mirror of
https://github.com/lrnselfreliance/wrolpi.git
synced 2026-10-26 19:01:39 -04:00
2f27ce49a7
ai.yaml is the source of truth (opt-in: enabled=False by default) with active model, idle-unload minutes, context override, and tool-call bound. The model catalog follows the map pattern: a bundled constant keeps the Manage tab working offline, the CDN manifest (ai/models.json + detached GPG signature) wins when reachable. GGUF downloads clone the map-extract flow — the per-file meta4 is GPG-verified once and the same bytes handed to aria2c, so the verified hash is the enforced one; unverified downloads are refused. Models land in <media>/ai/models/ (gated by the existing media_mounted download rules). Manage endpoints (catalog with RAM-tier recommendation, settings) live under /api/ai/manage/ which the future agent loop excludes from its tool catalog. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2 lines
140 B
Python
2 lines
140 B
Python
from modules.ai.api import ai_bp # noqa
|
|
from modules.ai.downloader import ModelDownloader # noqa Instantiation registers the downloader.
|