Roberto
052c7e3741
refactor(contextual): drop floating WS frame, runner, and prompt fallback
...
contextual_request + contextual_scope_update are the only WS
flows for ad-hoc contextual chat now. Floating system prompt
constant removed; Langfuse 'floating_system' is deleted in a
separate manual step. Also removes floating-agent LLM slot from
llm.py and the associated LLM_MODEL_FLOATING_AGENT setting entry.
2026-05-15 18:53:01 +02:00
Roberto
67562b8092
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 >
2026-05-04 15:09:58 +02:00
Roberto
6f4c68b359
Update note management from db vector to index
2026-04-30 00:11:17 +02:00
Roberto
ea9094f47f
Add llm providers
2026-04-19 00:32:12 +02:00
Roberto Musso
d5fea95561
Phase 3 — WS frame + REST fallbacka
2026-04-18 22:18:53 +02:00
Roberto Musso
0b5ef48463
Phase 7: audit memory
2026-04-17 22:43:55 +02:00
Roberto Musso
ca8721e1ac
PHASE 5 — Proactive mining (Power tier only)
2026-04-17 17:58:30 +02:00
Roberto Musso
741b9b87fb
PHASE 2 — Mem0-style Extract/Update pipeline
2026-04-16 17:57:49 +02:00
Roberto Musso
3cf067faea
feat: enhance agent configuration and model management with per-agent overrides
2026-04-10 08:45:14 +02:00
Roberto Musso
41db3a7089
update env variables
2026-04-08 23:52:52 +02:00
5bc9ea6cd6
fix: make planner schema copilot-compatible and silence usage warning
2026-03-12 23:17:31 +01:00
9332e29e53
bug fix sending component
2026-03-10 09:11:24 +01:00
ac71d99f9a
add cerebras models
2026-03-08 00:53:25 +01:00
a775a2da18
feat(step-3.6): cloud provider integrations (Gmail, Outlook, Teams)
...
- Add app/integrations/__init__.py: Fernet token encryption helpers,
EmailMessage/ChatMessage dataclasses, get_provider() factory
- Add app/integrations/gmail.py: GmailClient with async fetch_messages(),
token refresh, configurable label/sender/date filters
- Add app/integrations/ms_graph.py: MSGraphClient with fetch_emails()
(Outlook) and fetch_messages() (Teams), MSAL token refresh, OData filters
- Update app/core/agent_runner.py: replace run_cloud_agent() stub with
full 8-step implementation; extend _finalize_run() for cloud config type
- Update app/config/settings.py: add OAuth + Fernet encryption settings
- Update requirements.txt: google-api-python-client, google-auth-*,
msal, cryptography
- Add tests/test_integrations.py: 47 tests covering all integration code
- Update tests/test_agent_runner.py: replace stub test with 7 real tests
All 76 new/updated tests pass.
2026-03-05 18:05:07 +01:00
27c087d5d8
step B.2 complete: all 23 tools use execute_on_client(); add embed() to llm
2026-03-05 00:03:01 +01:00
314780d59a
Add LLM configuration options and update deployment workflow
...
- Introduced new API keys for Anthropic and Google in .env.example and settings.py
- Updated llm.py to retrieve API keys directly from settings
- Modified deploy.yaml to streamline code checkout and improve deployment process
2026-03-03 16:52:56 +01:00
8bfce9da00
Refactor LLM instantiation across agents and orchestrator
...
- Replaced direct instantiation of ChatOpenAI with a centralized get_llm function in CheckpointAgent, NoteAgent, ProjectAgent, and TaskAgent.
- Introduced a new llm.py module to handle LLM model instantiation and API key management.
- Updated settings.py to include LLM_MODEL and LLM_ROUTER_MODEL configurations.
- Modified orchestrator.py to use get_router_llm for intent classification.
- Updated requirements.txt to include litellm for LLM management.
- Adjusted tests to mock get_llm instead of ChatOpenAI directly.
2026-03-03 15:46:44 +01:00
