mirror of
https://github.com/morluto/rea.git
synced 2026-11-12 09:52:27 +00:00
morluto
dcee59f273
Require delivered facts, exact cancellation and malformed-input boundaries, and independent metadata expectations. Transfer unique assertions into stronger keepers before removing duplicate cases and overwritten fixture writes; preserve all consumed core fixture bytes. Validation: 1,190 focused tests passed with 39 platform-dependent skips; 134 composition and conformance tests passed. Typecheck, lint, formatting, discovery and Knip passed. Independent preservation reviews and targeted regression controls passed.
1608 lines
54 KiB
TypeScript
1608 lines
54 KiB
TypeScript
import { createHash } from "node:crypto";
|
|
import { open, writeFile, symlink, truncate } from "node:fs/promises";
|
|
import { join } from "node:path";
|
|
import { expect, it, onTestFinished } from "vitest";
|
|
import { ModelArtifactProvider } from "../../../src/model/ModelArtifactProvider.js";
|
|
import { ModelHeaderReader } from "../../../src/model/ModelHeaderReader.js";
|
|
import {
|
|
MODEL_JSON_NESTING,
|
|
MODEL_METADATA_NESTING,
|
|
MODEL_REPORT_BYTES,
|
|
ModelFormatFailure,
|
|
modelCapacityRemediation,
|
|
modelCapacityReportedLimits,
|
|
} from "../../../src/model/ModelFormat.js";
|
|
import { readSafetensorsHeader } from "../../../src/model/SafetensorsHeader.js";
|
|
import { GgufHeader } from "../../../src/model/GgufHeader.js";
|
|
import { createModelArtifactService } from "../../../src/composition/model.js";
|
|
import { parseEvidence } from "../../../src/domain/evidence.js";
|
|
import { modelArtifactSchema } from "../../../src/domain/model/modelArtifact.js";
|
|
import { createTestTempDirectory } from "../../fixtures/temporaryDirectory.js";
|
|
import {
|
|
ggufFixture,
|
|
ggufKLayouts,
|
|
ggufShiftedTypeLayouts,
|
|
safetensorsFixture,
|
|
} from "../../fixtures/model/model.js";
|
|
|
|
const hash = (bytes: Buffer) =>
|
|
createHash("sha256").update(bytes).digest("hex");
|
|
const providerAt = async (bytes: Buffer) => {
|
|
const root = await createTestTempDirectory("rea-model-reader-");
|
|
const path = join(root, "content.without-format-extension");
|
|
await writeFile(path, bytes);
|
|
const provider = new ModelArtifactProvider();
|
|
onTestFinished(() => provider.close());
|
|
return { provider, path, root };
|
|
};
|
|
|
|
it.each([
|
|
["01000000", 1, 16_777_216],
|
|
["00000001", 16_777_216, 1],
|
|
["04000000", 4, 67_108_864],
|
|
["00000004", 67_108_864, 4],
|
|
["e7030000", 999, 3_875_733_504],
|
|
["000003e7", 3_875_733_504, 999],
|
|
["00000000", 0, 0],
|
|
["ffffffff", 4_294_967_295, 4_294_967_295],
|
|
] as const)(
|
|
"preserves unsupported GGUF version bytes %s without assuming byte order",
|
|
async (versionBytes, little, big) => {
|
|
// No counts are needed to explain a version refusal. Do not reinterpret
|
|
// an unknown version's subsequent layout or publish a header observation.
|
|
const { provider, path } = await providerAt(
|
|
Buffer.from(`47475546${versionBytes}`, "hex"),
|
|
);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Unknown version admitted");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "AnalysisUnsupportedTargetError",
|
|
reason: `GGUF version bytes ${versionBytes} are unsupported (little-endian ${String(little)}, big-endian ${String(big)}; byte order unknown); supported versions are 2 and 3`,
|
|
});
|
|
},
|
|
);
|
|
|
|
it("continues reading little-endian GGUF v2 declarations", async () => {
|
|
const { provider, path } = await providerAt(
|
|
ggufFixture({ version: 2 }).bytes,
|
|
);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value).toMatchObject({ version: 2, byte_order: "little" });
|
|
expect(result.value.tensors.map(({ name }) => name)).toEqual([
|
|
"weight",
|
|
"quant",
|
|
]);
|
|
});
|
|
|
|
it("continues refusing the unsupported big-endian GGUF v2 layout", async () => {
|
|
const { provider, path } = await providerAt(
|
|
ggufFixture({ version: 2, bigEndian: true }).bytes,
|
|
);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Big-endian GGUF v2 admitted");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "BinaryTargetError",
|
|
constraint: "file_format_rejected",
|
|
});
|
|
});
|
|
|
|
it.each([false, true])(
|
|
"reads exact GGUF declarations, endian=%s, without hashing tensor payload",
|
|
async (bigEndian) => {
|
|
const fixture = ggufFixture({ bigEndian });
|
|
const { provider, path } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.artifact).toEqual({
|
|
path,
|
|
file_size: fixture.bytes.length,
|
|
header_sha256: hash(fixture.header),
|
|
header_length: fixture.header.length,
|
|
sha256: null,
|
|
bytes_read: fixture.header.length,
|
|
read_scope: "header",
|
|
});
|
|
expect(result.value.byte_order).toBe(bigEndian ? "big" : "little");
|
|
expect(
|
|
result.value.metadata.find((row) => row.key === "custom.exact")?.value,
|
|
).toBe("18446744073709551615");
|
|
expect(
|
|
result.value.metadata.find((row) => row.key === "tokenizer.ggml.tokens"),
|
|
).toMatchObject({
|
|
element_type: "STRING",
|
|
element_count: 10,
|
|
preview_complete: false,
|
|
value: Array.from({ length: 8 }, (_, n) => `token-${String(n)}`),
|
|
});
|
|
expect(
|
|
result.value.tensors.map(({ name, shape, byte_length, file_offset }) => ({
|
|
name,
|
|
shape,
|
|
byte_length,
|
|
file_offset,
|
|
})),
|
|
).toEqual([
|
|
{
|
|
name: "weight",
|
|
shape: ["2", "2"],
|
|
byte_length: 16,
|
|
file_offset: fixture.dataOffset,
|
|
},
|
|
{
|
|
name: "quant",
|
|
shape: ["32"],
|
|
byte_length: 18,
|
|
file_offset: fixture.dataOffset + 32,
|
|
},
|
|
]);
|
|
expect(result.value.totals).toMatchObject({
|
|
parameter_count: "36",
|
|
tensor_bytes: 34,
|
|
});
|
|
const full = await provider.inspect({ path, hash: "full" });
|
|
if (!full.ok) throw full.error;
|
|
expect(full.value.artifact.sha256).toBe(hash(fixture.bytes));
|
|
expect(full.value.artifact.header_sha256).toBe(
|
|
result.value.artifact.header_sha256,
|
|
);
|
|
},
|
|
);
|
|
|
|
it.each([false, true])(
|
|
"preserves GGUF empty extents, quantized empty rows and scalars, endian=%s",
|
|
async (bigEndian) => {
|
|
const declarations = [
|
|
{ name: "empty_first", type: 0, shape: [0n, 7n], offset: 0n, bytes: 0 },
|
|
{ name: "empty_later", type: 0, shape: [3n, 0n], offset: 0n, bytes: 0 },
|
|
{
|
|
name: "empty_quant_first",
|
|
type: 2,
|
|
shape: [0n, 32n],
|
|
offset: 0n,
|
|
bytes: 0,
|
|
},
|
|
{
|
|
name: "empty_quant_later",
|
|
type: 2,
|
|
shape: [32n, 0n],
|
|
offset: 0n,
|
|
bytes: 0,
|
|
},
|
|
{ name: "scalar", type: 0, shape: [], offset: 0n, bytes: 4 },
|
|
];
|
|
const fixture = ggufFixture({ bigEndian, tensors: declarations });
|
|
const { provider, path } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(
|
|
result.value.tensors.map(
|
|
({ name, shape, byte_length, parameter_count }) => ({
|
|
name,
|
|
shape,
|
|
byte_length,
|
|
parameter_count,
|
|
}),
|
|
),
|
|
).toEqual(
|
|
declarations.map(({ name, shape, bytes }) => ({
|
|
name,
|
|
shape: shape.map(String),
|
|
byte_length: bytes,
|
|
parameter_count: name === "scalar" ? "1" : "0",
|
|
})),
|
|
);
|
|
expect(result.value.totals).toMatchObject({
|
|
parameter_count: "1",
|
|
tensor_bytes: 4,
|
|
});
|
|
expect(result.value.artifact.bytes_read).toBe(fixture.header.length);
|
|
},
|
|
);
|
|
|
|
it.each([
|
|
{ name: "excess rank", type: 0, shape: [1n, 1n, 1n, 1n, 1n], bytes: 4 },
|
|
{ name: "quantized scalar", type: 2, shape: [], bytes: 0 },
|
|
{ name: "Q8_1 incomplete block", type: 9, shape: [31n], bytes: 40 },
|
|
])(
|
|
"rejects GGUF $name without relaxing representation constraints",
|
|
async (tensor) => {
|
|
const fixture = ggufFixture({ tensors: [{ ...tensor, offset: 0n }] });
|
|
const { provider, path } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Expected format refusal");
|
|
expect(result.error).toMatchObject({
|
|
constraint: "file_format_rejected",
|
|
});
|
|
},
|
|
);
|
|
|
|
it.each([8, 24, 40])(
|
|
"accepts format-valid GGUF alignment %s and preserves exact offsets",
|
|
async (alignment) => {
|
|
const fixture = ggufFixture({ alignment });
|
|
const { path, provider } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.alignment).toBe(alignment);
|
|
expect(result.value.tensor_data_offset).toBe(fixture.dataOffset);
|
|
expect(
|
|
result.value.tensors.every((row) => row.file_offset % alignment === 0),
|
|
).toBe(true);
|
|
expect(result.value.tensors[1]?.file_offset).toBe(
|
|
fixture.dataOffset + Math.ceil(16 / alignment) * alignment,
|
|
);
|
|
},
|
|
);
|
|
|
|
it("aligns the GGUF data section after an empty tensor directory", async () => {
|
|
const base = ggufFixture({ tensors: [], metadata: [] });
|
|
const dataOffset = Math.ceil(base.header.length / 32) * 32;
|
|
const bytes = Buffer.concat([
|
|
base.header,
|
|
Buffer.alloc(dataOffset - base.header.length),
|
|
]);
|
|
const { path, provider } = await providerAt(bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.tensors).toEqual([]);
|
|
expect(result.value.tensor_data_offset).toBe(dataOffset);
|
|
expect(result.value.artifact.header_length).toBe(base.header.length);
|
|
});
|
|
|
|
it.each([0, 1, 2, 4, 12])(
|
|
"rejects GGUF alignment %s outside positive multiples of eight",
|
|
async (alignment) => {
|
|
const base = ggufFixture();
|
|
const fixture = ggufFixture({
|
|
metadata: [
|
|
{ key: "general.alignment", type: 4, value: base.u32(alignment) },
|
|
],
|
|
});
|
|
const { path, provider } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Invalid alignment accepted");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "BinaryTargetError",
|
|
constraint: "file_format_rejected",
|
|
});
|
|
},
|
|
);
|
|
|
|
it.each([
|
|
"General.name",
|
|
"general.naïve",
|
|
"general..name",
|
|
"general/name",
|
|
"general.-name",
|
|
"general.name-",
|
|
"general.double--name",
|
|
"general.name_",
|
|
"general.__name",
|
|
])(
|
|
"rejects invalid GGUF metadata key %s before publishing facts",
|
|
async (key) => {
|
|
const fixture = ggufFixture({
|
|
metadata: [{ key, type: 7, value: Buffer.from([1]) }],
|
|
});
|
|
const { path, provider } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Invalid metadata key accepted");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "BinaryTargetError",
|
|
constraint: "file_format_rejected",
|
|
});
|
|
},
|
|
);
|
|
|
|
it("accepts standardized GGUF metadata keys containing numeric hierarchy components", async () => {
|
|
const base = ggufFixture();
|
|
const fixture = ggufFixture({
|
|
metadata: [
|
|
{ key: "general.base_model.0.name", type: 8, value: base.text("parent") },
|
|
],
|
|
});
|
|
const { path, provider } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.metadata[0]).toMatchObject({
|
|
key: "general.base_model.0.name",
|
|
value: "parent",
|
|
});
|
|
});
|
|
|
|
it.each([67_324_752, 67_324_760, 99_999_993, 100_000_000])(
|
|
"admits safetensors declared header length %s before its independent representation limit",
|
|
async (length) => {
|
|
const bytes = Buffer.alloc(9);
|
|
bytes.writeBigUInt64LE(BigInt(length));
|
|
bytes[8] = 0x7b;
|
|
const { path, provider } = await providerAt(bytes);
|
|
const file = await open(path, "r+");
|
|
try {
|
|
await file.truncate(8 + length);
|
|
} finally {
|
|
await file.close();
|
|
}
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Representation limit was bypassed");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "AnalysisResourceConstraintError",
|
|
reason: expect.stringContaining("32 MiB"),
|
|
});
|
|
},
|
|
);
|
|
|
|
it("retains the absolute header budget for GGUF without allocating that extent", async () => {
|
|
const { path } = await providerAt(Buffer.alloc(0));
|
|
const file = await open(path, "r+");
|
|
onTestFinished(() => file.close());
|
|
await file.truncate(100_000_009);
|
|
const reader = new ModelHeaderReader(file, 100_000_009);
|
|
expect(() => reader.guarantee(100_000_000)).not.toThrow();
|
|
expect(() => reader.guarantee(100_000_001)).toThrow(ModelFormatFailure);
|
|
try {
|
|
reader.guarantee(100_000_001);
|
|
} catch (cause) {
|
|
expect(cause).toBeInstanceOf(ModelFormatFailure);
|
|
if (!(cause instanceof ModelFormatFailure))
|
|
throw new Error("Expected a model header capacity failure");
|
|
expect(cause.limit).toBe("header-bytes");
|
|
expect(cause.message).toContain("100,000,000 bytes");
|
|
expect(cause.message).not.toContain("Safetensors");
|
|
}
|
|
});
|
|
|
|
it("separates impossible string lengths from nesting capacity", async () => {
|
|
const base = ggufFixture({ tensors: [] });
|
|
const oversized = ggufFixture({
|
|
metadata: [
|
|
{
|
|
key: "custom.length",
|
|
type: 8,
|
|
value: base.u64(BigInt(Number.MAX_SAFE_INTEGER) + 1n),
|
|
},
|
|
],
|
|
tensors: [],
|
|
});
|
|
let nested = Buffer.from([1]);
|
|
for (let frame = 0; frame < 33; frame += 1)
|
|
nested = Buffer.concat([
|
|
base.u32(frame === 0 ? 7 : 9),
|
|
base.u64(1n),
|
|
nested,
|
|
]);
|
|
const deep = ggufFixture({
|
|
metadata: [{ key: "custom.nested", type: 9, value: nested }],
|
|
tensors: [],
|
|
});
|
|
const invalid = await providerAt(oversized.bytes);
|
|
expect(
|
|
await invalid.provider.inspect({ path: invalid.path, hash: "header" }),
|
|
).toMatchObject({ ok: false, error: { _tag: "BinaryTargetError" } });
|
|
for (const [label, bytes, allowance] of [
|
|
["nesting", deep.bytes, "32 array frames"],
|
|
] as const) {
|
|
const { path, provider } = await providerAt(bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error(`${label} capacity was accepted`);
|
|
expect(result.error).toMatchObject({
|
|
_tag: "AnalysisResourceConstraintError",
|
|
retryable: false,
|
|
remediationAction: expect.stringContaining(allowance),
|
|
});
|
|
const remediation =
|
|
"remediationAction" in result.error ? result.error.remediationAction : "";
|
|
expect(remediation).not.toContain(String(MODEL_REPORT_BYTES));
|
|
expect(remediation).not.toContain("100,000,000");
|
|
expect(result.error).toMatchObject({
|
|
reportedLimits: expect.not.objectContaining({
|
|
maximum_report_bytes: MODEL_REPORT_BYTES,
|
|
}),
|
|
});
|
|
}
|
|
});
|
|
|
|
it("preserves safetensors scalar, empty and packed tensor declarations and raw string metadata", async () => {
|
|
const fixture = safetensorsFixture();
|
|
const { provider, path } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.artifact.header_sha256).toBe(hash(fixture.header));
|
|
expect(
|
|
result.value.tensors.map((row) => [row.name, row.shape, row.byte_length]),
|
|
).toEqual([
|
|
["empty", ["0", "7"], 0],
|
|
["weight", ["2", "2"], 16],
|
|
]);
|
|
expect(result.value.metadata.map((row) => [row.key, row.value])).toEqual([
|
|
["format", "pt"],
|
|
["license", "Apache-2.0"],
|
|
]);
|
|
const packed = safetensorsFixture(
|
|
JSON.stringify({
|
|
scalar: { dtype: "F4", shape: [2], data_offsets: [0, 1] },
|
|
empty: { dtype: "F32", shape: [0], data_offsets: [0, 0] },
|
|
}),
|
|
Buffer.alloc(1),
|
|
);
|
|
await writeFile(path, packed.bytes);
|
|
const checked = await provider.inspect({ path, hash: "full" });
|
|
if (!checked.ok) throw checked.error;
|
|
expect(checked.value.totals).toMatchObject({
|
|
parameter_count: "2",
|
|
tensor_bytes: 1,
|
|
});
|
|
});
|
|
|
|
it("returns unknown lengths for unknown GGUF types without inventing storage size", async () => {
|
|
const fixture = ggufFixture({
|
|
tensors: [{ name: "future", type: 999, shape: [1n], offset: 0n, bytes: 1 }],
|
|
});
|
|
const { provider, path } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.tensors[0]).toMatchObject({
|
|
type_id: 999,
|
|
type: "UNKNOWN_999",
|
|
byte_length: null,
|
|
byte_length_state: "unknown",
|
|
});
|
|
expect(result.value.coverage.tensor_ranges).toBe("partial");
|
|
expect(result.value.totals.tensor_bytes).toBeNull();
|
|
});
|
|
|
|
it.each([
|
|
{ version: 2, bigEndian: false, blockBytes: 36 },
|
|
{ version: 2, bigEndian: false, blockBytes: 40 },
|
|
{ version: 3, bigEndian: false, blockBytes: 36 },
|
|
{ version: 3, bigEndian: false, blockBytes: 40 },
|
|
{ version: 3, bigEndian: true, blockBytes: 36 },
|
|
{ version: 3, bigEndian: true, blockBytes: 40 },
|
|
])(
|
|
"preserves unresolved Q8_1 storage for GGUF v$version, endian=$bigEndian, block bytes=$blockBytes",
|
|
async ({ version, bigEndian, blockBytes }) => {
|
|
const base = ggufFixture({ bigEndian });
|
|
const fixture = ggufFixture({
|
|
version,
|
|
bigEndian,
|
|
metadata: [
|
|
{ key: "general.quantization_version", type: 4, value: base.u32(2) },
|
|
],
|
|
tensors: [
|
|
{ name: "control", type: 0, shape: [4n], offset: 0n, bytes: 16 },
|
|
{
|
|
name: "weight",
|
|
type: 9,
|
|
shape: [320n],
|
|
offset: 32n,
|
|
bytes: 10 * blockBytes,
|
|
},
|
|
],
|
|
});
|
|
const { provider, path } = await providerAt(
|
|
Buffer.concat([fixture.bytes, Buffer.alloc(16)]),
|
|
);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.tensors).toMatchObject([
|
|
{ name: "control", byte_length: 16, storage_validation: "consistent" },
|
|
{
|
|
name: "weight",
|
|
type: "Q8_1",
|
|
type_id: 9,
|
|
shape: ["320"],
|
|
data_offset: 32,
|
|
file_offset: fixture.dataOffset + 32,
|
|
parameter_count: "320",
|
|
byte_length: null,
|
|
byte_length_state: "unknown",
|
|
storage_validation: "unknown",
|
|
},
|
|
]);
|
|
expect(result.value.totals).toMatchObject({
|
|
parameter_count: "324",
|
|
tensor_bytes: null,
|
|
by_type: [
|
|
{ type: "F32", bytes: 16, parameter_count: "4" },
|
|
{ type: "Q8_1", bytes: null, parameter_count: "320" },
|
|
],
|
|
});
|
|
expect(result.value.coverage).toMatchObject({
|
|
header: "complete",
|
|
tensor_ranges: "partial",
|
|
storage_sizes: "partial",
|
|
});
|
|
expect(result.value.limitations).toContainEqual(
|
|
expect.stringContaining("Q8_1 has released 40-byte and 36-byte layouts"),
|
|
);
|
|
expect(result.value.limitations.join(" ")).not.toContain(
|
|
"Unknown tensor type Q8_1",
|
|
);
|
|
expect(result.value.artifact.bytes_read).toBe(fixture.header.length);
|
|
},
|
|
);
|
|
|
|
it("derives empty Q8_1 storage without choosing a historical block layout", async () => {
|
|
const fixture = ggufFixture({
|
|
metadata: [],
|
|
tensors: [
|
|
{ name: "empty", type: 9, shape: [32n, 0n], offset: 0n, bytes: 0 },
|
|
],
|
|
});
|
|
const { provider, path } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.tensors[0]).toMatchObject({
|
|
type: "Q8_1",
|
|
parameter_count: "0",
|
|
byte_length: 0,
|
|
byte_length_state: "derived",
|
|
storage_validation: "consistent",
|
|
});
|
|
expect(result.value.totals.tensor_bytes).toBe(0);
|
|
expect(result.value.coverage).toMatchObject({
|
|
tensor_ranges: "complete",
|
|
storage_sizes: "complete",
|
|
});
|
|
});
|
|
|
|
it.each(ggufKLayouts)(
|
|
"preserves $name identity while leaving released K64/K256 storage unresolved",
|
|
async ({ id, name, bytes64, bytes256 }) => {
|
|
// The released GGUF writer pads each tensor to 32 bytes. For 256 elements,
|
|
// both layouts have the same padded extent, despite different byte lengths.
|
|
expect(Math.ceil((4 * bytes64) / 32)).toBe(Math.ceil(bytes256 / 32));
|
|
for (const [elements, bytes] of [
|
|
[64, bytes64],
|
|
[256, 4 * bytes64],
|
|
[256, bytes256],
|
|
] as const) {
|
|
const base = ggufFixture();
|
|
const fixture = ggufFixture({
|
|
metadata: [
|
|
{ key: "general.quantization_version", type: 4, value: base.u32(2) },
|
|
{ key: "general.file_type", type: 4, value: base.u32(15) },
|
|
],
|
|
tensors: [
|
|
{
|
|
name: "weight",
|
|
type: id,
|
|
shape: [BigInt(elements)],
|
|
offset: 0n,
|
|
bytes,
|
|
},
|
|
],
|
|
});
|
|
const { provider, path } = await providerAt(
|
|
Buffer.concat([
|
|
fixture.bytes,
|
|
Buffer.alloc(Math.ceil(bytes / 32) * 32 - bytes),
|
|
]),
|
|
);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.tensors[0]).toMatchObject({
|
|
type: name,
|
|
type_id: id,
|
|
shape: [String(elements)],
|
|
parameter_count: String(elements),
|
|
byte_length: null,
|
|
storage_validation: "unknown",
|
|
});
|
|
expect(result.value.coverage).toMatchObject({
|
|
tensor_ranges: "partial",
|
|
storage_sizes: "partial",
|
|
});
|
|
expect(result.value.totals.tensor_bytes).toBeNull();
|
|
expect(result.value.limitations).toContainEqual(
|
|
expect.stringContaining("common 64-element row constraint"),
|
|
);
|
|
}
|
|
const { provider, path } = await providerAt(
|
|
ggufFixture({
|
|
tensors: [
|
|
{
|
|
name: "invalid",
|
|
type: id,
|
|
shape: [32n],
|
|
offset: 0n,
|
|
bytes: bytes64,
|
|
},
|
|
],
|
|
}).bytes,
|
|
);
|
|
const rejected = await provider.inspect({ path, hash: "header" });
|
|
if (rejected.ok) throw new Error("Incomplete common K row admitted");
|
|
expect(rejected.error).toMatchObject({
|
|
constraint: "file_format_rejected",
|
|
reason: expect.stringContaining("multiple of 64 elements"),
|
|
});
|
|
},
|
|
);
|
|
|
|
it.each(ggufShiftedTypeLayouts)(
|
|
"retains ambiguous numeric type $id for released integer and $modernName bodies",
|
|
async ({ id, integerBytes, modernName, modernBytes256 }) => {
|
|
for (const [elements, bytes] of [
|
|
[3, 3 * integerBytes],
|
|
[256, 256 * integerBytes],
|
|
[256, modernBytes256],
|
|
[0, 0],
|
|
] as const) {
|
|
const fixture = ggufFixture({
|
|
tensors: [
|
|
{
|
|
name: "weight",
|
|
type: id,
|
|
shape: [BigInt(elements)],
|
|
offset: 0n,
|
|
bytes,
|
|
},
|
|
],
|
|
});
|
|
const { provider, path } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.tensors[0]).toMatchObject({
|
|
type: `AMBIGUOUS_${String(id)}`,
|
|
type_id: id,
|
|
shape: [String(elements)],
|
|
parameter_count: String(elements),
|
|
byte_length: elements === 0 ? 0 : null,
|
|
storage_validation: elements === 0 ? "consistent" : "unknown",
|
|
});
|
|
expect(result.value.limitations).toContainEqual(
|
|
expect.stringContaining(`type ID ${String(id)} has released`),
|
|
);
|
|
expect(result.value.limitations.join(" ")).toContain(modernName);
|
|
expect(result.value.totals.tensor_bytes).toBe(elements === 0 ? 0 : null);
|
|
}
|
|
},
|
|
);
|
|
|
|
it("retains established storage for stable GGUF types and zero-byte K declarations", async () => {
|
|
const fixture = ggufFixture({
|
|
tensors: [
|
|
{ name: "integer", type: 26, shape: [3n], offset: 0n, bytes: 12 },
|
|
{ name: "empty-k", type: 10, shape: [64n, 0n], offset: 32n, bytes: 0 },
|
|
{ name: "quant", type: 2, shape: [32n], offset: 32n, bytes: 18 },
|
|
],
|
|
});
|
|
const { provider, path } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.tensors).toMatchObject([
|
|
{ type: "I32", byte_length: 12, storage_validation: "consistent" },
|
|
{ type: "Q2_K", byte_length: 0, storage_validation: "consistent" },
|
|
{ type: "Q4_0", byte_length: 18, storage_validation: "consistent" },
|
|
]);
|
|
expect(result.value.totals.tensor_bytes).toBe(30);
|
|
expect(result.value.coverage).toMatchObject({
|
|
tensor_ranges: "complete",
|
|
storage_sizes: "complete",
|
|
});
|
|
});
|
|
|
|
it("keeps unknown safetensors storage validation separate from observed valid byte ranges", async () => {
|
|
const fixture = safetensorsFixture(
|
|
'{"future":{"dtype":"FUTURE4","shape":[2],"data_offsets":[0,4]}}',
|
|
Buffer.alloc(4),
|
|
);
|
|
const { path, provider } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.tensors[0]).toMatchObject({
|
|
byte_length: 4,
|
|
byte_length_state: "declared",
|
|
storage_validation: "unknown",
|
|
});
|
|
expect(result.value.coverage).toMatchObject({
|
|
tensor_ranges: "complete",
|
|
storage_sizes: "partial",
|
|
});
|
|
});
|
|
|
|
it("preserves nonfinite floating metadata and negative zero without JSON coercion", async () => {
|
|
const values = [NaN, Infinity, -Infinity, -0];
|
|
const fixture = ggufFixture({
|
|
metadata: values.map((value, index) => {
|
|
const b = Buffer.alloc(8);
|
|
b.writeDoubleLE(value);
|
|
return { key: `custom.float_${String(index)}`, type: 12, value: b };
|
|
}),
|
|
});
|
|
const { path, provider } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.metadata.map((row) => [row.type, row.value])).toEqual(
|
|
["NaN", "+Infinity", "-Infinity", "-0"].map((value) => ["FLOAT64", value]),
|
|
);
|
|
});
|
|
|
|
it("validates booleans beyond an array preview without allocating the full value list", async () => {
|
|
const base = ggufFixture();
|
|
const values = Buffer.alloc(10000);
|
|
values[9999] = 2;
|
|
const fixture = ggufFixture({
|
|
metadata: [
|
|
{
|
|
key: "custom.flags",
|
|
type: 9,
|
|
value: Buffer.concat([base.u32(7), base.u64(10000n), values]),
|
|
},
|
|
],
|
|
});
|
|
const { path, provider } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Invalid omitted boolean was accepted");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "BinaryTargetError",
|
|
constraint: "file_format_rejected",
|
|
});
|
|
});
|
|
|
|
it.each([false, true])(
|
|
"validates omitted UTF-8 strings across chunk boundaries, big endian=%s",
|
|
async (bigEndian) => {
|
|
const base = ggufFixture({ bigEndian });
|
|
const preview = Array.from({ length: 8 }, (_, n) => `\uFEFFtoken-${n} 🦙`);
|
|
const strings = [
|
|
...preview,
|
|
"",
|
|
"a".repeat(65533) + "€",
|
|
"a".repeat(65535) + "🦙",
|
|
"\0tail",
|
|
];
|
|
const fixture = ggufFixture({
|
|
bigEndian,
|
|
metadata: [
|
|
{
|
|
key: "custom.strings",
|
|
type: 9,
|
|
value: Buffer.concat([
|
|
base.u32(8),
|
|
base.u64(BigInt(strings.length)),
|
|
...strings.map(base.text),
|
|
]),
|
|
},
|
|
],
|
|
});
|
|
const { path, provider } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.metadata[0]).toMatchObject({
|
|
value: preview,
|
|
element_count: strings.length,
|
|
preview_complete: false,
|
|
});
|
|
expect(result.value.artifact).toMatchObject({
|
|
bytes_read: fixture.header.length,
|
|
header_sha256: createHash("sha256").update(fixture.header).digest("hex"),
|
|
});
|
|
expect(result.value.tensors).toHaveLength(2);
|
|
},
|
|
);
|
|
|
|
it.each([
|
|
["short", Buffer.from([0xc0, 0x80])],
|
|
[
|
|
"chunk-sized",
|
|
Buffer.concat([Buffer.alloc(65535, 0x61), Buffer.from([0xe2])]),
|
|
],
|
|
[
|
|
"cross-chunk",
|
|
Buffer.concat([
|
|
Buffer.alloc(65535, 0x61),
|
|
Buffer.from([0xf0, 0x9f, 0x61, 0x80]),
|
|
]),
|
|
],
|
|
] as const)(
|
|
"rejects malformed omitted %s UTF-8 strings",
|
|
async (_, invalid) => {
|
|
const base = ggufFixture();
|
|
const fixture = ggufFixture({
|
|
metadata: [
|
|
{
|
|
key: "custom.strings",
|
|
type: 9,
|
|
value: Buffer.concat([
|
|
base.u32(8),
|
|
base.u64(9n),
|
|
...Array.from({ length: 8 }, () => base.text("valid")),
|
|
base.u64(BigInt(invalid.length)),
|
|
invalid,
|
|
]),
|
|
},
|
|
],
|
|
});
|
|
const { path, provider } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Invalid omitted UTF-8 string was accepted");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "BinaryTargetError",
|
|
constraint: "file_format_rejected",
|
|
message: expect.stringContaining("GGUF string is not valid UTF-8"),
|
|
});
|
|
},
|
|
);
|
|
|
|
it("chooses model recovery from the producing limit", () => {
|
|
const header = modelCapacityRemediation("header-bytes");
|
|
expect(header).toContain("100,000,000 bytes");
|
|
expect(header).not.toContain("Safetensors");
|
|
expect(header).not.toContain(String(MODEL_REPORT_BYTES));
|
|
const report = modelCapacityRemediation("report-bytes");
|
|
expect(report).toContain(`report allowance is ${String(MODEL_REPORT_BYTES)}`);
|
|
expect(report).not.toContain("representation");
|
|
const representation = modelCapacityRemediation("representation-bytes");
|
|
expect(representation).toContain("representation allowance");
|
|
expect(representation).not.toContain("report allowance");
|
|
const offset = modelCapacityRemediation("exact-offset");
|
|
expect(offset).toContain(String(Number.MAX_SAFE_INTEGER));
|
|
expect(offset).not.toContain(String(MODEL_REPORT_BYTES));
|
|
const nesting = modelCapacityRemediation("metadata-nesting");
|
|
expect(nesting).toContain(`${String(MODEL_METADATA_NESTING)} array frames`);
|
|
expect(nesting).not.toContain(String(MODEL_REPORT_BYTES));
|
|
const jsonNesting = modelCapacityRemediation("json-nesting");
|
|
expect(jsonNesting).toContain(`${String(MODEL_JSON_NESTING)} levels`);
|
|
expect(jsonNesting).not.toContain(String(MODEL_REPORT_BYTES));
|
|
expect(modelCapacityReportedLimits("report-bytes")).toEqual({
|
|
maximum_report_bytes: MODEL_REPORT_BYTES,
|
|
});
|
|
expect(modelCapacityReportedLimits("exact-offset")).toEqual({
|
|
maximum_exact_offset: Number.MAX_SAFE_INTEGER,
|
|
});
|
|
expect(modelCapacityReportedLimits("json-nesting")).toEqual({
|
|
maximum_json_depth: MODEL_JSON_NESTING,
|
|
});
|
|
});
|
|
|
|
it("refuses an oversized declared header before reading or expanding it", async () => {
|
|
const bytes = Buffer.alloc(9);
|
|
bytes.writeBigUInt64LE(100_000_001n);
|
|
bytes[8] = 0x7b;
|
|
const { path, provider } = await providerAt(bytes);
|
|
const file = await open(path, "r+");
|
|
try {
|
|
await file.truncate(100_000_009);
|
|
} finally {
|
|
await file.close();
|
|
}
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Oversized header was accepted");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "AnalysisResourceConstraintError",
|
|
retryable: false,
|
|
reportedLimits: { maximum_header_bytes: 100_000_000 },
|
|
remediationAction: expect.stringContaining("100,000,000"),
|
|
});
|
|
expect(result.error.message).not.toContain("Safetensors");
|
|
expect(
|
|
"remediationAction" in result.error ? result.error.remediationAction : "",
|
|
).not.toContain("Safetensors");
|
|
expect(
|
|
"reportedLimits" in result.error ? result.error.reportedLimits : {},
|
|
).not.toHaveProperty("maximum_report_bytes");
|
|
});
|
|
|
|
const malformed = [
|
|
["truncated GGUF", () => ggufFixture().bytes.subarray(0, 21)],
|
|
[
|
|
"GGUF string whose declared bytes exceed the file and report budget",
|
|
() => {
|
|
const base = ggufFixture({ tensors: [] });
|
|
return ggufFixture({
|
|
tensors: [],
|
|
metadata: [
|
|
{ key: "custom.value", type: 8, value: base.u64(6_000_000n) },
|
|
],
|
|
}).bytes;
|
|
},
|
|
],
|
|
[
|
|
"GGUF count whose minimum directory exceeds the file and report budget",
|
|
() => {
|
|
const header = Buffer.alloc(24);
|
|
header.write("GGUF");
|
|
header.writeUInt32LE(3, 4);
|
|
header.writeBigUInt64LE(65537n, 8);
|
|
return header;
|
|
},
|
|
],
|
|
[
|
|
"invalid UTF8",
|
|
() => {
|
|
const f = ggufFixture({
|
|
metadata: [
|
|
{
|
|
key: "x",
|
|
type: 8,
|
|
value: Buffer.concat([
|
|
Buffer.from([1, 0, 0, 0, 0, 0, 0, 0]),
|
|
Buffer.from([0xff]),
|
|
]),
|
|
},
|
|
],
|
|
});
|
|
return f.bytes;
|
|
},
|
|
],
|
|
[
|
|
"duplicate GGUF metadata",
|
|
() =>
|
|
ggufFixture({
|
|
metadata: [
|
|
{ key: "x", type: 7, value: Buffer.from([0]) },
|
|
{ key: "x", type: 7, value: Buffer.from([1]) },
|
|
],
|
|
}).bytes,
|
|
],
|
|
[
|
|
"invalid boolean",
|
|
() =>
|
|
ggufFixture({
|
|
metadata: [{ key: "x", type: 7, value: Buffer.from([2]) }],
|
|
}).bytes,
|
|
],
|
|
[
|
|
"misaligned GGUF tensor",
|
|
() =>
|
|
ggufFixture({
|
|
tensors: [{ name: "x", type: 0, shape: [1n], offset: 1n, bytes: 4 }],
|
|
}).bytes,
|
|
],
|
|
[
|
|
"invalid quantization row",
|
|
() =>
|
|
ggufFixture({
|
|
tensors: [
|
|
{ name: "x", type: 2, shape: [16n, 2n], offset: 0n, bytes: 18 },
|
|
],
|
|
}).bytes,
|
|
],
|
|
[
|
|
"overlapping GGUF tensors",
|
|
() =>
|
|
ggufFixture({
|
|
tensors: [
|
|
{ name: "a", type: 0, shape: [1n], offset: 0n, bytes: 4 },
|
|
{ name: "b", type: 0, shape: [1n], offset: 0n, bytes: 4 },
|
|
],
|
|
}).bytes,
|
|
],
|
|
[
|
|
"duplicate JSON keys",
|
|
() =>
|
|
safetensorsFixture(
|
|
'{"x":{"dtype":"F32","dtype":"F16","shape":[2],"data_offsets":[0,4]}}',
|
|
Buffer.alloc(4),
|
|
).bytes,
|
|
],
|
|
[
|
|
"safetensors dimension exceeding uint64",
|
|
() =>
|
|
safetensorsFixture(
|
|
'{"x":{"dtype":"F32","shape":[0,18446744073709551616],"data_offsets":[0,0]}}',
|
|
Buffer.alloc(0),
|
|
).bytes,
|
|
],
|
|
[
|
|
"overlong safetensors integer",
|
|
() =>
|
|
safetensorsFixture(
|
|
'{"x":{"dtype":"F32","shape":[0,100000000000000000000],"data_offsets":[0,0]}}',
|
|
Buffer.alloc(0),
|
|
).bytes,
|
|
],
|
|
[
|
|
"safetensors shape product overflowing before a zero extent",
|
|
() =>
|
|
safetensorsFixture(
|
|
'{"x":{"dtype":"F32","shape":[18446744073709551615,18446744073709551615,0],"data_offsets":[0,0]}}',
|
|
Buffer.alloc(0),
|
|
).bytes,
|
|
],
|
|
[
|
|
"safetensors shape mismatch",
|
|
() =>
|
|
safetensorsFixture(
|
|
'{"x":{"dtype":"F32","shape":[3],"data_offsets":[0,16]}}',
|
|
).bytes,
|
|
],
|
|
[
|
|
"safetensors gap",
|
|
() =>
|
|
safetensorsFixture(
|
|
'{"x":{"dtype":"F32","shape":[3],"data_offsets":[4,16]}}',
|
|
).bytes,
|
|
],
|
|
[
|
|
"safetensors overlap",
|
|
() =>
|
|
safetensorsFixture(
|
|
'{"a":{"dtype":"F32","shape":[4],"data_offsets":[0,16]},"b":{"dtype":"F32","shape":[1],"data_offsets":[0,4]}}',
|
|
).bytes,
|
|
],
|
|
["safetensors trailing data", () => safetensorsFixture("{}").bytes],
|
|
[
|
|
"safetensors non-string metadata",
|
|
() => safetensorsFixture('{"__metadata__":{"x":1}}', Buffer.alloc(0)).bytes,
|
|
],
|
|
[
|
|
"safetensors decimal metadata container",
|
|
() => safetensorsFixture('{"__metadata__":1.25}', Buffer.alloc(0)).bytes,
|
|
],
|
|
[
|
|
"safetensors negative metadata container",
|
|
() => safetensorsFixture('{"__metadata__":-1}', Buffer.alloc(0)).bytes,
|
|
],
|
|
[
|
|
"safetensors overflowing metadata container",
|
|
() =>
|
|
safetensorsFixture(
|
|
'{"__metadata__":18446744073709551616}',
|
|
Buffer.alloc(0),
|
|
).bytes,
|
|
],
|
|
[
|
|
"safetensors noninteger shape sentinel",
|
|
() =>
|
|
safetensorsFixture(
|
|
'{"x":{"dtype":"F32","shape":[1.25],"data_offsets":[0,0]}}',
|
|
Buffer.alloc(0),
|
|
).bytes,
|
|
],
|
|
[
|
|
"safetensors negative data-offset sentinel",
|
|
() =>
|
|
safetensorsFixture(
|
|
'{"x":{"dtype":"F32","shape":[1],"data_offsets":[-1,4]}}',
|
|
Buffer.alloc(0),
|
|
).bytes,
|
|
],
|
|
[
|
|
"safetensors tensor missing a required declaration",
|
|
() =>
|
|
safetensorsFixture('{"x":{"dtype":"F32","shape":[1]}}', Buffer.alloc(0))
|
|
.bytes,
|
|
],
|
|
[
|
|
"safetensors unpaired surrogate",
|
|
() =>
|
|
safetensorsFixture('{"__metadata__":{"x":"\\ud800"}}', Buffer.alloc(0))
|
|
.bytes,
|
|
],
|
|
] as const;
|
|
it.each(malformed)(
|
|
"rejects %s with typed file_format_rejected",
|
|
async (_name, make) => {
|
|
const { provider, path } = await providerAt(make());
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Malformed model was accepted");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "BinaryTargetError",
|
|
constraint: "file_format_rejected",
|
|
});
|
|
},
|
|
);
|
|
|
|
it("retains GGUF representation capacity when declared string bytes can fit", async () => {
|
|
const base = ggufFixture({ tensors: [] });
|
|
const bytes = ggufFixture({
|
|
tensors: [],
|
|
metadata: [{ key: "custom.value", type: 8, value: base.u64(6_000_000n) }],
|
|
}).bytes;
|
|
const { provider, path } = await providerAt(bytes);
|
|
await truncate(path, bytes.length + 6_000_000);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Oversized representation was accepted");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "AnalysisResourceConstraintError",
|
|
reportedLimits: { maximum_representation_bytes: MODEL_REPORT_BYTES },
|
|
});
|
|
});
|
|
|
|
it("retains GGUF representation capacity when the declared directory can fit", async () => {
|
|
const header = Buffer.alloc(24);
|
|
header.write("GGUF");
|
|
header.writeUInt32LE(3, 4);
|
|
header.writeBigUInt64LE(65537n, 8);
|
|
const { provider, path } = await providerAt(header);
|
|
await truncate(path, 24 + 65537 * 24);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Oversized representation was accepted");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "AnalysisResourceConstraintError",
|
|
reportedLimits: { maximum_representation_bytes: MODEL_REPORT_BYTES },
|
|
});
|
|
});
|
|
|
|
it("retains GGUF declarations and metadata when storage overlap is refused", async () => {
|
|
const seed = ggufFixture();
|
|
const fixture = ggufFixture({
|
|
metadata: [{ key: "general.name", type: 8, value: seed.text("Overlap") }],
|
|
tensors: [
|
|
{ name: "a", type: 0, shape: [1n], offset: 0n, bytes: 4 },
|
|
{ name: "b", type: 0, shape: [1n], offset: 0n, bytes: 4 },
|
|
],
|
|
});
|
|
const { provider, path } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Overlapping tensors admitted");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "BinaryTargetError",
|
|
constraint: "file_format_rejected",
|
|
});
|
|
const evidence = parseEvidence(result.error.partialObservation);
|
|
expect(evidence.subject).toBeNull();
|
|
expect(evidence.normalized_result).toMatchObject({
|
|
artifact: {
|
|
header_sha256: null,
|
|
sha256: null,
|
|
file_identity: "unverified",
|
|
},
|
|
coverage: { header: "partial", metadata: "complete", tensors: "partial" },
|
|
metadata: [{ key: "general.name", value: "Overlap" }],
|
|
tensors: [],
|
|
tensor_declarations: [
|
|
{
|
|
name: "a",
|
|
file_offset: fixture.dataOffset,
|
|
storage_validation: "not-established",
|
|
},
|
|
{
|
|
name: "b",
|
|
file_offset: fixture.dataOffset,
|
|
storage_validation: "not-established",
|
|
},
|
|
],
|
|
});
|
|
});
|
|
|
|
it("accepts null safetensors metadata and ignores tensor extension fields", async () => {
|
|
const fixture = safetensorsFixture(
|
|
'{"__metadata__":null,"weight":{"dtype":"F32","shape":[1],"data_offsets":[0,4],"note":{"source":"local","flags":[null,false,-1,1.25]}}}',
|
|
Buffer.alloc(4),
|
|
);
|
|
const { provider, path } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.metadata).toEqual([]);
|
|
expect(
|
|
result.value.tensors.map(({ name, type, shape }) => ({
|
|
name,
|
|
type,
|
|
shape,
|
|
})),
|
|
).toEqual([{ name: "weight", type: "F32", shape: ["1"] }]);
|
|
});
|
|
|
|
it("accepts nested JSON values in ignored Safetensors extension fields", async () => {
|
|
const nested = `${"[".repeat(12)}0${"]".repeat(12)}`;
|
|
const fixture = safetensorsFixture(
|
|
`{"weight":{"dtype":"F32","shape":[1],"data_offsets":[0,4],"note":${nested}}}`,
|
|
Buffer.alloc(4),
|
|
);
|
|
const { provider, path } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
expect(result.ok).toBe(true);
|
|
});
|
|
|
|
it("classifies over-depth Safetensors extension JSON as a resource limit", async () => {
|
|
const nested = `${"[".repeat(MODEL_JSON_NESTING + 1)}0${"]".repeat(MODEL_JSON_NESTING + 1)}`;
|
|
const fixture = safetensorsFixture(
|
|
`{"weight":{"dtype":"F32","shape":[1],"data_offsets":[0,4],"note":${nested}}}`,
|
|
Buffer.alloc(4),
|
|
);
|
|
const { provider, path } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Over-depth JSON was accepted");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "AnalysisResourceConstraintError",
|
|
resource: "memory",
|
|
reason: expect.stringContaining("Safetensors JSON nesting"),
|
|
reportedLimits: { maximum_json_depth: MODEL_JSON_NESTING },
|
|
});
|
|
});
|
|
|
|
it.each([640, 896, 1152, 1408, 66_176])(
|
|
"admits safetensors header length %s whose prefix bytes resemble a pickle protocol marker",
|
|
async (length) => {
|
|
const header = JSON.stringify({
|
|
weight: { dtype: "F32", shape: [1], data_offsets: [0, 4] },
|
|
});
|
|
const fixture = safetensorsFixture(
|
|
header.padEnd(length, " "),
|
|
Buffer.alloc(4),
|
|
);
|
|
const { provider, path } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value).toMatchObject({ format: "safetensors" });
|
|
expect(result.value.tensors.map(({ name }) => name)).toEqual(["weight"]);
|
|
},
|
|
);
|
|
|
|
it.each([
|
|
// Protocol 2 pickle of {"a": 1}: PROTO 2, EMPTY_DICT, BINPUT 0, ...
|
|
["a ZIP local header", Buffer.from("504b0304140000000000", "hex")],
|
|
["a short ZIP signature", Buffer.from("504b0304", "hex")],
|
|
[
|
|
"a ZIP signature followed by a brace and an inadmissible length",
|
|
Buffer.from("504b0304140000007b", "hex"),
|
|
],
|
|
["a real pickle", Buffer.from("80027d710058010000006171014b01732e", "hex")],
|
|
// Protocol 2 pickle of {}: six bytes, shorter than a safetensors prefix.
|
|
["an empty dict", Buffer.from("80027d71002e", "hex")],
|
|
// Protocol 4 FRAME pickle of {"a": 1}.
|
|
[
|
|
"a protocol 4 frame",
|
|
Buffer.from("8004950a000000000000007d948c0161944b01732e", "hex"),
|
|
],
|
|
// The magic number torch.save writes first in its legacy format.
|
|
[
|
|
"the legacy torch.save magic",
|
|
Buffer.from("80028a0a6cfc9c46f9206aa850192e", "hex"),
|
|
],
|
|
// Protocol 2 pickle of "x{": its brace lands at offset 8.
|
|
[
|
|
"a brace after an inadmissible length",
|
|
Buffer.from("80025802000000787b71002e", "hex"),
|
|
],
|
|
[
|
|
"an in-file length without a JSON brace",
|
|
Buffer.concat([
|
|
Buffer.from("8002000000000000", "hex"),
|
|
Buffer.alloc(644, 0x2e),
|
|
]),
|
|
],
|
|
] as const)(
|
|
"refuses pickle protocol bytes followed by %s",
|
|
async (_case, bytes) => {
|
|
const { provider, path } = await providerAt(bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Pickle admitted");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "AnalysisUnsupportedTargetError",
|
|
reason: expect.stringContaining("PyTorch pickle"),
|
|
});
|
|
},
|
|
);
|
|
|
|
it("reports a truncated safetensors header whose length resembles a pickle marker as malformed", async () => {
|
|
const fixture = safetensorsFixture(
|
|
JSON.stringify({
|
|
weight: { dtype: "F32", shape: [1], data_offsets: [0, 4] },
|
|
}).padEnd(896, " "),
|
|
Buffer.alloc(4),
|
|
);
|
|
const { provider, path } = await providerAt(fixture.bytes.subarray(0, 500));
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (result.ok) throw new Error("Truncated model was accepted");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "BinaryTargetError",
|
|
constraint: "file_format_rejected",
|
|
});
|
|
});
|
|
|
|
it("bounds expansion before allocation and distinguishes unsupported pickle and paths", async () => {
|
|
const fixture = ggufFixture();
|
|
fixture.bytes.writeBigUInt64LE(0xffffffffffffffffn, 8);
|
|
const { provider, path, root } = await providerAt(fixture.bytes);
|
|
const huge = await provider.inspect({ path, hash: "header" });
|
|
if (huge.ok) throw new Error("Huge count admitted");
|
|
expect(huge.error._tag).toBe("BinaryTargetError");
|
|
await writeFile(path, Buffer.from([0x80, 4, 0, 0]));
|
|
const pickle = await provider.inspect({ path, hash: "header" });
|
|
if (pickle.ok) throw new Error("Pickle admitted");
|
|
expect(pickle.error._tag).toBe("AnalysisUnsupportedTargetError");
|
|
await writeFile(path, ggufFixture().bytes);
|
|
expect((await provider.inspect({ path, hash: "header" })).ok).toBe(true);
|
|
const alias = join(root, "link");
|
|
await symlink(path, alias);
|
|
const linked = await provider.inspect({ path: alias, hash: "header" });
|
|
if (linked.ok) throw new Error("Selected symlink admitted");
|
|
expect(linked.error.message).toMatch(/symlink|symbolic.link/iu);
|
|
const service = createModelArtifactService();
|
|
onTestFinished(() => service.close());
|
|
const invalid = await service.inspect({
|
|
path: "relative",
|
|
detail: "complete",
|
|
});
|
|
if (invalid.ok) throw new Error("Relative path admitted");
|
|
expect(invalid.error._tag).toBe("AnalysisInputError");
|
|
});
|
|
|
|
it("reads only the exact header, even when it ends in the middle of a normal buffer", async () => {
|
|
const fixture = safetensorsFixture();
|
|
const { path } = await providerAt(fixture.bytes);
|
|
const file = await open(path, "r");
|
|
onTestFinished(() => file.close());
|
|
const requests: [number, number][] = [];
|
|
const read = file.read.bind(file);
|
|
const boundary = {
|
|
read: async (
|
|
buffer: Buffer,
|
|
offset: number,
|
|
length: number,
|
|
position: number,
|
|
) => {
|
|
requests.push([position, length]);
|
|
expect(position + length).toBeLessThanOrEqual(fixture.header.length);
|
|
return read(buffer, offset, length, position);
|
|
},
|
|
} as Pick<typeof file, "read">;
|
|
const reader = new ModelHeaderReader(
|
|
boundary as typeof file,
|
|
fixture.bytes.length,
|
|
);
|
|
await readSafetensorsHeader(reader, await reader.take(4));
|
|
expect(await reader.finish(false)).toMatchObject({
|
|
bytes_read: fixture.header.length,
|
|
header_sha256: hash(fixture.header),
|
|
});
|
|
expect(requests.reduce((n, [, length]) => n + length, 0)).toBe(
|
|
fixture.header.length,
|
|
);
|
|
});
|
|
|
|
it.each(["header", "full"] as const)(
|
|
"classifies real truncation after admission during %s reading as an identity change",
|
|
async (mode) => {
|
|
const fixture = ggufFixture();
|
|
const { path } = await providerAt(fixture.bytes);
|
|
const file = await open(path, "r");
|
|
onTestFinished(() => file.close());
|
|
const admitted = await file.stat();
|
|
const reader = new ModelHeaderReader(file, admitted.size);
|
|
if (mode === "full") await reader.take(fixture.header.length);
|
|
await truncate(path, mode === "header" ? 0 : fixture.header.length);
|
|
const reading = mode === "header" ? reader.take(4) : reader.finish(true);
|
|
await expect(reading).rejects.toMatchObject({ reason: "integrity" });
|
|
},
|
|
);
|
|
|
|
it("keeps GGUF read-ahead inside the directory and hashes precisely that prefix", async () => {
|
|
const fixture = ggufFixture();
|
|
const { path } = await providerAt(fixture.bytes);
|
|
const file = await open(path, "r");
|
|
onTestFinished(() => file.close());
|
|
const read = file.read.bind(file);
|
|
let bytesRead = 0;
|
|
const boundary = {
|
|
read: async (
|
|
buffer: Buffer,
|
|
offset: number,
|
|
length: number,
|
|
position: number,
|
|
) => {
|
|
expect(position + length).toBeLessThanOrEqual(fixture.header.length);
|
|
const result = await read(buffer, offset, length, position);
|
|
bytesRead += result.bytesRead;
|
|
return result;
|
|
},
|
|
} as Pick<typeof file, "read">;
|
|
const reader = new ModelHeaderReader(
|
|
boundary as typeof file,
|
|
fixture.bytes.length,
|
|
);
|
|
await reader.take(4);
|
|
await new GgufHeader(reader).read();
|
|
await reader.finish(false);
|
|
expect(bytesRead).toBe(fixture.header.length);
|
|
});
|
|
|
|
it("inspects a 1 GiB sparse safetensors declaration using only its small header", async () => {
|
|
const dataBytes = 1024 ** 3;
|
|
const fixture = safetensorsFixture(
|
|
JSON.stringify({
|
|
weight: { dtype: "U8", shape: [dataBytes], data_offsets: [0, dataBytes] },
|
|
}),
|
|
Buffer.alloc(0),
|
|
);
|
|
const { path, provider } = await providerAt(fixture.header);
|
|
const file = await open(path, "r+");
|
|
try {
|
|
await file.truncate(fixture.header.length + dataBytes);
|
|
} finally {
|
|
await file.close();
|
|
}
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.artifact.bytes_read).toBe(fixture.header.length);
|
|
expect(result.value.tensors[0]).toMatchObject({
|
|
byte_length: dataBytes,
|
|
parameter_count: String(dataBytes),
|
|
});
|
|
});
|
|
|
|
it("supports true scalar shapes and prototype-named metadata without changing their spelling", async () => {
|
|
const fixture = safetensorsFixture(
|
|
'{"__metadata__":{"__proto__":"raw","constructor":"kept"},"scalar":{"dtype":"F32","shape":[],"data_offsets":[0,4]}}',
|
|
Buffer.alloc(4),
|
|
);
|
|
const { path, provider } = await providerAt(fixture.bytes);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.tensors[0]).toMatchObject({
|
|
shape: [],
|
|
parameter_count: "1",
|
|
byte_length: 4,
|
|
});
|
|
expect(result.value.metadata.map(({ key, value }) => [key, value])).toEqual([
|
|
["__proto__", "raw"],
|
|
["constructor", "kept"],
|
|
]);
|
|
});
|
|
|
|
it("yields while validating a large metadata array, preserves cancellation and releases admission", async () => {
|
|
const f = ggufFixture();
|
|
const count = 1_000_000;
|
|
const fixture = ggufFixture({
|
|
metadata: [
|
|
{
|
|
key: "custom.bools",
|
|
type: 9,
|
|
value: Buffer.concat([
|
|
f.u32(7),
|
|
f.u64(BigInt(count)),
|
|
Buffer.alloc(count),
|
|
]),
|
|
},
|
|
],
|
|
});
|
|
const { path, provider } = await providerAt(fixture.bytes);
|
|
const controller = new AbortController();
|
|
const reason = new Error("stop large array");
|
|
const pending = provider.inspect(
|
|
{ path, hash: "header" },
|
|
{ signal: controller.signal },
|
|
);
|
|
setTimeout(() => controller.abort(reason), 0);
|
|
const result = await pending;
|
|
if (result.ok) throw new Error("Cancellation ignored");
|
|
expect(result.error).toMatchObject({
|
|
_tag: "AnalysisCancelledError",
|
|
cause: reason,
|
|
});
|
|
expect(result.error.cause).toBe(reason);
|
|
await writeFile(path, ggufFixture().bytes);
|
|
const recovered = await provider.inspect({ path, hash: "header" });
|
|
if (!recovered.ok) throw recovered.error;
|
|
expect(recovered.value.tensors).toHaveLength(2);
|
|
});
|
|
|
|
it("retains explicit scoped identity through shared service and preserves caller abort reasons", async () => {
|
|
const fixture = ggufFixture();
|
|
const { path } = await providerAt(fixture.bytes);
|
|
const service = createModelArtifactService();
|
|
onTestFinished(() => service.close());
|
|
const result = await service.inspect({ path, detail: "complete" });
|
|
if (!result.ok) throw result.error;
|
|
expect(result.value.subject).toBeNull();
|
|
expect(
|
|
modelArtifactSchema.parse(result.value.normalized_result).artifact.sha256,
|
|
).toBeNull();
|
|
const full = await service.inspect({
|
|
path,
|
|
hash: "full",
|
|
detail: "complete",
|
|
});
|
|
if (!full.ok) throw full.error;
|
|
expect(full.value.subject?.digest.sha256).toBe(hash(fixture.bytes));
|
|
const controller = new AbortController();
|
|
const reason = new Error("selected caller stop");
|
|
controller.abort(reason);
|
|
const stopped = await service.inspect(
|
|
{ path, detail: "complete" },
|
|
{ signal: controller.signal },
|
|
);
|
|
if (stopped.ok) throw new Error("Cancellation ignored");
|
|
expect(stopped.error.cause).toBe(reason);
|
|
});
|
|
|
|
it.each([false, true])(
|
|
"rejects raw uint64 extents before host conversion (big endian: %s)",
|
|
async (bigEndian) => {
|
|
const maximum = 0xffffffffffffffffn;
|
|
const base = ggufFixture({ bigEndian, tensors: [], metadata: [] });
|
|
const countCases = [8, 16].map((offset) => {
|
|
const bytes = Buffer.from(base.bytes);
|
|
(bigEndian
|
|
? bytes.writeBigUInt64BE.bind(bytes)
|
|
: bytes.writeBigUInt64LE.bind(bytes))(maximum, offset);
|
|
return bytes;
|
|
});
|
|
const tensor = ggufFixture({
|
|
bigEndian,
|
|
metadata: [],
|
|
tensors: [{ name: "x", type: 0, shape: [1n], offset: 0n, bytes: 4 }],
|
|
});
|
|
base.u64(maximum).copy(tensor.bytes, tensor.header.length - 8);
|
|
const cases = [
|
|
tensor.bytes,
|
|
...countCases,
|
|
ggufFixture({
|
|
bigEndian,
|
|
tensors: [],
|
|
metadata: [{ key: "value", type: 8, value: base.u64(maximum) }],
|
|
}).bytes,
|
|
ggufFixture({
|
|
bigEndian,
|
|
tensors: [],
|
|
metadata: [
|
|
{
|
|
key: "array",
|
|
type: 9,
|
|
value: Buffer.concat([base.u32(0), base.u64(maximum)]),
|
|
},
|
|
],
|
|
}).bytes,
|
|
];
|
|
for (const bytes of cases) {
|
|
const { provider, path } = await providerAt(bytes);
|
|
expect(await provider.inspect({ path, hash: "header" })).toMatchObject({
|
|
ok: false,
|
|
error: { _tag: "BinaryTargetError" },
|
|
});
|
|
}
|
|
},
|
|
);
|
|
|
|
it("rejects impossible safetensors header and data extents before numeric conversion", async () => {
|
|
const prefix = Buffer.alloc(8);
|
|
prefix.writeBigUInt64LE(0xffffffffffffffffn);
|
|
const header = Buffer.from(
|
|
'{"x":{"dtype":"F32","shape":[1],"data_offsets":[0,18446744073709551615]}}',
|
|
);
|
|
const length = Buffer.alloc(8);
|
|
length.writeBigUInt64LE(BigInt(header.length));
|
|
for (const bytes of [
|
|
Buffer.concat([prefix, Buffer.from("{")]),
|
|
Buffer.concat([length, header, Buffer.alloc(4)]),
|
|
]) {
|
|
const { provider, path } = await providerAt(bytes);
|
|
expect(await provider.inspect({ path, hash: "header" })).toMatchObject({
|
|
ok: false,
|
|
error: { _tag: "BinaryTargetError" },
|
|
});
|
|
}
|
|
});
|
|
|
|
it("rejects a tensor directory whose old 20-byte estimate fits but fixed fields do not", async () => {
|
|
const header = Buffer.alloc(24);
|
|
header.write("GGUF");
|
|
header.writeUInt32LE(3, 4);
|
|
header.writeBigUInt64LE(65537n, 8);
|
|
const { provider, path } = await providerAt(header);
|
|
await truncate(path, 24 + 65537 * 20);
|
|
expect(await provider.inspect({ path, hash: "header" })).toMatchObject({
|
|
ok: false,
|
|
error: { _tag: "BinaryTargetError" },
|
|
});
|
|
});
|
|
|
|
it("retains decoded counts when a physically fitting GGUF header exceeds the header budget", async () => {
|
|
const count = 4_166_667;
|
|
const header = Buffer.alloc(24);
|
|
header.write("GGUF");
|
|
header.writeUInt32LE(3, 4);
|
|
header.writeBigUInt64LE(BigInt(count), 8);
|
|
const { provider, path } = await providerAt(header);
|
|
await truncate(path, header.length + count * 24);
|
|
const result = await provider.inspect({ path, hash: "header" });
|
|
expect(result).toMatchObject({
|
|
ok: false,
|
|
error: {
|
|
_tag: "AnalysisResourceConstraintError",
|
|
partialObservation: {
|
|
normalized_result: {
|
|
declared_tensor_count: count,
|
|
declared_metadata_count: 0,
|
|
},
|
|
},
|
|
},
|
|
});
|
|
});
|