- Add strategy_signals field to AgentState (list of StrategySignal dicts)
- Compute signals once in Propagator.create_initial_state() with graceful fallback
- Add strategy_utils.get_signal_section() helper for role-based formatting
- Inject signals into all 4 analyst nodes (market, fundamentals, news, social)
- Inject signals into bull/bear researchers and research manager
- Inject signals into all 3 risk debators (aggressive, conservative, neutral)
- Inject signals into portfolio manager and trader
- Log strategy_signals in state output JSON
Add effort parameter (high/medium/low) for Claude 4.5+ and 4.6 models,
consistent with OpenAI reasoning_effort and Google thinking_level.
Also add content normalization for Anthropic responses.
InvestDebateState was missing bull_history, bear_history, judge_decision.
RiskDebateState was missing aggressive_history, conservative_history,
neutral_history, latest_speaker, judge_decision. This caused KeyError
in _log_state() and reflection, especially with edge-case config values.
Prevents UnicodeEncodeError on Windows where the default encoding
(cp1252/gbk) cannot handle Unicode characters in LLM output.
Closes#77, closes#114, closes#126, closes#215, closes#332
- Add StatsCallbackHandler for tracking LLM calls, tool calls, and tokens
- Integrate callbacks into TradingAgentsGraph and all LLM clients
- Dynamic agent/report counts based on selected analysts
- Fix report completion counting (tied to agent completion)
Clayton Brown
Yijia-Xiao
makk9
luohy15
mirza-samad-ahmed-baig
Edward Sun
maxer137