root 45dd793b69 fix: sidecar process kill was not awaiting wait() — old server held GPU VRAM ... - _kill_llama_server() was sync calling an unawaited coroutine. process.wait() created a discarded coroutine object — the old llama-server was never waited on to release GPU memory before starting a new one, causing OOM on rapid model switches. Fixed with async await + 10s SIGTERM timeout + SIGKILL fallback. - Changed _switch_lock from threading.Lock to asyncio.Lock() to prevent event loop deadlock during long switch operations. - Router proxy: only trigger model switches for POST /v1/chat/completions and /v1/completions. Non-chat endpoints (GET probes, /api/show) no longer trigger unwanted model reloads. - _ollama_show_lookup: return active profile context size when model_name is empty. Previously returned 404, causing Hermes Desktop to default to 256k context. - Always drain_queue() + complete_switch() after switch failure so queued requests don't hang forever waiting on a never-set switching event.		2026-06-17 23:49:57 +00:00
..
__init__.py	Epic: Model Switching via Sidecar — Issues #2-#3	2026-06-15 00:49:24 +00:00
app.py	fix: sidecar process kill was not awaiting wait() — old server held GPU VRAM	2026-06-17 23:49:57 +00:00
manifest.py	Epic: Model Switching via Sidecar — Issues #2-#3	2026-06-15 00:49:24 +00:00