8 Commits

Include renames

Author	SHA1	Message	Date
snowspeeder	a4ae96f01b	feat: default to qwen2.5-vl-3b and cap tool schema length constraints ... - Default LLM_MODEL to qwen2.5-vl-3b across agent, task worker, tests, compose, workflow, and docs - Cap min/max length-style constraints in tool schemas to 1000 before LLM requests; llama.cpp rejects grammar repetitions >= 2000 and the memory MCP's update_note body maxLength (200000) broke qwen2.5-vl-3b with 'Failed to initialize samplers: failed to parse grammar'	2026-08-29 12:46:20 -04:00
snowspeeder	360e3276b0	feat: switch LLM to OpenWebUI with live model selection ... - Point the agent at OpenWebUI's OpenAI-compatible API (LLM_BASE_URL, LLM_API_KEY, LLM_MODEL) with GEMMA_* env fallbacks - Add list_available_models() fetching {base_url}/models, filtering non-chat ids (embedding/reranker) - Rename GemmaLLM -> HopeLLM with update_options(model=...) for runtime model switching (mutates _opts.model) and instance-based compaction - Data channel: agent publishes {type: models} after connect and on get_models; set_model switches live and acks model_changed - Web UI: Brain section in the settings sheet with a model picker that persists the choice in localStorage - Update tests, CI workflow env, and docs for the new endpoint	2026-08-29 12:09:03 -04:00
snowspeeder	024c42ffb1	fix: require usable recipe task results	2026-08-29 08:16:48 -04:00
snowspeeder	63e15b6023	fix: restore controls after task completion	2026-08-29 07:57:23 -04:00
snowspeeder	120ab192f1	feat: add seamless text and voice chat	2026-08-29 07:49:29 -04:00
snowspeeder	321421e37f	fix: reliably dispatch and return background tasks	2026-08-29 07:29:38 -04:00
Shane	44e8d05e2c	feat: background task dispatch system with live UI panel ... - agent/task_registry.py: file-based JSONL event registry (cross-process) - agent/task_worker.py: autonomous LLM loop with weather/time/memory/web tools - agent/dispatch_mcp.py: MCP tool exposing dispatch_task to the main agent - agent/agent.py: registers dispatch toolset, polls task events → room data - web: slide-out task panel (FAB button + badge), live step streaming via data channel topic 'tasks', status dots (running/completed/failed) - Dockerfile: copies new task_*.py and dispatch_mcp.py files The dispatch MCP runs in its own process; events flow through /tmp/tasks/events.jsonl which the main agent tails every second and forwards to the browser. Tasks run up to 10 LLM iterations with tool calls.	2026-08-22 18:06:23 -04:00
Shane	d372adca7d	fix: strengthen memory tool prompt — Gemma 4B needs explicit examples ... The 4B model was responding conversationally instead of calling memory_save/ memory_recall. Added imperative language (MUST call), concrete examples of trigger phrases, and explicit instructions to never skip the tool call. Verified: model now reliably generates tool_calls for save/recall/list.	2026-08-22 17:42:26 -04:00