);
|
||||
const reasons = planLines?.map(l => /^REVIEW_DEPTH: .*?\breasons=(\S+)/.exec(l)?.[1]).find(Boolean);
|
||||
if (!cls || !reasons) return true;
|
||||
return !['code', 'docs'].includes(cls) || !reasons.split(',').every(r => /^runtime=\d+$/.test(r));
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -201,17 +226,17 @@ const hasCleanMarker = (reader: string, output: string) => output.replace(/\r\n/
|
||||
* review: false. With unavailable (the outside voice only) the output is its failure text, recorded as missing coverage. With a
|
||||
* failed tree check (GST-482: the reply reviewed another checkout, or names none) nothing is merged and the output is no review.
|
||||
*/
|
||||
export function collect(ledger: string, reader: string, output: string, mergedFile: string, outputFile?: string, unavailable?: string, tree?: TreeCheck): { sha: string; lines: MergedLine[]; review: boolean } {
|
||||
export function collect(ledger: string, reader: string, output: string, mergedFile: string, outputFile?: string, unavailable?: string, tree?: TreeCheck, raises = true): { sha: string; lines: MergedLine[]; review: boolean } {
|
||||
const sha = promptHash(output);
|
||||
const prior = readLedger(ledger).filter(e => e.event === 'output' && e.reader === reader).length;
|
||||
const wrongTree = !unavailable && tree !== undefined && !tree.ok;
|
||||
const lines = unavailable || wrongTree ? [] : parseFindings(reader, output).map((f, i) => {
|
||||
const lines = unavailable || wrongTree ? [] : parseFindings(reader, output, raises).map((f, i) => {
|
||||
const s = stated(f.raw);
|
||||
return { id: `${reader}#${prior ? `${prior + 1}.` : ''}${i + 1}`, reader, label: f.label, ...(s ? { stated: s } : {}), raw: f.raw, output_sha256: sha };
|
||||
});
|
||||
const review = !unavailable && !wrongTree && (lines.length > 0 || hasCleanMarker(reader, output));
|
||||
fs.appendFileSync(mergedFile, lines.map(l => JSON.stringify(l) + '\n').join(''), { mode: 0o600 });
|
||||
appendEvent(ledger, { event: 'output', reader, sha256: sha, file: outputFile ? path.resolve(outputFile) : null, merged: path.resolve(mergedFile), ids: lines.map(l => l.id), review, ...(unavailable ? { unavailable } : {}),
|
||||
appendEvent(ledger, { event: 'output', reader, sha256: sha, file: outputFile ? path.resolve(outputFile) : null, merged: path.resolve(mergedFile), ids: lines.map(l => l.id), review, ...(unavailable ? { unavailable } : {}), ...(raises ? {} : { fixable_raises: false }),
|
||||
...(tree && !unavailable ? { tree: tree.expected, reported_tree: tree.reported, tree_ok: tree.ok } : {}) });
|
||||
return { sha, lines, review };
|
||||
}
|
||||
@@ -408,7 +433,7 @@ export function verify(ledger: string): { rows: VerifyRow[]; clean: boolean; bri
|
||||
notes.push(typeof o.file === 'string' ? 'output_file_missing' : 'output_file_unrecorded');
|
||||
differs.push(...ids);
|
||||
} else if (promptHash(text) === o.sha256) {
|
||||
const parsed = parseFindings(reader, text);
|
||||
const parsed = parseFindings(reader, text, o.fixable_raises !== false);
|
||||
const off = ids.filter((id, k) => { const m = lines.find(l => l.id === id); return !m || parsed[k]?.label !== m.label || parsed[k]?.raw !== m.raw; });
|
||||
if (unavailableOutput(o) && parsed.length) { status = 'MISMATCH'; notes.push('unavailable_output_has_findings'); }
|
||||
else if (!unavailableOutput(o)) {
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "gstack",
|
||||
"version": "1.93.20",
|
||||
"version": "1.93.21",
|
||||
"description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
|
||||
"license": "MIT",
|
||||
"type": "module",
|
||||
|
||||
@@ -0,0 +1,6 @@
|
||||
# garrytan/gstack-evals#141: native adversarial findings #4 and #6, head a752186 (tree 0ac70e872724875710ccc47f9c93b7b30a58604a)
|
||||
Copied verbatim from /home/user/.capy/work/ship-141/run/p2/out/adversarial-native.txt
|
||||
|
||||
4. **driver.ts:352, 561 and 618 (the C1 ruling): skill-eval sessions now end with background Agents still running and leave no structured record.** run-host.ts:352 passes no wait. Claude Code 2.1.314 runs Agent calls in the background by default. So a skill-eval `--host claude` session ends and is graded on its "agents launched, waiting" turn, which is the original GST-734 bug. Its record also has no `session_end`, only a line in cli-stderr.log. The CREW rule asks for a per-arm count of sessions that ended with tasks pending, and these records can't give that count. Grades for skills that hand work to Agents may be deflated with nothing marking them. Old cached sessions do not mix in, because adapterSha256 hashes driver.ts. The fix: keep emitting `session_end` (cause `tasks_pending`, `waited_ms` 0) when no wait is set, and leave the hold opt-in. That reverses the C1 test's `"session_end" in r.outcome === false` assertion, so the C1 owner needs to agree. FIXABLE. Severity: Medium. Blocks: no
|
||||
|
||||
6. **driver.ts:404-407: the timeout branch for an idle session sets `overdue = true` without checking `stop`.** Here is the case. A background agent's refused request sets a stop while the main agent is idle, such as `cap_stop`, or an infra failure does. The timer then fires during abort teardown. The record ends up with a `cap_stop` or infra termination but `session_end.cause` "deadline". The `watch` interval already checks `stop`. Fix: `else if (idleSince !== null && !stop)`. FIXABLE. Severity: Low. Blocks: no
|
||||
+1
-1
@@ -1 +1 @@
|
||||
{"note":"parseFindings labels at main 82e9d7ec (GST-976): every input the review-dispatch and prose-voice-floor tests pass it, every reader fixture here, and generated Severity field shapes. Regenerate only from a frozen main.","main":"82e9d7ec7a2c222f20b04aaf5b965fa50d7b6bdb","entries":[{"source":"pinned","reader":"adversarial-native","output":"FIXABLE: race in a.ts:3\nSeverity: Medium\nBlocks: no","main":["CRITICAL"]},{"source":"pinned","reader":"adversarial-native","output":"INVESTIGATE: odd lock in b.ts:9\nSeverity: Low\nBlocks: yes","main":["CRITICAL"]},{"source":"pinned","reader":"adversarial-native","output":"INVESTIGATE: odd lock in b.ts:9\nBlocks: no","main":["INVESTIGATE"]},{"source":"pinned","reader":"adversarial-native","output":"FIXABLE: race in a.ts:3. Severity: Medium. Blocks: no","main":["CRITICAL"]},{"source":"pinned","reader":"adversarial-native","output":"1. FIXABLE: race in a.ts:3 — Severity: Low, Blocks: no","main":["CRITICAL"]},{"source":"pinned","reader":"adversarial-native","output":"- FIXABLE: race in a.ts:3\n- Severity: Medium\n- Blocks: no","main":["CRITICAL"]},{"source":"pinned","reader":"outside-voice","output":"1. Drops the last row (q.ts:7). Severity: Critical. Blocks: no","main":["Critical"]},{"source":"pinned","reader":"outside-voice","output":"1. Cache evicts sessions (c.ts:4)\n Severity: High","main":["High"]},{"source":"pinned","reader":"outside-voice","output":"1. Retry storm (r.ts:2)\n Severity: Medium\n Blocks: yes","main":["CRITICAL"]},{"source":"pinned","reader":"outside-voice","output":"1. Index drift (i.ts:5). Severity: Low. Blocks: Yes, it loses the row","main":["CRITICAL"]},{"source":"pinned","reader":"outside-voice","output":"1. Naming (n.ts:1)\n Severity: Low\n Blocks: no","main":["Low"]},{"source":"pinned","reader":"specialist/testing","output":"REVIEWED_TREE: d0dd42d6a88fbc2a6abca4f6b2dfde7e35520c5a /home/user/.capy/work/gst976/wt\nNO FINDINGS\n","main":[]},{"source":"pinned","reader":"specialist/testing","output":"REVIEWED_TREE: d0dd42d6a88fbc2a6abca4f6b2dfde7e35520c5a /home/user/.capy/work/gst976/wt\n{\"severity\":\"CRITICAL\",\"path\":\"a.ts\",\"line\":3,\"category\":\"logic\",\"summary\":\"off by one\",\"specialist\":\"testing\"}\n{\"severity\":\"INFORMATIONAL\",\"path\":\"a.ts\",\"line\":9,\"category\":\"style\",\"summary\":\"name\",\"specialist\":\"testing\"}\n","main":["CRITICAL","INFORMATIONAL"]},{"source":"pinned","reader":"outside-voice","output":"REVIEWED_TREE: d0dd42d6a88fbc2a6abca4f6b2dfde7e35520c5a /home/user/.capy/work/gst976/wt\nFindings:\n1. **High**: retry loop never backs off (q.ts:78)\n2. Low - log line is noisy\nRecommendation: Fix the retry because it DoSes the pool\n","main":["High","Low"]},{"source":"pinned","reader":"specialist/testing","output":"REVIEWED_TREE: d0dd42d6a88fbc2a6abca4f6b2dfde7e35520c5a /home/user/.capy/work/gst976/wt\n{\"severity\":\"CRITICAL\",\"path\":\"a.ts\",\"line\":3,\"category\":\"logic\",\"summary\":\"x\",\"specialist\":\"testing\"}\n","main":["CRITICAL"]},{"source":"pinned","reader":"red-team","output":"REVIEWED_TREE: d0dd42d6a88fbc2a6abca4f6b2dfde7e35520c5a /home/user/.capy/work/gst976/wt\n{\"severity\":\"CRITICAL\",\"path\":\"b.ts\",\"line\":1,\"category\":\"x\",\"summary\":\"y\",\"specialist\":\"red-team\"}\n","main":["CRITICAL"]},{"source":"pinned","reader":"specialist/testing","output":"REVIEWED_TREE: d0dd42d6a88fbc2a6abca4f6b2dfde7e35520c5a /home/user/.capy/work/gst976/wt\n{\"severity\":\"CRITICAL\",\"path\":\"a.ts\",\"line\":3,\"category\":\"logic\",\"summary\":\"x\",\"specialist\":\"testing\"}\n{\"severity\":\"INFORMATIONAL\",\"path\":\"b.ts\",\"line\":1,\"category\":\"n\",\"summary\":\"y\",\"specialist\":\"testing\"}\n","main":["CRITICAL","INFORMATIONAL"]},{"source":"pinned","reader":"r","output":"NO FINDINGS\n","main":[]},{"source":"pinned","reader":"r","output":"## High\n1. The auth check skips webhooks (a.ts:4)\n - Impact: nested evidence\n **Fix:**\n- second one\n## Notes\n- not a finding\n**Critical findings**\n- real one\n**Recommendations**\n- consider renaming foo\n","main":["High","High","Critical"]},{"source":"pinned","reader":"r","output":"1. **Unbounded retry in queue.ts:78** (FIXABLE): loops on 429\n2. `auth.ts:42` skips token expiry check — INVESTIGATE\n### CRITICAL: missing auth check in api.ts:10\n#### [P1] token not expired\n### High: authorization bypass (auth.ts:14)\n- **HIGH**: leak\n| High | race in queue.ts:4 |\nClassification: INVESTIGATE\n7. **Informational: reads every file**","main":["FIXABLE","INVESTIGATE","CRITICAL","P1","High","HIGH","High","INVESTIGATE","Informational"]},{"source":"pinned","reader":"r","output":"FIXABLE: race in a.ts:3\nINVESTIGATE: odd lock\nRecommendation: Fix the race because x\n","main":["FIXABLE","INVESTIGATE"]},{"source":"pinned","reader":"outside-voice","output":"No CRITICAL issues except the token leak in log.ts:3","main":["CRITICAL"]},{"source":"pinned","reader":"fix-check","output":"No CRITICAL issues except the token leak in lLine truncated
|
||||
{"note":"parseFindings labels at main 82e9d7ec (GST-976): every input the review-dispatch and prose-voice-floor tests pass it, every reader fixture here, and generated Severity field shapes. Regenerate only from a frozen main.","main":"82e9d7ec7a2c222f20b04aaf5b965fa50d7b6bdb","entries":[{"source":"pinned","reader":"adversarial-native","output":"FIXABLE: race in a.ts:3\nSeverity: Medium\nBlocks: no","main":["CRITICAL"]},{"source":"pinned","reader":"adversarial-native","output":"INVESTIGATE: odd lock in b.ts:9\nSeverity: Low\nBlocks: yes","main":["CRITICAL"]},{"source":"pinned","reader":"adversarial-native","output":"INVESTIGATE: odd lock in b.ts:9\nBlocks: no","main":["INVESTIGATE"]},{"source":"pinned","reader":"adversarial-native","output":"FIXABLE: race in a.ts:3. Severity: Medium. Blocks: no","main":["CRITICAL"]},{"source":"pinned","reader":"adversarial-native","output":"1. FIXABLE: race in a.ts:3 — Severity: Low, Blocks: no","main":["CRITICAL"]},{"source":"pinned","reader":"adversarial-native","output":"- FIXABLE: race in a.ts:3\n- Severity: Medium\n- Blocks: no","main":["CRITICAL"]},{"source":"pinned","reader":"outside-voice","output":"1. Drops the last row (q.ts:7). Severity: Critical. Blocks: no","main":["Critical"]},{"source":"pinned","reader":"outside-voice","output":"1. Cache evicts sessions (c.ts:4)\n Severity: High","main":["High"]},{"source":"pinned","reader":"outside-voice","output":"1. Retry storm (r.ts:2)\n Severity: Medium\n Blocks: yes","main":["CRITICAL"]},{"source":"pinned","reader":"outside-voice","output":"1. Index drift (i.ts:5). Severity: Low. Blocks: Yes, it loses the row","main":["CRITICAL"]},{"source":"pinned","reader":"outside-voice","output":"1. Naming (n.ts:1)\n Severity: Low\n Blocks: no","main":["Low"]},{"source":"pinned","reader":"specialist/testing","output":"REVIEWED_TREE: d0dd42d6a88fbc2a6abca4f6b2dfde7e35520c5a /home/user/.capy/work/gst976/wt\nNO FINDINGS\n","main":[]},{"source":"pinned","reader":"specialist/testing","output":"REVIEWED_TREE: d0dd42d6a88fbc2a6abca4f6b2dfde7e35520c5a /home/user/.capy/work/gst976/wt\n{\"severity\":\"CRITICAL\",\"path\":\"a.ts\",\"line\":3,\"category\":\"logic\",\"summary\":\"off by one\",\"specialist\":\"testing\"}\n{\"severity\":\"INFORMATIONAL\",\"path\":\"a.ts\",\"line\":9,\"category\":\"style\",\"summary\":\"name\",\"specialist\":\"testing\"}\n","main":["CRITICAL","INFORMATIONAL"]},{"source":"pinned","reader":"outside-voice","output":"REVIEWED_TREE: d0dd42d6a88fbc2a6abca4f6b2dfde7e35520c5a /home/user/.capy/work/gst976/wt\nFindings:\n1. **High**: retry loop never backs off (q.ts:78)\n2. Low - log line is noisy\nRecommendation: Fix the retry because it DoSes the pool\n","main":["High","Low"]},{"source":"pinned","reader":"specialist/testing","output":"REVIEWED_TREE: d0dd42d6a88fbc2a6abca4f6b2dfde7e35520c5a /home/user/.capy/work/gst976/wt\n{\"severity\":\"CRITICAL\",\"path\":\"a.ts\",\"line\":3,\"category\":\"logic\",\"summary\":\"x\",\"specialist\":\"testing\"}\n","main":["CRITICAL"]},{"source":"pinned","reader":"red-team","output":"REVIEWED_TREE: d0dd42d6a88fbc2a6abca4f6b2dfde7e35520c5a /home/user/.capy/work/gst976/wt\n{\"severity\":\"CRITICAL\",\"path\":\"b.ts\",\"line\":1,\"category\":\"x\",\"summary\":\"y\",\"specialist\":\"red-team\"}\n","main":["CRITICAL"]},{"source":"pinned","reader":"specialist/testing","output":"REVIEWED_TREE: d0dd42d6a88fbc2a6abca4f6b2dfde7e35520c5a /home/user/.capy/work/gst976/wt\n{\"severity\":\"CRITICAL\",\"path\":\"a.ts\",\"line\":3,\"category\":\"logic\",\"summary\":\"x\",\"specialist\":\"testing\"}\n{\"severity\":\"INFORMATIONAL\",\"path\":\"b.ts\",\"line\":1,\"category\":\"n\",\"summary\":\"y\",\"specialist\":\"testing\"}\n","main":["CRITICAL","INFORMATIONAL"]},{"source":"pinned","reader":"r","output":"NO FINDINGS\n","main":[]},{"source":"pinned","reader":"r","output":"## High\n1. The auth check skips webhooks (a.ts:4)\n - Impact: nested evidence\n **Fix:**\n- second one\n## Notes\n- not a finding\n**Critical findings**\n- real one\n**Recommendations**\n- consider renaming foo\n","main":["High","High","Critical"]},{"source":"pinned","reader":"r","output":"1. **Unbounded retry in queue.ts:78** (FIXABLE): loops on 429\n2. `auth.ts:42` skips token expiry check — INVESTIGATE\n### CRITICAL: missing auth check in api.ts:10\n#### [P1] token not expired\n### High: authorization bypass (auth.ts:14)\n- **HIGH**: leak\n| High | race in queue.ts:4 |\nClassification: INVESTIGATE\n7. **Informational: reads every file**","main":["FIXABLE","INVESTIGATE","CRITICAL","P1","High","HIGH","High","INVESTIGATE","Informational"]},{"source":"pinned","reader":"r","output":"FIXABLE: race in a.ts:3\nINVESTIGATE: odd lock\nRecommendation: Fix the race because x\n","main":["FIXABLE","INVESTIGATE"]},{"source":"pinned","reader":"outside-voice","output":"No CRITICAL issues except the token leak in log.ts:3","main":["CRITICAL"]},{"source":"pinned","reader":"fix-check","output":"No CRITICAL issues except the token leak in lLine truncated
|
||||
@@ -0,0 +1,91 @@
|
||||
import { describe, expect, test } from 'bun:test';
|
||||
import { spawnSync } from 'node:child_process';
|
||||
import * as fs from 'node:fs';
|
||||
import * as os from 'node:os';
|
||||
import * as path from 'node:path';
|
||||
import { collect, fixableRaises, parseFindings, verify } from '../lib/review-ledger';
|
||||
|
||||
const ROOT = path.resolve(import.meta.dir, '..');
|
||||
const NATIVE = fs.readFileSync(path.join(ROOT, 'test/fixtures/review-ledger/gsta-141-native.md'), 'utf8').split('\n').filter(l => /^\d+\. /.test(l)).join('\n\n');
|
||||
const plan = (cls: string, reasons: string) => [`REVIEW_CLASS: ${cls} (x)`, `REVIEW_DEPTH: full runtime_lines=9 rules=r reasons=${reasons} codes=none`];
|
||||
const CODE = plan('code', 'runtime=9');
|
||||
|
||||
describe('native FIXABLE by review class (GST-987)', () => {
|
||||
// Value: protects=outside the gate class with no risk reason a native finding's own Severity field decides, so gstack-evals #141's
|
||||
// eval-driver findings (FIXABLE. Severity: Medium/Low. Blocks: no) collect as Medium and Low, while gate, risk and unreadable plans
|
||||
// keep normalizer v2; fails_when=FIXABLE raises a fielded finding on a code-class plan, or a gate, risk, error or missing plan stops
|
||||
// raising it; why_new=GEVA-2 reported #141 collecting both as CRITICAL; seam=fixableRaises, parseFindings and collect --manifest;
|
||||
// no_claim=which class a diff belongs to (lib/review-depth.ts decides)
|
||||
test('#141 native #4 and #6 collect at their own Severity on a code-class plan', () => {
|
||||
expect(parseFindings('adversarial-native', NATIVE, fixableRaises(CODE)).map(f => f.label)).toEqual(['Medium', 'Low']);
|
||||
expect(parseFindings('adversarial-native', NATIVE).map(f => f.label)).toEqual(['CRITICAL', 'CRITICAL']);
|
||||
});
|
||||
test('gate class, any risk reason, a depth error or an unreadable plan keeps normalizer v2', () => {
|
||||
for (const lines of [plan('gate', 'gate-class,runtime=9'), plan('code', 'risk:money,runtime=9'), plan('code', 'risk:data,runtime=9'), plan('code', 'error:DIFF,runtime=9'), plan('code', 'runtime=9,history:fixed-blocking'), plan('code', 'runtime=9,floor:full'), plan('code', ''), plan('unknown', 'runtime=9'), [CODE[0]!], [], undefined])
|
||||
expect(fixableRaises(lines)).toBe(true);
|
||||
expect(fixableRaises(CODE)).toBe(false);
|
||||
expect(fixableRaises(plan('docs', 'runtime=0'))).toBe(false);
|
||||
});
|
||||
test('on a code-class plan FIXABLE without a Severity field still collects CRITICAL, and Blocks: yes still raises', () => {
|
||||
expect(parseFindings('adversarial-native', '1. Race in a.ts:3. FIXABLE', false).map(f => f.label)).toEqual(['CRITICAL']);
|
||||
expect(parseFindings('adversarial-native', 'FIXABLE: race in a.ts:3\nSeverity: Medium\nBlocks: no', false).map(f => f.label)).toEqual(['Medium']);
|
||||
expect(parseFindings('adversarial-native', 'FIXABLE: race in a.ts:3\nSeverity: Medium\nBlocks: yes', false).map(f => f.label)).toEqual(['CRITICAL']);
|
||||
expect(parseFindings('adversarial-native', '1. Race in a.ts:3. Severity: FIXABLE', false).map(f => f.label)).toEqual(['CRITICAL']);
|
||||
expect(parseFindings('adversarial-native', '1. FIXABLE: race in store.ts:40. Severity: High', false).map(f => f.label)).toEqual(['CRITICAL']);
|
||||
expect(parseFindings('adversarial-native', '1. FIXABLE: race in store.ts:40\nSeverity: High\nBlocks: no', false).map(f => f.label)).toEqual(['High']);
|
||||
expect(parseFindings('adversarial-native', '## FIXABLE\n1. Leak in a.ts:3. Severity: Low. Blocks: no\n2. Race in b.ts:4\n3. Drift in c.ts:5. Severity: Low', false).map(f => f.label)).toEqual(['Low', 'CRITICAL', 'CRITICAL']);
|
||||
expect(parseFindings('adversarial-native', '**FIXABLE**\n- Leak in a.ts:3\n Severity: Medium', false).map(f => f.label)).toEqual(['CRITICAL']);
|
||||
expect(parseFindings('adversarial-native', 'FIXABLE: race in a.ts:3. Severity: Low. Blocks: no-op path only', false).map(f => f.label)).toEqual(['CRITICAL']);
|
||||
});
|
||||
// Value: protects=a paragraph under a numbered finding heading joins that heading's finding, so the reader's later Severity and Blocks
|
||||
// fields attach to it instead of splitting it into a CRITICAL heading plus a body item (gstack-evals #149); fails_when=any of the three
|
||||
// shapes collects 4 findings or the heading alone keeps CRITICAL on a code-class plan; why_new=#149 split native findings in both
|
||||
// classes; seam=parseFindings; no_claim=how unnumbered headings group
|
||||
test.each([
|
||||
['### 1. FIXABLE: race in a.ts:3\n\nThe body explains it.\n\nSeverity: Medium, Blocks: no\n\n### 2. FIXABLE: drift in b.ts:9\n\nMore body.\n\nSeverity: Low, Blocks: no'],
|
||||
['**1. Race in a.ts:3** FIXABLE\n\nBody.\n\nSeverity: Medium, Blocks: no\n\n**2. Drift in b.ts:9** FIXABLE\n\nBody.\n\nSeverity: Low, Blocks: no'],
|
||||
['### 1. Race in a.ts:3 — FIXABLE\n\nBody.\n\n**Severity:** Medium\n**Blocks:** no\n\n### 2. Drift in b.ts:9 — FIXABLE\n\nBody.\n\n**Severity:** Low\n**Blocks:** no'],
|
||||
])('a numbered finding heading keeps its body paragraph and fields (#149) %#', (output) => {
|
||||
expect(parseFindings('adversarial-native', output, false).map(f => f.label)).toEqual(['Medium', 'Low']);
|
||||
expect(parseFindings('adversarial-native', output, true).map(f => f.label)).toEqual(['CRITICAL', 'CRITICAL']);
|
||||
});
|
||||
test('a labeled or located paragraph after a numbered heading stays its own finding (#149 joins only plain body text)', () => {
|
||||
for (const raises of [true, false]) {
|
||||
expect(parseFindings('outside-voice', '### 1. P2 race in a.ts:3\n\nP0: also data loss in b.ts:9\n\nSeverity: Medium', raises).map(f => f.label)).toEqual(['P2', 'P0']);
|
||||
expect(parseFindings('outside-voice', '### 1. P2 race in a.ts:3\n\nBody.\n\nP1: second issue in b.ts:9', raises).map(f => f.label)).toEqual(['P2', 'P1']);
|
||||
}
|
||||
});
|
||||
test('collect reads the class from --manifest and defaults to the gate class without one', () => {
|
||||
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'gst987-'));
|
||||
const out = path.join(dir, 'native.txt');
|
||||
fs.writeFileSync(out, NATIVE + '\n');
|
||||
const manifest = path.join(dir, 'pass-manifest.json');
|
||||
const ledger = path.join(dir, 'ledger.jsonl');
|
||||
fs.writeFileSync(manifest, JSON.stringify({ version: 1, ledger, plan_lines: CODE, readers: [] }));
|
||||
const foreign = path.join(dir, 'foreign.json');
|
||||
fs.writeFileSync(foreign, JSON.stringify({ version: 1, ledger: path.join(dir, 'other.jsonl'), plan_lines: CODE, readers: [] }));
|
||||
let n = 0;
|
||||
const labels = (extra: string[]) => {
|
||||
fs.rmSync(ledger, { force: true });
|
||||
const merged = path.join(dir, `${n++}.merged.jsonl`);
|
||||
const r = spawnSync(path.join(ROOT, 'bin/gstack-review-dispatch'), ['collect', '--ledger', ledger, '--role', 'adversarial-native', '--output', out, '--merged', merged, ...extra], { cwd: ROOT, encoding: 'utf8', timeout: 60_000 });
|
||||
expect(r.stderr).toBe('');
|
||||
return fs.readFileSync(merged, 'utf8').trim().split('\n').map(l => JSON.parse(l).label);
|
||||
};
|
||||
expect(labels(['--manifest', manifest])).toEqual(['Medium', 'Low']);
|
||||
expect(fs.readFileSync(ledger, 'utf8')).toContain('"fixable_raises":false');
|
||||
expect(labels([])).toEqual(['CRITICAL', 'CRITICAL']);
|
||||
expect(fs.readFileSync(ledger, 'utf8')).not.toContain('fixable_raises');
|
||||
expect(labels(['--manifest', foreign])).toEqual(['CRITICAL', 'CRITICAL']);
|
||||
fs.rmSync(dir, { recursive: true, force: true });
|
||||
});
|
||||
test('verify re-derives a code-class collect with the class it was collected under', () => {
|
||||
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'gst987v-'));
|
||||
const out = path.join(dir, 'native.txt');
|
||||
fs.writeFileSync(out, NATIVE + '\n');
|
||||
const c = collect(path.join(dir, 'l.jsonl'), 'adversarial-native', NATIVE + '\n', path.join(dir, 'm.jsonl'), out, undefined, undefined, false);
|
||||
expect(c.lines.map(l => l.label)).toEqual(['Medium', 'Low']);
|
||||
expect(JSON.stringify(verify(path.join(dir, 'l.jsonl')))).not.toContain('merged_line_differs');
|
||||
fs.rmSync(dir, { recursive: true, force: true });
|
||||
});
|
||||
});
|
||||
@@ -11,6 +11,7 @@ const FIELD = new RegExp(`(?:(?:^|\\| )(?:[-*+>]\\s+|\\d+[.)]\\s+)?\\**\\s*Sever
|
||||
const LEAD = new RegExp(`(?:^|\\| )[^\\p{L}\\p{N}]*(?:\\d+[.)]\\s*[^\\p{L}\\p{N}]*)?(?:\\w[\\w./-]*:\\d+(?:[-–:,]\\s*\\d+)*\\S*\\s+[^\\p{L}\\p{N}]*)?(?:${LABELS})(?![a-z])`, 'u');
|
||||
const HEADING = new RegExp(`^(?:#{1,6}\\s*|\\*\\*)(?:${LABELS})\\b`, 'm');
|
||||
const LABEL = new RegExp(`${LABELS}`, 'gi');
|
||||
const LEAD_NO_FIXABLE = new RegExp(LEAD.source.replace('|FIXABLE|INVESTIGATE', ''), 'u');
|
||||
|
||||
describe('parseFindings is never weaker than main (GST-976 invariant)', () => {
|
||||
// Value: protects=no input the suite pins, no reader fixture and no Severity field shape collects below the label main (82e9d7ec)
|
||||
@@ -18,8 +19,10 @@ describe('parseFindings is never weaker than main (GST-976 invariant)', () => {
|
||||
// leading label, a label heading, Blocks: yes or the native voice's FIXABLE raises it; fails_when=a field chain (High/Critical) keeps
|
||||
// its weaker label (b3ddd6c) or a field whose clause runs on stops counting and a body P0 raises the finding (f3810d4);
|
||||
// why_new=three GST-976 review rounds each found a shape the row tables missed; seam=parseFindings; no_claim=that main's label was
|
||||
// right (it is the floor), or coverage of stored private reader outputs (checked outside the repo)
|
||||
test('every pinned input, reader fixture and generated field shape', () => {
|
||||
// right (it is the floor), or coverage of stored private reader outputs (checked outside the repo). GST-987: the gate class (and every
|
||||
// risk class) keeps this rule; outside it the native voice's FIXABLE beside Blocks: no no longer counts as a raise, so such a fielded
|
||||
// finding collects at its field unless a lead, a label heading or Blocks: yes raises it
|
||||
test.each([['gate', true], ['code', false]] as const)('every pinned input, reader fixture and generated field shape (%s class)', (_cls, raises) => {
|
||||
const { entries, shapes } = JSON.parse(fs.readFileSync(path.join(ROOT, 'test/fixtures/review-ledger/main-labels.json'), 'utf8'));
|
||||
const { bodies, fields: tails, joins, readers, generated } = shapes;
|
||||
for (const [b, f, j, r, main] of generated) entries.push({ reader: readers[r], output: bodies[b] + joins[j] + tails[f], main });
|
||||
@@ -27,14 +30,14 @@ describe('parseFindings is never weaker than main (GST-976 invariant)', () => {
|
||||
let findings = 0;
|
||||
for (const e of entries as Array<{ reader: string; output?: string; fixture?: string; main: string[] }>) {
|
||||
const output = e.output ?? fs.readFileSync(path.join(ROOT, 'test/fixtures', e.fixture!), 'utf8');
|
||||
const got = parseFindings(e.reader, output);
|
||||
const got = parseFindings(e.reader, output, raises);
|
||||
if (!e.main.length) continue;
|
||||
if (got.length !== e.main.length) { bad.push(`count ${got.length}/${e.main.length} ${JSON.stringify(output.slice(0, 80))}`); continue; }
|
||||
got.forEach((f, i) => {
|
||||
findings++;
|
||||
const fields = [...f.raw.matchAll(FIELD)].map(m => (m[1] ?? m[2])!);
|
||||
const single = fields.length === 1 && fields[0]!.match(LABEL)!.length === 1 ? fields[0]!.match(LABEL)![0] : undefined;
|
||||
const raised = /Blocks:?\**:?\s*\**\s*yes/i.test(f.raw) || (e.reader.startsWith('adversarial-native') && /FIXABLE/.test(f.raw)) || LEAD.test(f.raw) || HEADING.test(output);
|
||||
const raised = /Blocks:?\**:?\s*\**\s*yes/i.test(f.raw) || (e.reader.startsWith('adversarial-native') && /FIXABLE/.test(f.raw) && (raises || !/Blocks:?\**:?\s*\**\s*no\b/i.test(f.raw))) || (raises ? LEAD : LEAD_NO_FIXABLE).test(f.raw) || HEADING.test(output);
|
||||
const ok = single === undefined ? (rank(f.label) ?? 0) >= (rank(e.main[i]) ?? 0)
|
||||
: (rank(f.label) ?? 0) >= (rank(single) ?? 0) && (raised || (rank(f.label) ?? 0) === (rank(single) ?? 0));
|
||||
if (!ok) bad.push(`${e.reader} main=${e.main[i]} got=${f.label} field=${single ?? '-'} ${JSON.stringify(f.raw.slice(0, 100))}`);
|
||||
|
||||
Reference in new issue
Block a user