ThothII/backend/scripts/p1-render-snapshot.mjs

#!/usr/bin/env node
import { spawnSync } from "node:child_process";
import { createHash } from "node:crypto";
import { constants, lstatSync, realpathSync } from "node:fs";
import { lstat, mkdir, open, readFile, realpath } from "node:fs/promises";
import { basename, dirname, isAbsolute, join, relative, resolve, sep } from "node:path";
import { fileURLToPath } from "node:url";

// This acceptance-only adapter deliberately imports the built production runner.
import { ThtRunner } from "../dist/tht/tht-runner.js";

const modulePath = fileURLToPath(import.meta.url);
const defaultRepositoryRoot = realpathSync(resolve(dirname(modulePath), "../.."));
const HEX40 = /^[0-9a-f]{40}$/;
const HEX64 = /^[0-9a-f]{64}$/;

function fixedRoot(repositoryRoot) { return join(realpathSync(repositoryRoot), ".artifacts", "manual-acceptance", "p1"); }
function below(parent, child) { const rel = relative(parent, child); return rel !== "" && !rel.startsWith(`..${sep}`) && rel !== ".." && !isAbsolute(rel); }
function assertNoSymlinks(root, path, allowMissingLeaf = false) {
  const rel = relative(root, path);
  if (rel.startsWith("..") || isAbsolute(rel)) throw new Error("path is outside owned root");
  let cursor = root;
  for (const [index, part] of rel.split(sep).filter(Boolean).entries()) {
    cursor = join(cursor, part);
    try { if (lstatSync(cursor).isSymbolicLink()) throw new Error("owned path contains a symlink"); }
    catch (error) {
      if (allowMissingLeaf && error.code === "ENOENT" && index === rel.split(sep).filter(Boolean).length - 1) return;
      throw error;
    }
  }
}
async function ownership(repositoryRoot, ownershipPath) {
  const root = fixedRoot(repositoryRoot);
  const expected = join(root, "ownership.json");
  if (resolve(ownershipPath) !== expected) throw new Error("ownership path is not owned");
  const rootEntry = await lstat(root); const ownershipEntry = await lstat(expected);
  if (!rootEntry.isDirectory() || rootEntry.isSymbolicLink() || !ownershipEntry.isFile() || ownershipEntry.isSymbolicLink()) throw new Error("ownership is unsafe");
  if (await realpath(root) !== root) throw new Error("ownership root is not canonical");
  let value; try { value = JSON.parse(await readFile(expected, "utf8")); } catch { throw new Error("ownership is malformed"); }
  if (value?.schemaVersion !== 1 || value.kind !== "p1-manual-acceptance" || !HEX64.test(value.nonce ?? "")
      || value.repositoryRoot !== realpathSync(repositoryRoot) || value.root !== root || value.status !== "PENDING"
      || value.listener?.host !== "127.0.0.1" || value.listener?.port !== 8791) throw new Error("ownership identity mismatch");
  return { root, value };
}
const ANCHORED_PUBLISH_SOURCE=String.raw`import os,secrets,stat,sys
parent,name,expected_dev,expected_ino=sys.argv[1:]
pfd=fd=None;stage=".render-stage-"+secrets.token_hex(16);published=False
def fail(): raise RuntimeError("anchored publication refused")
try:
    pfd=os.open(parent,os.O_RDONLY|os.O_DIRECTORY|os.O_NOFOLLOW)
    identity=os.fstat(pfd)
    if (identity.st_dev,identity.st_ino)!=(int(expected_dev),int(expected_ino)): fail()
    try: os.stat(name,dir_fd=pfd,follow_symlinks=False); fail()
    except FileNotFoundError: pass
    fd=os.open(stage,os.O_WRONLY|os.O_CREAT|os.O_EXCL|os.O_NOFOLLOW,0o600,dir_fd=pfd)
    data=sys.stdin.buffer.read(33554433)
    if len(data)>33554432: fail()
    view=memoryview(data)
    while view:
        written=os.write(fd,view)
        if written<=0: fail()
        view=view[written:]
    os.fsync(fd);os.close(fd);fd=None;os.rename(stage,name,src_dir_fd=pfd,dst_dir_fd=pfd);published=True;os.fsync(pfd)
    current=os.stat(parent,follow_symlinks=False)
    if not stat.S_ISDIR(current.st_mode) or (current.st_dev,current.st_ino)!=(identity.st_dev,identity.st_ino): fail()
except Exception:
    if published:
        try: os.unlink(name,dir_fd=pfd);os.fsync(pfd)
        except Exception: pass
    print("anchored output publication refused (details redacted)",file=sys.stderr);raise SystemExit(1)
finally:
    if fd is not None: os.close(fd)
    if pfd is not None:
        try: os.unlink(stage,dir_fd=pfd)
        except FileNotFoundError: pass
        os.close(pfd)
`;
async function atomicCopy(source,output) {
  const parent=dirname(output),entry=await lstat(parent);if(!entry.isDirectory()||entry.isSymbolicLink())throw new Error("rendered parent identity is unsafe");const bytes=await readFile(source);
  const result=spawnSync("python3",["-c",ANCHORED_PUBLISH_SOURCE,parent,basename(output),String(entry.dev),String(entry.ino)],{input:bytes,encoding:"utf8",maxBuffer:1024*1024});
  if(result.error||result.status!==0)throw new Error("anchored output publication refused; rendered parent identity changed or output is unsafe");
}

function sameEntry(actual, expected) { return actual.dev === expected.dev && actual.ino === expected.ino; }
async function readBounded(path, max, label) {
  let handle;
  try {
    handle = await open(path, constants.O_RDONLY | constants.O_NOFOLLOW);
    const before = await handle.stat(), pathEntry = await lstat(path);
    if (!before.isFile() || pathEntry.isSymbolicLink() || !pathEntry.isFile() || !sameEntry(before, pathEntry)) throw new Error(`${label} is unsafe`);
    if (before.size < 1 || before.size > max) throw new Error(`${label} is unbounded`);
    const bytes = Buffer.alloc(before.size); let offset = 0;
    while (offset < bytes.length) {
      const { bytesRead } = await handle.read(bytes, offset, bytes.length - offset, offset);
      if (bytesRead < 1) throw new Error(`${label} changed while reading`);
      offset += bytesRead;
    }
    const after = await handle.stat();
    if (!sameEntry(before, after) || after.size !== before.size) throw new Error(`${label} changed while reading`);
    return bytes;
  } finally {
    if (handle) await handle.close().catch(() => {});
  }
}
async function readSnapshotManifest(root, manifestPath, commit, yamlName, expectedDigest) {
  let manifestEntry;
  try { assertNoSymlinks(root, manifestPath); manifestEntry = await lstat(manifestPath); }
  catch (error) { if (error?.code === "ENOENT") throw new Error("snapshot manifest is missing or unbounded"); throw error; }
  if (!manifestEntry.isFile() || manifestEntry.isSymbolicLink() || await realpath(manifestPath) !== manifestPath) throw new Error("snapshot manifest is unsafe");
  const bytes = await readBounded(manifestPath, 1048576, "snapshot manifest");
  let manifest; try { manifest = JSON.parse(bytes.toString("utf8")); } catch { throw new Error("snapshot manifest is malformed"); }
  const files = manifest?.files;
  if (manifest?.head !== commit || !files || typeof files !== "object" || Array.isArray(files)) throw new Error("snapshot manifest identity is unsafe");
  if (!HEX64.test(files[yamlName] ?? "") || files[yamlName] !== expectedDigest) throw new Error("snapshot manifest digest is unsafe");
  return manifest;
}

export async function renderOwnedSnapshot({ repositoryRoot = defaultRepositoryRoot, ownershipPath, snapshotPath, outputPath, snapshotSha256, env = process.env, beforePublish }) {
  const repo = realpathSync(repositoryRoot); const { root } = await ownership(repo, resolve(repo, ownershipPath));
  const snapshot = resolve(repo, snapshotPath); const output = resolve(repo, outputPath);
  const snapshotsRoot = join(root, "installation", "registry", "snapshots");
  const renderedRoot = join(root, "rendered");
  if (!isAbsolute(snapshotPath) || !below(snapshotsRoot, snapshot)) throw new Error("snapshot is not an owned absolute path");
  const match = /^([0-9a-f]{40})\/([a-z][a-z0-9-]{2,62})\.yaml$/.exec(relative(snapshotsRoot, snapshot).split(sep).join("/"));
  if (!match || !HEX40.test(match[1])) throw new Error("snapshot is not commit addressed");
  if (!HEX64.test(snapshotSha256 ?? "")) throw new Error("snapshot digest identity is unsafe");
  assertNoSymlinks(root, snapshot); const snapshotEntry = await lstat(snapshot);
  if (!snapshotEntry.isFile() || snapshotEntry.isSymbolicLink() || await realpath(snapshot) !== snapshot) throw new Error("snapshot is unsafe");
  const yamlName = `${match[2]}.yaml`;
  const manifestPath = join(snapshotsRoot, match[1], "snapshot.json");
  await readSnapshotManifest(root, manifestPath, match[1], yamlName, snapshotSha256);
  const snapshotBytes = await readBounded(snapshot, 1048576, "snapshot");
  if (createHash("sha256").update(snapshotBytes).digest("hex") !== snapshotSha256) throw new Error("snapshot bytes changed");
  if (!below(renderedRoot, output) || dirname(output) !== renderedRoot || !output.endsWith(".yaml")) throw new Error("output is not an owned rendered path");
  assertNoSymlinks(root, dirname(output));
  try { if ((await lstat(output)).isSymbolicLink()) throw new Error("output is unsafe"); } catch (error) { if (error.code !== "ENOENT") throw error; }
  await mkdir(join(snapshotsRoot, "runtime"), { recursive: true, mode: 0o700 });
  const prior = {};
  for (const [key, value] of Object.entries(env)) { prior[key] = process.env[key]; if (value === undefined) delete process.env[key]; else process.env[key] = value; }
  const runner = new ThtRunner({
    thtBin: join(repo, "harness", ".venv", "bin", "tht"), harnessDir: join(repo, "harness"),
    configPath: join(root, "installation", "base.yaml"), dataRoot: join(root, "installation", "data"),
    runtimeSnapshotRoot: join(snapshotsRoot, "runtime"), secretRoots: [join(root, "fixture-secrets")],
    semanticRuntime: { internalQdrantUrl: "http://qdrant:6333", internalEmbeddingUrl: "http://embedding:11434", internalEmbeddingModel: "qwen3-embedding:0.6b", internalEmbeddingDimensions: 1024 },
  });
  let lease;
  try {
    lease = runner.acquireWorkspaceRuntime(snapshot);
    const verifySnapshot = async () => {
      const current = await readBounded(snapshot, 1048576, "snapshot");
      if (createHash("sha256").update(current).digest("hex") !== snapshotSha256) throw new Error("snapshot content changed during rendering");
    };
    await verifySnapshot();
    if(beforePublish)await beforePublish({output,renderedRoot});
    await verifySnapshot();
    await atomicCopy(lease.path, output);
  }
  finally {
    if (lease) lease.release();
    for (const key of Object.keys(env)) { if (prior[key] === undefined) delete process.env[key]; else process.env[key] = prior[key]; }
  }
  return output;
}
function parseArgs(argv) {
  if (argv.length !== 8) throw new Error("usage: p1-render-snapshot.mjs --ownership PATH --snapshot ABSOLUTE_PATH --output PATH --snapshot-sha256 HEX");
  const result = {}; for (let i=0;i<argv.length;i+=2) { if (!["--ownership","--snapshot","--output","--snapshot-sha256"].includes(argv[i]) || result[argv[i]]) throw new Error("invalid arguments"); result[argv[i]]=argv[i+1]; }
  if (!result["--ownership"] || !result["--snapshot"] || !result["--output"] || !result["--snapshot-sha256"]) throw new Error("missing arguments"); return result;
}
if (process.argv[1] && realpathSync(process.argv[1]) === modulePath) {
  try { const args=parseArgs(process.argv.slice(2)); await renderOwnedSnapshot({ ownershipPath:args["--ownership"], snapshotPath:args["--snapshot"], outputPath:args["--output"], snapshotSha256:args["--snapshot-sha256"] }); console.log(`rendered ${resolve(args["--output"])}`); }
  catch(error) { console.error(`p1 render refused: ${error.message}`); process.exitCode=1; }
}