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>

app/schemas.py

@@ -87,6 +87,8 @@ class WsFrameType(str, Enum):
     journey_reply = "journey_reply"
     # ── v5 brief frame types ──────────────────────────────────────────
     brief_request = "brief_request"
+    # ── v6 task brief frame types ─────────────────────────────────────
+    task_brief_request = "task_brief_request"
 
 
 class WsToolCall(BaseModel):
@@ -209,6 +211,7 @@ class WsStreamEnd(BaseModel):
     type: Literal[WsFrameType.stream_end] = WsFrameType.stream_end
     request_id: str
     error: str | None = None
+    mutations: list[dict[str, Any]] | None = None
 
 
 class WsDomain(BaseModel):