mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-31 22:14:25 +01:00
* fix(capy): the install trailer says behind=<n> and its fix, so a stale install shows in every relayed trailer (field list 2 item 13, #2378) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(capy): a lease records its holder's start identity, so a pid reused after a wake is reclaimed; a skipped session-start upgrade ends fail behind, never ok (GBRA-105, GBRA-106) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(lease): stale needs proof (unreadable or malformed identities keep the lease), ps identity is timezone-independent, and reclaim never deletes a concurrent renewal Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(autoplan): enforced round cap and spend budget, deferred close, public export without machine paths, opt-in durable checkpoints (field list 2 W5-W7) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(lease): one directory lock for publish, prune and reclaim; reclaim rereads the record judged stale, so a renewal is never deleted or hidden Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(lease): the directory lock names its holder; broken only when the holder is dead or its pid reused, unlock removes only its own lock, touch exits 3 under a live holder Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(lease): breakers serialize on .lock.break and reread the lock before removing it; gstack-skill-start reports a lease the held lock kept out Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(lease): name the double-crash limit of breaking a dead lock Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(capy): --for review-voice install profile, no-Drive bootstrap command, reviewer prompt trailer (field list 2 W11) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit89bf556c11) * test: pin review-voice row, helpers row and the no-Drive fallback in existing install tests Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit7f6c70459a) * test: the DRIVER template names the reviewer trailer relay (pregate lane) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit2545d9a6d2) * test(context-budget): capy skill eager ceiling for the review-voice subagent paragraph (W11; ratchet protocol, capture value) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(eval-plan): prereg diagnostics dry run (W8) and .gstack/eval-models.json lint (W9), WIP Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commitb509096218) * feat(eval-plan): W8/W9 tests, docs/eval-models.md, troubleshooting anchors, /eval-plan steps Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit9335e45de2) * test(eval-plan): eval-plan/SKILL.md names only defined codes and accepted flags Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commita7a974d268) * test(review-voice): the launch line points at the verdict's bun-only directory (#3233's launch contract) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(third-party-actions): the Aside drive-offer detector matches the product name, not the English idiom (paid run 38988927989 tpa-absent-linux false positive) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): export refuses artifact paths outside the run before writing; a deferred close keeps earlier undecided findings; reopening CEO grants Eng its rerun (review of #3234) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(restamp): gate-ahead keeps the lane CHANGELOG entry when both PRs took the same tentative stamp (GBRA-102 diagnosis fixture) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit43c75a6bb6) * test(tree-receipt): a real gbrain stamp pair is same-modulo-stamps under gbrain committed policy (W1 acceptance) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit6cf53f9fed) * feat(ship-policy): gate_command, full_e2e and min_gstack_version; unknown keys stay fail-closed; validate prints introducing versions Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit878a7123d7) * feat(ship-queue): gstack-ship-queue ready, stamp, verify and gate-ahead (WIP, tests next) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit409a5957ad) * test(ship-queue): stamp journal and resume, verify from a separate clone, gate-ahead attempts, ready Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commitade554087b) * docs(ship-policy): Run a shared merge queue; new keys and compatibility rule; troubleshooting anchors; /ship pointer Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit7fc73e8892) * fix(ship): shared-queue pointer rides the show-effective ship: line (ship skeleton has 2 bytes of parity headroom) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit5b33d4a015) * test(windows): curate the shared-queue tests out of the Windows subset (shebang spawns) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit8deee14728) * test(fixtures): register the gbrain stamp-pair fixture as free-only Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit563a07aa03) * test(ship-queue): receipt digest contract names lib/ship-queue.ts for its pregate lane Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit501637c258) * feat(pregate): timing check flags elapsed-time bounds and sleep-then-assert in added test lines (W4) lib/pregate/checks/timing.ts prints TIMING_ASSERTION: <file>:<line> <pattern> and a TIMING_ASSERTIONS summary; gstack-timing-ok: <reason> in any comment syntax on the line or the line above escapes one. It warns (PREGATE_TIMING_ASSERTION): measured on gstack (9 of 47 test-touching commits, 263 hits in the tree) and gbrain (37 of 95 commits; 31 of 38 sites of the five timing-flake fixes), blocking would stop a fifth to two fifths of test changes. Adds the /review checklist rule and the /investigate timing-flake playbook. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commita3b86b10b2) * feat(update-check): an equal VERSION with a moved main is an upgrade, via the compare API (W12) When VERSION matches but ls-remote's main SHA differs from this checkout's HEAD, bin/gstack-update-check asks the GitHub compare API (status, ahead_by) through the existing receipted curl and prints UPGRADE_AVAILABLE <ver> <ver>+<n> <sha>; a diverged or unreadable compare is CHECK_FAILED (unknown), and behind/identical is up to date. Never fetches. The cache gains an IDENTITY line (head, compared remote SHA, upstream): an outcome replays only for the same HEAD and upstream, a same-remote refresh reuses it without another compare, and a git checkout ignores a legacy one-line cache (non-git installs keep the one-line format). The snooze is keyed by the SHA. gstack-upgrade's question, snooze note and What's New step handle the four-field line; gstack-skill-end reports it. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit421e66d2a4) * fix(pregate): treat planning and evidence markdown as an empty lane A docs-only diff with no .gstack/pregate.json failed lanes as PREGATE_NO_LANE. Planning and evidence Markdown is now a docs/no-tests empty lane. Unmapped source files still fail closed. Co-authored-by: Nick <surlymo@apache.org> (cherry picked from commite8793e59e8) * fix(pregate): keep test-read markdown on its test lane Unmarked Markdown that no test depends on is a docs/no-tests empty lane. A file a test reads, including a fixture, still selects that test through the import graph. Unmapped source and unreferenced test-tree files still fail closed. Co-authored-by: Nick <surlymo@apache.org> (cherry picked from commit7aabbddf3d) * test(pregate): reviewer edges for the docs/no-tests empty lane (#3215) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit2fb3fa8613) * test(pregate): requires-remote on a gbrain-shaped repo (ci:ubicloud, UBI_OWNER) (W10) A base pregate.json with gbrain's dependencies and remote_gate "bun run ci:ubicloud" (a package script whose stub needs UBICLOUD_API_KEY, names VMs from UBI_OWNER and prints PREGATE_REMOTE). Under 8 cores the test tier is one obligation naming the command; --remote passes the caller's UBI_OWNER and key through and clears it on the report; without the key the gate's own error shows and the obligation stays uncleared. #3190's path needed no change. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit4d69ff02df) * test(pregate): the ship receipt counts the timing check (7 checks) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commitcb03ef67e7) * test(context-budget): gstack-upgrade eager ceiling for the W12 equal-version upgrade question (ratchet protocol, capture value) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(approval-classes): gstack-approval-classes and ship-receipt citation enforcement (W2, WIP) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit847c7dae3d) * feat(approval-classes): tests, docs, /review and /ship wiring (W2) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit269bd5b8b5) * feat(review): state-machines specialist and gstack-state-matrix round-trip check with a captured #6792 regression (W3) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit1a634979c6) * fix(review-army): keep the --simplification force flag pinned; approval test timeouts Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit789d392bce) * test(free-fixtures): register the state-matrix-6792 fixture Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit1bacef296d) * test(state-matrix): cover state-machines NEVER_GATE in gstack-specialist-stats Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> (cherry picked from commit859063d56f) * test(fixtures): register the pregate-timing fixtures as free-only (W4) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ship-queue): full_e2e needs bound gate evidence in ready and verify, CI reads every check-run page and commit status, next: quotes its paths (review #3235 P1-1, P1-5, P2-1) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(pregate): timing reads a native diff and never passes an unread one The timing check's git diff honored diff.external, textconv and diff.noprefix, so a configured driver hid every added line and the check passed. Run it with --no-ext-diff --no-textconv and explicit a/ b/ prefixes, and report a git diff that fails or does not finish as incomplete (PREGATE_INCOMPLETE), which a warn downgrade does not soften. Review of #3235, sibling of P1-4 (lib/pregate/checks/timing.ts:189). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(approval-classes): only affirmative APPROVED evidence counts, explicit tokens are authoritative, native diffs fail closed (review #3235 P1-2, P1-3, P1-4) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(state-matrix): detect reads the native diff, ignoring diff.external and textconv (review #3235 P1-4) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(e2e): review-army-state-matrix behavior case on the #6792 fixture (field list 2, W3) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review-army): tighten the State Machines dispatch line so /ship stays under its parity size ratio with main's #3231 review-army text Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(approval-classes): only top-level approval lines count; quoted, fenced, indented-code and commented text never does (review #3235 r2) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(approval-classes): approval evidence is the first non-blank line only, at column 0 (review #3235 r3) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(autoplan-budget): bind the reservation expectation to lib/autoplan-budget's default estimate (test-of-test ratchet) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: keep gstack-upgrade under its size budget, exempt state-matrix's fetch hint, fit the periodic plan's 37 slices Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(evals): the docs observer accepts the spawned-prefixed gstack-skill-start --help read Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(windows): curate capy-review-voice out of the Windows subset (POSIX launcher contract) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: changelog entry for field list 2 wave A Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: stamp v1.91.115.0 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: the scope-signal clarity check follows helper-printed signals; the hermetic update-check fixture writes the identity cache Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * refactor: move the release-path result codes to lib/result-codes-release.ts (module-size ratchet); fit the periodic plan's 38 slices Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: changelog entry for field list 2 wave B Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: stamp v1.91.116.0 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: copy lib/result-codes-release.ts wherever a fixture copies lib/result-codes.ts; the scope-signal check requires the helper's computed emission Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: state-matrix stats test resolves its slug under its own state root (home containment) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(windows): curate pregate-docs-lane-review out of the Windows subset (runBin shebang, like the other pregate fixtures) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(windows): curate pregate-remote-gbrain out of the Windows subset (runBin shebang, like pregate-remote) 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> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Nick <surlymo@apache.org>
144 lines
9.9 KiB
TypeScript
144 lines
9.9 KiB
TypeScript
/**
|
||
* state-matrix — the round-trip matrix for proposal, hold and approval state
|
||
* machines (field list 2, W3; #6792: accepting a deactivate or a same-claim
|
||
* replace proposal deleted the take because only the remove path was
|
||
* tested). Two deterministic halves around the /review state-machines
|
||
* specialist (review/specialists/state-machines.md):
|
||
*
|
||
* - `detectStateMachine` decides dispatch: added code lines (tests and docs
|
||
* excluded) that name a pending record (proposal, hold, approval, pending)
|
||
* and an owner action (accept, approve, drop, reject, ...).
|
||
* - `checkStateMatrix` reads the specialist's output: one `matrix` record
|
||
* per machine (kinds × owner actions → resulting row → test) plus findings.
|
||
* Every kind × action pair needs a cell with a resulting row; a test
|
||
* reference must exist in the checkout; an untested cell needs a CRITICAL
|
||
* `state-matrix` finding for that cell (the rule's High tier). With an
|
||
* expectation file (a fixture's ground truth) every expected kind, action
|
||
* and untested cell must be named.
|
||
*
|
||
* Caller: bin/gstack-state-matrix (detect, check).
|
||
*/
|
||
import * as fs from 'node:fs';
|
||
import * as path from 'node:path';
|
||
|
||
const SUBJECT = new Set(['proposal', 'proposals', 'propose', 'proposed', 'hold', 'holds', 'held', 'approval', 'approvals', 'pending']);
|
||
const ACTION = new Set(['accept', 'accepted', 'accepts', 'approve', 'approved', 'approves', 'drop', 'dropped', 'drops', 'reject', 'rejected', 'rejects', 'deny', 'denied', 'dismiss', 'dismissed', 'withdraw', 'withdrawn', 'release', 'released']);
|
||
const NOT_CODE = [/(^|\/)(test|tests|spec|__tests__|fixtures?|docs?)\//, /\.(test|spec)\.[a-z0-9]+$/i, /_(test|spec)\.[a-z0-9]+$/i, /\.(md|txt|json|ya?ml|lock)$/i];
|
||
|
||
/** Identifier words: camelCase, snake_case and kebab-case split, lowercased. */
|
||
export function words(text: string): string[] {
|
||
return text.replace(/([a-z0-9])([A-Z])/g, '$1 $2').split(/[^A-Za-z0-9]+/).filter(Boolean).map(w => w.toLowerCase());
|
||
}
|
||
|
||
export interface StateMachineHit { file: string; line: number; subject: string[]; action: string[] }
|
||
|
||
/** Added code lines that name a pending record or an owner action; dispatch needs both somewhere in the diff. */
|
||
export function detectStateMachine(files: Map<string, Array<{ line: number; text: string }>>): { detected: boolean; hits: StateMachineHit[] } {
|
||
const hits: StateMachineHit[] = [];
|
||
for (const [file, lines] of files) {
|
||
if (NOT_CODE.some(re => re.test(file))) continue;
|
||
for (const l of lines) {
|
||
const w = words(l.text);
|
||
const subject = [...new Set(w.filter(x => SUBJECT.has(x)))];
|
||
const action = [...new Set(w.filter(x => ACTION.has(x)))];
|
||
if (subject.length || action.length) hits.push({ file, line: l.line, subject, action });
|
||
}
|
||
}
|
||
const detected = hits.some(h => h.subject.length) && hits.some(h => h.action.length);
|
||
return { detected, hits: detected ? hits : [] };
|
||
}
|
||
|
||
export interface MatrixCell { kind: string; action: string; row: string; test: string | null }
|
||
export interface Matrix { machine: string; kinds: string[]; actions: string[]; cells: MatrixCell[] }
|
||
export interface MatrixFinding { severity?: string; category?: string; cell?: { kind?: string; action?: string }; summary?: string; path?: string }
|
||
export interface Expectation { kinds: string[]; actions: string[]; untested: Array<{ kind: string; action: string }> }
|
||
export interface Gap { code: string; cell?: string; detail: string }
|
||
export interface MatrixCheck { machines: Array<{ machine: string; kinds: number; actions: number; cells: number; tested: number; untested: number; reported: number }>; gaps: Gap[]; findings: number; noFindings: boolean }
|
||
|
||
/** Matrix records, findings and whether the output is the literal `NO FINDINGS`; unparseable lines are gaps. */
|
||
export function parseSpecialistOutput(text: string): { matrices: Matrix[]; findings: MatrixFinding[]; noFindings: boolean; gaps: Gap[] } {
|
||
const matrices: Matrix[] = [];
|
||
const findings: MatrixFinding[] = [];
|
||
const gaps: Gap[] = [];
|
||
const lines = text.split('\n').map(l => l.trim()).filter(Boolean);
|
||
const noFindings = lines.length === 1 && lines[0] === 'NO FINDINGS';
|
||
if (noFindings) return { matrices, findings, noFindings, gaps };
|
||
for (const line of lines) {
|
||
let obj: any;
|
||
try { obj = JSON.parse(line); } catch { gaps.push({ code: 'unparsed-line', detail: line.slice(0, 120) }); continue; }
|
||
if (obj && typeof obj === 'object' && obj.matrix) {
|
||
const m = obj.matrix;
|
||
const ok = typeof m.machine === 'string' && Array.isArray(m.kinds) && Array.isArray(m.actions) && Array.isArray(m.cells) && m.kinds.length && m.actions.length;
|
||
if (!ok) { gaps.push({ code: 'matrix-malformed', detail: 'a matrix record needs machine, non-empty kinds and actions, and cells' }); continue; }
|
||
matrices.push({ machine: m.machine, kinds: m.kinds.map(String), actions: m.actions.map(String), cells: m.cells.map((c: any) => ({ kind: String(c?.kind ?? ''), action: String(c?.action ?? ''), row: typeof c?.row === 'string' ? c.row : '', test: typeof c?.test === 'string' && c.test.trim() ? c.test.trim() : null })) });
|
||
} else if (obj && typeof obj === 'object') findings.push(obj);
|
||
}
|
||
return { matrices, findings, noFindings, gaps };
|
||
}
|
||
|
||
/** A test reference `path[:line]` (anything after a space is a test name) that exists in the checkout. */
|
||
export function testRefExists(repoRoot: string, ref: string): boolean {
|
||
const m = /^([^\s:#]+)(?::(\d+))?/.exec(ref);
|
||
if (!m) return false;
|
||
const abs = path.resolve(repoRoot, m[1]!);
|
||
if (!abs.startsWith(path.resolve(repoRoot) + path.sep) || !fs.existsSync(abs) || fs.statSync(abs).isDirectory()) return false;
|
||
return !m[2] || Number(m[2]) <= fs.readFileSync(abs, 'utf8').split('\n').length;
|
||
}
|
||
|
||
const same = (a: string, b: string) => a.trim().toLowerCase() === b.trim().toLowerCase();
|
||
/** A fixture's expected kind matches a matrix kind that contains it (`deactivate` ~ `takes_deactivate`). */
|
||
const names = (actual: string, expected: string) => actual.toLowerCase().includes(expected.toLowerCase());
|
||
|
||
function checkMatrix(m: Matrix, findings: MatrixFinding[], repoRoot: string, gaps: Gap[]): MatrixCheck['machines'][number] {
|
||
let tested = 0; let untested = 0; let reported = 0;
|
||
for (const kind of m.kinds) for (const action of m.actions) {
|
||
const cell = `${kind}×${action}`;
|
||
const cells = m.cells.filter(c => same(c.kind, kind) && same(c.action, action));
|
||
if (!cells.length) { gaps.push({ code: 'cell-absent', cell, detail: `${m.machine} has no row for this kind and owner action` }); continue; }
|
||
if (cells.length > 1) gaps.push({ code: 'cell-duplicate', cell, detail: `${cells.length} rows` });
|
||
const c = cells[0]!;
|
||
if (!c.row.trim()) gaps.push({ code: 'row-missing', cell, detail: 'no resulting row' });
|
||
if (c.test) {
|
||
tested += 1;
|
||
if (!testRefExists(repoRoot, c.test)) gaps.push({ code: 'test-unresolved', cell, detail: `${c.test} is not a file (and line) in this checkout` });
|
||
continue;
|
||
}
|
||
untested += 1;
|
||
const f = findings.filter(x => x.category === 'state-matrix' && x.cell && same(String(x.cell.kind ?? ''), kind) && same(String(x.cell.action ?? ''), action));
|
||
if (!f.length) gaps.push({ code: 'unreported', cell, detail: 'untested cell without a state-matrix finding' });
|
||
else if (!f.some(x => x.severity === 'CRITICAL')) gaps.push({ code: 'not-high', cell, detail: `reported as ${f[0]!.severity ?? 'no severity'}; an untested cell is CRITICAL` });
|
||
else reported += 1;
|
||
}
|
||
for (const c of m.cells) if (!m.kinds.some(k => same(k, c.kind)) || !m.actions.some(a => same(a, c.action))) gaps.push({ code: 'cell-unlisted', cell: `${c.kind}×${c.action}`, detail: 'a row whose kind or action is not in the lists' });
|
||
return { machine: m.machine, kinds: m.kinds.length, actions: m.actions.length, cells: m.cells.length, tested, untested, reported };
|
||
}
|
||
|
||
function checkExpectation(matrices: Matrix[], expect: Expectation, gaps: Gap[]): void {
|
||
if (!matrices.length) { gaps.push({ code: 'no-matrix', detail: 'the diff has a state machine, but the output has no matrix record' }); return; }
|
||
for (const kind of expect.kinds) if (!matrices.some(m => m.kinds.some(k => names(k, kind)))) gaps.push({ code: 'kind-missing', detail: `no matrix lists the kind ${kind}` });
|
||
for (const action of expect.actions) if (!matrices.some(m => m.actions.some(a => names(a, action)))) gaps.push({ code: 'action-missing', detail: `no matrix lists the owner action ${action}` });
|
||
for (const u of expect.untested) {
|
||
const cell = matrices.flatMap(m => m.cells).find(c => names(c.kind, u.kind) && names(c.action, u.action));
|
||
if (cell?.test) gaps.push({ code: 'untested-cell-claimed', cell: `${u.kind}×${u.action}`, detail: `mapped to ${cell.test}, which does not exercise this cell` });
|
||
}
|
||
}
|
||
|
||
/** Every gap the output leaves; an empty list means the matrix is complete and every untested cell is reported CRITICAL. */
|
||
export function checkStateMatrix(text: string, repoRoot: string, expect?: Expectation): MatrixCheck {
|
||
const parsed = parseSpecialistOutput(text);
|
||
const gaps = [...parsed.gaps];
|
||
const machines = parsed.matrices.map(m => checkMatrix(m, parsed.findings, repoRoot, gaps));
|
||
if (expect) checkExpectation(parsed.matrices, expect, gaps);
|
||
if (!expect && !parsed.matrices.length && parsed.findings.some(f => f.category === 'state-matrix')) gaps.push({ code: 'no-matrix', detail: 'state-matrix findings without the matrix they come from' });
|
||
return { machines, gaps, findings: parsed.findings.length, noFindings: parsed.noFindings };
|
||
}
|
||
|
||
export function renderStateMatrixCheck(r: MatrixCheck): string {
|
||
const lines = [
|
||
...r.machines.map(m => `STATE_MATRIX: ${m.machine} kinds=${m.kinds} actions=${m.actions} cells=${m.cells} tested=${m.tested} untested=${m.untested} reported=${m.reported}`),
|
||
...r.gaps.map(g => `STATE_MATRIX_GAP: ${g.code}${g.cell ? ' ' + g.cell : ''} — ${g.detail}`),
|
||
`STATE_MATRIX_CHECK: ${r.gaps.length ? `incomplete gaps=${r.gaps.length}` : 'ok'} machines=${r.machines.length}`,
|
||
];
|
||
return lines.join('\n') + '\n';
|
||
}
|