feat(autotag): scored suggestions with a configurable count behind a shared model gate

- py/model_gate.py: one process-wide, non-blocking gate for loading,
  swapping, running, downloading and unloading a tagging model. Worker
  calls run shielded; a release requested while one still runs takes
  effect only when it exits (client disconnect keeps the gate).
- Legacy /autotag/single, /start, /download/{type} and /unload hold the
  gate and answer 409 {code: "model-busy"} while another operation holds
  it; their bodies are otherwise unchanged. /autotag/models gains
  suggestion_limit.
- AutoTagService.generate_tag_suggestions: WD14 (name, probability) best
  first, GGUF/HF (name, None) in output order, first `limit` distinct
  case-insensitively; generate_tags keeps its return; the image file is
  closed before inference returns.
- POST /prompt_manager/image-annotations/suggest runs one engine on the
  pinned capture, with strict per-engine options, never downloads
  (409 model-unavailable) and never writes.
- config.json autotag.defaults.suggestion_limit, integer 1..100, default
  10, validated on load.
- Capture probe decides Generate from the image header alone, so prompt
  metadata over the inspection budgets no longer blocks it.
This commit is contained in:
Vito Sansevero
2026-10-22 09:12:01 -07:00
parent 06bd642611
commit 489d449ec8
15 changed files with 1772 additions and 51 deletions
+129
View File
@@ -16,8 +16,18 @@ from pathlib import Path
from aiohttp import web
from .annotation_suggest import (
SUGGEST_FIELDS,
OptionError,
run_suggestions,
suggestion_rows,
unavailable_message,
validate_options,
)
from .autotag_routes import model_busy_response
from .images import _forbidden, _has_traversal, _unavailable_link, _verified_title
from .prompts import bad_request
from .. import model_gate
try:
from ...database.annotations import (
@@ -87,6 +97,7 @@ _STATUS = {
"storage-changed": 409,
"tag-conflict": 409,
"capture-expired": 409,
"model-unavailable": 409,
}
_MESSAGES = {
"source-changed": (
@@ -190,6 +201,9 @@ class AnnotationRoutesMixin:
routes.get(CAPTURE_URL + "{token}")(self.get_capture_preview)
routes.delete(CAPTURE_URL + "{token}")(self.release_capture)
routes.put("/prompt_manager/image-annotations/tags")(self.save_image_tags)
routes.post("/prompt_manager/image-annotations/suggest")(
self.suggest_image_tags
)
# -- capture store lifetime ------------------------------------------------
@@ -474,6 +488,121 @@ class AnnotationRoutesMixin:
{"success": True, **receipt}, headers={"Cache-Control": "no-store"}
)
# -- suggest ---------------------------------------------------------------
async def suggest_image_tags(self, request: web.Request) -> web.Response:
"""POST: the top N tags of the captured bytes from one legacy engine.
Runs only on the private capture (pinned for the whole inference),
under the shared model gate (``model-busy`` while anything else holds
it, including a legacy batch), never downloads (``model-unavailable``)
and never writes.
"""
from ..autotag import MODELS, get_autotag_service
from ..config import MAX_SUGGESTION_LIMIT, AutotagConfig
data, error = await self._annotation_body(request, SUGGEST_FIELDS)
if error is not None:
return error
target, error = _target(data["target"])
if error is not None:
return error
try:
model_type, options = validate_options(
data["model_type"],
data["options"],
default_limit=AutotagConfig.suggestion_limit(),
max_limit=MAX_SUGGESTION_LIMIT,
)
except OptionError as exc:
return bad_request(str(exc))
token, epoch = data["capture_token"], data["expected_epoch"]
if not isinstance(token, str) or _TOKEN.fullmatch(token) is None:
return bad_request("Invalid capture token")
if not isinstance(epoch, str) or _UUID.fullmatch(epoch) is None:
return bad_request("expected_epoch must be a canonical UUID")
index, scope, relative = target
root, error = self._scoped_root(index, scope)
if error is not None:
return error
store = self._captures
capture = store.acquire(token) if store is not None else None
if capture is None:
return _coded("capture-expired")
started = False
try:
error = await self._suggest_guards(capture, target, root, epoch)
if error is not None:
return error
service = get_autotag_service()
status = await self._run_in_executor(service.get_models_status)
if not status.get(model_type, {}).get("downloaded"):
name = MODELS.get(model_type, {}).get("name", model_type)
return _coded("model-unavailable", unavailable_message(name))
owner = model_gate.new_owner("image-annotations")
if not model_gate.try_acquire(owner):
return model_busy_response()
try:
started = True
pairs = await model_gate.run(
owner,
_pinned_suggestions,
store,
token,
service,
capture,
model_type,
options,
)
except Exception:
self.logger.exception("Tag suggestion failed")
return _error(
500,
"suggest-failed",
"Auto-tagging failed. Check server logs for details.",
)
finally:
model_gate.release(owner)
finally:
if not started:
store.release_use(token)
return web.json_response(
{
"success": True,
"model_type": model_type,
"options": options,
"suggestions": suggestion_rows(pairs),
},
headers={"Cache-Control": "no-store"},
)
async def _suggest_guards(self, capture, target, root, epoch):
"""The capture must be this target's, of this epoch, and inferable."""
index, scope, relative = target
expected = os.path.normcase(
os.path.join(os.path.realpath(root), *relative.split("/"))
)
if (
capture.root_index != index
or capture.scope != scope
or capture.locator != expected
):
return _coded("capture-expired", _OTHER_FILE)
if epoch != capture.epoch:
current = await self._run_in_executor(self.db.get_execution_epoch)
return _coded("storage-changed", library_epoch=current)
if not capture.inferable:
return _coded("unsupported-media", capture.inferable_reason)
return None
def _pinned_suggestions(store, token, service, capture, model_type, options):
"""Worker thread: infer on the capture, then end its pin (even on error)."""
try:
return run_suggestions(service, capture.path, model_type, options)
finally:
store.release_use(token)
def _verify_captured_file(store: CaptureStore, capture, root, relative: str):
"""Re-hash the current file, or None when the token names another file.