mesh-catalog/modules/lab/tools/runs.ts

// A lab run: fresh checkouts of the named branches, side by side, then the lab's suite on the named
// beds (novox/hq ADR 0172).
//
// **A run is a detached script with its own process group**, so it outlives the tool call that started
// it and `stop` ends everything it started. It writes what it is doing to a status file beside its log,
// and that file is the whole of what the tools read back: a runtime that restarts mid-run still answers
// for it, and says it was lost rather than pretending it is still going.

import { spawn } from "node:child_process";
import { existsSync, mkdirSync, readFileSync, readdirSync, rmSync, writeFileSync } from "node:fs";
import { join } from "node:path";

/**
 * The repositories a lab run checks out, side by side, as the lab expects its siblings. mesh-tools-go is
 * one since genesis builds the Go toolchain at its base step, from the repository beside mesh-tools
 * (novox/hq issue 616): a bed that raises genesis serves it from its forge.
 */
export const REPOSITORIES = ["mesh-lab", "mesh-controller", "mesh-host", "mesh-catalog", "mesh-tools", "mesh-tools-go", "mesh-sdk"];

/** The checkouts whose JavaScript dependencies a run installs: the lab, the SDK and the base. */
export const NPM_REPOSITORIES = ["mesh-sdk", "mesh-tools", "mesh-lab"];

/**
 * Where a checkout's JavaScript dependencies are installed (novox/hq issue 624): its root when the root
 * holds a lock file, otherwise each directory one level down that holds one. `npm ci` installs only from a
 * lock file, and a repository that moved its package into a directory of its own (mesh-tools' node-tools)
 * has none at its root; the run asked for one there and failed before it built anything. A package.json
 * with no lock file beside it cannot be installed reproducibly, and is named rather than installed.
 */
export function installPlan(root: string): { install: string[]; unlocked: string[] } {
  const has = (dir: string, file: string) => existsSync(join(dir, file));
  if (has(root, "package-lock.json")) return { install: [root], unlocked: [] };
  const install: string[] = [];
  const unlocked: string[] = has(root, "package.json") ? [root] : [];
  for (const entry of readdirSync(root, { withFileTypes: true })) {
    if (!entry.isDirectory() || entry.name.startsWith(".") || entry.name === "node_modules") continue;
    const dir = join(root, entry.name);
    if (has(dir, "package-lock.json")) install.push(dir);
    else if (has(dir, "package.json")) unlocked.push(dir);
  }
  return { install: install.sort(), unlocked: unlocked.sort() };
}

/**
 * installStep is the shell a run installs one checkout with: the same rule as installPlan, so what
 * lab_check says a run would install is what it installs. Building runs where the package says how.
 */
export function installStep(root: string, build: boolean): string {
  const q = shellQuote(root);
  const install = `(cd "$d" && npm ci --no-audit --no-fund --loglevel=error${build ? " && npm run build --if-present" : ""})`;
  return `if [ -f ${q}/package-lock.json ]; then d=${q}; ${install}; else
  [ ! -f ${q}/package.json ] || { echo "${root}: a package.json and no package-lock.json, so npm ci cannot install it (novox/hq issue 624)" >&2; exit 1; }
  found=0
  for d in ${q}/*/; do
    d="\${d%/}"; [ "$(basename "$d")" = node_modules ] && continue
    if [ -f "$d/package-lock.json" ]; then found=1; ${install}
    elif [ -f "$d/package.json" ]; then echo "$d: a package.json and no package-lock.json, so npm ci cannot install it (novox/hq issue 624)" >&2; exit 1; fi
  done
  [ "$found" = 1 ] || { echo "${root}: no package-lock.json at its root or one directory down, so nothing of it can be installed (novox/hq issue 624)" >&2; exit 1; }
fi`;
}

/**
 * The forge credential a run's clones may present, as a git credential-store line —
 * scheme://user:password@host[:port] — for the forge's own origin, or undefined when the lab holds none.
 *
 * **The mesh's credential for the forge, the way the build agent holds it** (novox/hq issue 624): the lab
 * requires the package registry, the forge's provisioner binds it an account (`as`) and seals that
 * account's password, and the forge that answers npm is the forge that hosts the repositories. Private
 * repositories (mesh-tools-go) are cloned with it; public ones clone as before. Written to a file git reads
 * through its credential store, never into a URL, an argument, the run's script or its log, and offered
 * only to the forge's own scheme, host and port.
 */
export function forgeCredential(forge: string, bindingFile: string, secretFile: string): string | undefined {
  if (!forge || !bindingFile || !secretFile) return undefined;
  let as = "";
  let secret = "";
  try {
    as = String((JSON.parse(readFileSync(bindingFile, "utf8")) as { as?: string }).as ?? "");
    secret = readFileSync(secretFile, "utf8").trim();
  } catch {
    return undefined;
  }
  if (!as || !secret) return undefined;
  let origin: URL;
  try {
    origin = new URL(forge);
  } catch {
    return undefined;
  }
  const line = new URL(`${origin.protocol}//${origin.host}`);
  line.username = as;
  line.password = secret;
  return line.toString().replace(/\/$/, "");
}

/** Where a run keeps its forge credential: beside its directory, never in it, and removed when it ends. */
export function credentialPath(work: string, id: string): string {
  return join(work, `.${id}.git-credentials`);
}

/** writeCredential puts a credential-store line where git reads it, readable by this account alone. */
export function writeCredential(path: string, line: string | undefined): string | undefined {
  if (!line) return undefined;
  writeFileSync(path, `${line}\n`, { mode: 0o600 });
  return path;
}

/**
 * credentialGuard is the shell that removes the credential however the script ends — its end, an error,
 * or a stop's SIGTERM to the run's process group, which kills the wrapper before its own cleanup runs
 * (review 196 on mesh-catalog #272). The script also removes it as soon as its clones are done.
 */
export function credentialGuard(path: string | undefined): string {
  if (!path) return "";
  const rm = `rm -f ${shellQuote(path)}`;
  return `trap ${shellQuote(rm)} EXIT
trap ${shellQuote(`${rm}; exit 143`)} TERM
trap ${shellQuote(`${rm}; exit 130`)} INT
trap ${shellQuote(`${rm}; exit 129`)} HUP`;
}

/**
 * cleanCredentials removes every run's credential file left in the work directory but the one named — what
 * a crash or a reboot left behind, which no trap could remove. Answers what it removed.
 */
export function cleanCredentials(work: string, keep?: string): string[] {
  if (!existsSync(work)) return [];
  const removed: string[] = [];
  for (const name of readdirSync(work)) {
    if (!/^\.run-.*\.git-credentials$/.test(name)) continue;
    const path = join(work, name);
    if (path === keep) continue;
    rmSync(path, { force: true });
    removed.push(path);
  }
  return removed;
}

/** The arguments that have git offer the credential in that file, and only that one. */
export function credentialArgs(path: string | undefined): string {
  if (!path) return "";
  return `-c credential.helper= -c ${shellQuote(`credential.helper=store --file=${path}`)} `;
}

export interface RunStatus {
  id: string;
  state: "checking-out" | "building" | "running" | "passed" | "failed" | "stopped" | "lost";
  started: string;
  ended?: string;
  tests: string[];
  refs: Record<string, string>;
  commits?: Record<string, string>;
  exit?: number;
  pid?: number;
}

export function runDir(work: string, id: string): string {
  return join(work, id);
}

function statusPath(work: string, id: string): string {
  return join(runDir(work, id), "status.json");
}

export function readStatus(work: string, id: string): RunStatus | undefined {
  try {
    const s = JSON.parse(readFileSync(statusPath(work, id), "utf8")) as RunStatus;
    // A run whose process is gone while its status still says it is going was lost — the runtime or
    // the machine restarted under it. Said, rather than left reading as running for ever.
    if (!["passed", "failed", "stopped", "lost"].includes(s.state) && s.pid && !alive(s.pid)) {
      s.state = "lost";
    }
    return s;
  } catch {
    return undefined;
  }
}

function alive(pid: number): boolean {
  try {
    process.kill(pid, 0);
    return true;
  } catch {
    return false;
  }
}

export function listRuns(work: string): RunStatus[] {
  if (!existsSync(work)) return [];
  return readdirSync(work)
    .filter((d) => d.startsWith("run-"))
    .map((id) => readStatus(work, id))
    .filter((s): s is RunStatus => !!s)
    .sort((a, b) => b.started.localeCompare(a.started));
}

/** The run still going, if any: one at a time, because two would contend for the same machine. */
export function running(work: string): RunStatus | undefined {
  return listRuns(work).find((s) => !["passed", "failed", "stopped", "lost"].includes(s.state));
}

const shellQuote = (s: string) => `'${s.replace(/'/g, `'\\''`)}'`;

/**
 * The script one run executes. Every step writes its state first, so a run that dies says where.
 *
 * The environment is the one the lab's README describes for a run against sibling checkouts, pointed
 * at this run's own tree, so what is built and claimed is exactly what was checked out.
 */
export function script(work: string, id: string, forge: string, tests: string[], refs: Record<string, string>,
  credential?: string): string {
  const dir = runDir(work, id);
  const setState = (state: string) =>
    `node -e ${shellQuote(
      `const f=${JSON.stringify(join(dir, "status.json"))};const s=JSON.parse(require("fs").readFileSync(f,"utf8"));s.state=${JSON.stringify(state)};require("fs").writeFileSync(f,JSON.stringify(s,null,2))`,
    )}`;
  const clones = REPOSITORIES.map((repo) => {
    const ref = refs[repo] ?? "main";
    return [
      `git ${credentialArgs(credential)}clone --quiet --depth 50 --branch ${shellQuote(ref)} ${shellQuote(`${forge}/novox/${repo}.git`)} ${shellQuote(join(dir, repo))}`,
      `echo "${repo} $(git -C ${shellQuote(join(dir, repo))} rev-parse HEAD)" >> ${shellQuote(join(dir, "commits.txt"))}`,
    ].join("\n");
  }).join("\n");
  const bin = join(dir, "bin");
  return `set -euo pipefail
# A repository the forge will not show fails its clone at once, rather than waiting on a prompt.
export GIT_TERMINAL_PROMPT=0
${credentialGuard(credential)}
cd ${shellQuote(dir)}
${setState("checking-out")}
${clones}
${credential ? `# The forge credential is for the clones, and nothing after them runs with it on disk.\nrm -f ${shellQuote(credential)}` : ""}
node -e ${shellQuote(
    `const fs=require("fs");const f=${JSON.stringify(join(dir, "status.json"))};const s=JSON.parse(fs.readFileSync(f,"utf8"));s.commits=Object.fromEntries(fs.readFileSync(${JSON.stringify(join(dir, "commits.txt"))},"utf8").trim().split("\\n").map(l=>l.split(" ")));fs.writeFileSync(f,JSON.stringify(s,null,2))`,
  )}
${setState("building")}
# The @novox scope resolves from the mesh's own package registry on the forge, as the builder
# resolves it; nothing else is asked of it.
printf '%s\n' ${shellQuote(`@novox:registry=${forge}/api/packages/novox/npm/`)} > ${shellQuote(join(dir, ".npmrc"))}
export NPM_CONFIG_USERCONFIG=${shellQuote(join(dir, ".npmrc"))}
${NPM_REPOSITORIES.map((repo) => installStep(join(dir, repo), repo !== "mesh-lab")).join("\n")}
mkdir -p ${shellQuote(bin)}
for p in postgres-provisioner objectstore-provisioner route-proxy; do
  (cd ${shellQuote(dir)}/mesh-controller && CGO_ENABLED=0 go build -o ${shellQuote(bin)}/$p ./examples/$p)
done
export MESH_LAB_HOST_BINARY=${shellQuote(join(dir, "mesh-host", "mesh-host"))}
export MESH_LAB_BUNDLE=${shellQuote(join(dir, "mesh-host", "examples", "foundation-first-node.lock"))}
export MESH_LAB_MODULES=${shellQuote(join(dir, "mesh-controller", "examples", "modules"))}
export MESH_LAB_BUILDER=${shellQuote(join(dir, "mesh-controller", "build", "mesh-builder"))}
export MESH_LAB_BOOTSTRAP_BINARY=${shellQuote(join(dir, "mesh-host", "mesh-bootstrap"))}
export MESH_LAB_CATALOG=${shellQuote(join(dir, "mesh-catalog", "modules"))}
# Where a bed that serves repositories from its own forge finds them: this run's checkouts, side by side.
export MESH_LAB_REPOS=${shellQuote(dir)}
export MESH_LAB_PROVISIONER=${shellQuote(join(bin, "postgres-provisioner"))}
export MESH_LAB_OBJECTSTORE_PROVISIONER=${shellQuote(join(bin, "objectstore-provisioner"))}
export MESH_LAB_ROUTE_PROXY=${shellQuote(join(bin, "route-proxy"))}
${setState("running")}
cd ${shellQuote(join(dir, "mesh-lab"))}
node --experimental-strip-types src/cli.ts suite ${tests.map(shellQuote).join(" ")}
`;
}

/** start begins a run and returns at once with its status. */
export function start(work: string, forge: string, tests: string[], refs: Record<string, string>,
  credential?: string): RunStatus {
  const id = `run-${new Date().toISOString().replace(/[:.]/g, "-")}`;
  const dir = runDir(work, id);
  mkdirSync(dir, { recursive: true });
  const status: RunStatus = { id, state: "checking-out", started: new Date().toISOString(), tests, refs };
  writeFileSync(statusPath(work, id), JSON.stringify(status, null, 2));
  // What a crashed or rebooted run left behind goes before this run writes its own.
  cleanCredentials(work);
  const credentials = writeCredential(credentialPath(work, id), credential);
  writeFileSync(join(dir, "run.sh"), script(work, id, forge, tests, refs, credentials), { mode: 0o700 });

  // The wrapper records how the run ended, then removes the checkouts and keeps the log and status: a
  // run's tree is its own, and the next run starts from fresh ones (novox/hq ADR 0172).
  const wrapper = `bash ${shellQuote(join(dir, "run.sh"))} > ${shellQuote(join(dir, "run.log"))} 2>&1; code=$?
node -e ${shellQuote(
    `const f=${JSON.stringify(statusPath(work, id))};const s=JSON.parse(require("fs").readFileSync(f,"utf8"));if(s.state!=="stopped"){s.state=process.argv[1]==="0"?"passed":"failed"};s.exit=Number(process.argv[1]);s.ended=new Date().toISOString();require("fs").writeFileSync(f,JSON.stringify(s,null,2))`,
  )} "$code"
rm -f ${shellQuote(credentialPath(work, id))}
cd ${shellQuote(dir)} && rm -rf ${REPOSITORIES.map(shellQuote).join(" ")} bin`;
  const child = spawn("bash", ["-c", wrapper], { detached: true, stdio: "ignore" });
  child.unref();
  status.pid = child.pid;
  writeFileSync(statusPath(work, id), JSON.stringify(status, null, 2));
  return status;
}

/** stop ends a run and everything it started, by its process group. */
export function stop(work: string, id: string): RunStatus | undefined {
  const s = readStatus(work, id);
  if (!s || !s.pid) return s;
  if (["passed", "failed", "stopped", "lost"].includes(s.state)) return s;
  s.state = "stopped";
  writeFileSync(statusPath(work, id), JSON.stringify(s, null, 2));
  try {
    process.kill(-s.pid, "SIGTERM");
  } catch {
    // Already gone between the read and the kill.
  }
  return s;
}

/** tail is the last lines of a run's log. */
export function tail(work: string, id: string, lines: number): string {
  try {
    const all = readFileSync(join(runDir(work, id), "run.log"), "utf8").split("\n");
    return all.slice(-Math.max(1, lines)).join("\n");
  } catch {
    return "";
  }
}