Resolve adapters by what is mounted, and say why each kind is not loaded

runtime.py resolved adapters at 7 call sites and only ever looked in the
adapter library, so an adapter attached to a cartridge (cartridge.py:230
copies it into <cartridge>/adapters/{kind}/) was never loaded by anything.
Resolution now lives in adapters.py: it reads the mounted cartridge set,
prefers a mounted cartridge's copy over the library, and answers every one
of the six kinds with a state the facts support — loaded, available,
deferred (base_model mismatch or missing weights, both models named in the
reason), missing — plus a shadowed row for each adapter that lost the
choice. A mounted cartridge is the scenario selection; neither manifest
carries a scenario field, so none was invented.

Two bugs the new tests caught: the preference sort lost reverse=True, so a
library adapter beat a mounted cartridge's copy, and the load branch had
never been executed by a test. Stub weights now prove peft is asked to
attach, that the returned model is put in eval mode, and that the endpoint
reports loaded until unload clears it.

Faces: GET /api/runtime/adapters, `ely-eye adapters`, and a log line naming
the reason whenever a generation runs without an adapter.

Gates: 222 passed; ruff clean; mypy cold cache on the 7 touched files gives
the same 2 errors as HEAD's runtime.py, and pyright gives the same 2 as
HEAD — both are qwen_vl_utils typing artifacts (process_vision_info returns
2 or 3 values depending on return_video_kwargs; the product takes 2).
This commit is contained in:
ZacharyZhang-NY committed 2026-10-07 23:09:28 -04:00
1 parent 9f0f7993e5
commit 2fbb4af96b
8 files changed
+585 -86

No files matched your search

+229
View File
@@ -0,0 +1,229 @@
"""One place decides which adapter loads, and says out loud why the others do not."""
from __future__ import annotations
import logging
from dataclasses import dataclass
from datetime import datetime
from pathlib import Path
from typing import Any
from pydantic import ValidationError
from . import cartridge_store
from .config import Settings
from .db import Database
from .runtime_schemas import AdapterChoice, AdapterLoadReport, AdapterOrigin, AdapterState
from .schemas import AdapterManifest, TrainingAdapterKind
logger = logging.getLogger("ely_eye.adapters")
MANIFEST_FILE = "adapter_manifest.json"
WEIGHTS_FILE = "adapter_model.safetensors"
@dataclass(frozen=True)
class AdapterSource:
"""One adapter found on disk, plus where it was found."""
path: Path
manifest: AdapterManifest
origin: AdapterOrigin
cartridge_id: str | None
@dataclass(frozen=True)
class LoadRecord:
"""An adapter this process actually attached to a live model."""
kind: TrainingAdapterKind
adapter_id: str
path: str
sha256: str
loaded_at: str
_LOADED: dict[str, LoadRecord] = {}
def read_manifest(path: Path) -> AdapterManifest:
try:
text = path.read_text(encoding="utf-8")
except OSError as error:
raise ValueError(f"{path}: the adapter manifest cannot be read ({error})") from error
try:
return AdapterManifest.model_validate_json(text)
except ValidationError as error:
raise ValueError(f"{path}: the adapter manifest is not a valid AdapterManifest ({error})") from error
def cartridge_roots(database: Database) -> dict[str, Path]:
roots: dict[str, Path] = {}
for row in database.list_cartridges():
roots[str(row["cartridge_id"])] = Path(str(row["root_path"]))
return roots
def library_sources(settings: Settings) -> list[AdapterSource]:
"""Adapters in the library directory, for callers that have no database open."""
if settings.adapter_dir is not None:
pinned = settings.adapter_dir.expanduser()
if not (pinned / MANIFEST_FILE).exists():
logger.warning("adapter_dir %s holds no %s", pinned, MANIFEST_FILE)
return []
manifest = read_manifest(pinned / MANIFEST_FILE)
return [
AdapterSource(
path=pinned,
manifest=manifest,
origin="library",
cartridge_id=manifest.cartridge_id,
)
]
sources: list[AdapterSource] = []
for manifest_path in sorted(settings.adapters_dir.glob(f"*/{MANIFEST_FILE}")):
manifest = read_manifest(manifest_path)
sources.append(
AdapterSource(
path=manifest_path.parent,
manifest=manifest,
origin="library",
cartridge_id=manifest.cartridge_id,
)
)
return sources
def discover(settings: Settings, database: Database) -> tuple[list[AdapterSource], list[str]]:
"""Every adapter the runtime could use: the library plus the copies inside mounted cartridges."""
mounted = cartridge_store.mounted_ids(database)
roots = cartridge_roots(database)
sources = library_sources(settings)
for cartridge_id in mounted:
root = roots.get(cartridge_id)
if root is None:
logger.warning("cartridge %s is mounted but its directory is not registered", cartridge_id)
continue
for manifest_path in sorted((root / "adapters").glob(f"*/{MANIFEST_FILE}")):
sources.append(
AdapterSource(
path=manifest_path.parent,
manifest=read_manifest(manifest_path),
origin="cartridge",
cartridge_id=cartridge_id,
)
)
return sources, mounted
def resolve(
sources: list[AdapterSource],
settings: Settings,
kind: TrainingAdapterKind,
) -> tuple[AdapterSource | None, AdapterState, str]:
"""Pick the adapter to load for one kind, or say which state it is stuck in and why."""
candidates = [source for source in sources if source.manifest.kind == kind]
if not candidates:
return None, "missing", f"no adapter of kind {kind.value} is on disk"
matching = [source for source in candidates if source.manifest.base_model == settings.model_id]
if not matching:
trained_on = ", ".join(sorted({source.manifest.base_model for source in candidates}))
return (
None,
"deferred",
f"every {kind.value} adapter is trained on {trained_on}; the runtime holds {settings.model_id}",
)
ready = [source for source in matching if (source.path / WEIGHTS_FILE).exists()]
if not ready:
return None, "deferred", f"the {kind.value} manifests are present but none carries {WEIGHTS_FILE}"
ready.sort(key=_preference, reverse=True)
chosen = ready[0]
if chosen.origin == "cartridge":
return chosen, "available", f"selected from mounted cartridge {chosen.cartridge_id}"
return chosen, "available", "selected from the adapter library"
def resolve_library_adapter(
settings: Settings,
kind: TrainingAdapterKind = TrainingAdapterKind.hme_core_lora,
) -> tuple[AdapterSource | None, AdapterState, str]:
"""Resolution without a database: the library only, no mounted cartridges."""
return resolve(library_sources(settings), settings, kind)
def _preference(source: AdapterSource) -> tuple[bool, float]:
weights = source.path / WEIGHTS_FILE
return (source.origin == "cartridge", weights.stat().st_mtime if weights.exists() else 0.0)
def load_records() -> list[LoadRecord]:
return list(_LOADED.values())
def clear_loads() -> None:
_LOADED.clear()
def record_load(source: AdapterSource) -> LoadRecord:
record = LoadRecord(
kind=source.manifest.kind,
adapter_id=source.manifest.adapter_id,
path=str(source.path),
sha256=source.manifest.sha256,
loaded_at=datetime.now().astimezone().isoformat(),
)
_LOADED[record.kind.value] = record
logger.info("loaded adapter %s (%s) from %s", record.adapter_id, record.kind.value, record.path)
return record
def load_into_model(model: Any, path: Path) -> Any:
"""Attach one LoRA to a live model; the only place generation imports peft."""
from .training import bitsandbytes_gaudi_probe_guard
with bitsandbytes_gaudi_probe_guard():
from peft import PeftModel
return PeftModel.from_pretrained(model, str(path))
def plan(settings: Settings, database: Database) -> AdapterLoadReport:
"""One row per adapter kind, plus a row for every adapter that lost the choice."""
sources, mounted = discover(settings, database)
rows: list[AdapterChoice] = []
for kind in TrainingAdapterKind:
source, state, reason = resolve(sources, settings, kind)
record = next((item for item in load_records() if item.kind == kind), None)
if record is not None:
reason = f"attached to the live model from {record.path}"
state = "loaded"
rows.append(
AdapterChoice(
kind=kind,
state=state,
reason=reason,
path=str(source.path) if source else None,
adapter_id=source.manifest.adapter_id if source else None,
base_model=source.manifest.base_model if source else settings.model_id,
origin=source.origin if source else None,
cartridge_id=source.cartridge_id if source else None,
)
)
chosen_paths = {row.path for row in rows if row.path}
for source in sources:
if str(source.path) in chosen_paths:
continue
rows.append(
AdapterChoice(
kind=source.manifest.kind,
state="deferred",
reason="another adapter of this kind wins for the current mount",
path=str(source.path),
adapter_id=source.manifest.adapter_id,
base_model=source.manifest.base_model,
origin=source.origin,
cartridge_id=source.cartridge_id,
shadowed=True,
)
)
return AdapterLoadReport(model_id=settings.model_id, mounted=mounted, adapters=rows)