gstack/lib/pregate/lane-selection.ts

/**
 * pregate/lane-selection — from touched files to the tests that must run and
 * the platform lanes that must run them (plan C8 `lanes`). Mapping goes
 * through lib/pregate/import-graph.ts plus the generated-file registry (a
 * touched template selects the tests of its rendered outputs). Lane file
 * sets come from the workflow files: literal test paths in run steps, or the
 * runner-owned selection manifest `.gstack/pregate.json` declares for a
 * planner-computed matrix. Every uncertainty widens the selection.
 */
import { spawnSync } from 'node:child_process';
import { GENERATED_PATH } from '../regen';
import { matchesAny } from '../ship-policy';
import { PREGATE_CONFIG_PATH } from './config';
import { buildGraph, isTestFile, listRepoFiles, testsFor, type Graph } from './import-graph';
import type { PregateContext, RemoteObligation } from './types';
import type { Lane } from './workflows';

export interface Selection {
  /** Touched files with no lane and no `[]` declaration. */
  noLane: string[];
  /** Every test the touched files select, sorted. */
  tests: string[];
  /** Tests that run on this machine. */
  localTests: string[];
  /** Platform lanes this machine cannot run that select part of the set. */
  remote: RemoteObligation[];
  /** Tiers of the local lanes the selection touches. */
  tiersRan: string[];
  /** `lane id → files` for every lane whose set is known, plus `?` for planner-computed lanes without a manifest. */
  laneSets: Record<string, string[] | '?'>;
  provenance: string[];
}

/** Resolve one lane's test-file set: literal paths, then the declared selection manifest, else `?` when its matrix is an expression. */
export function laneFileSet(ctx: PregateContext, lane: Lane): string[] | '?' | 'all' {
  const files = new Set(lane.testFiles);
  const manifest = ctx.config.selection[lane.id];
  if (manifest) {
    if (!ctx.allowRepoCommands) { ctx.explain.push(`lane ${lane.id}: selection manifest \`${manifest}\` not run (pass --allow-repo-commands); treated as unknown`); return files.size ? [...files] : '?'; }
    const r = spawnSync('bash', ['-c', `set -o pipefail; ${manifest}`], { cwd: ctx.repoRoot, encoding: 'utf8', timeout: Math.min(ctx.timeoutMs, 300_000), maxBuffer: 64 * 1024 * 1024, env: ctx.env });
    if (r.status !== 0) { ctx.explain.push(`lane ${lane.id}: selection manifest exited ${r.status}; treated as unknown`); return '?'; }
    for (const line of (r.stdout ?? '').split('\n')) { const m = /((?:[\w.-]+\/)*[\w.-]+\.(?:test|spec)\.[cm]?[jt]sx?|(?:[\w.-]+\/)*test_[\w.-]+\.py)/.exec(line.trim()); if (m) files.add(m[1]!); }
    ctx.explain.push(`lane ${lane.id}: ${files.size} files from manifest \`${manifest}\``);
    return [...files];
  }
  if (lane.matrixExpression && files.size === 0) { ctx.explain.push(`lane ${lane.id}: unsupported workflow expression ${JSON.stringify(lane.matrixExpression)} and no selection manifest; treated as unknown`); return '?'; }
  return files.size ? [...files] : 'all';
}

/** Tracked files matching a registry entry's output globs. */
function outputsOf(all: readonly string[], globs: readonly string[]): string[] { return all.filter(f => matchesAny(globs, f)); }

export function selectLanes(ctx: PregateContext): Selection {
  const touched = ctx.touched;
  const gone = touched.flatMap(t => [t.status === 'D' ? t.path : null, t.renamedFrom ?? null]).filter((p): p is string => !!p);
  const graph: Graph = buildGraph(ctx.repoRoot, { declarations: ctx.config.dependencies, extraFiles: gone });
  const all = listRepoFiles(ctx.repoRoot);
  const provenance: string[] = [];
  const tests = new Set<string>();
  const noLane: string[] = [];
  const seeds = new Map<string, string>();
  for (const t of touched) { seeds.set(t.path, t.status === 'D' ? 'deleted' : 'touched'); if (t.renamedFrom) seeds.set(t.renamedFrom, `renamed to ${t.path}`); }
  for (const e of ctx.registry.entries) {
    if (!touched.some(t => matchesAny(e.inputs, t.path) || matchesAny(e.outputs, t.path))) continue;
    for (const out of outputsOf(all, e.outputs)) if (!seeds.has(out)) seeds.set(out, `generated by ${e.id}`);
  }
  for (const [file, why] of seeds) {
    const m = testsFor(graph, file, ctx.config.dependencies);
    for (const t of m.tests) tests.add(t);
    provenance.push(...m.provenance.map(p => `${p} [${why}]`));
    if (m.tests.length || m.declaredNone || why.startsWith('generated')) continue;
    // A renamed file keeps the lane its old name had: those tests run (and fail loudly if they still import the old path).
    const renamedFrom = touched.find(t => t.path === file && t.renamedFrom)?.renamedFrom;
    if (renamedFrom && testsFor(graph, renamedFrom, ctx.config.dependencies).tests.length) { provenance.push(`${file}: lane via its old name ${renamedFrom}`); continue; }
    // A registry input with a regen command is verified by the `regen` check (its outputs are compared fresh).
    const generator = ctx.registry.entries.find(e => e.command && matchesAny(e.inputs, file));
    if (generator) { provenance.push(`${file}: covered by regen ${generator.id} (registry input)`); continue; }
    // The pin files are validated by pregate itself (validateConfig / validateRegistry) on every run.
    if (file === PREGATE_CONFIG_PATH || file === GENERATED_PATH) { provenance.push(`${file}: pin file validated by pregate`); continue; }
    noLane.push(file);
  }
  const laneSets: Record<string, string[] | '?'> = {};
  const local = new Set<string>();
  const remote: RemoteObligation[] = [];
  const tiers = new Set<string>();
  const selected = [...tests].sort();
  let anyLocalAll = false;
  for (const lane of ctx.lanes.filter(l => l.runsTests && !l.manual)) {
    const set = laneFileSet(ctx, lane);
    if (set !== 'all') laneSets[lane.id] = set;
    const inLane = set === 'all' ? selected : set === '?' ? selected : selected.filter(t => set.includes(t));
    if (lane.tier === 'platform') {
      if (inLane.length) remote.push({ lane: lane.id, platform: lane.platform, workflow: lane.workflow, job: lane.job, tests: inLane, receipt: null });
      continue;
    }
    if (set === 'all') anyLocalAll = true;
    if (inLane.length) { tiers.add(lane.tier); for (const t of inLane) local.add(t); }
  }
  if (anyLocalAll || ctx.lanes.filter(l => l.runsTests && !l.manual && l.tier !== 'platform').length === 0) for (const t of selected) local.add(t);
  for (const t of selected) if (!local.has(t) && !remote.some(r => r.tests.includes(t))) local.add(t);
  if (local.size && tiers.size === 0) tiers.add('unit');
  return { noLane: noLane.sort(), tests: selected, localTests: [...local].sort(), remote, tiersRan: [...tiers].sort(), laneSets, provenance };
}

export function isTest(file: string): boolean { return isTestFile(file); }