wrolpi/modules/ai/__init__.py

from modules.ai.api import ai_bp  # noqa
from modules.ai.downloader import ModelDownloader  # noqa  Instantiation registers the downloader.
from modules.ai import service  # noqa  Import registers the idle-unload perpetual worker.
ai: add the /api/ai blueprint, the read-only LLM tool catalog Lean, flat, LLM-shaped read-only endpoints over the library: global, video, archive, and doc search; paged captions, archive text, and zim entries; collections, inventories, and a media-directory text reader. Links are server-computed; big content is paged, never truncated. This ports the formatting layer from wrolpi_mcp (untouched for now) into tested code. First phase of ai.md. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> 2026-08-25 21:03:11 -06:00			`from modules.ai.api import ai_bp # noqa`
ai: ai.yaml config, model catalog, and the GGUF downloader 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> 2026-08-25 21:21:34 -06:00			`from modules.ai.downloader import ModelDownloader # noqa Instantiation registers the downloader.`
ai: package llama-server for all three deployments, with idle unload install_llama_cpp.sh builds llama-server from the SHA-pinned v0.3.0 source tarball (single source of truth: on-device upgrade, Pi image, Live ISO, and the new docker/llm container all call it; version-marker makes re-runs no-ops). start_llama_server.sh refuses to start unless ai.yaml enables AI and the active model file exists — which also covers unmounted media. wrolpi-llm.service is installed but deliberately never enabled at boot: the Controller starts it on demand (registered in managed_services; the llm compose service follows the samba pattern), and the API's perpetual idle-unload worker asks the Controller to stop it after the configured idle minutes. llama-server is localhost-only natively, internal-network-only in docker, and never proxied by Caddy. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> 2026-08-25 21:36:00 -06:00			`from modules.ai import service # noqa Import registers the idle-unload perpetual worker.`