ZacharyZhang-NY
9145a23f18
Sixteen mutating routes now refuse a caller who cannot present the token the server started with; queries stay open, because a question is not a write. The environment variable is ELY_EYE_AUTH_TOKEN, following the repo's env_prefix convention — the shorter name I reached for first returned 403 where the smoke expected 401, and the server printed the reason. Words from a stranger are quarantined on the way in: an HTTP upload is third_party by definition, and a sentence carrying an instruction-shaped phrase is quarantined whoever wrote it. A quarantined atom stays findable and stays out of the compiled context until a second, live, unquarantined source agrees with its rarest words. Corroboration is computed at read time because it is a property of the corpus now, not of the moment a memory was written; it is term-level, and the docstring says so. forget now erases the source row and the compiled contexts beside the atoms, so a forgotten memory leaves nothing that can still speak. The semantic cache key carries a store revision, which fixes a real staleness: a context compiled before new evidence arrived kept its old quarantine decision forever. bench.audit --product still pointed at evals.py, which the p1-6 split moved into backend/src/ely_eye/proofs/. It failed fast, but the anti-self-justification rule had quietly stopped auditing the product; it now walks the package, and a test pins that the package exists and holds no re-roll. Gates: pytest 306 passed; ruff clean; mypy cold cache 24 errors in 9 files, the recorded baseline, net zero; pyright 0 errors on the 23 backend files and the 2 bench files; go build/vet/test and gofmt clean; npm run build 221.39 kB with eslint exit 0; bench/filesize_check clean; bench.audit --product clean over 31 harness files; scripts/mcp_write_smoke.sh PASS with the gate live across two servers and the MCP child.
101 lines
2.9 KiB
Python
101 lines
2.9 KiB
Python
"""Shared fixtures: a model snapshot the fingerprint can read without a 9B download."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import hashlib
|
|
import json
|
|
from collections.abc import Callable
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
import numpy as np
|
|
import pytest
|
|
|
|
ROPE: dict[str, Any] = {
|
|
"rope_type": "yarn",
|
|
"factor": 4.0,
|
|
"original_max_position_embeddings": 262_144,
|
|
"mrope_interleaved": True,
|
|
"mrope_section": [11, 11, 10],
|
|
}
|
|
TEMPLATE = "{% for message in messages %}{{ message['content'] }}{% endfor %}"
|
|
|
|
|
|
def write_model(model_dir: Path, **config_overrides: Any) -> Path:
|
|
config: dict[str, Any] = {
|
|
"model_type": "qwen3_5",
|
|
"max_position_embeddings": 262_144,
|
|
"partial_rotary_factor": 0.25,
|
|
"rope_parameters": dict(ROPE),
|
|
"chat_template": TEMPLATE,
|
|
}
|
|
config.update(config_overrides)
|
|
model_dir.mkdir(parents=True, exist_ok=True)
|
|
(model_dir / "config.json").write_text(json.dumps(config), encoding="utf-8")
|
|
(model_dir / "tokenizer.json").write_text('{"version": "1.0"}', encoding="utf-8")
|
|
(model_dir / "model.safetensors.index.json").write_text(
|
|
json.dumps({"metadata": {}, "weight_map": {"model-00001.safetensors": "0"}}),
|
|
encoding="utf-8",
|
|
)
|
|
return model_dir
|
|
|
|
|
|
@pytest.fixture
|
|
def chat_template() -> str:
|
|
return TEMPLATE
|
|
|
|
|
|
@pytest.fixture
|
|
def write_model_fixture() -> Callable[..., Path]:
|
|
return write_model
|
|
|
|
|
|
@pytest.fixture
|
|
def model_dir(tmp_path: Path) -> Path:
|
|
return write_model(tmp_path / "model")
|
|
|
|
|
|
@pytest.fixture
|
|
def write_token() -> str:
|
|
"""The credential a test client presents when it writes; unset, the server takes no writes."""
|
|
return "test-token"
|
|
|
|
|
|
class HashEmbeddings:
|
|
"""A stand-in for the embedding model: the same words give the same vector, no download.
|
|
|
|
Different words land in different directions, which is all a retrieval test needs; the
|
|
numbers mean nothing to a human, so no test should assert on a score's value.
|
|
"""
|
|
|
|
def __init__(self, dim: int = 16) -> None:
|
|
self.dim = dim
|
|
|
|
def enabled(self) -> bool:
|
|
return True
|
|
|
|
def encode_texts(self, texts: list[str]) -> np.ndarray:
|
|
if not texts:
|
|
raise ValueError("encode_texts was asked to encode nothing")
|
|
rows = [
|
|
np.frombuffer(hashlib.sha256(text.encode("utf-8")).digest()[: self.dim], dtype=np.int8).astype(np.float32)
|
|
for text in texts
|
|
]
|
|
matrix = np.stack(rows)
|
|
norms = np.linalg.norm(matrix, axis=1, keepdims=True)
|
|
return matrix / np.where(norms == 0, 1.0, norms)
|
|
|
|
def encode_atoms(self, atoms: list[Any]) -> np.ndarray:
|
|
return self.encode_texts([atom.text or "" for atom in atoms])
|
|
|
|
def embed_query(self, query: str) -> np.ndarray:
|
|
return self.encode_texts([query])[0]
|
|
|
|
def probe_dim(self) -> int:
|
|
return self.dim
|
|
|
|
|
|
@pytest.fixture
|
|
def fake_embeddings() -> Callable[[], HashEmbeddings]:
|
|
return HashEmbeddings
|