ZacharyZhang-NY
9fe13fffb3
A cartridge used to be an export: materialize it, hash it, and never let it
change behaviour again. The transactive-memory promise needs the opposite —
mounting the home cartridge must make the work cartridge's memories
unfindable, and appending to a cartridge must make a new memory findable
through it.
Cartridge scope (schema v2 -> v3):
- cartridge_atoms (which atoms are in which cartridge) and cartridge_mounts
(which cartridges this machine has mounted now); both rebuilt on reopen,
because a mount is a machine-local state, not a fact about the data.
- mount / switch / unmount / append refuse a cartridge that was built for a
different runtime, naming every differing field instead of a boolean.
- append rewrites atoms.parquet and sparse_index.bm25.zst, recomputes DNA and
the KV fingerprint, and keeps the cartridges row in one SQLite transaction;
the files are written first so a failed export cannot leave a half-cartridge
in the database.
- RetrievalService.search() now ranks inside the mounted scope by default, and
an explicit cartridge_ids filter overrides the mount. Nothing mounted means
the whole library, so an empty store behaves as it did before.
- forget() removes the forgotten atoms from every cartridge's membership:
forgetting must not leave a memory retrievable through a cartridge.
KV fingerprint (kv_fingerprint.py, stored in the manifest):
- model / tokenizer / chat-template hashes, the RoPE block (factor,
original_max_position_embeddings, mrope_interleaved, mrope_section,
partial_rotary_factor), the adapter hash, the context length, the engine
version, and the fingerprint format version.
- A snapshot we cannot read is recorded as unverifiable and listed in
unverifiable_fields; a blind machine refuses to mount rather than pretending
the runtime matches, because a wrong RoPE factor silently corrupts retrieval.
Two defects found by running the new tests, not by reading:
- atoms.parquet could not export a memory at all: pyarrow refuses a struct with
no child field, so metadata={} failed the whole table. The six JSON columns
are now written as JSON text and decoded by the cartridge reader.
- materialize() inserted cartridge membership before the cartridges row existed,
so the foreign key rejected every cartridge.
api.py crossed 500 lines, so the cartridge and mount routes moved to
api_cartridges.py. That module must not use `from __future__ import
annotations`: FastAPI then resolves Depends(settings_dep) against module
globals, where the injected dependency is only a parameter of register(), and
every route starts demanding settings as a query parameter.
Verification: 138 pytest passed (26 new: 10 fingerprint, 16 scope), Go
build/vet/gofmt/test clean, and scripts/mcp_write_smoke.sh now proves the whole
loop across two processes - mount narrows search, a memory written after the
upload is invisible until append_to_cartridge, unmount restores the library,
and rewriting the RoPE factor makes mount_cartridge refuse with "rope: factor:
cartridge 4.0 vs local 2.0". ruff clean on every touched file (the 20 remaining
package errors are in files this change did not touch; HEAD had 25). mypy: one
error, the pre-existing np.savez stub artifact at cartridge_assets.py:329
(HEAD:320). Repo pyright: 62 errors, unchanged from the p0-3 ledger.
54 lines
1.5 KiB
Python
54 lines
1.5 KiB
Python
"""Shared fixtures: a model snapshot the fingerprint can read without a 9B download."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from collections.abc import Callable
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
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")
|