Files
Yijia-Xiao bba147798f feat: structured-output Trader and Research Manager (#434, finishes the trio)
Extends the canonical structured-output pattern from the Portfolio Manager
to the other two decision-making agents.  Each of the three agents now
returns a typed Pydantic instance via llm.with_structured_output() in a
single primary call, and a render helper turns the result into the same
markdown shape downstream agents and saved reports already consume.

- ResearchPlan: 5-tier recommendation, conversational rationale, concrete
  strategic actions for the trader.
- TraderProposal: 3-tier action (transaction direction is naturally Buy /
  Hold / Sell — position sizing happens later at the Portfolio Manager),
  reasoning, and optional entry_price / stop_loss / position_sizing.
  Rendered output preserves the trailing "FINAL TRANSACTION PROPOSAL:
  **BUY/HOLD/SELL**" line for backward compatibility with the analyst
  stop-signal text.
- PortfolioDecision: 5-tier rating, executive summary, investment thesis,
  optional price_target / time_horizon (unchanged).

The shared try-structured-then-fallback pattern is extracted into
tradingagents/agents/utils/structured.py (bind_structured +
invoke_structured_or_freetext) so all three agents go through the same
code path and log the same warning when a provider lacks structured
output and the agent falls back to free-text generation.

Net effect for users: every saved markdown report (research/manager.md,
trading/trader.md, portfolio/decision.md) now has consistent section
headers across runs and providers, easier to scan.

Net effect for the runtime: the rating extraction round-trip is gone —
the rating comes from the structured response itself, not a second
LLM call. SignalProcessor was already simplified to a heuristic adapter
in the previous commit.

11 new tests in tests/test_structured_agents.py cover the Trader and
Research Manager render functions, structured-output happy paths, and
free-text fallback. Full suite: 88 tests pass in ~2s without API keys.
2026-04-25 20:27:23 +00:00

62 lines
2.3 KiB
Python

"""Trader: turns the Research Manager's investment plan into a concrete transaction proposal."""
from __future__ import annotations
import functools
from langchain_core.messages import AIMessage
from tradingagents.agents.schemas import TraderProposal, render_trader_proposal
from tradingagents.agents.utils.agent_utils import build_instrument_context
from tradingagents.agents.utils.structured import (
bind_structured,
invoke_structured_or_freetext,
)
def create_trader(llm):
structured_llm = bind_structured(llm, TraderProposal, "Trader")
def trader_node(state, name):
company_name = state["company_of_interest"]
instrument_context = build_instrument_context(company_name)
investment_plan = state["investment_plan"]
messages = [
{
"role": "system",
"content": (
"You are a trading agent analyzing market data to make investment decisions. "
"Based on your analysis, provide a specific recommendation to buy, sell, or hold. "
"Anchor your reasoning in the analysts' reports and the research plan."
),
},
{
"role": "user",
"content": (
f"Based on a comprehensive analysis by a team of analysts, here is an investment "
f"plan tailored for {company_name}. {instrument_context} This plan incorporates "
f"insights from current technical market trends, macroeconomic indicators, and "
f"social media sentiment. Use this plan as a foundation for evaluating your next "
f"trading decision.\n\nProposed Investment Plan: {investment_plan}\n\n"
f"Leverage these insights to make an informed and strategic decision."
),
},
]
trader_plan = invoke_structured_or_freetext(
structured_llm,
llm,
messages,
render_trader_proposal,
"Trader",
)
return {
"messages": [AIMessage(content=trader_plan)],
"trader_investment_plan": trader_plan,
"sender": name,
}
return functools.partial(trader_node, name="Trader")