adiuvAI/api
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
- 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>
This commit is contained in:
Roberto
2026-05-04 15:09:58 +02:00
parent 6f4c68b359
commit 67562b8092
9 changed files with 427 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
app/core/llm.py
View File

@@ -107,6 +107,7 @@ _AGENT_MODEL_SETTINGS: dict[str, Callable[[], str]] = {
"unified-processor": lambda: settings.LLM_MODEL_UNIFIED_PROCESSOR or settings.LLM_MODEL,
"cloud-processor": lambda: settings.LLM_MODEL_CLOUD_PROCESSOR or settings.LLM_MODEL,
"brief-agent": lambda: settings.LLM_MODEL_BRIEF_AGENT or settings.LLM_MODEL,
"task-brief-agent": lambda: settings.LLM_MODEL_TASK_BRIEF_AGENT or settings.LLM_MODEL,
"setup": lambda: settings.LLM_MODEL_SETUP_AGENT or settings.LLM_MODEL,
"memory-extractor": lambda: settings.LLM_MODEL_MEMORY_EXTRACTOR or "gpt-4o-mini",
"memory-miner": lambda: settings.LLM_MODEL_MEMORY_MINER or "gpt-4o-mini",