Roland 82e11cbaba ai: keep slow-CPU chat streams alive ... On the FX-8320 the first token took over a minute, and Sanic's default 60-second RESPONSE_TIMEOUT killed the stream before anything was sent. Raise the timeout above the chat loop's own 600s hard ceiling, and emit a status event before every model call so the stream is never silent — for proxies and for the user staring at a slow machine. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>		2026-09-24 14:09:55 -06:00
..
__init__.py	ai: add the /api/ai blueprint, the read-only LLM tool catalog	2026-09-24 14:09:52 -06:00
test_agent.py	ai: the /api/chat agent loop — SSE streaming, modes, tool execution	2026-09-24 14:09:54 -06:00
test_api.py	ai: wrolpi_mcp becomes a thin proxy over /api/ai	2026-09-24 14:09:54 -06:00
test_chat_api.py	ai: keep slow-CPU chat streams alive	2026-09-24 14:09:55 -06:00
test_config_catalog.py	ai: ai.yaml config, model catalog, and the GGUF downloader	2026-09-24 14:09:53 -06:00
test_help_docs.py	ai: live-chat fixes from first real-model run	2026-09-24 14:09:55 -06:00
test_lib.py	ai: ground the librarian — collection links, retry hints, no source URLs	2026-09-24 14:09:55 -06:00
test_mcp_parity.py	ai: wrolpi_mcp becomes a thin proxy over /api/ai	2026-09-24 14:09:54 -06:00
test_service.py	ai: package llama-server for all three deployments, with idle unload	2026-09-24 14:09:54 -06:00
test_system_api.py	ai: system endpoints — aggregate status, services, logs, disks	2026-09-24 14:09:53 -06:00