Add task brief research agent: Stage 1 deep-research + canvas draft emission

- run_task_brief_research() runner with brief-specific tool set and max_steps=12
- New agents: client_agent (list_clients, get_client) and relations_agent (query_relations)
- search_associative tool wrapping MemoryMiddleware semantic search
- BRIEF_RESEARCH_TOOLS constant: read-only task/project/note/timeline + memory + client/relations
- canvas block extraction in output_formatter (splits visible text from <canvas> draft)
- device_ws.py: task_brief_research request type; emits canvas_draft mutation on stream_end
- Stage 2 briefMode: briefing_context injected into floating system prompt when present
- briefingContext kwarg wired through compile_prompt call chain

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.env.example

@@ -56,6 +56,10 @@ LLM_MODEL_CLOUD_PROCESSOR=
 # A small model (e.g. gpt-4o-mini) is sufficient.
 # LLM_MODEL_BRIEF_AGENT=
 
+# Task-brief-agent — per-task deep research (Stage 1 executive assistant).
+# Needs tool-use + reasoning; a capable model recommended (e.g. gpt-4o, gemini-2.5-flash).
+# LLM_MODEL_TASK_BRIEF_AGENT=
+
 # Setup-agent — guided journey to build an AgentConfig via WebSocket chat.
 LLM_MODEL_SETUP_AGENT=