Roland f49ae3aee5 ai: live-chat fixes from first real-model run ... Three findings from running Qwen3-1.7B against the docker stack: the llm image lost libgomp when the build tools were removed (llama-server needs the OpenMP runtime); the Help prompt let the small model answer from memory instead of the docs, so it now requires search_help before any answer; and help search results called the slug "doc" while get_help_doc's argument is "slug", so the model invented slugs — the names now match. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>		2026-09-24 18:23:23 -06:00
..
__init__.py	ai: add the /api/ai blueprint, the read-only LLM tool catalog	2026-09-24 18:23:20 -06:00
test_agent.py	ai: the /api/chat agent loop — SSE streaming, modes, tool execution	2026-09-24 18:23:21 -06:00
test_api.py	ai: wrolpi_mcp becomes a thin proxy over /api/ai	2026-09-24 18:23:22 -06:00
test_chat_api.py	ai: the /api/chat agent loop — SSE streaming, modes, tool execution	2026-09-24 18:23:21 -06:00
test_config_catalog.py	ai: ai.yaml config, model catalog, and the GGUF downloader	2026-09-24 18:23:21 -06:00
test_help_docs.py	ai: live-chat fixes from first real-model run	2026-09-24 18:23:23 -06:00
test_lib.py	ai: add the /api/ai blueprint, the read-only LLM tool catalog	2026-09-24 18:23:20 -06:00
test_mcp_parity.py	ai: wrolpi_mcp becomes a thin proxy over /api/ai	2026-09-24 18:23:22 -06:00
test_service.py	ai: package llama-server for all three deployments, with idle unload	2026-09-24 18:23:21 -06:00
test_system_api.py	ai: system endpoints — aggregate status, services, logs, disks	2026-09-24 18:23:21 -06:00