The supervisor LLM now embeds <type>[id1,id2]</type> entity tags in its
response text. The HomeFormatter buffers streamed tokens, detects complete
tags across chunk boundaries, and emits WsStreamBlock with entity type +
specific IDs. This replaces the old approach of emitting blocks for every
tool_end event, which dumped ALL entities regardless of relevance.
Also fixes:
- NoneType guard on metadata in _run_graph_stream (metadata can be None)
- Updated _HOME_SYSTEM prompt with entity tag instructions
- Updated all affected tests
- Add app/core/deep_agent.py with Home and Floating supervisor graphs
using LangGraph create_react_agent (hierarchical pattern)
- Strip ChatAgent classes from all 4 agent files, keep @tool functions
- Rewrite output_formatter.py for event-based (token/tool_end/mutations) stream
- Update device_ws.py to use run_home_stream/run_floating_stream
- Rewrite chat.py REST route to use run_home
- Add update_core_memory tool to both supervisors
- Add langgraph>=0.3.0 to requirements.txt
- Remove orchestrator.py, execution_plan.py, agent_registry.py, plans.py
- Remove PlanAction, PlanStep, ExecutionPlan, execution_mode from schemas
- Update all affected tests to match new API
- Remove 6 deprecated test files for deleted modules
- Clean up stale docstrings referencing removed orchestrator
Code bugs fixed:
- checkpoint_agent.py, project_agent.py, note_agent.py: add missing
'import json' (used in handle() for context serialization)
Test fixes:
- test_agents.py: add autouse ws_executor fixture that sets a fake
execute_on_client so tools can run in unit tests without a WS session
- Rewrite all TestXxxAgentTools tests: patch execute_on_client per-test,
assert on call_args (what payload was sent to the client) and on the
formatted string return value — matching actual tool behavior
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- device_ws.py: dispatch home_request/popup_request to HomeFormatter/PopupFormatter
via async tasks; each request gets a UUID request_id for frame correlation
- chat.py: remove chat_stream WS endpoint (superseded by unified device WS);
keep POST /chat REST fallback unchanged
- 5 new integration tests pass; all 22 existing device_ws tests still pass
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- orchestrate_v3(user_id, message, context): classifies intent, returns
(agent_name, agent_instance) — caller drives execution
- orchestrate_v3_stream(user_id, message, context): yields (agent_name, token)
pairs; first yield is always (agent_name, "") as a domain-detection signal
- ChatAgent.handle_stream(): default implementation yields handle() result as
one chunk; subclasses override for true token-level streaming
- Fix stale test_orchestrator.py assertions that expected a JSON final frame
that orchestrate_stream never emitted
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- ChatAgent.__init__: adds tool_results: list[dict] = []
- _tool_loop: wraps execution in a result collector; populates
self.tool_results with raw execute_on_client dicts after each run
- _tool_loop_stream: streaming variant — uses ainvoke for tool-call
iterations, llm.astream() for the final answer; same result capture
- ws_context.py: adds _tool_result_collector ContextVar +
set/clear helpers; execute_on_client appends to collector when set
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- 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.
- Updated `TestModuleSingletons` in `test_execution_plan.py` to reflect new agent templates and playbook names.
- Changed assertions in playbook tests to match updated templates and agents.
- Introduced `test_storage.py` to cover the storage layer, including encryption, BlobStore, and VectorStore functionalities.
- Added tests for S3 interactions, ensuring upload, download, delete, and list operations work as expected.
- Implemented mock tests for Pinecone and Qdrant vector stores to validate upsert, search, and delete operations.
