Files
ac20ef1e13 v1.91.16.0 fix: safe installs and upgrades, skills start everywhere, truthful completion (parallel wave) (#3014)
* fix(make-pdf,design): real TOC page numbers and anchors; design models move to gpt-5.5 + gpt-image-2 (#2903, #2807)

* ci: pin every action to a SHA, Scorecard, checksummed Bun, scoped Codex CLI in the CI image, macOS named-regressions job (#1948, #1706, #1997)

* fix(cso,browse): Windows/macOS lease identity, retention skips bad runs, truthful 'not assessed' reports, env.kv false positive, Windows browse spawn fixes (#2894, #2912, #2048, #2637, #2805)

* fix(outside-voice): one Codex model precedence for probe and dispatch, bounded timeouts with KILL escalation, probe cache identity, guarded mktemp, skills hidden in nested Codex (#2776, #2914, #2787, #2881, #2847)

* feat(setup): install registry, ./setup --status, staged activation, per-scope migrations, host tiers and conformance kit, OpenCode/Hermes fixes, Copilot CLI (experimental), disabled_skills, slimmer CLAUDE.md (#1925, #2879, #2347, #2338, #2626, #2629, #2825, #2015, #393, #1206, #2096)

Co-authored-by: Andrey Esipov <61357035+andrey-esipov@users.noreply.github.com>
Co-authored-by: Matthew Williams <5863886+ridermw@users.noreply.github.com>
Co-authored-by: Rocky Wu <92764750+lolisaigao1234@users.noreply.github.com>

* fix(preamble): skills start in worktree-isolated Claude Code sessions — one literal skill-start line, context-recovery helper, no eval in skill blocks, $N token tripwire, honest plan-mode precedence (#2763, #2896, #2851)

* fix(setup): per-install renders for renamed, vendored and custom-config installs, space-safe alias roots, per-host /cso launcher path (#1882, #2906)

* test: free tests never write the real HOME (home-write tripwire), no orphaned browse daemons, symlinked-TMPDIR (macOS) fixes, gbrain-on-PATH isolation (#2895, #2816, #2829, #2841, #2982, #2911, #2909, #2908, #2910)

* chore: integrate wave follow-ups — regenerate all hosts, README model docs, TODOS, touchfiles, duration seeds, Bun 1.3 telemetry test fix, replay fixtures pinned to their recorded bytes

* v1.91.14.0: release metadata

* test(browse): group-kill cleanup falls back to the leader when macOS returns EPERM for a live group

* ci: Codex login steps run under bash (the CI container's default sh rejects pipefail)

* fix: full-suite repairs — private state roots for 7 real-HOME writers, truthful home-guard attribution with --attribute-home, gstack-paths shim in ship-hook fixtures, Copilot in team-init probes, test-of-test detector, cookie review fixture pinned to the approved excerpt

* fix(windows): LF for Dockerfiles, normalized home-guard exclusions, path.relative fixture containment, ship push test spawn timeouts

* test(design-detect): widen the whole-scan budget test's timing margins so a loaded macOS runner can't time out the single-batch call

* fix(evals): qa protocol names defined for the judge, async PTY judge so overlapping sessions keep their cleanup deadline, bws setup cases use the standard JUDGE_MS tier

* test(pty): the non-blocking judge case is POSIX-only (its fake judge is a shebang script, like the PTY harness it covers)

* test(evals): ship-coverage-audit names absolute skill paths, uses Read, and skips the Step 7 artifact nothing consumes (removes the mechanism behind 3 of 4 historical timeouts)

* test: deflake terminal-agent concurrent startup (write the placeholder record before spawning, like the product) and qa-evidence resumed pipe (barrier on a full high-water mark instead of a sleep)

* fix(design): daemon log stream handles open errors instead of crashing the daemon; shutdown test awaits the stubbed exit

* test(evals): skillify checks the product's resolved state root (no GSTACK_HOME bypass), negative cases check every root; tpa shims live outside the agent's cwd and answer consistently

* test(evals): coverage-audit detector splits parallel columns at │ rails and [+] groups; coverage prompts name absolute skill paths; TODOs from the gate eval census

* fix(plan-eng-review): scope gate always sends the menu (no headless 'Scope pending' exit); PTY harness ends idle turn-ends and API-error panels promptly with a precise diagnostic

* test(evals): one position-bound coverage-read rule credits read-only && chains (labels, context ranges, git displays in either order) and still rejects forged output

* fix(ship): documentation section has one saved source inserted by cat (never retyped); spawned-marker evidence is the child output; refreshed codex/factory ship goldens

* test(docsync): the byte-exact insert positive is POSIX-only (the bash-command observer refuses backslash paths by design)

* test(evals): plan-design-with-ui focus-title rule accepts the comma-less 'dimensions or focus' wording (replayed on the captured CI run, negative controls kept)

* fix(qa-callers): exploratory preflight says the scope/method Reads come after exploratory.md; design-review scan check credits an executed scan proven by one engine run over the changed files

---------

Co-authored-by: Andrey Esipov <61357035+andrey-esipov@users.noreply.github.com>
Co-authored-by: Matthew Williams <5863886+ridermw@users.noreply.github.com>
Co-authored-by: Rocky Wu <92764750+lolisaigao1234@users.noreply.github.com>
2026-10-03 07:54:09 -07:00

42 lines
2.7 KiB
TypeScript

import { isDeepStrictEqual } from 'node:util';
import * as path from 'node:path';
import type { SkillTestResult } from './session-runner';
import { coverageAuditReadEvidence } from './coverage-audit-evidence';
export interface CoverageFile { path: string; content: string }
/** Require both nonce-bearing fixtures in successful, owned native tool output.
* coverageAuditReadEvidence is the single owner of what counts as a read: a
* native Read of the path, or a closed read-only Bash command whose cat/sed
* output holds the complete file at its own position. A command, assistant
* claim, pending call or echoed copy is no proof.
*/
export function requireCoverageFileReads(transcript: any[], cwd: string, files: CoverageFile[]): void {
// A retained transcript keeps the originating filesystem's path namespace.
const paths = /^(?:[A-Za-z]:[\\/]|\\\\)/.test(cwd) ? path.win32 : path.posix;
const required = ['src/billing.ts', 'test/billing.test.ts'].map(file => paths.join(cwd, file));
if (!isDeepStrictEqual(files.map(file => file.path).sort(), [...required].sort())
|| files.some(file => typeof file.content !== 'string' || !file.content.trim())) {
throw new Error('Coverage audit: source and test expectations are required');
}
const [source, tests] = required.map(file => files.find(candidate => candidate.path === file)!);
const reads = coverageAuditReadEvidence(Array.isArray(transcript) ? transcript : [], { cwd, source: source!, tests: tests! });
const missing = [[reads.sourceRead, source!], [reads.testsRead, tests!] as const]
.filter(([read]) => !read).map(([, file]) => paths.relative(cwd, (file as CoverageFile).path));
if (missing.length) throw new Error(`Coverage audit: no successful complete file read: ${missing.join(', ')}`);
}
export function validateCoverageAudit(result: SkillTestResult, cwd: string, files: CoverageFile[]): void {
if (result.exitReason !== 'success') throw new Error(`Coverage audit process: ${result.exitReason}`);
if (result.browseErrors.length) throw new Error('Coverage audit reported browser errors');
const output = result.output || '';
const lower = output.toLowerCase();
const hasGap = lower.includes('gap') || lower.includes('no test');
const hasTested = /\btested\b/i.test(output) || output.includes('✓') || output.includes('★');
const hasCoverage = lower.includes('coverage') || lower.includes('paths tested');
if (!hasGap || !hasTested || !hasCoverage || !output.includes('processPayment') || !output.includes('refundPayment')) {
throw new Error('Coverage audit: diagram must name both functions and show tested paths, gaps and coverage');
}
requireCoverageFileReads(result.transcript, cwd, files);
}