feat(graph): accept the caller's portfolio as run input (#1304, #1166)

- 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

tradingagents/agents/risk_mgmt/aggressive_debator.py

@@ -1,6 +1,7 @@
 from tradingagents.agents.utils.agent_utils import (
     get_instrument_context_from_state,
     get_language_instruction,
+    get_portfolio_context_from_state,
     opponent_argument_or_opening,
 )
 
@@ -23,6 +24,7 @@ def create_aggressive_debator(llm):
         news_report = state["news_report"]
         fundamentals_report = state["fundamentals_report"]
         instrument_context = get_instrument_context_from_state(state)
+        portfolio_context = get_portfolio_context_from_state(state)
 
         trader_decision = state["trader_investment_plan"]
 
@@ -33,6 +35,7 @@ def create_aggressive_debator(llm):
 Your task is to create a compelling case for the trader's decision by questioning and critiquing the conservative and neutral stances to demonstrate why your high-reward perspective offers the best path forward. Incorporate insights from the following sources into your arguments:
 
 {instrument_context}
+{portfolio_context}
 Market Research Report: {market_research_report}
 Social Media Sentiment Report: {sentiment_report}
 Latest World Affairs Report: {news_report}