- the Research Manager's plan and the Portfolio Manager's decision live only in investment_plan and final_trade_decision; the debate states no longer copy them as judge_decision
- the saved state log writes the Trader's plan as trader_investment_plan, its state key
- the report tree, the final display and the live CLI read the decisions from those fields
- the typed rating is the state's final_rating; propagate returns it, and the memory log tag, the state log and the CLI review check read it
- the decision text is parsed only when the Portfolio Manager answered in free text
- TradingAgentsGraph.process_signal is removed
- resolve_benchmark, fetch_returns and settle_pending are module functions; the graph's settle_pending runs them under its config
- create_run_state settles through settle_pending, so the CLI path also settles under the graph's config
- tools.py: the analysts' data tools, previously seven modules under utils
- context.py (was agent_utils, without its tool re-exports), state.py, rating.py and structured.py sit beside schemas.py
- every role package has an __init__
- PortfolioContext input, rendered once into state and read by the trader, risk and portfolio agents
- --portfolio JSON file on the CLI
- a run without it is never treated as a flat book
- the checkpoint signature keys on the portfolio
Yijia-Xiao