mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 20:50:34 +00:00
* feat: diff-aware E2E test selector Adds scripts/select-e2e.ts: reads git diff vs origin/master, classifies the change set (EMPTY/DOC_ONLY/SRC), and emits the relevant E2E test files on stdout. Fail-closed by design: any unmapped src/ change runs all E2E. - scripts/e2e-test-map.ts: hand-tuned path-glob -> test files map - scripts/select-e2e.ts: pure-function selector with three explicit cases - scripts/run-e2e.sh: accepts optional file list from argv + --dry-run-list - test/select-e2e.test.ts: 24 cases including 3 codex regression guards (skills/, untracked files, unmapped src/) * feat: local CI gate via docker compose Adds bun run ci:local — runs every check GH Actions runs (gitleaks + unit + 29 E2E files) inside a Docker container that bind-mounts the repo. Pure bind-mount + named volumes (gbrain-ci-node-modules, gbrain-ci-bun-cache, gbrain-ci-pg-data) for fast warm restarts. - docker-compose.ci.yml: pgvector/pgvector:pg16 + oven/bun:1 - scripts/ci-local.sh: orchestrator with --diff, --no-pull, --clean - gitleaks runs on host (scoped to working dir + branch commits) - DATABASE_URL unset for unit phase (matches GH Actions split) - git installed in container at startup (oven/bun:1 omits it) - Postgres host port via GBRAIN_CI_PG_PORT env (default 5434) Stronger than PR CI: runs all 29 E2E files vs CI's 2-file Tier 1. * chore: bump version and changelog (v0.23.1) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: document local CI gate for v0.23.1 CLAUDE.md gains key-files entries for docker-compose.ci.yml, scripts/ci-local.sh, scripts/select-e2e.ts + e2e-test-map.ts, and the scripts/run-e2e.sh argv tweak. Pre-ship requirements section now lists the Docker-based local gate as Path A alongside the manual lifecycle. CONTRIBUTING.md tests section adds the bun run ci:local / ci:local:diff / ci:select-e2e block with prerequisites (Docker engine + gitleaks) and the GBRAIN_CI_PG_PORT override. AGENTS.md "Before shipping" promotes ci:local as the easiest path and keeps the manual lifecycle as a fallback. README.md Contributing section points to ci:local for the full gate. CHANGELOG.md untouched — v0.23.1 entry already finalized. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> * feat: SHARD=N/M env support in scripts/run-e2e.sh Filters the E2E file list to every M-th file starting at index N (1-indexed). Sequential execution within a shard preserves the TRUNCATE CASCADE no-race property documented at the top of the file. Empty-shard handling under `set -u` uses ${arr[@]:-} fallback. Standalone change; not yet wired up in ci-local.sh. * feat: 4-way parallel E2E shards in ci:local Replaces the single postgres service with 4 (postgres-1..4) on host ports 5434-5437. scripts/ci-local.sh fans 4 workers via xargs -P4 inside the runner container; each pinned to its own DATABASE_URL via SHARD=N/4. Wall-time on a 16-core host: ~6 min sequential -> ~1.5-2 min sharded. Total full-gate wall-time goes from ~25 min to ~3-5 min warm. Also handles git-worktree (Conductor) layouts: when /app/.git is a file instead of a directory, parse the gitdir + commondir and bind-mount the shared host gitdir at its absolute path. Without this, in-container `git ls-files` (used by scripts/check-trailing-newline.sh and friends) exits 128 with "not a git repository". Also runs `git config --global --add safe.directory '*'` inside the container so the root-uid container can read host-uid gitdir without "dubious ownership" rejection. CHANGELOG entry updated to cover the speedup. - docker-compose.ci.yml: 4 pgvector services + per-shard named volumes - scripts/ci-local.sh: parallel xargs orchestration + worktree mount fix - CHANGELOG.md v0.23.1: 4-way sharded wall-time, 36 E2E files, --no-shard flag * chore: regenerate llms-full.txt for v0.23.1 doc updates Required by test/build-llms.test.ts case 4 — committed llms-full.txt must match `bun run build:llms` output. The CHANGELOG + CLAUDE.md updates in this branch shifted bytes; regen catches up. * feat: scripts/run-unit-shard.sh + slow-test convention Tier 1 + Tier 4 plumbing: - scripts/run-unit-shard.sh: SHARD=N/M filter for unit files (excludes test/e2e/*). Excludes *.slow.test.ts (Tier 4 convention) so the fast shard fan-out skips known-slow files; CI's `bun run test` still includes them via default discovery. - scripts/run-slow-tests.sh: companion that runs ONLY *.slow.test.ts. Wired as `bun run test:slow`. - scripts/profile-tests.sh: portable awk parser that extracts the top-N slowest tests from any captured `bun test` output. Wired as `bun run test:profile`. Use it to pick demotion candidates. * feat: PGLite snapshot fixture for ~4.5x faster cold init (Tier 3) scripts/build-pglite-snapshot.ts boots a fresh PGLite, runs the full initSchema() (forward bootstrap + 30 migrations), and dumps the post-init state to test/fixtures/pglite-snapshot.tar plus a SHA-256 schema hash sidecar (.version). Both gitignored — built on demand via `bun run build:pglite-snapshot`. PGLiteEngine.connect() reads GBRAIN_PGLITE_SNAPSHOT env: validates the sidecar hash against the in-process MIGRATIONS hash, loads via PGLite's loadDataDir blob, sets _snapshotLoaded so initSchema() short-circuits. Measured per-file cold init drops from 828ms → 181ms. Bootstrap-correctness tests (bootstrap.test.ts, schema-bootstrap-coverage.test.ts) explicitly delete the env at file top so they keep exercising the cold path they verify. * feat: --classify-only + heartbeat tolerance fix (Tiers 2 + flake fix) - scripts/select-e2e.ts: --classify-only flag emits EMPTY|DOC_ONLY|SRC. Used by ci-local.sh's --diff fast-path to skip the heavy gate when only docs changed. - test/progress.test.ts: startHeartbeat tolerance widened to 1-20 over 200ms (was 2-6 over 85ms). Under 4-way parallel shard load on a contended host, setTimeout's effective quantum balloons and the tight bound flakes. The test still verifies "fires multiple times, stops cleanly" — exact count was never load-bearing. * feat: 4-way unit + E2E sharding in ci-local.sh + CHANGELOG (Tiers 1-4) ci-local.sh ties the four tiers together: - Tier 2: pre-flight diff classification on host. DOC_ONLY exits in ~5s (gitleaks only, no postgres, no container). - Tier 1: guards + typecheck run ONCE before fan-out. xargs -P4 then spawns 4 shards inside the runner container, each running unit phase (env -u DATABASE_URL bash run-unit-shard.sh) followed by E2E phase (DATABASE_URL=postgres-N bash run-e2e.sh) — both sharded N/4. Per-shard logs in /tmp/shard-logs/shard-N.log; printed in shard order at the end. - Tier 3: snapshot fixture built once at runner startup if missing, GBRAIN_PGLITE_SNAPSHOT exported so all shards inherit. - Tier 4: run-unit-shard.sh excludes *.slow.test.ts; run-slow-tests.sh + test:slow npm script handle the demoted set. - --no-shard preserves the legacy single-process flow for debug. package.json: build:pglite-snapshot, test:slow, test:profile scripts. Measured wall-time on 16-core host: 100s warm (down from ~22 min cold single-process). 4 shards × ~640-1024 unit tests each, plus 9 E2E files each. PGLite snapshot saves 4.5× per cold init (828ms → 181ms). CHANGELOG.md updated with measured numbers + four-tier breakdown. --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
246 lines
7.6 KiB
TypeScript
246 lines
7.6 KiB
TypeScript
#!/usr/bin/env bun
|
|
// scripts/select-e2e.ts
|
|
//
|
|
// Fail-closed diff-based E2E test selector. Reads the working-tree diff vs
|
|
// origin/master plus untracked files, classifies the change set as
|
|
// EMPTY / DOC_ONLY / SRC, and emits the relevant E2E test files on stdout.
|
|
//
|
|
// CONTRACT (fail-closed):
|
|
// - When in doubt, run all E2E. The map narrows from "all"; it never widens
|
|
// from "none". An unmapped src/ change emits ALL test/e2e/*.test.ts.
|
|
// - Doc-only diffs emit nothing (the only case where stdout is empty).
|
|
// - Empty diff emits ALL (clean branch shouldn't run nothing).
|
|
//
|
|
// Selection algorithm:
|
|
// 1. Read changed files from three git sources, union them:
|
|
// - git diff --name-only origin/master...HEAD (committed)
|
|
// - git diff --name-only HEAD (unstaged + staged)
|
|
// - git ls-files --others --exclude-standard (untracked, NOT .gitignore'd)
|
|
// 2. EMPTY -> emit ALL test/e2e/*.test.ts
|
|
// DOC_ONLY (every path matches doc allowlist) -> emit nothing
|
|
// SRC (at least one path is outside doc allowlist):
|
|
// a. Any escape-hatch path matched -> emit ALL
|
|
// b. Else union map matches; include directly-modified test/e2e/*.test.ts
|
|
// c. If still empty -> FAIL-CLOSED -> emit ALL
|
|
//
|
|
// On git command failure: print error to stderr and exit 2 so callers see the
|
|
// failure (xargs -r will run nothing AND the human sees the error).
|
|
//
|
|
// Usage:
|
|
// bun run scripts/select-e2e.ts
|
|
// bun run scripts/select-e2e.ts | xargs -r bash scripts/run-e2e.sh
|
|
|
|
import { spawnSync } from "node:child_process";
|
|
import { readdirSync, existsSync } from "node:fs";
|
|
import { join } from "node:path";
|
|
|
|
import { E2E_TEST_MAP } from "./e2e-test-map.ts";
|
|
|
|
// Doc allowlist (inclusive). A path counts as doc-only ONLY if it matches one
|
|
// of these patterns. Unrecognized paths fall through to SRC, never silently
|
|
// doc-only. skills/ is intentionally NOT here — skills are product input.
|
|
const DOC_ROOT_FILES = new Set([
|
|
"README.md",
|
|
"CLAUDE.md",
|
|
"AGENTS.md",
|
|
"CHANGELOG.md",
|
|
"TODOS.md",
|
|
"LICENSE",
|
|
"VERSION",
|
|
]);
|
|
|
|
function isDocPath(p: string): boolean {
|
|
if (DOC_ROOT_FILES.has(p)) return true;
|
|
// Any *.md at repo root.
|
|
if (!p.includes("/") && p.endsWith(".md")) return true;
|
|
// Anything under docs/.
|
|
if (p.startsWith("docs/")) return true;
|
|
return false;
|
|
}
|
|
|
|
// Escape-hatch triggers. Any match -> emit ALL.
|
|
const ESCAPE_HATCH_FILES = new Set([
|
|
"src/schema.sql",
|
|
"src/core/migrate.ts",
|
|
"src/core/db.ts",
|
|
"src/core/engine-factory.ts",
|
|
"src/core/operations.ts",
|
|
"package.json",
|
|
"bun.lock",
|
|
"Dockerfile.ci",
|
|
"docker-compose.ci.yml",
|
|
"scripts/ci-local.sh",
|
|
"scripts/run-e2e.sh",
|
|
"scripts/select-e2e.ts",
|
|
"scripts/e2e-test-map.ts",
|
|
"test/e2e/helpers.ts",
|
|
]);
|
|
|
|
const ESCAPE_HATCH_PREFIXES = [
|
|
"src/commands/migrations/",
|
|
"test/e2e/fixtures/",
|
|
"skills/",
|
|
".github/workflows/",
|
|
];
|
|
|
|
function isEscapeHatch(p: string): boolean {
|
|
if (ESCAPE_HATCH_FILES.has(p)) return true;
|
|
for (const prefix of ESCAPE_HATCH_PREFIXES) {
|
|
if (p.startsWith(prefix)) return true;
|
|
}
|
|
return false;
|
|
}
|
|
|
|
// Minimal glob matcher: supports ** (any segments) and * (one segment, no /).
|
|
// Throws on unsupported syntax so map mistakes surface loudly.
|
|
export function matchGlob(glob: string, path: string): boolean {
|
|
if (glob.includes("?") || glob.includes("[") || glob.includes("{")) {
|
|
throw new Error(
|
|
`select-e2e: unsupported glob syntax in "${glob}" (only ** and * are supported)`
|
|
);
|
|
}
|
|
// Build a regex: ** -> .*, * -> [^/]*, escape other regex meta-chars.
|
|
let regex = "";
|
|
let i = 0;
|
|
while (i < glob.length) {
|
|
const c = glob[i];
|
|
if (c === "*" && glob[i + 1] === "*") {
|
|
regex += ".*";
|
|
i += 2;
|
|
} else if (c === "*") {
|
|
regex += "[^/]*";
|
|
i += 1;
|
|
} else if (/[.+^${}()|\\]/.test(c)) {
|
|
regex += "\\" + c;
|
|
i += 1;
|
|
} else {
|
|
regex += c;
|
|
i += 1;
|
|
}
|
|
}
|
|
return new RegExp("^" + regex + "$").test(path);
|
|
}
|
|
|
|
function listAllE2ETests(repoRoot: string): string[] {
|
|
const dir = join(repoRoot, "test/e2e");
|
|
if (!existsSync(dir)) return [];
|
|
return readdirSync(dir)
|
|
.filter((f) => f.endsWith(".test.ts"))
|
|
.map((f) => `test/e2e/${f}`)
|
|
.sort();
|
|
}
|
|
|
|
// Pure function — exposed for unit tests. Decides what to emit given the
|
|
// inputs, without touching git or filesystem (callers pass arrays in).
|
|
export interface SelectInputs {
|
|
changedFiles: string[]; // union of three git sources
|
|
allE2ETests: string[]; // glob result of test/e2e/*.test.ts
|
|
map: Record<string, string[]>; // E2E_TEST_MAP
|
|
}
|
|
|
|
export type Classification = "EMPTY" | "DOC_ONLY" | "SRC";
|
|
|
|
export function classify(changedFiles: string[]): Classification {
|
|
if (changedFiles.length === 0) return "EMPTY";
|
|
for (const f of changedFiles) {
|
|
if (!isDocPath(f)) return "SRC";
|
|
}
|
|
return "DOC_ONLY";
|
|
}
|
|
|
|
export function selectTests(inputs: SelectInputs): string[] {
|
|
const { changedFiles, allE2ETests, map } = inputs;
|
|
const cls = classify(changedFiles);
|
|
const allSorted = allE2ETests.slice().sort();
|
|
|
|
if (cls === "EMPTY") return allSorted;
|
|
if (cls === "DOC_ONLY") return [];
|
|
|
|
// SRC case.
|
|
// 3a. Any escape-hatch -> ALL.
|
|
for (const f of changedFiles) {
|
|
if (isEscapeHatch(f)) return allSorted;
|
|
}
|
|
|
|
// 3b. Union map matches; include directly-modified test files.
|
|
const result = new Set<string>();
|
|
for (const f of changedFiles) {
|
|
if (isDocPath(f)) continue;
|
|
// Direct test file modification: include it.
|
|
if (f.startsWith("test/e2e/") && f.endsWith(".test.ts")) {
|
|
result.add(f);
|
|
continue;
|
|
}
|
|
for (const [glob, tests] of Object.entries(map)) {
|
|
if (matchGlob(glob, f)) {
|
|
for (const t of tests) result.add(t);
|
|
}
|
|
}
|
|
}
|
|
|
|
// 3c. Fail-closed: if no map entry matched any src/ path AND no test files
|
|
// were directly modified, run everything.
|
|
if (result.size === 0) return allSorted;
|
|
|
|
// Sort for determinism (helps tests + readability).
|
|
return Array.from(result).sort();
|
|
}
|
|
|
|
function runGit(args: string[], cwd: string): string {
|
|
const result = spawnSync("git", args, { cwd, encoding: "utf8" });
|
|
if (result.status !== 0) {
|
|
const stderr = (result.stderr || "").trim();
|
|
process.stderr.write(
|
|
`select-e2e: git ${args.join(" ")} failed: ${stderr}\n`
|
|
);
|
|
process.exit(2);
|
|
}
|
|
return result.stdout || "";
|
|
}
|
|
|
|
function readChangedFiles(repoRoot: string): string[] {
|
|
const sources = [
|
|
runGit(["diff", "--name-only", "origin/master...HEAD"], repoRoot),
|
|
runGit(["diff", "--name-only", "HEAD"], repoRoot),
|
|
runGit(["ls-files", "--others", "--exclude-standard"], repoRoot),
|
|
];
|
|
const set = new Set<string>();
|
|
for (const out of sources) {
|
|
for (const line of out.split("\n")) {
|
|
const trimmed = line.trim();
|
|
if (trimmed.length > 0) set.add(trimmed);
|
|
}
|
|
}
|
|
return Array.from(set).sort();
|
|
}
|
|
|
|
// Entrypoint. Skipped under test (Bun.main check).
|
|
if (import.meta.main) {
|
|
const repoRoot = spawnSync("git", ["rev-parse", "--show-toplevel"], {
|
|
encoding: "utf8",
|
|
}).stdout?.trim();
|
|
if (!repoRoot) {
|
|
process.stderr.write("select-e2e: not a git repository\n");
|
|
process.exit(2);
|
|
}
|
|
|
|
const changedFiles = readChangedFiles(repoRoot);
|
|
|
|
// --classify-only: print EMPTY|DOC_ONLY|SRC + exit. Used by ci-local.sh's
|
|
// Tier 2 fast-path so doc-only diffs skip the unit phase entirely.
|
|
if (process.argv.includes("--classify-only")) {
|
|
process.stdout.write(classify(changedFiles) + "\n");
|
|
process.exit(0);
|
|
}
|
|
|
|
const allE2ETests = listAllE2ETests(repoRoot);
|
|
const tests = selectTests({
|
|
changedFiles,
|
|
allE2ETests,
|
|
map: E2E_TEST_MAP,
|
|
});
|
|
|
|
process.stdout.write(tests.join(" "));
|
|
if (tests.length > 0) process.stdout.write("\n");
|
|
}
|