import { createHash, randomUUID } from "node:crypto"; import { z } from "zod"; import { setTimeout as delay } from "node:timers/promises"; import type { StorageProvider } from "../storage/types.js"; const MAX_INDEX_LEVEL = 52; const MAX_OBJECT_BYTES = 4 * 1024 * 1024; const offset = z.number().int().nonnegative().max(Number.MAX_SAFE_INTEGER); const referenceSchema = z .object({ key: z.string(), start: offset, end: offset, sha256: z.string().regex(/^[a-f0-9]{64}$/), }) .strict(); type Reference = z.infer; const nodeSchema = z .object({ level: z.number().int().min(0).max(MAX_INDEX_LEVEL), children: z.array(referenceSchema).min(1).max(64), }) .strict(); type Node = z.infer; const rootSchema = referenceSchema.extend({ level: z.number().int().min(0).max(MAX_INDEX_LEVEL) }); type Root = z.infer; const headSchema = z .object({ v: z.literal(1), owner: z.string().uuid(), generation: offset, end: offset, sequence: offset.default(0), sourceCursor: offset.default(0), root: referenceSchema.nullable(), roots: z .array(rootSchema) .max(MAX_INDEX_LEVEL + 1) .optional(), closed: z.boolean(), deleted: z.boolean(), cleanupAfter: offset.default(0), }) .strict(); export type ObjectJournalHead = z.infer; export interface ObjectJournalWriter { head: ObjectJournalHead; etag: string; } export class ObjectJournalConflictError extends Error { readonly code = "object_journal_writer_conflict"; constructor() { super("The output journal is owned by another writer"); } } export function isObjectPreconditionFailure(error: unknown) { const e = error as { name?: string; $metadata?: { httpStatusCode?: number } }; return e?.name === "PreconditionFailed" || e?.$metadata?.httpStatusCode === 412; } function isRetryable(error: unknown) { const e = error as { name?: string; code?: string; $metadata?: { httpStatusCode?: number } }; const status = e?.$metadata?.httpStatusCode; return ( e?.name === "ConditionalRequestConflict" || status === 409 || status === 429 || (status !== undefined && status >= 500) || ["TimeoutError", "RequestTimeout", "NetworkingError"].includes(e?.name ?? "") || ["ECONNRESET", "ECONNREFUSED", "ETIMEDOUT", "EPIPE"].includes(e?.code ?? "") ); } async function retryObjectOperation(operation: () => Promise, signal?: AbortSignal) { for (let attempt = 0; ; attempt++) { signal?.throwIfAborted(); try { return await operation(); } catch (error) { if (attempt >= 2 || !isRetryable(error)) throw error; await delay(100 * 2 ** attempt, undefined, { signal }); } } } function isMissing(error: unknown) { const e = error as { name?: string; status?: number; $metadata?: { httpStatusCode?: number } }; return ( e?.name === "NoSuchKey" || e?.name === "NotFound" || e?.status === 404 || e?.$metadata?.httpStatusCode === 404 ); } const sha256 = (bytes: Buffer) => createHash("sha256").update(bytes).digest("hex"); interface ConditionalQualification { work: Promise; controller: AbortController; waiters: number; } const qualifiedProviders = new WeakSet(); const qualifications = new WeakMap(); async function qualifyConditionalWrites( provider: StorageProvider, prefix: string, signal?: AbortSignal, ) { signal?.throwIfAborted(); if (qualifiedProviders.has(provider)) return; let qualification = qualifications.get(provider); if (!qualification || qualification.controller.signal.aborted) { const controller = new AbortController(); const probeSignal = AbortSignal.any([controller.signal, AbortSignal.timeout(15_000)]); const current: ConditionalQualification = { controller, waiters: 0, work: Promise.resolve() }; qualification = current; current.work = (async () => { const objectKey = `${prefix}/conditional-probe-${randomUUID()}`; const body = Buffer.from("paperclip-conditional-probe-v1"); const put = provider.putObjectConditional!.bind(provider); try { await retryObjectOperation( () => put({ objectKey, body, contentLength: body.length, contentType: "text/plain", ifNoneMatch: "*", signal: probeSignal, }), probeSignal, ); for (const condition of [ { ifNoneMatch: "*" as const }, { ifMatch: '"paperclip-impossible-etag"' }, ]) { let rejected = false; try { await retryObjectOperation( () => put({ objectKey, body, contentLength: body.length, contentType: "text/plain", ...condition, signal: probeSignal, }), probeSignal, ); } catch (error) { if (!isObjectPreconditionFailure(error)) throw error; rejected = true; } if (!rejected) throw new Error("Object storage does not enforce conditional publication"); } } finally { await provider.deleteObject({ objectKey, signal: probeSignal }); } probeSignal.throwIfAborted(); qualifiedProviders.add(provider); })().finally(() => { if (qualifications.get(provider) === current) qualifications.delete(provider); }); qualifications.set(provider, current); void current.work.catch(() => undefined); } const pending = qualification; pending.waiters++; await new Promise((resolve, reject) => { let finished = false; const release = () => { if (finished) return false; finished = true; signal?.removeEventListener("abort", abort); pending.waiters--; return true; }; const abort = () => { if (!release()) return; if (!pending.waiters) { pending.controller.abort(signal!.reason); void pending.work.then( () => reject(signal!.reason), () => reject(signal!.reason), ); } else reject(signal!.reason); }; signal?.addEventListener("abort", abort, { once: true }); if (signal?.aborted) abort(); pending.work.then( () => { if (release()) resolve(); }, (error) => { if (release()) reject(error); }, ); }); } let activeIO = 0; const waitingIO: Array<() => void> = []; async function objectIO(operation: () => Promise): Promise { if (activeIO >= 8) { if (waitingIO.length >= 32) throw new Error("object_journal_io_capacity_exceeded"); await new Promise((resolve) => waitingIO.push(resolve)); } else activeIO++; try { return await operation(); } finally { const next = waitingIO.shift(); if (next) next(); else activeIO--; } } export interface ObjectByteJournalOptions { provider: StorageProvider; prefix: string; encode?: (bytes: Buffer) => Promise; decode?: (bytes: Buffer) => Promise; } export function createObjectByteJournal(options: ObjectByteJournalOptions) { const { provider } = options; const prefix = options.prefix.replace(/\/+$/, ""); if ( !prefix || prefix.length > 512 || prefix.startsWith("/") || prefix.split("/").some((p) => !/^[a-zA-Z0-9._-]+$/.test(p)) ) { throw new Error("invalid_object_journal_prefix"); } if (!provider.putObjectConditional || !provider.listObjects) throw new Error("Object storage requires conditional writes and scoped listing"); const headKey = `${prefix}/head.json`; const objectPrefix = `${prefix}/objects/`; const putConditional = ( input: Parameters>[0], ) => objectIO(() => provider.putObjectConditional!(input)); async function getBytes(key: string, limit: number, signal?: AbortSignal) { return objectIO(async () => { signal?.throwIfAborted(); signal = signal ? AbortSignal.any([signal, AbortSignal.timeout(15_000)]) : AbortSignal.timeout(15_000); const result = await retryObjectOperation( () => provider.getObject({ objectKey: key, signal }), signal, ); const chunks: Buffer[] = []; let size = 0; try { for await (const chunk of result.stream) { const bytes = Buffer.from(chunk); size += bytes.length; if (size > limit) throw new Error("object_journal_object_too_large"); chunks.push(bytes); } } finally { result.stream.destroy(); } signal?.throwIfAborted(); return { bytes: Buffer.concat(chunks), etag: result.etag }; }); } async function head(signal?: AbortSignal): Promise { let result; try { result = await getBytes(headKey, 64 * 1024, signal); } catch (error) { if (isMissing(error)) return null; throw error; } if (!result.etag) throw new Error("object_journal_missing_etag"); const value = headSchema.parse(JSON.parse(result.bytes.toString("utf8"))); if (value.roots) { let end = 0, level = MAX_INDEX_LEVEL + 1; if (value.root) throw new Error("object_journal_invalid_head"); for (const root of value.roots) { validateReference(root); if (root.start !== end || root.level >= level) throw new Error("object_journal_invalid_head"); end = root.end; level = root.level; } if (end !== value.end) throw new Error("object_journal_invalid_head"); } else if ((value.root?.end ?? 0) !== value.end || (value.root && value.root.start !== 0)) { throw new Error("object_journal_invalid_head"); } return { head: value, etag: result.etag }; } async function publish(value: ObjectJournalHead, etag: string | null, signal?: AbortSignal) { value = headSchema.parse(value); signal = signal ? AbortSignal.any([signal, AbortSignal.timeout(15_000)]) : AbortSignal.timeout(15_000); const bytes = Buffer.from(JSON.stringify(value)); return retryObjectOperation(async () => { try { const result = await putConditional({ objectKey: headKey, body: bytes, contentLength: bytes.length, contentType: "application/json", signal, ...(etag ? { ifMatch: etag } : { ifNoneMatch: "*" as const }), }); return { head: value, etag: result.etag }; } catch (error) { const observed = await head(signal); if (observed && JSON.stringify(observed.head) === JSON.stringify(value)) return observed; if (isObjectPreconditionFailure(error) || (observed?.etag ?? null) !== etag) throw new ObjectJournalConflictError(); throw error; } }, signal); } async function claim(input: { expectedOwner: string | null; assertAuthority: () => Promise; signal?: AbortSignal; }) { const current = await head(input.signal); if (current?.head.deleted || (current?.head.owner ?? null) !== input.expectedOwner) throw new ObjectJournalConflictError(); await input.assertAuthority(); await qualifyConditionalWrites(provider, prefix, input.signal); await input.assertAuthority(); const value: ObjectJournalHead = { v: 1, owner: randomUUID(), generation: (current?.head.generation ?? 0) + 1, end: current?.head.end ?? 0, sequence: current?.head.sequence ?? 0, sourceCursor: current?.head.sourceCursor ?? 0, root: current?.head.root ?? null, ...(current?.head.roots ? { roots: current.head.roots } : {}), closed: false, deleted: false, cleanupAfter: 0, }; return publish(value, current?.etag ?? null, input.signal); } function validateReference(ref: Reference) { if ( !ref.key.startsWith(objectPrefix) || ref.key !== `${objectPrefix}${ref.sha256}` || ref.end <= ref.start ) throw new Error("object_journal_invalid_reference"); } async function load(ref: Reference, signal?: AbortSignal) { validateReference(ref); const stored = await getBytes(ref.key, MAX_OBJECT_BYTES * 2, signal); const bytes = options.decode ? await options.decode(stored.bytes) : stored.bytes; if (bytes.length > MAX_OBJECT_BYTES || sha256(bytes) !== ref.sha256) throw new Error("object_journal_integrity_error"); return bytes; } async function save( bytes: Buffer, start: number, end: number, signal?: AbortSignal, ): Promise { if (bytes.length > MAX_OBJECT_BYTES) throw new Error("object_journal_segment_too_large"); signal = signal ? AbortSignal.any([signal, AbortSignal.timeout(15_000)]) : AbortSignal.timeout(15_000); const digest = sha256(bytes), key = `${objectPrefix}${digest}`; const body = options.encode ? await options.encode(bytes) : bytes; try { await retryObjectOperation( () => putConditional({ objectKey: key, body, contentLength: body.length, contentType: "application/octet-stream", ifNoneMatch: "*", signal, }), signal, ); } catch (error) { const ref = { key, sha256: digest, start, end }; try { await load(ref, signal); } catch { throw error; } } return { key, start, end, sha256: digest }; } async function loadNode(ref: Reference, signal?: AbortSignal): Promise { const node = nodeSchema.parse(JSON.parse((await load(ref, signal)).toString("utf8"))); let next = ref.start; for (const child of node.children) { validateReference(child); if (child.start !== next) throw new Error("object_journal_noncontiguous_index"); next = child.end; } if (next !== ref.end) throw new Error("object_journal_invalid_index_range"); return node; } const saveNode = (node: Node, signal?: AbortSignal) => save( Buffer.from(JSON.stringify(node)), node.children[0]!.start, node.children.at(-1)!.end, signal, ); async function readRange( snapshot: ObjectJournalHead, start: number, limit: number, signal?: AbortSignal, ): Promise { if (snapshot.deleted) throw new Error("object_journal_deleted"); if ( !Number.isSafeInteger(start) || start < 0 || !Number.isSafeInteger(limit) || limit < 0 || limit > MAX_OBJECT_BYTES ) throw new Error("invalid_object_journal_range"); if ((!snapshot.root && !snapshot.roots?.length) || limit === 0 || start >= snapshot.end) return Buffer.alloc(0); const end = Math.min(snapshot.end, start + limit), chunks: Buffer[] = []; async function readPayload(ref: Reference) { const bytes = await load(ref, signal); if (bytes.length !== ref.end - ref.start) throw new Error("object_journal_invalid_segment_length"); chunks.push( bytes.subarray(Math.max(0, start - ref.start), Math.min(bytes.length, end - ref.start)), ); } async function visit(ref: Reference, expectedLevel?: number) { const node = await loadNode(ref, signal); if (expectedLevel !== undefined && node.level !== expectedLevel) throw new Error("object_journal_invalid_index_level"); for (const child of node.children) { if (child.end <= start || child.start >= end) continue; if (node.level > 0) await visit(child, node.level - 1); else await readPayload(child); } } if (snapshot.roots) { for (const root of snapshot.roots) { if (root.end <= start || root.start >= end) continue; if (root.level === 0) await readPayload(root); else await visit(root, root.level - 1); } } else if (snapshot.root) await visit(snapshot.root); const bytes = Buffer.concat(chunks); if (bytes.length !== end - start) throw new Error("object_journal_missing_range"); return bytes; } async function append( writer: ObjectJournalWriter, bytes: Buffer, signal?: AbortSignal, sequence = writer.head.sequence, sourceCursor = writer.head.sourceCursor, ) { signal = signal ? AbortSignal.any([signal, AbortSignal.timeout(15_000)]) : AbortSignal.timeout(15_000); if (writer.head.closed || writer.head.deleted) throw new ObjectJournalConflictError(); if (bytes.length === 0) return writer; if ( bytes.length > 8 * 1024 * 1024 || !Number.isSafeInteger(writer.head.end + bytes.length) || !Number.isSafeInteger(sequence) || sequence < writer.head.sequence || !Number.isSafeInteger(sourceCursor) || sourceCursor < writer.head.sourceCursor ) throw new Error("object_journal_invalid_batch"); const roots: Root[] = writer.head.roots ? [...writer.head.roots] : writer.head.root ? [{ ...writer.head.root, level: (await loadNode(writer.head.root, signal)).level + 1 }] : []; let end = writer.head.end; for (let start = 0; start < bytes.length; start += 1024 * 1024) { const part = bytes.subarray(start, start + 1024 * 1024); let root: Root = { ...(await save(part, end, end + part.length, signal)), level: 0 }; end = root.end; while (roots.at(-1)?.level === root.level) { const left = roots.pop()!; const { level: leftLevel, ...leftRef } = left; const { level, ...rightRef } = root; if (level >= MAX_INDEX_LEVEL || leftLevel !== level) throw new Error("object_journal_index_capacity_exceeded"); root = { ...(await saveNode({ level, children: [leftRef, rightRef] }, signal)), level: level + 1, }; } roots.push(root); } return publish( { ...writer.head, end, root: null, roots, sequence, sourceCursor }, writer.etag, signal, ); } async function close(writer: ObjectJournalWriter, signal?: AbortSignal) { return publish({ ...writer.head, closed: true }, writer.etag, signal); } async function remove(signal?: AbortSignal) { let tombstone: ObjectJournalWriter | undefined; for (let attempt = 0; attempt < 8; attempt++) { const current = await head(signal); if (current?.head.deleted) { tombstone = current; break; } const value: ObjectJournalHead = current ? { ...current.head, deleted: true, closed: true, cleanupAfter: current.head.closed ? 0 : Date.now() + 30_000, } : { v: 1, sourceCursor: 0, owner: randomUUID(), generation: 0, end: 0, sequence: 0, root: null, deleted: true, closed: true, cleanupAfter: 0, }; try { tombstone = await publish(value, current?.etag ?? null, signal); break; } catch (error) { if (!(error instanceof ObjectJournalConflictError)) throw error; } } if (!tombstone) throw new ObjectJournalConflictError(); if (tombstone.head.cleanupAfter > Date.now()) throw new Error("object_journal_cleanup_pending"); let continuationToken: string | undefined; do { const deadline = () => signal ? AbortSignal.any([signal, AbortSignal.timeout(15_000)]) : AbortSignal.timeout(15_000); const page = await objectIO(() => provider.listObjects!({ prefix: objectPrefix, continuationToken, signal: deadline() }), ); for (const key of page.keys) { if (!key.startsWith(objectPrefix)) throw new Error("object_journal_invalid_listing"); await objectIO(() => provider.deleteObject({ objectKey: key, signal: deadline() })); } continuationToken = page.continuationToken; } while (continuationToken); } return { head, claim, append, close, readRange, remove }; } export type ObjectByteJournal = ReturnType;