curo1305 40aa934431 fix(setup): filter LM Studio models by state == "loaded_instance" ...

LM Studio's /v1/models returns all downloaded models, not just loaded
ones. Use /api/v0/models with state filtering in both fetch_loaded_models()
and _fetch_local_models() so only RAM-resident models are shown as loaded.
This also restores the _choose_model() fallback that offers downloaded-but-
unloaded models when nothing is active in LM Studio.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-05-19 14:54:06 +02:00

..

integration

feat(setup): dynamic model discovery for local providers in wizard

2026-05-19 10:53:15 +02:00

security

feat(plugins): Stage 2.1 — plugin framework and AI tool-use

2026-05-17 15:35:20 +02:00

unit

fix(setup): filter LM Studio models by state == "loaded_instance"

2026-05-19 14:54:06 +02:00

__init__.py

chore: init project skeleton

2026-05-17 12:48:32 +02:00

conftest.py

test: add memory database tests and update conftest for DB isolation

2026-05-18 15:23:57 +02:00