charieswei
/
TradingAgents
mirror of https://github.com/TauricResearch/TradingAgents.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge e6a18061a1 into 13b826a31d

This commit is contained in:
Jeffrey Chu 2025-10-23 13:44:03 -03:00 committed by GitHub
parent 13b826a31d e6a18061a1
commit 5e5ad664f1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
25 changed files with 879 additions and 449 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
.env.example
View File

@ -1,2 +1,7 @@
ALPHA_VANTAGE_API_KEY=alpha_vantage_api_key_placeholder
OPENAI_API_KEY=openai_api_key_placeholder
# only select 1 to your .env
OPENAI_API_KEY=openai_api_key_placeholder
OPENROUTER_API_KEY=openrouter_api_key_placeholder
ANTHROPIC_API_KEY=anthropic_api_key_placeholder
GOOGLE_API_KEY=google_api_key_placeholder
XAI_API_KEY=xai_api_key_placeholder

2
.gitignore vendored
View File

@ -9,3 +9,5 @@ eval_results/
eval_data/
*.egg-info/
.env
.history
.idea

193
cli/main.py
View File

@ -1,16 +1,15 @@
from typing import Optional
import datetime
import typer
from pathlib import Path
from functools import wraps
from rich.console import Console
from pathlib import Path
import typer
from dotenv import load_dotenv
from rich.console import Console
# Load environment variables from .env file
load_dotenv()
from rich.panel import Panel
from rich.spinner import Spinner
from rich.live import Live
from rich.columns import Columns
from rich.markdown import Markdown
from rich.layout import Layout
@ -18,15 +17,11 @@ from rich.text import Text
from rich.live import Live
from rich.table import Table
from collections import deque
import time
from rich.tree import Tree
from rich import box
from rich.align import Align
from rich.rule import Rule
from tradingagents.graph.trading_graph import TradingAgentsGraph
from tradingagents.default_config import DEFAULT_CONFIG
from cli.models import AnalystType
from cli.utils import *
console = Console()
@ -66,13 +61,13 @@ class MessageBuffer:
}
self.current_agent = None
self.report_sections = {
"market_report": None,
"sentiment_report": None,
"news_report": None,
"fundamentals_report": None,
"investment_plan": None,
"trader_investment_plan": None,
"final_trade_decision": None,
"market_analysis": None,
"sentiment_analysis": None,
"news_analysis": None,
"fundamentals_analysis": None,
"research_team_decision": None,
"trader_team_plan": None,
"final_portfolio_management_decision": None,
}
def add_message(self, message_type, content):
@ -103,17 +98,17 @@ class MessageBuffer:
if content is not None:
latest_section = section
latest_content = content
if latest_section and latest_content:
# Format the current section for display
section_titles = {
"market_report": "Market Analysis",
"sentiment_report": "Social Sentiment",
"news_report": "News Analysis",
"fundamentals_report": "Fundamentals Analysis",
"investment_plan": "Research Team Decision",
"trader_investment_plan": "Trading Team Plan",
"final_trade_decision": "Portfolio Management Decision",
"market_analysis": "Market Analysis",
"sentiment_analysis": "Social Sentiment",
"news_analysis": "News Analysis",
"fundamentals_analysis": "Fundamentals Analysis",
"research_team_decision": "Research Team Decision",
"trader_team_plan": "Trading Team Plan",
"final_portfolio_management_decision": "Portfolio Management Decision",
}
self.current_report = (
f"### {section_titles[latest_section]}\n{latest_content}"
@ -127,46 +122,46 @@ class MessageBuffer:
# Analyst Team Reports
if any(
self.report_sections[section]
for section in [
"market_report",
"sentiment_report",
"news_report",
"fundamentals_report",
]
self.report_sections[section]
for section in [
"market_analysis",
"sentiment_analysis",
"news_analysis",
"fundamentals_analysis",
]
):
report_parts.append("## Analyst Team Reports")
if self.report_sections["market_report"]:
if self.report_sections["market_analysis"]:
report_parts.append(
f"### Market Analysis\n{self.report_sections['market_report']}"
f"### Market Analysis\n{self.report_sections['market_analysis']}"
)
if self.report_sections["sentiment_report"]:
if self.report_sections["sentiment_analysis"]:
report_parts.append(
f"### Social Sentiment\n{self.report_sections['sentiment_report']}"
f"### Social Sentiment\n{self.report_sections['sentiment_analysis']}"
)
if self.report_sections["news_report"]:
if self.report_sections["news_analysis"]:
report_parts.append(
f"### News Analysis\n{self.report_sections['news_report']}"
f"### News Analysis\n{self.report_sections['news_analysis']}"
)
if self.report_sections["fundamentals_report"]:
if self.report_sections["fundamentals_analysis"]:
report_parts.append(
f"### Fundamentals Analysis\n{self.report_sections['fundamentals_report']}"
f"### Fundamentals Analysis\n{self.report_sections['fundamentals_analysis']}"
)
# Research Team Reports
if self.report_sections["investment_plan"]:
if self.report_sections["research_team_decision"]:
report_parts.append("## Research Team Decision")
report_parts.append(f"{self.report_sections['investment_plan']}")
report_parts.append(f"{self.report_sections['research_team_decision']}")
# Trading Team Reports
if self.report_sections["trader_investment_plan"]:
if self.report_sections["trader_team_plan"]:
report_parts.append("## Trading Team Plan")
report_parts.append(f"{self.report_sections['trader_investment_plan']}")
report_parts.append(f"{self.report_sections['trader_team_plan']}")
# Portfolio Management Decision
if self.report_sections["final_trade_decision"]:
if self.report_sections["final_portfolio_management_decision"]:
report_parts.append("## Portfolio Management Decision")
report_parts.append(f"{self.report_sections['final_trade_decision']}")
report_parts.append(f"{self.report_sections['final_portfolio_management_decision']}")
self.final_report = "\n\n".join(report_parts) if report_parts else None
@ -317,7 +312,7 @@ def update_display(layout, spinner_text=None):
content_str = ' '.join(text_parts)
elif not isinstance(content_str, str):
content_str = str(content)
# Truncate message content if too long
if len(content_str) > 200:
content_str = content_str[:197] + "..."
@ -429,6 +424,14 @@ def get_user_selections():
box_content += f"\n[dim]Default: {default}[/dim]"
return Panel(box_content, border_style="blue", padding=(1, 2))
# Step 0: Language Selection
console.print(
create_question_box(
"Step 0: Language Selection", "Choose language for agent outputs"
)
)
selected_language = select_language()
# Step 1: Ticker symbol
console.print(
create_question_box(
@ -474,7 +477,7 @@ def get_user_selections():
)
)
selected_llm_provider, backend_url = select_llm_provider()
# Step 6: Thinking agents
console.print(
create_question_box(
@ -493,6 +496,7 @@ def get_user_selections():
"backend_url": backend_url,
"shallow_thinker": selected_shallow_thinker,
"deep_thinker": selected_deep_thinker,
"language": selected_language,
}
@ -528,10 +532,10 @@ def display_complete_report(final_state):
analyst_reports = []
# Market Analyst Report
if final_state.get("market_report"):
if final_state.get("market_analysis"):
analyst_reports.append(
Panel(
Markdown(final_state["market_report"]),
Markdown(final_state["market_analysis"]),
title="Market Analyst",
border_style="blue",
padding=(1, 2),
@ -539,10 +543,10 @@ def display_complete_report(final_state):
)
# Social Analyst Report
if final_state.get("sentiment_report"):
if final_state.get("sentiment_analysis"):
analyst_reports.append(
Panel(
Markdown(final_state["sentiment_report"]),
Markdown(final_state["sentiment_analysis"]),
title="Social Analyst",
border_style="blue",
padding=(1, 2),
@ -550,10 +554,10 @@ def display_complete_report(final_state):
)
# News Analyst Report
if final_state.get("news_report"):
if final_state.get("news_analysis"):
analyst_reports.append(
Panel(
Markdown(final_state["news_report"]),
Markdown(final_state["news_analysis"]),
title="News Analyst",
border_style="blue",
padding=(1, 2),
@ -561,10 +565,10 @@ def display_complete_report(final_state):
)
# Fundamentals Analyst Report
if final_state.get("fundamentals_report"):
if final_state.get("fundamentals_analysis"):
analyst_reports.append(
Panel(
Markdown(final_state["fundamentals_report"]),
Markdown(final_state["fundamentals_analysis"]),
title="Fundamentals Analyst",
border_style="blue",
padding=(1, 2),
@ -630,11 +634,11 @@ def display_complete_report(final_state):
)
# III. Trading Team Reports
if final_state.get("trader_investment_plan"):
if final_state.get("trader_team_plan"):
console.print(
Panel(
Panel(
Markdown(final_state["trader_investment_plan"]),
Markdown(final_state["trader_team_plan"]),
title="Trader",
border_style="blue",
padding=(1, 2),
@ -716,6 +720,7 @@ def update_research_team_status(status):
for agent in research_team:
message_buffer.update_agent_status(agent, status)
def extract_content_string(content):
"""Extract string content from various message formats."""
if isinstance(content, str):
@ -735,12 +740,14 @@ def extract_content_string(content):
else:
return str(content)
def run_analysis():
# First get all user selections
selections = get_user_selections()
# Create config with selected research depth
config = DEFAULT_CONFIG.copy()
config["output_language"] = selections["language"]
config["max_debate_rounds"] = selections["research_depth"]
config["max_risk_discuss_rounds"] = selections["research_depth"]
config["quick_think_llm"] = selections["shallow_thinker"]
@ -763,6 +770,7 @@ def run_analysis():
def save_message_decorator(obj, func_name):
func = getattr(obj, func_name)
@wraps(func)
def wrapper(*args, **kwargs):
func(*args, **kwargs)
@ -770,10 +778,12 @@ def run_analysis():
content = content.replace("\n", " ") # Replace newlines with spaces
with open(log_file, "a") as f:
f.write(f"{timestamp} [{message_type}] {content}\n")
return wrapper
def save_tool_call_decorator(obj, func_name):
func = getattr(obj, func_name)
@wraps(func)
def wrapper(*args, **kwargs):
func(*args, **kwargs)
@ -781,10 +791,12 @@ def run_analysis():
args_str = ", ".join(f"{k}={v}" for k, v in args.items())
with open(log_file, "a") as f:
f.write(f"{timestamp} [Tool Call] {tool_name}({args_str})\n")
return wrapper
def save_report_section_decorator(obj, func_name):
func = getattr(obj, func_name)
@wraps(func)
def wrapper(section_name, content):
func(section_name, content)
@ -794,6 +806,7 @@ def run_analysis():
file_name = f"{section_name}.md"
with open(report_dir / file_name, "w") as f:
f.write(content)
return wrapper
message_buffer.add_message = save_message_decorator(message_buffer, "add_message")
@ -861,7 +874,7 @@ def run_analysis():
msg_type = "System"
# Add message to buffer
message_buffer.add_message(msg_type, content)
message_buffer.add_message(msg_type, content)
# If it's a tool call, add it to tool calls
if hasattr(last_message, "tool_calls"):
@ -876,9 +889,9 @@ def run_analysis():
# Update reports and agent status based on chunk content
# Analyst Team Reports
if "market_report" in chunk and chunk["market_report"]:
if "market_analysis" in chunk and chunk["market_analysis"]:
message_buffer.update_report_section(
"market_report", chunk["market_report"]
"market_analysis", chunk["market_analysis"]
)
message_buffer.update_agent_status("Market Analyst", "completed")
# Set next analyst to in_progress
@ -887,9 +900,9 @@ def run_analysis():
"Social Analyst", "in_progress"
)
if "sentiment_report" in chunk and chunk["sentiment_report"]:
if "sentiment_analysis" in chunk and chunk["sentiment_analysis"]:
message_buffer.update_report_section(
"sentiment_report", chunk["sentiment_report"]
"sentiment_analysis", chunk["sentiment_analysis"]
)
message_buffer.update_agent_status("Social Analyst", "completed")
# Set next analyst to in_progress
@ -898,9 +911,9 @@ def run_analysis():
"News Analyst", "in_progress"
)
if "news_report" in chunk and chunk["news_report"]:
if "news_analysis" in chunk and chunk["news_analysis"]:
message_buffer.update_report_section(
"news_report", chunk["news_report"]
"news_analysis", chunk["news_analysis"]
)
message_buffer.update_agent_status("News Analyst", "completed")
# Set next analyst to in_progress
@ -909,9 +922,9 @@ def run_analysis():
"Fundamentals Analyst", "in_progress"
)
if "fundamentals_report" in chunk and chunk["fundamentals_report"]:
if "fundamentals_analysis" in chunk and chunk["fundamentals_analysis"]:
message_buffer.update_report_section(
"fundamentals_report", chunk["fundamentals_report"]
"fundamentals_analysis", chunk["fundamentals_analysis"]
)
message_buffer.update_agent_status(
"Fundamentals Analyst", "completed"
@ -921,8 +934,8 @@ def run_analysis():
# Research Team - Handle Investment Debate State
if (
"investment_debate_state" in chunk
and chunk["investment_debate_state"]
"investment_debate_state" in chunk
and chunk["investment_debate_state"]
):
debate_state = chunk["investment_debate_state"]
@ -937,7 +950,7 @@ def run_analysis():
message_buffer.add_message("Reasoning", latest_bull)
# Update research report with bull's latest analysis
message_buffer.update_report_section(
"investment_plan",
"research_team_decision",
f"### Bull Researcher Analysis\n{latest_bull}",
)
@ -952,14 +965,14 @@ def run_analysis():
message_buffer.add_message("Reasoning", latest_bear)
# Update research report with bear's latest analysis
message_buffer.update_report_section(
"investment_plan",
f"{message_buffer.report_sections['investment_plan']}\n\n### Bear Researcher Analysis\n{latest_bear}",
"research_team_decision",
f"{message_buffer.report_sections['research_team_decision']}\n\n### Bear Researcher Analysis\n{latest_bear}",
)
# Update Research Manager status and final decision
if (
"judge_decision" in debate_state
and debate_state["judge_decision"]
"judge_decision" in debate_state
and debate_state["judge_decision"]
):
# Keep all research team members in progress until final decision
update_research_team_status("in_progress")
@ -969,8 +982,8 @@ def run_analysis():
)
# Update research report with final decision
message_buffer.update_report_section(
"investment_plan",
f"{message_buffer.report_sections['investment_plan']}\n\n### Research Manager Decision\n{debate_state['judge_decision']}",
"research_team_decision",
f"{message_buffer.report_sections['research_team_decision']}\n\n### Research Manager Decision\n{debate_state['judge_decision']}",
)
# Mark all research team members as completed
update_research_team_status("completed")
@ -981,11 +994,11 @@ def run_analysis():
# Trading Team
if (
"trader_investment_plan" in chunk
and chunk["trader_investment_plan"]
"trader_team_plan" in chunk
and chunk["trader_team_plan"]
):
message_buffer.update_report_section(
"trader_investment_plan", chunk["trader_investment_plan"]
"trader_team_plan", chunk["trader_team_plan"]
)
# Set first risk analyst to in_progress
message_buffer.update_agent_status("Risky Analyst", "in_progress")
@ -996,8 +1009,8 @@ def run_analysis():
# Update Risky Analyst status and report
if (
"current_risky_response" in risk_state
and risk_state["current_risky_response"]
"current_risky_response" in risk_state
and risk_state["current_risky_response"]
):
message_buffer.update_agent_status(
"Risky Analyst", "in_progress"
@ -1008,14 +1021,14 @@ def run_analysis():
)
# Update risk report with risky analyst's latest analysis only
message_buffer.update_report_section(
"final_trade_decision",
"final_portfolio_management_decision",
f"### Risky Analyst Analysis\n{risk_state['current_risky_response']}",
)
# Update Safe Analyst status and report
if (
"current_safe_response" in risk_state
and risk_state["current_safe_response"]
"current_safe_response" in risk_state
and risk_state["current_safe_response"]
):
message_buffer.update_agent_status(
"Safe Analyst", "in_progress"
@ -1026,14 +1039,14 @@ def run_analysis():
)
# Update risk report with safe analyst's latest analysis only
message_buffer.update_report_section(
"final_trade_decision",
"final_portfolio_management_decision",
f"### Safe Analyst Analysis\n{risk_state['current_safe_response']}",
)
# Update Neutral Analyst status and report
if (
"current_neutral_response" in risk_state
and risk_state["current_neutral_response"]
"current_neutral_response" in risk_state
and risk_state["current_neutral_response"]
):
message_buffer.update_agent_status(
"Neutral Analyst", "in_progress"
@ -1044,7 +1057,7 @@ def run_analysis():
)
# Update risk report with neutral analyst's latest analysis only
message_buffer.update_report_section(
"final_trade_decision",
"final_portfolio_management_decision",
f"### Neutral Analyst Analysis\n{risk_state['current_neutral_response']}",
)
@ -1059,7 +1072,7 @@ def run_analysis():
)
# Update risk report with final decision only
message_buffer.update_report_section(
"final_trade_decision",
"final_portfolio_management_decision",
f"### Portfolio Manager Decision\n{risk_state['judge_decision']}",
)
# Mark risk analysts as completed
@ -1079,7 +1092,7 @@ def run_analysis():
# Get final state and decision
final_state = trace[-1]
decision = graph.process_signal(final_state["final_trade_decision"])
decision = graph.process_signal(final_state["final_portfolio_management_decision"])
# Update all agent statuses to completed
for agent in message_buffer.agent_status:

67
cli/utils.py
View File

@ -1,6 +1,8 @@
import questionary
from typing import List, Optional, Tuple, Dict
from typing import List
import questionary
from cli.main import console
from cli.models import AnalystType
ANALYST_ORDER = [
@ -48,7 +50,7 @@ def get_analysis_date() -> str:
date = questionary.text(
"Enter the analysis date (YYYY-MM-DD):",
validate=lambda x: validate_date(x.strip())
or "Please enter a valid date in YYYY-MM-DD format.",
or "Please enter a valid date in YYYY-MM-DD format.",
style=questionary.Style(
[
("text", "fg:green"),
@ -146,12 +148,17 @@ def select_shallow_thinking_agent(provider) -> str:
],
"openrouter": [
("Meta: Llama 4 Scout", "meta-llama/llama-4-scout:free"),
("Meta: Llama 3.3 8B Instruct - A lightweight and ultra-fast variant of Llama 3.3 70B", "meta-llama/llama-3.3-8b-instruct:free"),
("google/gemini-2.0-flash-exp:free - Gemini Flash 2.0 offers a significantly faster time to first token", "google/gemini-2.0-flash-exp:free"),
("Meta: Llama 3.3 8B Instruct - A lightweight and ultra-fast variant of Llama 3.3 70B",
"meta-llama/llama-3.3-8b-instruct:free"),
("google/gemini-2.0-flash-exp:free - Gemini Flash 2.0 offers a significantly faster time to first token",
"google/gemini-2.0-flash-exp:free"),
],
"ollama": [
("llama3.1 local", "llama3.1"),
("llama3.2 local", "llama3.2"),
],
"xai": [
("grok-4-fast-non-reasoning", "grok-4-fast-non-reasoning"),
]
}
@ -209,14 +216,18 @@ def select_deep_thinking_agent(provider) -> str:
],
"openrouter": [
("DeepSeek V3 - a 685B-parameter, mixture-of-experts model", "deepseek/deepseek-chat-v3-0324:free"),
("Deepseek - latest iteration of the flagship chat model family from the DeepSeek team.", "deepseek/deepseek-chat-v3-0324:free"),
("Deepseek - latest iteration of the flagship chat model family from the DeepSeek team.",
"deepseek/deepseek-chat-v3-0324:free"),
],
"ollama": [
("llama3.1 local", "llama3.1"),
("qwen3", "qwen3"),
],
"xai": [
("grok-4-fast-reasoning", "grok-4-fast-reasoning"),
]
}
choice = questionary.select(
"Select Your [Deep-Thinking LLM Engine]:",
choices=[
@ -239,17 +250,19 @@ def select_deep_thinking_agent(provider) -> str:
return choice
def select_llm_provider() -> tuple[str, str]:
"""Select the OpenAI api url using interactive selection."""
# Define OpenAI api options with their corresponding endpoints
BASE_URLS = [
("XAI", "https://api.x.ai/v1"),
("OpenAI", "https://api.openai.com/v1"),
("Anthropic", "https://api.anthropic.com/"),
("Google", "https://generativelanguage.googleapis.com/v1"),
("Openrouter", "https://openrouter.ai/api/v1"),
("Ollama", "http://localhost:11434/v1"),
("Ollama", "http://localhost:11434/v1"),
]
choice = questionary.select(
"Select your LLM Provider:",
choices=[
@ -265,12 +278,42 @@ def select_llm_provider() -> tuple[str, str]:
]
),
).ask()
if choice is None:
console.print("\n[red]no OpenAI backend selected. Exiting...[/red]")
exit(1)
display_name, url = choice
print(f"You selected: {display_name}\tURL: {url}")
return display_name, url
def select_language() -> int:
"""Select output language for agent responses."""
LANGUAGE_OPTIONS = [
("English", "en"),
("Traditional Chinese", "zh-tw"),
("Simplified Chinese", "zh-cn"),
]
choice = questionary.select(
"Select Output Language for Agents:",
choices=[
questionary.Choice(display, value=value) for display, value in LANGUAGE_OPTIONS
],
instruction="\n- Use arrow keys to navigate\n- Press Enter to select",
style=questionary.Style(
[
("selected", "fg:yellow noinherit"),
("highlighted", "fg:yellow noinherit"),
("pointer", "fg:yellow noinherit"),
]
),
).ask()
if choice is None:
console.print("\n[red]No langauge selected. Exiting...[/red]")
exit(1)
return choice

2
requirements.txt
View File

@ -24,3 +24,5 @@ rich
questionary
langchain_anthropic
langchain-google-genai
langchain-xai
sentence-transformers

60
tradingagents/agents/analysts/fundamentals_analyst.py
View File

@ -1,11 +1,12 @@
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
import time
import json
from tradingagents.agents.utils.agent_utils import get_fundamentals, get_balance_sheet, get_cashflow, get_income_statement, get_insider_sentiment, get_insider_transactions
from tradingagents.dataflows.config import get_config
from tradingagents.agents.utils.agent_utils import get_fundamentals, get_balance_sheet, get_cashflow, \
get_income_statement
def create_fundamentals_analyst(llm):
def create_fundamentals_analyst(llm, config):
"""Create the fundamentals analyst node with language support."""
def fundamentals_analyst_node(state):
current_date = state["trade_date"]
ticker = state["company_of_interest"]
@ -18,34 +19,49 @@ def create_fundamentals_analyst(llm):
get_income_statement,
]
language = config["output_language"]
language_prompts = {
"en": "",
"zh-tw": "Use Traditional Chinese as the output.",
"zh-cn": "Use Simplified Chinese as the output.",
}
language_prompt = language_prompts.get(language, "")
system_message = (
"You are a researcher tasked with analyzing fundamental information over the past week about a company. Please write a comprehensive report of the company's fundamental information such as financial documents, company profile, basic company financials, and company financial history to gain a full view of the company's fundamental information to inform traders. Make sure to include as much detail as possible. Do not simply state the trends are mixed, provide detailed and finegrained analysis and insights that may help traders make decisions."
+ " Make sure to append a Markdown table at the end of the report to organize key points in the report, organized and easy to read."
+ " Use the available tools: `get_fundamentals` for comprehensive company analysis, `get_balance_sheet`, `get_cashflow`, and `get_income_statement` for specific financial statements.",
f"""
You are a researcher tasked with analyzing fundamental information over the past week about a company.
Please write a comprehensive report of the company's fundamental information such as financial documents, company profile, basic company financials, and company financial history to gain a full view of the company's fundamental information to inform traders.
Make sure to include as much detail as possible.
Do not simply state the trends are mixed, provide detailed and finegrained analysis and insights that may help traders make decisions.
Make sure to append a Markdown table at the end of the report to organize key points in the report, organized and easy to read.
Use the available tools: `get_fundamentals` for comprehensive company analysis, `get_balance_sheet`, `get_cashflow`, and `get_income_statement` for specific financial statements.
"""
)
prompt = ChatPromptTemplate.from_messages(
[
(
"system",
"You are a helpful AI assistant, collaborating with other assistants."
" Use the provided tools to progress towards answering the question."
" If you are unable to fully answer, that's OK; another assistant with different tools"
" will help where you left off. Execute what you can to make progress."
" If you or any other assistant has the FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** or deliverable,"
" prefix your response with FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** so the team knows to stop."
" You have access to the following tools: {tool_names}.\n{system_message}"
"For your reference, the current date is {current_date}. The company we want to look at is {ticker}",
f"""
You are a helpful AI assistant, collaborating with other assistants.
Use the provided tools to progress towards answering the question.
If you are unable to fully answer, that's OK; another assistant with different tools will help where you left off. Execute what you can to make progress.
If you or any other assistant has the FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** or deliverable, prefix your response with FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** so the team knows to stop.
You have access to the following tools: {tools}.
{system_message}
For your reference, the current date is {current_date}.
The company we want to look at is {ticker}
Output language: ***{language_prompt}***
""",
),
MessagesPlaceholder(variable_name="messages"),
]
)
prompt = prompt.partial(system_message=system_message)
prompt = prompt.partial(tool_names=", ".join([tool.name for tool in tools]))
prompt = prompt.partial(current_date=current_date)
prompt = prompt.partial(ticker=ticker)
chain = prompt | llm.bind_tools(tools)
result = chain.invoke(state["messages"])
@ -57,7 +73,7 @@ def create_fundamentals_analyst(llm):
return {
"messages": [result],
"fundamentals_report": report,
"fundamentals_analysis": report,
}
return fundamentals_analyst_node

101
tradingagents/agents/analysts/market_analyst.py
View File

@ -1,11 +1,10 @@
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
import time
import json
from tradingagents.agents.utils.agent_utils import get_stock_data, get_indicators
from tradingagents.dataflows.config import get_config
def create_market_analyst(llm):
def create_market_analyst(llm, config):
"""Create the market analyst node with language support."""
def market_analyst_node(state):
current_date = state["trade_date"]
@ -17,57 +16,69 @@ def create_market_analyst(llm):
get_indicators,
]
language = config["output_language"]
language_prompts = {
"en": "",
"zh-tw": "Use Traditional Chinese as the output.",
"zh-cn": "Use Simplified Chinese as the output.",
}
language_prompt = language_prompts.get(language, "")
system_message = (
"""You are a trading assistant tasked with analyzing financial markets. Your role is to select the **most relevant indicators** for a given market condition or trading strategy from the following list. The goal is to choose up to **8 indicators** that provide complementary insights without redundancy. Categories and each category's indicators are:
Moving Averages:
- close_50_sma: 50 SMA: A medium-term trend indicator. Usage: Identify trend direction and serve as dynamic support/resistance. Tips: It lags price; combine with faster indicators for timely signals.
- close_200_sma: 200 SMA: A long-term trend benchmark. Usage: Confirm overall market trend and identify golden/death cross setups. Tips: It reacts slowly; best for strategic trend confirmation rather than frequent trading entries.
- close_10_ema: 10 EMA: A responsive short-term average. Usage: Capture quick shifts in momentum and potential entry points. Tips: Prone to noise in choppy markets; use alongside longer averages for filtering false signals.
MACD Related:
- macd: MACD: Computes momentum via differences of EMAs. Usage: Look for crossovers and divergence as signals of trend changes. Tips: Confirm with other indicators in low-volatility or sideways markets.
- macds: MACD Signal: An EMA smoothing of the MACD line. Usage: Use crossovers with the MACD line to trigger trades. Tips: Should be part of a broader strategy to avoid false positives.
- macdh: MACD Histogram: Shows the gap between the MACD line and its signal. Usage: Visualize momentum strength and spot divergence early. Tips: Can be volatile; complement with additional filters in fast-moving markets.
Momentum Indicators:
- rsi: RSI: Measures momentum to flag overbought/oversold conditions. Usage: Apply 70/30 thresholds and watch for divergence to signal reversals. Tips: In strong trends, RSI may remain extreme; always cross-check with trend analysis.
Volatility Indicators:
- boll: Bollinger Middle: A 20 SMA serving as the basis for Bollinger Bands. Usage: Acts as a dynamic benchmark for price movement. Tips: Combine with the upper and lower bands to effectively spot breakouts or reversals.
- boll_ub: Bollinger Upper Band: Typically 2 standard deviations above the middle line. Usage: Signals potential overbought conditions and breakout zones. Tips: Confirm signals with other tools; prices may ride the band in strong trends.
- boll_lb: Bollinger Lower Band: Typically 2 standard deviations below the middle line. Usage: Indicates potential oversold conditions. Tips: Use additional analysis to avoid false reversal signals.
- atr: ATR: Averages true range to measure volatility. Usage: Set stop-loss levels and adjust position sizes based on current market volatility. Tips: It's a reactive measure, so use it as part of a broader risk management strategy.
Volume-Based Indicators:
- vwma: VWMA: A moving average weighted by volume. Usage: Confirm trends by integrating price action with volume data. Tips: Watch for skewed results from volume spikes; use in combination with other volume analyses.
- Select indicators that provide diverse and complementary information. Avoid redundancy (e.g., do not select both rsi and stochrsi). Also briefly explain why they are suitable for the given market context. When you tool call, please use the exact name of the indicators provided above as they are defined parameters, otherwise your call will fail. Please make sure to call get_stock_data first to retrieve the CSV that is needed to generate indicators. Then use get_indicators with the specific indicator names. Write a very detailed and nuanced report of the trends you observe. Do not simply state the trends are mixed, provide detailed and finegrained analysis and insights that may help traders make decisions."""
+ """ Make sure to append a Markdown table at the end of the report to organize key points in the report, organized and easy to read."""
f"""You are a trading assistant tasked with analyzing financial markets. Your role is to select the **most relevant indicators** for a given market condition or trading strategy from the following list. The goal is to choose up to **8 indicators** that provide complementary insights without redundancy. Categories and each category's indicators are:
Moving Averages:
- close_50_sma: 50 SMA: A medium-term trend indicator. Usage: Identify trend direction and serve as dynamic support/resistance. Tips: It lags price; combine with faster indicators for timely signals.
- close_200_sma: 200 SMA: A long-term trend benchmark. Usage: Confirm overall market trend and identify golden/death cross setups. Tips: It reacts slowly; best for strategic trend confirmation rather than frequent trading entries.
- close_10_ema: 10 EMA: A responsive short-term average. Usage: Capture quick shifts in momentum and potential entry points. Tips: Prone to noise in choppy markets; use alongside longer averages for filtering false signals.
MACD Related:
- macd: MACD: Computes momentum via differences of EMAs. Usage: Look for crossovers and divergence as signals of trend changes. Tips: Confirm with other indicators in low-volatility or sideways markets.
- macds: MACD Signal: An EMA smoothing of the MACD line. Usage: Use crossovers with the MACD line to trigger trades. Tips: Should be part of a broader strategy to avoid false positives.
- macdh: MACD Histogram: Shows the gap between the MACD line and its signal. Usage: Visualize momentum strength and spot divergence early. Tips: Can be volatile; complement with additional filters in fast-moving markets.
Momentum Indicators:
- rsi: RSI: Measures momentum to flag overbought/oversold conditions. Usage: Apply 70/30 thresholds and watch for divergence to signal reversals. Tips: In strong trends, RSI may remain extreme; always cross-check with trend analysis.
Volatility Indicators:
- boll: Bollinger Middle: A 20 SMA serving as the basis for Bollinger Bands. Usage: Acts as a dynamic benchmark for price movement. Tips: Combine with the upper and lower bands to effectively spot breakouts or reversals.
- boll_ub: Bollinger Upper Band: Typically 2 standard deviations above the middle line. Usage: Signals potential overbought conditions and breakout zones. Tips: Confirm signals with other tools; prices may ride the band in strong trends.
- boll_lb: Bollinger Lower Band: Typically 2 standard deviations below the middle line. Usage: Indicates potential oversold conditions. Tips: Use additional analysis to avoid false reversal signals.
- atr: ATR: Averages true range to measure volatility. Usage: Set stop-loss levels and adjust position sizes based on current market volatility. Tips: It's a reactive measure, so use it as part of a broader risk management strategy.
Volume-Based Indicators:
- vwma: VWMA: A moving average weighted by volume. Usage: Confirm trends by integrating price action with volume data. Tips: Watch for skewed results from volume spikes; use in combination with other volume analyses.
- Select indicators that provide diverse and complementary information. Avoid redundancy (e.g., do not select both rsi and stochrsi). Also briefly explain why they are suitable for the given market context. When you tool call, please use the exact name of the indicators provided above as they are defined parameters, otherwise your call will fail. Please make sure to call get_stock_data first to retrieve the CSV that is needed to generate indicators. Then use get_indicators with the specific indicator names. Write a very detailed and nuanced report of the trends you observe. Do not simply state the trends are mixed, provide detailed and finegrained analysis and insights that may help traders make decisions.
Make sure to append a Markdown table at the end of the report to organize key points in the report, organized and easy to read.
"""
)
prompt = ChatPromptTemplate.from_messages(
[
(
"system",
"You are a helpful AI assistant, collaborating with other assistants."
" Use the provided tools to progress towards answering the question."
" If you are unable to fully answer, that's OK; another assistant with different tools"
" will help where you left off. Execute what you can to make progress."
" If you or any other assistant has the FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** or deliverable,"
" prefix your response with FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** so the team knows to stop."
" You have access to the following tools: {tool_names}.\n{system_message}"
"For your reference, the current date is {current_date}. The company we want to look at is {ticker}",
f"""
You are a helpful AI assistant, collaborating with other assistants.
Use the provided tools to progress towards answering the question.
If you are unable to fully answer, that's OK; another assistant with different tools will help where you left off. Execute what you can to make progress.
If you or any other assistant has the FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** or deliverable, prefix your response with FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** so the team knows to stop.
You have access to the following tools: {tools}.
{system_message}
For your reference, the current date is {current_date}.
The company we want to look at is {ticker}
Output language: ***{language_prompt}***
""",
),
MessagesPlaceholder(variable_name="messages"),
]
)
prompt = prompt.partial(system_message=system_message)
prompt = prompt.partial(tool_names=", ".join([tool.name for tool in tools]))
prompt = prompt.partial(current_date=current_date)
prompt = prompt.partial(ticker=ticker)
chain = prompt | llm.bind_tools(tools)
result = chain.invoke(state["messages"])
@ -76,10 +87,10 @@ Volume-Based Indicators:
if len(result.tool_calls) == 0:
report = result.content
return {
"messages": [result],
"market_report": report,
"market_analysis": report,
}
return market_analyst_node

55
tradingagents/agents/analysts/news_analyst.py
View File

@ -1,11 +1,11 @@
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
import time
import json
from tradingagents.agents.utils.agent_utils import get_news, get_global_news
from tradingagents.dataflows.config import get_config
def create_news_analyst(llm):
def create_news_analyst(llm, config):
"""Create the news analyst node with language support."""
def news_analyst_node(state):
current_date = state["trade_date"]
ticker = state["company_of_interest"]
@ -15,33 +15,48 @@ def create_news_analyst(llm):
get_global_news,
]
language = config["output_language"]
language_prompts = {
"en": "",
"zh-tw": "Use Traditional Chinese as the output.",
"zh-cn": "Use Simplified Chinese as the output.",
}
language_prompt = language_prompts.get(language, "")
system_message = (
"You are a news researcher tasked with analyzing recent news and trends over the past week. Please write a comprehensive report of the current state of the world that is relevant for trading and macroeconomics. Use the available tools: get_news(query, start_date, end_date) for company-specific or targeted news searches, and get_global_news(curr_date, look_back_days, limit) for broader macroeconomic news. Do not simply state the trends are mixed, provide detailed and finegrained analysis and insights that may help traders make decisions."
+ """ Make sure to append a Markdown table at the end of the report to organize key points in the report, organized and easy to read."""
f"""
You are a news researcher tasked with analyzing recent news and trends over the past week.
Please write a comprehensive report of the current state of the world that is relevant for trading and macroeconomics.
Use the available tools: get_news(query, start_date, end_date) for company-specific or targeted news searches, and get_global_news(curr_date, look_back_days, limit) for broader macroeconomic news.
Do not simply state the trends are mixed, provide detailed and finegrained analysis and insights that may help traders make decisions.
Make sure to append a Markdown table at the end of the report to organize key points in the report, organized and easy to read.
"""
)
prompt = ChatPromptTemplate.from_messages(
[
(
"system",
"You are a helpful AI assistant, collaborating with other assistants."
" Use the provided tools to progress towards answering the question."
" If you are unable to fully answer, that's OK; another assistant with different tools"
" will help where you left off. Execute what you can to make progress."
" If you or any other assistant has the FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** or deliverable,"
" prefix your response with FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** so the team knows to stop."
" You have access to the following tools: {tool_names}.\n{system_message}"
"For your reference, the current date is {current_date}. We are looking at the company {ticker}",
f"""
You are a helpful AI assistant, collaborating with other assistants.
Use the provided tools to progress towards answering the question.
If you are unable to fully answer, that's OK; another assistant with different tools will help where you left off. Execute what you can to make progress.
If you or any other assistant has the FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** or deliverable, prefix your response with FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** so the team knows to stop.
You have access to the following tools: {tools}.
{system_message}
For your reference, the current date is {current_date}.
The company we want to look at is {ticker}
Output language: ***{language_prompt}***
""",
),
MessagesPlaceholder(variable_name="messages"),
]
)
prompt = prompt.partial(system_message=system_message)
prompt = prompt.partial(tool_names=", ".join([tool.name for tool in tools]))
prompt = prompt.partial(current_date=current_date)
prompt = prompt.partial(ticker=ticker)
chain = prompt | llm.bind_tools(tools)
result = chain.invoke(state["messages"])
@ -52,7 +67,7 @@ def create_news_analyst(llm):
return {
"messages": [result],
"news_report": report,
"news_analysis": report,
}
return news_analyst_node

55
tradingagents/agents/analysts/social_media_analyst.py
View File

@ -1,11 +1,11 @@
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
import time
import json
from tradingagents.agents.utils.agent_utils import get_news
from tradingagents.dataflows.config import get_config
def create_social_media_analyst(llm):
def create_social_media_analyst(llm, config):
"""Create the social media analyst node with language support."""
def social_media_analyst_node(state):
current_date = state["trade_date"]
ticker = state["company_of_interest"]
@ -15,33 +15,48 @@ def create_social_media_analyst(llm):
get_news,
]
language = config["output_language"]
language_prompts = {
"en": "",
"zh-tw": "Use Traditional Chinese as the output.",
"zh-cn": "Use Simplified Chinese as the output.",
}
language_prompt = language_prompts.get(language, "")
system_message = (
"You are a social media and company specific news researcher/analyst tasked with analyzing social media posts, recent company news, and public sentiment for a specific company over the past week. You will be given a company's name your objective is to write a comprehensive long report detailing your analysis, insights, and implications for traders and investors on this company's current state after looking at social media and what people are saying about that company, analyzing sentiment data of what people feel each day about the company, and looking at recent company news. Use the get_news(query, start_date, end_date) tool to search for company-specific news and social media discussions. Try to look at all sources possible from social media to sentiment to news. Do not simply state the trends are mixed, provide detailed and finegrained analysis and insights that may help traders make decisions."
+ """ Make sure to append a Markdown table at the end of the report to organize key points in the report, organized and easy to read.""",
f"""
You are a social media and company specific news researcher/analyst tasked with analyzing social media posts, recent company news, and public sentiment for a specific company over the past week.
You will be given a company's name your objective is to write a comprehensive long report detailing your analysis, insights, and implications for traders and investors on this company's current state after looking at social media and what people are saying about that company, analyzing sentiment data of what people feel each day about the company, and looking at recent company news.
Use the get_news(query, start_date, end_date) tool to search for company-specific news and social media discussions.
Try to look at all sources possible from social media to sentiment to news. Do not simply state the trends are mixed, provide detailed and finegrained analysis and insights that may help traders make decisions.
Make sure to append a Markdown table at the end of the report to organize key points in the report, organized and easy to read.
"""
)
prompt = ChatPromptTemplate.from_messages(
[
(
"system",
"You are a helpful AI assistant, collaborating with other assistants."
" Use the provided tools to progress towards answering the question."
" If you are unable to fully answer, that's OK; another assistant with different tools"
" will help where you left off. Execute what you can to make progress."
" If you or any other assistant has the FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** or deliverable,"
" prefix your response with FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** so the team knows to stop."
" You have access to the following tools: {tool_names}.\n{system_message}"
"For your reference, the current date is {current_date}. The current company we want to analyze is {ticker}",
f"""
You are a helpful AI assistant, collaborating with other assistants.
Use the provided tools to progress towards answering the question.
If you are unable to fully answer, that's OK; another assistant with different tools will help where you left off. Execute what you can to make progress.
If you or any other assistant has the FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** or deliverable, prefix your response with FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** so the team knows to stop.
You have access to the following tools: {tools}.
{system_message}
For your reference, the current date is {current_date}.
The company we want to look at is {ticker}
Output language: ***{language_prompt}***
""",
),
MessagesPlaceholder(variable_name="messages"),
]
)
prompt = prompt.partial(system_message=system_message)
prompt = prompt.partial(tool_names=", ".join([tool.name for tool in tools]))
prompt = prompt.partial(current_date=current_date)
prompt = prompt.partial(ticker=ticker)
chain = prompt | llm.bind_tools(tools)
result = chain.invoke(state["messages"])
@ -53,7 +68,7 @@ def create_social_media_analyst(llm):
return {
"messages": [result],
"sentiment_report": report,
"sentiment_analysis": report,
}
return social_media_analyst_node

35
tradingagents/agents/managers/research_manager.py
View File

@ -1,28 +1,32 @@
import time
import json
def create_research_manager(llm, memory, config):
"""Create the research manager node with language support."""
language = config["output_language"]
language_prompts = {
"en": "",
"zh-tw": "Use Traditional Chinese as the output.",
"zh-cn": "Use Simplified Chinese as the output.",
}
language_prompt = language_prompts.get(language, "")
def create_research_manager(llm, memory):
def research_manager_node(state) -> dict:
history = state["investment_debate_state"].get("history", "")
market_research_report = state["market_report"]
sentiment_report = state["sentiment_report"]
news_report = state["news_report"]
fundamentals_report = state["fundamentals_report"]
market_research_report = state["market_analysis"]
sentiment_analysis = state["sentiment_analysis"]
news_analysis = state["news_analysis"]
fundamentals_analysis = state["fundamentals_analysis"]
investment_debate_state = state["investment_debate_state"]
curr_situation = f"{market_research_report}\n\n{sentiment_report}\n\n{news_report}\n\n{fundamentals_report}"
curr_situation = f"{market_research_report}\n\n{sentiment_analysis}\n\n{news_analysis}\n\n{fundamentals_analysis}"
past_memories = memory.get_memories(curr_situation, n_matches=2)
past_memory_str = ""
for i, rec in enumerate(past_memories, 1):
past_memory_str += rec["recommendation"] + "\n\n"
prompt = f"""As the portfolio manager and debate facilitator, your role is to critically evaluate this round of debate and make a definitive decision: align with the bear analyst, the bull analyst, or choose Hold only if it is strongly justified based on the arguments presented.
prompt = f"""
As the portfolio manager and debate facilitator, your role is to critically evaluate this round of debate and make a definitive decision: align with the bear analyst, the bull analyst, or choose Hold only if it is strongly justified based on the arguments presented.
Summarize the key points from both sides concisely, focusing on the most compelling evidence or reasoning. Your recommendation—Buy, Sell, or Hold—must be clear and actionable. Avoid defaulting to Hold simply because both sides have valid points; commit to a stance grounded in the debate's strongest arguments.
Additionally, develop a detailed investment plan for the trader. This should include:
Your Recommendation: A decisive stance supported by the most convincing arguments.
@ -35,7 +39,10 @@ Here are your past reflections on mistakes:
Here is the debate:
Debate History:
{history}"""
{history}
Output language: ***{language_prompt}***
"""
response = llm.invoke(prompt)
new_investment_debate_state = {
@ -49,7 +56,7 @@ Debate History:
return {
"investment_debate_state": new_investment_debate_state,
"investment_plan": response.content,
"research_team_decision": response.content,
}
return research_manager_node

36
tradingagents/agents/managers/risk_manager.py
View File

@ -1,28 +1,33 @@
import time
import json
def create_risk_manager(llm, memory, config):
"""Create the risk manager node with language support."""
language = config["output_language"]
language_prompts = {
"en": "",
"zh-tw": "Use Traditional Chinese as the output.",
"zh-cn": "Use Simplified Chinese as the output.",
}
language_prompt = language_prompts.get(language, "")
def create_risk_manager(llm, memory):
def risk_manager_node(state) -> dict:
company_name = state["company_of_interest"]
history = state["risk_debate_state"]["history"]
risk_debate_state = state["risk_debate_state"]
market_research_report = state["market_report"]
news_report = state["news_report"]
fundamentals_report = state["news_report"]
sentiment_report = state["sentiment_report"]
trader_plan = state["investment_plan"]
market_research_report = state["market_analysis"]
news_analysis = state["news_analysis"]
fundamentals_analysis = state["news_analysis"]
sentiment_analysis = state["sentiment_analysis"]
trader_plan = state["research_team_decision"]
curr_situation = f"{market_research_report}\n\n{sentiment_report}\n\n{news_report}\n\n{fundamentals_report}"
curr_situation = f"{market_research_report}\n\n{sentiment_analysis}\n\n{news_analysis}\n\n{fundamentals_analysis}"
past_memories = memory.get_memories(curr_situation, n_matches=2)
past_memory_str = ""
for i, rec in enumerate(past_memories, 1):
past_memory_str += rec["recommendation"] + "\n\n"
prompt = f"""As the Risk Management Judge and Debate Facilitator, your goal is to evaluate the debate between three risk analysts—Risky, Neutral, and Safe/Conservative—and determine the best course of action for the trader. Your decision must result in a clear recommendation: Buy, Sell, or Hold. Choose Hold only if strongly justified by specific arguments, not as a fallback when all sides seem valid. Strive for clarity and decisiveness.
prompt = f"""
As the Risk Management Judge and Debate Facilitator, your goal is to evaluate the debate between three risk analysts—Risky, Neutral, and Safe/Conservative—and determine the best course of action for the trader. Your decision must result in a clear recommendation: Buy, Sell, or Hold. Choose Hold only if strongly justified by specific arguments, not as a fallback when all sides seem valid. Strive for clarity and decisiveness.
Guidelines for Decision-Making:
1. **Summarize Key Arguments**: Extract the strongest points from each analyst, focusing on relevance to the context.
@ -41,7 +46,10 @@ Deliverables:
---
Focus on actionable insights and continuous improvement. Build on past lessons, critically evaluate all perspectives, and ensure each decision advances better outcomes."""
Focus on actionable insights and continuous improvement. Build on past lessons, critically evaluate all perspectives, and ensure each decision advances better outcomes.
Output language: ***{language_prompt}***
"""
response = llm.invoke(prompt)
@ -60,7 +68,7 @@ Focus on actionable insights and continuous improvement. Build on past lessons,
return {
"risk_debate_state": new_risk_debate_state,
"final_trade_decision": response.content,
"final_portfolio_management_decision": response.content,
}
return risk_manager_node

75
tradingagents/agents/researchers/bear_researcher.py
View File

@ -1,28 +1,35 @@
from langchain_core.messages import AIMessage
import time
import json
def create_bear_researcher(llm, memory, config):
"""Create the bear researcher node with language support."""
language = config["output_language"]
language_prompts = {
"en": "",
"zh-tw": "Use Traditional Chinese as the output.",
"zh-cn": "Use Simplified Chinese as the output.",
}
language_prompt = language_prompts.get(language, "")
def create_bear_researcher(llm, memory):
def bear_node(state) -> dict:
investment_debate_state = state["investment_debate_state"]
history = investment_debate_state.get("history", "")
bear_history = investment_debate_state.get("bear_history", "")
current_response = investment_debate_state.get("current_response", "")
market_research_report = state["market_report"]
sentiment_report = state["sentiment_report"]
news_report = state["news_report"]
fundamentals_report = state["fundamentals_report"]
market_research_report = state["market_analysis"]
sentiment_analysis = state["sentiment_analysis"]
news_analysis = state["news_analysis"]
fundamentals_analysis = state["fundamentals_analysis"]
curr_situation = f"{market_research_report}\n\n{sentiment_report}\n\n{news_report}\n\n{fundamentals_report}"
curr_situation = f"{market_research_report}\n\n{sentiment_analysis}\n\n{news_analysis}\n\n{fundamentals_analysis}"
past_memories = memory.get_memories(curr_situation, n_matches=2)
past_memory_str = ""
for i, rec in enumerate(past_memories, 1):
past_memory_str += rec["recommendation"] + "\n\n"
prompt = f"""You are a Bear Analyst making the case against investing in the stock. Your goal is to present a well-reasoned argument emphasizing risks, challenges, and negative indicators. Leverage the provided research and data to highlight potential downsides and counter bullish arguments effectively.
prompt = f"""
You are a Bear Analyst making the case against investing in the stock.
Your goal is to present a well-reasoned argument emphasizing risks, challenges, and negative indicators.
Leverage the provided research and data to highlight potential downsides and counter bullish arguments effectively.
Key points to focus on:
@ -33,15 +40,45 @@ Key points to focus on:
- Engagement: Present your argument in a conversational style, directly engaging with the bull analyst's points and debating effectively rather than simply listing facts.
Resources available:
Market research report:
{market_research_report}
Market research report: {market_research_report}
Social media sentiment report: {sentiment_report}
Latest world affairs news: {news_report}
Company fundamentals report: {fundamentals_report}
Conversation history of the debate: {history}
Last bull argument: {current_response}
Reflections from similar situations and lessons learned: {past_memory_str}
Use this information to deliver a compelling bear argument, refute the bull's claims, and engage in a dynamic debate that demonstrates the risks and weaknesses of investing in the stock. You must also address reflections and learn from lessons and mistakes you made in the past.
--------------------------------------
Social media sentiment report:
{sentiment_analysis}
--------------------------------------
Latest world affairs news:
{news_analysis}
--------------------------------------
Company fundamentals report:
{fundamentals_analysis}
--------------------------------------
Conversation history of the debate:
{history}
--------------------------------------
Last bull argument:
{current_response}
--------------------------------------
Reflections from similar situations and lessons learned:
{past_memory_str}
--------------------------------------
Use this information to deliver a compelling bear argument, refute the bull's claims, and engage in a dynamic debate that demonstrates the risks and weaknesses of investing in the stock.
You must also address reflections and learn from lessons and mistakes you made in the past.
Output language: ***{language_prompt}***
"""
response = llm.invoke(prompt)

75
tradingagents/agents/researchers/bull_researcher.py
View File

@ -1,28 +1,35 @@
from langchain_core.messages import AIMessage
import time
import json
def create_bull_researcher(llm, memory, config):
"""Create the bull researcher node with language support."""
language = config["output_language"]
language_prompts = {
"en": "",
"zh-tw": "Use Traditional Chinese as the output.",
"zh-cn": "Use Simplified Chinese as the output.",
}
language_prompt = language_prompts.get(language, "")
def create_bull_researcher(llm, memory):
def bull_node(state) -> dict:
investment_debate_state = state["investment_debate_state"]
history = investment_debate_state.get("history", "")
bull_history = investment_debate_state.get("bull_history", "")
current_response = investment_debate_state.get("current_response", "")
market_research_report = state["market_report"]
sentiment_report = state["sentiment_report"]
news_report = state["news_report"]
fundamentals_report = state["fundamentals_report"]
market_research_report = state["market_analysis"]
sentiment_analysis = state["sentiment_analysis"]
news_analysis = state["news_analysis"]
fundamentals_analysis = state["fundamentals_analysis"]
curr_situation = f"{market_research_report}\n\n{sentiment_report}\n\n{news_report}\n\n{fundamentals_report}"
curr_situation = f"{market_research_report}\n\n{sentiment_analysis}\n\n{news_analysis}\n\n{fundamentals_analysis}"
past_memories = memory.get_memories(curr_situation, n_matches=2)
past_memory_str = ""
for i, rec in enumerate(past_memories, 1):
past_memory_str += rec["recommendation"] + "\n\n"
prompt = f"""You are a Bull Analyst advocating for investing in the stock. Your task is to build a strong, evidence-based case emphasizing growth potential, competitive advantages, and positive market indicators. Leverage the provided research and data to address concerns and counter bearish arguments effectively.
prompt = f"""
You are a Bull Analyst advocating for investing in the stock.
Your task is to build a strong, evidence-based case emphasizing growth potential, competitive advantages, and positive market indicators.
Leverage the provided research and data to address concerns and counter bearish arguments effectively.
Key points to focus on:
- Growth Potential: Highlight the company's market opportunities, revenue projections, and scalability.
@ -32,14 +39,44 @@ Key points to focus on:
- Engagement: Present your argument in a conversational style, engaging directly with the bear analyst's points and debating effectively rather than just listing data.
Resources available:
Market research report: {market_research_report}
Social media sentiment report: {sentiment_report}
Latest world affairs news: {news_report}
Company fundamentals report: {fundamentals_report}
Conversation history of the debate: {history}
Last bear argument: {current_response}
Reflections from similar situations and lessons learned: {past_memory_str}
Use this information to deliver a compelling bull argument, refute the bear's concerns, and engage in a dynamic debate that demonstrates the strengths of the bull position. You must also address reflections and learn from lessons and mistakes you made in the past.
Market research report:
{market_research_report}
--------------------------------------
Social media sentiment report:
{sentiment_analysis}
--------------------------------------
Latest world affairs news:
{news_analysis}
--------------------------------------
Company fundamentals report:
{fundamentals_analysis}
--------------------------------------
Conversation history of the debate:
{history}
--------------------------------------
Last bear argument:
{current_response}
--------------------------------------
Reflections from similar situations and lessons learned:
{past_memory_str}
--------------------------------------
Use this information to deliver a compelling bull argument, refute the bear's concerns, and engage in a dynamic debate that demonstrates the strengths of the bull position.
You must also address reflections and learn from lessons and mistakes you made in the past.
Output language: ***{language_prompt}***
"""
response = llm.invoke(prompt)

84
tradingagents/agents/risk_mgmt/aggresive_debator.py
View File

@ -1,8 +1,13 @@
import time
import json
def create_risky_debator(llm, config):
"""Create the risky debator node with language support."""
language = config["output_language"]
language_prompts = {
"en": "",
"zh-tw": "Use Traditional Chinese as the output.",
"zh-cn": "Use Simplified Chinese as the output.",
}
language_prompt = language_prompts.get(language, "")
def create_risky_debator(llm):
def risky_node(state) -> dict:
risk_debate_state = state["risk_debate_state"]
history = risk_debate_state.get("history", "")
@ -11,26 +16,69 @@ def create_risky_debator(llm):
current_safe_response = risk_debate_state.get("current_safe_response", "")
current_neutral_response = risk_debate_state.get("current_neutral_response", "")
market_research_report = state["market_report"]
sentiment_report = state["sentiment_report"]
news_report = state["news_report"]
fundamentals_report = state["fundamentals_report"]
market_research_report = state["market_analysis"]
sentiment_analysis = state["sentiment_analysis"]
news_analysis = state["news_analysis"]
fundamentals_analysis = state["fundamentals_analysis"]
trader_decision = state["trader_investment_plan"]
prompt = f"""As the Risky Risk Analyst, your role is to actively champion high-reward, high-risk opportunities, emphasizing bold strategies and competitive advantages. When evaluating the trader's decision or plan, focus intently on the potential upside, growth potential, and innovative benefits—even when these come with elevated risk. Use the provided market data and sentiment analysis to strengthen your arguments and challenge the opposing views. Specifically, respond directly to each point made by the conservative and neutral analysts, countering with data-driven rebuttals and persuasive reasoning. Highlight where their caution might miss critical opportunities or where their assumptions may be overly conservative. Here is the trader's decision:
trader_decision = state["trader_team_plan"]
prompt = f"""
As the Risky Risk Analyst, your role is to actively champion high-reward, high-risk opportunities, emphasizing bold strategies and competitive advantages.
When evaluating the trader's decision or plan, focus intently on the potential upside, growth potential, and innovative benefits—even when these come with elevated risk.
Use the provided market data and sentiment analysis to strengthen your arguments and challenge the opposing views.
Specifically, respond directly to each point made by the conservative and neutral analysts, countering with data-driven rebuttals and persuasive reasoning.
Highlight where their caution might miss critical opportunities or where their assumptions may be overly conservative.
Here is the trader's decision:
{trader_decision}
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:
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:
Market Research Report: {market_research_report}
Social Media Sentiment Report: {sentiment_report}
Latest World Affairs Report: {news_report}
Company Fundamentals Report: {fundamentals_report}
Here is the current conversation history: {history} Here are the last arguments from the conservative analyst: {current_safe_response} Here are the last arguments from the neutral analyst: {current_neutral_response}. If there are no responses from the other viewpoints, do not halluncinate and just present your point.
Market Research Report:
{market_research_report}
Engage actively by addressing any specific concerns raised, refuting the weaknesses in their logic, and asserting the benefits of risk-taking to outpace market norms. Maintain a focus on debating and persuading, not just presenting data. Challenge each counterpoint to underscore why a high-risk approach is optimal. Output conversationally as if you are speaking without any special formatting."""
--------------------------------------
Social Media Sentiment Report:
{sentiment_analysis}
--------------------------------------
Latest World Affairs Report:
{news_analysis}
--------------------------------------
Company Fundamentals Report:
{fundamentals_analysis}
--------------------------------------
Here is the current conversation history:
{history}
--------------------------------------
Here are the last arguments from the conservative analyst:
{current_safe_response}
--------------------------------------
Here are the last arguments from the neutral analyst:
{current_neutral_response}
--------------------------------------
If there are no responses from the other viewpoints, do not halluncinate and just present your point.
Engage actively by addressing any specific concerns raised, refuting the weaknesses in their logic, and asserting the benefits of risk-taking to outpace market norms.
Maintain a focus on debating and persuading, not just presenting data.
Challenge each counterpoint to underscore why a high-risk approach is optimal. Output conversationally as if you are speaking without any special formatting.
Output language: ***{language_prompt}***
"""
response = llm.invoke(prompt)

84
tradingagents/agents/risk_mgmt/conservative_debator.py
View File

@ -1,9 +1,14 @@
from langchain_core.messages import AIMessage
import time
import json
def create_safe_debator(llm, config):
"""Create the safe debator node with language support."""
language = config["output_language"]
language = config["output_language"]
language_prompts = {
"en": "",
"zh-tw": "Use Traditional Chinese as the output.",
"zh-cn": "Use Simplified Chinese as the output.",
}
language_prompt = language_prompts.get(language, "")
def create_safe_debator(llm):
def safe_node(state) -> dict:
risk_debate_state = state["risk_debate_state"]
history = risk_debate_state.get("history", "")
@ -12,26 +17,67 @@ def create_safe_debator(llm):
current_risky_response = risk_debate_state.get("current_risky_response", "")
current_neutral_response = risk_debate_state.get("current_neutral_response", "")
market_research_report = state["market_report"]
sentiment_report = state["sentiment_report"]
news_report = state["news_report"]
fundamentals_report = state["fundamentals_report"]
market_research_report = state["market_analysis"]
sentiment_analysis = state["sentiment_analysis"]
news_analysis = state["news_analysis"]
fundamentals_analysis = state["fundamentals_analysis"]
trader_decision = state["trader_investment_plan"]
prompt = f"""As the Safe/Conservative Risk Analyst, your primary objective is to protect assets, minimize volatility, and ensure steady, reliable growth. You prioritize stability, security, and risk mitigation, carefully assessing potential losses, economic downturns, and market volatility. When evaluating the trader's decision or plan, critically examine high-risk elements, pointing out where the decision may expose the firm to undue risk and where more cautious alternatives could secure long-term gains. Here is the trader's decision:
trader_decision = state["trader_team_plan"]
prompt = f"""
As the Safe/Conservative Risk Analyst, your primary objective is to protect assets, minimize volatility, and ensure steady, reliable growth.
You prioritize stability, security, and risk mitigation, carefully assessing potential losses, economic downturns, and market volatility.
When evaluating the trader's decision or plan, critically examine high-risk elements, pointing out where the decision may expose the firm to undue risk and where more cautious alternatives could secure long-term gains.
Here is the trader's decision:
{trader_decision}
Your task is to actively counter the arguments of the Risky and Neutral Analysts, highlighting where their views may overlook potential threats or fail to prioritize sustainability. Respond directly to their points, drawing from the following data sources to build a convincing case for a low-risk approach adjustment to the trader's decision:
Your task is to actively counter the arguments of the Risky and Neutral Analysts, highlighting where their views may overlook potential threats or fail to prioritize sustainability.
Respond directly to their points, drawing from the following data sources to build a convincing case for a low-risk approach adjustment to the trader's decision:
Market Research Report: {market_research_report}
Social Media Sentiment Report: {sentiment_report}
Latest World Affairs Report: {news_report}
Company Fundamentals Report: {fundamentals_report}
Here is the current conversation history: {history} Here is the last response from the risky analyst: {current_risky_response} Here is the last response from the neutral analyst: {current_neutral_response}. If there are no responses from the other viewpoints, do not halluncinate and just present your point.
Market Research Report:
{market_research_report}
Engage by questioning their optimism and emphasizing the potential downsides they may have overlooked. Address each of their counterpoints to showcase why a conservative stance is ultimately the safest path for the firm's assets. Focus on debating and critiquing their arguments to demonstrate the strength of a low-risk strategy over their approaches. Output conversationally as if you are speaking without any special formatting."""
--------------------------------------
Social Media Sentiment Report:
{sentiment_analysis}
--------------------------------------
Latest World Affairs Report:
{news_analysis}
--------------------------------------
Company Fundamentals Report:
{fundamentals_analysis}
--------------------------------------
Here is the current conversation history:
{history}
--------------------------------------
Here is the last response from the risky analyst:
{current_risky_response}
--------------------------------------
Here is the last response from the neutral analyst:
{current_neutral_response}
--------------------------------------
If there are no responses from the other viewpoints, do not halluncinate and just present your point.
Engage by questioning their optimism and emphasizing the potential downsides they may have overlooked.
Address each of their counterpoints to showcase why a conservative stance is ultimately the safest path for the firm's assets.
Focus on debating and critiquing their arguments to demonstrate the strength of a low-risk strategy over their approaches.
Output conversationally as if you are speaking without any special formatting.
Output language: ***{language_prompt}***
"""
response = llm.invoke(prompt)

79
tradingagents/agents/risk_mgmt/neutral_debator.py
View File

@ -1,8 +1,13 @@
import time
import json
def create_neutral_debator(llm, config):
"""Create the neutral debator node with language support."""
language = config["output_language"]
language_prompts = {
"en": "",
"zh-tw": "Use Traditional Chinese as the output.",
"zh-cn": "Use Simplified Chinese as the output.",
}
language_prompt = language_prompts.get(language, "")
def create_neutral_debator(llm):
def neutral_node(state) -> dict:
risk_debate_state = state["risk_debate_state"]
history = risk_debate_state.get("history", "")
@ -11,26 +16,66 @@ def create_neutral_debator(llm):
current_risky_response = risk_debate_state.get("current_risky_response", "")
current_safe_response = risk_debate_state.get("current_safe_response", "")
market_research_report = state["market_report"]
sentiment_report = state["sentiment_report"]
news_report = state["news_report"]
fundamentals_report = state["fundamentals_report"]
market_research_report = state["market_analysis"]
sentiment_analysis = state["sentiment_analysis"]
news_analysis = state["news_analysis"]
fundamentals_analysis = state["fundamentals_analysis"]
trader_decision = state["trader_investment_plan"]
trader_decision = state["trader_team_plan"]
prompt = f"""As the Neutral Risk Analyst, your role is to provide a balanced perspective, weighing both the potential benefits and risks of the trader's decision or plan. You prioritize a well-rounded approach, evaluating the upsides and downsides while factoring in broader market trends, potential economic shifts, and diversification strategies.Here is the trader's decision:
prompt = f"""
As the Neutral Risk Analyst, your role is to provide a balanced perspective, weighing both the potential benefits and risks of the trader's decision or plan.
You prioritize a well-rounded approach, evaluating the upsides and downsides while factoring in broader market trends, potential economic shifts, and diversification strategies.
Here is the trader's decision:
{trader_decision}
Your task is to challenge both the Risky and Safe Analysts, pointing out where each perspective may be overly optimistic or overly cautious. Use insights from the following data sources to support a moderate, sustainable strategy to adjust the trader's decision:
Your task is to challenge both the Risky and Safe Analysts, pointing out where each perspective may be overly optimistic or overly cautious.
Use insights from the following data sources to support a moderate, sustainable strategy to adjust the trader's decision:
Market Research Report: {market_research_report}
Social Media Sentiment Report: {sentiment_report}
Latest World Affairs Report: {news_report}
Company Fundamentals Report: {fundamentals_report}
Here is the current conversation history: {history} Here is the last response from the risky analyst: {current_risky_response} Here is the last response from the safe analyst: {current_safe_response}. If there are no responses from the other viewpoints, do not halluncinate and just present your point.
Market Research Report:
{market_research_report}
Engage actively by analyzing both sides critically, addressing weaknesses in the risky and conservative arguments to advocate for a more balanced approach. Challenge each of their points to illustrate why a moderate risk strategy might offer the best of both worlds, providing growth potential while safeguarding against extreme volatility. Focus on debating rather than simply presenting data, aiming to show that a balanced view can lead to the most reliable outcomes. Output conversationally as if you are speaking without any special formatting."""
--------------------------------------
Social Media Sentiment Report:
{sentiment_analysis}
--------------------------------------
Latest World Affairs Report:
{news_analysis}
--------------------------------------
Company Fundamentals Report:
{fundamentals_analysis}
--------------------------------------
Here is the current conversation history:
{history}
--------------------------------------
Here is the last response from the risky analyst:
{current_risky_response}
--------------------------------------
Here is the last response from the safe analyst:
{current_safe_response}
--------------------------------------
If there are no responses from the other viewpoints, do not halluncinate and just present your point.
Engage actively by analyzing both sides critically, addressing weaknesses in the risky and conservative arguments to advocate for a more balanced approach.
Challenge each of their points to illustrate why a moderate risk strategy might offer the best of both worlds, providing growth potential while safeguarding against extreme volatility.
Focus on debating rather than simply presenting data, aiming to show that a balanced view can lead to the most reliable outcomes.
Output conversationally as if you are speaking without any special formatting.
Output language: ***{language_prompt}***
"""
response = llm.invoke(prompt)

54
tradingagents/agents/trader/trader.py
View File

@ -1,18 +1,25 @@
import functools
import time
import json
def create_trader(llm, memory):
def create_trader(llm, memory, config):
"""Create the trader node with language support."""
language = config["output_language"]
language_prompts = {
"en": "",
"zh-tw": "Use Traditional Chinese as the output.",
"zh-cn": "Use Simplified Chinese as the output.",
}
language_prompt = language_prompts.get(language, "")
def trader_node(state, name):
company_name = state["company_of_interest"]
investment_plan = state["investment_plan"]
market_research_report = state["market_report"]
sentiment_report = state["sentiment_report"]
news_report = state["news_report"]
fundamentals_report = state["fundamentals_report"]
research_team_decision = state["research_team_decision"]
market_research_report = state["market_analysis"]
sentiment_analysis = state["sentiment_analysis"]
news_analysis = state["news_analysis"]
fundamentals_analysis = state["fundamentals_analysis"]
curr_situation = f"{market_research_report}\n\n{sentiment_report}\n\n{news_report}\n\n{fundamentals_report}"
curr_situation = f"{market_research_report}\n\n{sentiment_analysis}\n\n{news_analysis}\n\n{fundamentals_analysis}"
past_memories = memory.get_memories(curr_situation, n_matches=2)
past_memory_str = ""
@ -24,13 +31,36 @@ def create_trader(llm, memory):
context = {
"role": "user",
"content": f"Based on a comprehensive analysis by a team of analysts, here is an investment plan tailored for {company_name}. This plan incorporates insights from current technical market trends, macroeconomic indicators, and social media sentiment. Use this plan as a foundation for evaluating your next trading decision.\n\nProposed Investment Plan: {investment_plan}\n\nLeverage these insights to make an informed and strategic decision.",
"content": f"""
Based on a comprehensive analysis by a team of analysts, here is an investment plan tailored for {company_name}.
This plan incorporates insights from current technical market trends, macroeconomic indicators, and social media sentiment.
Use this plan as a foundation for evaluating your next trading decision.
Proposed Investment Plan:
{research_team_decision}
--------------------------------------
Leverage these insights to make an informed and strategic decision.
""",
}
messages = [
{
"role": "system",
"content": f"""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. End with a firm decision and always conclude your response with 'FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL**' to confirm your recommendation. Do not forget to utilize lessons from past decisions to learn from your mistakes. Here is some reflections from similar situatiosn you traded in and the lessons learned: {past_memory_str}""",
"content": f"""
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.
End with a firm decision and always conclude your response with 'FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL**' to confirm your recommendation.
Do not forget to utilize lessons from past decisions to learn from your mistakes.
Here is some reflections from similar situations you traded in and the lessons learned:
{past_memory_str}
--------------------------------------
Output language: ***{language_prompt}***
""",
},
context,
]
@ -39,7 +69,7 @@ def create_trader(llm, memory):
return {
"messages": [result],
"trader_investment_plan": result.content,
"trader_team_plan": result.content,
"sender": name,
}

25
tradingagents/agents/utils/agent_states.py
View File

@ -1,10 +1,7 @@
from typing import Annotated, Sequence
from datetime import date, timedelta, datetime
from typing_extensions import TypedDict, Optional
from langchain_openai import ChatOpenAI
from tradingagents.agents import *
from langgraph.prebuilt import ToolNode
from langgraph.graph import END, StateGraph, START, MessagesState
from typing import Annotated
from langgraph.graph import MessagesState
from typing_extensions import TypedDict
# Researcher team state
@ -54,23 +51,23 @@ class AgentState(MessagesState):
sender: Annotated[str, "Agent that sent this message"]
# research step
market_report: Annotated[str, "Report from the Market Analyst"]
sentiment_report: Annotated[str, "Report from the Social Media Analyst"]
news_report: Annotated[
market_analysis: Annotated[str, "Report from the Market Analyst"]
sentiment_analysis: Annotated[str, "Report from the Social Media Analyst"]
news_analysis: Annotated[
str, "Report from the News Researcher of current world affairs"
]
fundamentals_report: Annotated[str, "Report from the Fundamentals Researcher"]
fundamentals_analysis: Annotated[str, "Report from the Fundamentals Researcher"]
# researcher team discussion step
investment_debate_state: Annotated[
InvestDebateState, "Current state of the debate on if to invest or not"
]
investment_plan: Annotated[str, "Plan generated by the Analyst"]
research_team_decision: Annotated[str, "Plan generated by the Analyst"]
trader_investment_plan: Annotated[str, "Plan generated by the Trader"]
trader_team_plan: Annotated[str, "Plan generated by the Trader"]
# risk management team discussion step
risk_debate_state: Annotated[
RiskDebateState, "Current state of the debate on evaluating risk"
]
final_trade_decision: Annotated[str, "Final decision made by the Risk Analysts"]
final_portfolio_management_decision: Annotated[str, "Final decision made by the Risk Analysts"]

34
tradingagents/agents/utils/memory.py
View File

@ -1,25 +1,41 @@
import chromadb
from chromadb.config import Settings
from openai import OpenAI
from sentence_transformers import SentenceTransformer
class FinancialSituationMemory:
def __init__(self, name, config):
if config["backend_url"] == "http://localhost:11434/v1":
# Based on llm_provider to select embeddings
if config["llm_provider"] == "ollama":
self.embedding = "nomic-embed-text"
else:
self.embedding_client = OpenAI(base_url="http://localhost:11434/v1")
self.use_local_embedding = False
elif config["llm_provider"] == "openai":
self.client = OpenAI(base_url=config["backend_url"], api_key=config.get("api_key"))
self.embedding = "text-embedding-3-small"
self.client = OpenAI(base_url=config["backend_url"])
self.embedding_client = self.client
self.use_local_embedding = False
else:
# use local Hugging Face model
self.embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
self.use_local_embedding = True
self.chroma_client = chromadb.Client(Settings(allow_reset=True))
self.situation_collection = self.chroma_client.create_collection(name=name)
def get_embedding(self, text):
"""Get OpenAI embedding for a text"""
response = self.client.embeddings.create(
model=self.embedding, input=text
)
return response.data[0].embedding
"""Get embedding for a text"""
if self.use_local_embedding:
# use local Hugging Face model
return self.embedding_model.encode(text).tolist()
else:
# use API
response = self.embedding_client.embeddings.create(
model=self.embedding,
input=text
)
return response.data[0].embedding
def add_situations(self, situations_and_advice):
"""Add financial situations and their corresponding advice. Parameter is a list of tuples (situation, rec)"""

1
tradingagents/default_config.py
View File

@ -30,4 +30,5 @@ DEFAULT_CONFIG = {
# Example: "get_stock_data": "alpha_vantage", # Override category default
# Example: "get_news": "openai", # Override category default
},
"output_language": "en",
}

12
tradingagents/graph/propagation.py
View File

@ -1,8 +1,8 @@
# TradingAgents/graph/propagation.py
from typing import Dict, Any
from tradingagents.agents.utils.agent_states import (
AgentState,
InvestDebateState,
RiskDebateState,
)
@ -16,7 +16,7 @@ class Propagator:
self.max_recur_limit = max_recur_limit
def create_initial_state(
self, company_name: str, trade_date: str
self, company_name: str, trade_date: str
) -> Dict[str, Any]:
"""Create the initial state for the agent graph."""
return {
@ -35,10 +35,10 @@ class Propagator:
"count": 0,
}
),
"market_report": "",
"fundamentals_report": "",
"sentiment_report": "",
"news_report": "",
"market_analysis": "",
"fundamentals_analysis": "",
"sentiment_analysis": "",
"news_analysis": "",
}
def get_graph_args(self) -> Dict[str, Any]:

39
tradingagents/graph/reflection.py
View File

@ -1,20 +1,29 @@
# TradingAgents/graph/reflection.py
from typing import Dict, Any
from langchain_openai import ChatOpenAI
from langchain_core.language_models.chat_models import BaseChatModel
class Reflector:
"""Handles reflection on decisions and updating memory."""
def __init__(self, quick_thinking_llm: ChatOpenAI):
def __init__(self, quick_thinking_llm: BaseChatModel, config):
"""Initialize the reflector with an LLM."""
language = config["output_language"]
language_prompts = {
"en": "",
"zh-tw": "Use Traditional Chinese as the output.",
"zh-cn": "Use Simplified Chinese as the output.",
}
self.language_prompt = language_prompts.get(language, "")
self.quick_thinking_llm = quick_thinking_llm
self.reflection_system_prompt = self._get_reflection_prompt()
def _get_reflection_prompt(self) -> str:
"""Get the system prompt for reflection."""
return """
return f"""
You are an expert financial analyst tasked with reviewing trading decisions/analysis and providing a comprehensive, step-by-step analysis.
Your goal is to deliver detailed insights into investment decisions and highlight opportunities for improvement, adhering strictly to the following guidelines:
@ -44,26 +53,36 @@ Your goal is to deliver detailed insights into investment decisions and highligh
- Ensure the condensed sentence captures the essence of the lessons and reasoning for easy reference.
Adhere strictly to these instructions, and ensure your output is detailed, accurate, and actionable. You will also be given objective descriptions of the market from a price movements, technical indicator, news, and sentiment perspective to provide more context for your analysis.
Output language: ***{self.language_prompt}***
"""
def _extract_current_situation(self, current_state: Dict[str, Any]) -> str:
"""Extract the current market situation from the state."""
curr_market_report = current_state["market_report"]
curr_sentiment_report = current_state["sentiment_report"]
curr_news_report = current_state["news_report"]
curr_fundamentals_report = current_state["fundamentals_report"]
curr_market_report = current_state["market_analysis"]
curr_sentiment_report = current_state["sentiment_analysis"]
curr_news_report = current_state["news_analysis"]
curr_fundamentals_report = current_state["fundamentals_analysis"]
return f"{curr_market_report}\n\n{curr_sentiment_report}\n\n{curr_news_report}\n\n{curr_fundamentals_report}"
def _reflect_on_component(
self, component_type: str, report: str, situation: str, returns_losses
self, component_type: str, report: str, situation: str, returns_losses
) -> str:
"""Generate reflection for a component."""
messages = [
("system", self.reflection_system_prompt),
(
"human",
f"Returns: {returns_losses}\n\nAnalysis/Decision: {report}\n\nObjective Market Reports for Reference: {situation}",
f"""
Returns: {returns_losses}
Analysis/Decision: {report}
Objective Market Reports for Reference: {situation}
""",
),
]
@ -93,7 +112,7 @@ Adhere strictly to these instructions, and ensure your output is detailed, accur
def reflect_trader(self, current_state, returns_losses, trader_memory):
"""Reflect on trader's decision and update memory."""
situation = self._extract_current_situation(current_state)
trader_decision = current_state["trader_investment_plan"]
trader_decision = current_state["trader_team_plan"]
result = self._reflect_on_component(
"TRADER", trader_decision, situation, returns_losses

54
tradingagents/graph/setup.py
View File

@ -1,13 +1,13 @@
# TradingAgents/graph/setup.py
from typing import Dict, Any
from langchain_openai import ChatOpenAI
from langchain_core.language_models.chat_models import BaseChatModel
from langgraph.graph import END, StateGraph, START
from langgraph.prebuilt import ToolNode
from tradingagents.agents import *
from tradingagents.agents.utils.agent_states import AgentState
from .conditional_logic import ConditionalLogic
@ -15,16 +15,17 @@ class GraphSetup:
"""Handles the setup and configuration of the agent graph."""
def __init__(
self,
quick_thinking_llm: ChatOpenAI,
deep_thinking_llm: ChatOpenAI,
tool_nodes: Dict[str, ToolNode],
bull_memory,
bear_memory,
trader_memory,
invest_judge_memory,
risk_manager_memory,
conditional_logic: ConditionalLogic,
self,
quick_thinking_llm: BaseChatModel,
deep_thinking_llm: BaseChatModel,
tool_nodes: Dict[str, ToolNode],
bull_memory,
bear_memory,
trader_memory,
invest_judge_memory,
risk_manager_memory,
conditional_logic: ConditionalLogic,
config: Dict[str, Any],
):
"""Initialize with required components."""
self.quick_thinking_llm = quick_thinking_llm
@ -36,9 +37,10 @@ class GraphSetup:
self.invest_judge_memory = invest_judge_memory
self.risk_manager_memory = risk_manager_memory
self.conditional_logic = conditional_logic
self.config = config
def setup_graph(
self, selected_analysts=["market", "social", "news", "fundamentals"]
self, selected_analysts=["market", "social", "news", "fundamentals"]
):
"""Set up and compile the agent workflow graph.
@ -59,50 +61,50 @@ class GraphSetup:
if "market" in selected_analysts:
analyst_nodes["market"] = create_market_analyst(
self.quick_thinking_llm
self.quick_thinking_llm, self.config
)
delete_nodes["market"] = create_msg_delete()
tool_nodes["market"] = self.tool_nodes["market"]
if "social" in selected_analysts:
analyst_nodes["social"] = create_social_media_analyst(
self.quick_thinking_llm
self.quick_thinking_llm, self.config
)
delete_nodes["social"] = create_msg_delete()
tool_nodes["social"] = self.tool_nodes["social"]
if "news" in selected_analysts:
analyst_nodes["news"] = create_news_analyst(
self.quick_thinking_llm
self.quick_thinking_llm, self.config
)
delete_nodes["news"] = create_msg_delete()
tool_nodes["news"] = self.tool_nodes["news"]
if "fundamentals" in selected_analysts:
analyst_nodes["fundamentals"] = create_fundamentals_analyst(
self.quick_thinking_llm
self.quick_thinking_llm, self.config
)
delete_nodes["fundamentals"] = create_msg_delete()
tool_nodes["fundamentals"] = self.tool_nodes["fundamentals"]
# Create researcher and manager nodes
bull_researcher_node = create_bull_researcher(
self.quick_thinking_llm, self.bull_memory
self.quick_thinking_llm, self.bull_memory, self.config
)
bear_researcher_node = create_bear_researcher(
self.quick_thinking_llm, self.bear_memory
self.quick_thinking_llm, self.bear_memory, self.config
)
research_manager_node = create_research_manager(
self.deep_thinking_llm, self.invest_judge_memory
self.deep_thinking_llm, self.invest_judge_memory, self.config
)
trader_node = create_trader(self.quick_thinking_llm, self.trader_memory)
trader_node = create_trader(self.quick_thinking_llm, self.trader_memory, self.config)
# Create risk analysis nodes
risky_analyst = create_risky_debator(self.quick_thinking_llm)
neutral_analyst = create_neutral_debator(self.quick_thinking_llm)
safe_analyst = create_safe_debator(self.quick_thinking_llm)
risky_analyst = create_risky_debator(self.quick_thinking_llm, self.config)
neutral_analyst = create_neutral_debator(self.quick_thinking_llm, self.config)
safe_analyst = create_safe_debator(self.quick_thinking_llm, self.config)
risk_manager_node = create_risk_manager(
self.deep_thinking_llm, self.risk_manager_memory
self.deep_thinking_llm, self.risk_manager_memory, self.config
)
# Create workflow
@ -147,7 +149,7 @@ class GraphSetup:
# Connect to next analyst or to Bull Researcher if this is the last analyst
if i < len(selected_analysts) - 1:
next_analyst = f"{selected_analysts[i+1].capitalize()} Analyst"
next_analyst = f"{selected_analysts[i + 1].capitalize()} Analyst"
workflow.add_edge(current_clear, next_analyst)
else:
workflow.add_edge(current_clear, "Bull Researcher")

21
tradingagents/graph/signal_processing.py
View File

@ -1,13 +1,22 @@
# TradingAgents/graph/signal_processing.py
from langchain_openai import ChatOpenAI
from langchain_core.language_models.chat_models import BaseChatModel
class SignalProcessor:
"""Processes trading signals to extract actionable decisions."""
def __init__(self, quick_thinking_llm: ChatOpenAI):
def __init__(self, quick_thinking_llm: BaseChatModel, config):
"""Initialize with an LLM for processing."""
language = config["output_language"]
language_prompts = {
"en": "",
"zh-tw": "Use Traditional Chinese as the output.",
"zh-cn": "Use Simplified Chinese as the output.",
}
self.language_prompt = language_prompts.get(language, "")
self.quick_thinking_llm = quick_thinking_llm
def process_signal(self, full_signal: str) -> str:
@ -23,7 +32,13 @@ class SignalProcessor:
messages = [
(
"system",
"You are an efficient assistant designed to analyze paragraphs or financial reports provided by a group of analysts. Your task is to extract the investment decision: SELL, BUY, or HOLD. Provide only the extracted decision (SELL, BUY, or HOLD) as your output, without adding any additional text or information.",
f"""
You are an efficient assistant designed to analyze paragraphs or financial reports provided by a group of analysts.
Your task is to extract the investment decision: SELL, BUY, or HOLD.
Provide only the extracted decision (SELL, BUY, or HOLD) as your output, without adding any additional text or information.
Output language: ***{self.language_prompt}***
""",
),
("human", full_signal),
]

78
tradingagents/graph/trading_graph.py
View File

@ -1,27 +1,16 @@
# TradingAgents/graph/trading_graph.py
import json
import os
from pathlib import Path
import json
from datetime import date
from typing import Dict, Any, Tuple, List, Optional
from typing import Dict, Any
from langchain_openai import ChatOpenAI
from langchain_anthropic import ChatAnthropic
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_openai import ChatOpenAI
from langchain_xai import ChatXAI
from langgraph.prebuilt import ToolNode
from tradingagents.agents import *
from tradingagents.default_config import DEFAULT_CONFIG
from tradingagents.agents.utils.memory import FinancialSituationMemory
from tradingagents.agents.utils.agent_states import (
AgentState,
InvestDebateState,
RiskDebateState,
)
from tradingagents.dataflows.config import set_config
# Import the new abstract tool methods from agent_utils
from tradingagents.agents.utils.agent_utils import (
get_stock_data,
@ -35,11 +24,13 @@ from tradingagents.agents.utils.agent_utils import (
get_insider_transactions,
get_global_news
)
from tradingagents.agents.utils.memory import FinancialSituationMemory
from tradingagents.dataflows.config import set_config
from tradingagents.default_config import DEFAULT_CONFIG
from .conditional_logic import ConditionalLogic
from .setup import GraphSetup
from .propagation import Propagator
from .reflection import Reflector
from .setup import GraphSetup
from .signal_processing import SignalProcessor
@ -47,10 +38,10 @@ class TradingAgentsGraph:
"""Main class that orchestrates the trading agents framework."""
def __init__(
self,
selected_analysts=["market", "social", "news", "fundamentals"],
debug=False,
config: Dict[str, Any] = None,
self,
selected_analysts=["market", "social", "news", "fundamentals"],
debug=False,
config: Dict[str, Any] = None,
):
"""Initialize the trading agents graph and components.
@ -72,18 +63,26 @@ class TradingAgentsGraph:
)
# Initialize LLMs
if self.config["llm_provider"].lower() == "openai" or self.config["llm_provider"] == "ollama" or self.config["llm_provider"] == "openrouter":
self.deep_thinking_llm = ChatOpenAI(model=self.config["deep_think_llm"], base_url=self.config["backend_url"])
self.quick_thinking_llm = ChatOpenAI(model=self.config["quick_think_llm"], base_url=self.config["backend_url"])
if self.config["llm_provider"].lower() == "openai" or self.config["llm_provider"] == "ollama" or self.config[
"llm_provider"] == "openrouter":
self.deep_thinking_llm = ChatOpenAI(model=self.config["deep_think_llm"],
base_url=self.config["backend_url"])
self.quick_thinking_llm = ChatOpenAI(model=self.config["quick_think_llm"],
base_url=self.config["backend_url"])
elif self.config["llm_provider"].lower() == "anthropic":
self.deep_thinking_llm = ChatAnthropic(model=self.config["deep_think_llm"], base_url=self.config["backend_url"])
self.quick_thinking_llm = ChatAnthropic(model=self.config["quick_think_llm"], base_url=self.config["backend_url"])
self.deep_thinking_llm = ChatAnthropic(model=self.config["deep_think_llm"],
base_url=self.config["backend_url"])
self.quick_thinking_llm = ChatAnthropic(model=self.config["quick_think_llm"],
base_url=self.config["backend_url"])
elif self.config["llm_provider"].lower() == "google":
self.deep_thinking_llm = ChatGoogleGenerativeAI(model=self.config["deep_think_llm"])
self.quick_thinking_llm = ChatGoogleGenerativeAI(model=self.config["quick_think_llm"])
elif self.config["llm_provider"].lower() == "xai":
self.deep_thinking_llm = ChatXAI(model=self.config["deep_think_llm"])
self.quick_thinking_llm = ChatXAI(model=self.config["quick_think_llm"])
else:
raise ValueError(f"Unsupported LLM provider: {self.config['llm_provider']}")
# Initialize memories
self.bull_memory = FinancialSituationMemory("bull_memory", self.config)
self.bear_memory = FinancialSituationMemory("bear_memory", self.config)
@ -106,11 +105,12 @@ class TradingAgentsGraph:
self.invest_judge_memory,
self.risk_manager_memory,
self.conditional_logic,
config=self.config,
)
self.propagator = Propagator()
self.reflector = Reflector(self.quick_thinking_llm)
self.signal_processor = SignalProcessor(self.quick_thinking_llm)
self.reflector = Reflector(self.quick_thinking_llm, self.config)
self.signal_processor = SignalProcessor(self.quick_thinking_llm, self.config)
# State tracking
self.curr_state = None
@ -190,17 +190,17 @@ class TradingAgentsGraph:
self._log_state(trade_date, final_state)
# Return decision and processed signal
return final_state, self.process_signal(final_state["final_trade_decision"])
return final_state, self.process_signal(final_state["final_portfolio_management_decision"])
def _log_state(self, trade_date, final_state):
"""Log the final state to a JSON file."""
self.log_states_dict[str(trade_date)] = {
"company_of_interest": final_state["company_of_interest"],
"trade_date": final_state["trade_date"],
"market_report": final_state["market_report"],
"sentiment_report": final_state["sentiment_report"],
"news_report": final_state["news_report"],
"fundamentals_report": final_state["fundamentals_report"],
"market_analysis": final_state["market_analysis"],
"sentiment_analysis": final_state["sentiment_analysis"],
"news_analysis": final_state["news_analysis"],
"fundamentals_analysis": final_state["fundamentals_analysis"],
"investment_debate_state": {
"bull_history": final_state["investment_debate_state"]["bull_history"],
"bear_history": final_state["investment_debate_state"]["bear_history"],
@ -212,7 +212,7 @@ class TradingAgentsGraph:
"judge_decision"
],
},
"trader_investment_decision": final_state["trader_investment_plan"],
"trader_investment_decision": final_state["trader_team_plan"],
"risk_debate_state": {
"risky_history": final_state["risk_debate_state"]["risky_history"],
"safe_history": final_state["risk_debate_state"]["safe_history"],
@ -220,8 +220,8 @@ class TradingAgentsGraph:
"history": final_state["risk_debate_state"]["history"],
"judge_decision": final_state["risk_debate_state"]["judge_decision"],
},
"investment_plan": final_state["investment_plan"],
"final_trade_decision": final_state["final_trade_decision"],
"research_team_decision": final_state["research_team_decision"],
"final_portfolio_management_decision": final_state["final_portfolio_management_decision"],
}
# Save to file
@ -229,8 +229,8 @@ class TradingAgentsGraph:
directory.mkdir(parents=True, exist_ok=True)
with open(
f"eval_results/{self.ticker}/TradingAgentsStrategy_logs/full_states_log_{trade_date}.json",
"w",
f"eval_results/{self.ticker}/TradingAgentsStrategy_logs/full_states_log_{trade_date}.json",
"w",
) as f:
json.dump(self.log_states_dict, f, indent=4)