20s was too tight for first-request model swaps in Ollama (model cold load can take 30-60s). 120s matches coordinator inference timeout. |
||
|---|---|---|
| .. | ||
| api | ||
| ingest | ||
| services | ||
| watch | ||
| __init__.py | ||
| mcp_server.py | ||
| rest.py | ||
20s was too tight for first-request model swaps in Ollama (model cold load can take 30-60s). 120s matches coordinator inference timeout. |
||
|---|---|---|
| .. | ||
| api | ||
| ingest | ||
| services | ||
| watch | ||
| __init__.py | ||
| mcp_server.py | ||
| rest.py | ||