TaskWorker resolved its model from LLM_MODEL env (frozen at MCP spawn),
so after a live set_model switch in the UI, dispatched background tasks
still asked for the old model. On local-vl-models (llama-swap
--models-max 1) that forces a swap against the loaded conversation
model; a force-kill mid-load surfaces as 400 'model failed to load'.
The agent now writes the selected model to <task_dir>/model.txt at
session start and on every switch; TaskWorker reads it with the env
value as fallback.
Background research tasks were producing garbage or failing because the
self-hosted Firecrawl /v1/scrape defaults to a ~30s timeout that's too short
for heavy news/research sites, and the small LLM won't reliably chain a
second scrape call after a search that only returns snippets.
task_worker.py:
- web_search now auto-fetches the top results directly from the container
(which has working outbound internet) and returns their real text, so the
model gets actual page content in one call instead of snippet echoes.
- web_scrape requests timeout: 90000 (Firecrawl renders heavy sites but needs
>30s), and falls back to a direct container fetch with tag-stripping if
Firecrawl times out or returns nothing.
task_registry.py / dispatch_mcp.py:
- Add task_status(id) and list_tasks() tools so Hope can check the live state
of any dispatched task (pending / running / completed / failed / STALLED).
- Track last_activity per task and surface a stall heuristic.
- Move the status summary into task_registry (no mcp dependency) so it's
unit-testable.
agent.py: prompt tells Hope about task_status / list_tasks.
tests: add task-status summary and last-activity regression tests.
- 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'
- 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
- 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.
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.
snowspeeder
Shane