pyr0ball bd132851ec fix(orch): tighten VRAM pre-flight to require full max_mb free (not half) ... max_mb // 2 was too loose — Qwen2.5-3B needs ~5.9 GB on an 8 GB card but the threshold only required 3.25 GB free, allowing Ollama to hold 4.5 GB while a load attempt was still dispatched (causing OOM crash). - node_selector: can_fit = free_mb >= service_max_mb (was // 2) - coordinator /start: same threshold fix + updated error message - tests: two new node_selector tests pin the full-ceiling semantics; updated stale docstring in coordinator app test		2026-04-02 16:44:36 -07:00
..
test_resources	fix(orch): tighten VRAM pre-flight to require full max_mb free (not half)	2026-04-02 16:44:36 -07:00
test_tasks	fix(tasks): fix VRAM accounting race, lock scope, type annotations	2026-03-31 09:15:09 -07:00
__init__.py	feat: scaffold circuitforge-core package	2026-03-25 11:02:26 -07:00
test_config.py	feat: add config module and vision router stub	2026-03-25 11:08:03 -07:00
test_db.py	feat: add db base connection and migration runner	2026-03-25 11:03:35 -07:00
test_llm_router.py	feat: add LLM router (extracted from Peregrine)	2026-03-25 11:06:29 -07:00
test_stubs.py	feat: add wizard and pipeline stubs	2026-03-25 11:09:40 -07:00
test_tiers.py	feat: add generalised tier system with BYOK and local vision unlocks	2026-03-25 11:04:55 -07:00