feat: add multi-language output support for analyst reports and final decision

- Add output_language config key to DEFAULT_CONFIG (default: English)
  - Add get_language_instruction() helper to agent_utils.py
  - Inject language instruction into 4 analyst agents and portfolio manager
  - Internal debate chain (Bull/Bear/Risk debaters) stays in English to preserve reasoning quality and BM25 memory compatibility
  - Fix OpenAI-compatible providers with custom base_url incorrectly using Responses API instead of Chat Completions

main.py

@@ -11,7 +11,7 @@ config = DEFAULT_CONFIG.copy()
 config["deep_think_llm"] = "gpt-5-mini"  # Use a different model
 config["quick_think_llm"] = "gpt-5-mini"  # Use a different model
 config["max_debate_rounds"] = 1  # Increase debate rounds
-
+                                                                                                                                   
 # Configure data vendors (default uses yfinance, no extra API keys needed)
 config["data_vendors"] = {
     "core_stock_apis": "yfinance",           # Options: alpha_vantage, yfinance

tradingagents/agents/analysts/fundamentals_analyst.py

@@ -8,6 +8,7 @@ from tradingagents.agents.utils.agent_utils import (
     get_fundamentals,
     get_income_statement,
     get_insider_transactions,
+    get_language_instruction,
 )
 from tradingagents.dataflows.config import get_config
 
@@ -27,7 +28,8 @@ def create_fundamentals_analyst(llm):
         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. Provide specific, actionable insights with supporting evidence to help traders make informed 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.",
+            + " Use the available tools: `get_fundamentals` for comprehensive company analysis, `get_balance_sheet`, `get_cashflow`, and `get_income_statement` for specific financial statements."
+            + get_language_instruction(),
         )
 
         prompt = ChatPromptTemplate.from_messages(

tradingagents/agents/analysts/market_analyst.py

@@ -4,6 +4,7 @@ import json
 from tradingagents.agents.utils.agent_utils import (
     build_instrument_context,
     get_indicators,
+    get_language_instruction,
     get_stock_data,
 )
 from tradingagents.dataflows.config import get_config
@@ -47,6 +48,7 @@ Volume-Based Indicators:
 
 - 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. Provide specific, actionable insights with supporting evidence to help traders make informed 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."""
+            + get_language_instruction()
         )
 
         prompt = ChatPromptTemplate.from_messages(

tradingagents/agents/analysts/news_analyst.py

@@ -4,6 +4,7 @@ import json
 from tradingagents.agents.utils.agent_utils import (
     build_instrument_context,
     get_global_news,
+    get_language_instruction,
     get_news,
 )
 from tradingagents.dataflows.config import get_config
@@ -22,6 +23,7 @@ def create_news_analyst(llm):
         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. Provide specific, actionable insights with supporting evidence to help traders make informed 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."""
+            + get_language_instruction()
         )
 
         prompt = ChatPromptTemplate.from_messages(

tradingagents/agents/analysts/social_media_analyst.py

@@ -1,7 +1,7 @@
 from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
 import time
 import json
-from tradingagents.agents.utils.agent_utils import build_instrument_context, get_news
+from tradingagents.agents.utils.agent_utils import build_instrument_context, get_language_instruction, get_news
 from tradingagents.dataflows.config import get_config
 
 
@@ -17,6 +17,7 @@ def create_social_media_analyst(llm):
         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. Provide specific, actionable insights with supporting evidence to help traders make informed 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."""
+            + get_language_instruction()
         )
 
         prompt = ChatPromptTemplate.from_messages(

tradingagents/agents/managers/portfolio_manager.py

@@ -1,4 +1,4 @@
-from tradingagents.agents.utils.agent_utils import build_instrument_context
+from tradingagents.agents.utils.agent_utils import build_instrument_context, get_language_instruction
 
 
 def create_portfolio_manager(llm, memory):
@@ -50,7 +50,7 @@ def create_portfolio_manager(llm, memory):
 
 ---
 
-Be decisive and ground every conclusion in specific evidence from the analysts."""
+Be decisive and ground every conclusion in specific evidence from the analysts.{get_language_instruction()}"""
 
         response = llm.invoke(prompt)
 

tradingagents/agents/utils/agent_utils.py

@@ -1,4 +1,5 @@
 from langchain_core.messages import HumanMessage, RemoveMessage
+from tradingagents.dataflows.config import get_config
 
 # Import tools from separate utility files
 from tradingagents.agents.utils.core_stock_tools import (
@@ -20,6 +21,15 @@ from tradingagents.agents.utils.news_data_tools import (
 )
 
 
+def get_language_instruction() -> str:
+    """Returns a prompt instruction to write output in the configured language.
+    Returns empty string when output_language is English (no instruction needed)."""
+    lang = get_config().get("output_language", "English")
+    if lang.strip().lower() == "english":
+        return ""
+    return f"\n\nIMPORTANT: Write your entire response in {lang} only."
+
+
 def build_instrument_context(ticker: str) -> str:
     """Describe the exact instrument so agents preserve exchange-qualified tickers."""
     return (

tradingagents/default_config.py

@@ -16,6 +16,10 @@ DEFAULT_CONFIG = {
     "google_thinking_level": None,      # "high", "minimal", etc.
     "openai_reasoning_effort": None,    # "medium", "high", "low"
     "anthropic_effort": None,           # "high", "medium", "low"
+    # Output language for analyst reports and final decision
+    # Internal agent debate stays in English for reasoning quality
+    # Examples: "English", "Arabic", "Chinese", "Spanish", "French"
+    "output_language": "English",
     # Debate and discussion settings
     "max_debate_rounds": 1,
     "max_risk_discuss_rounds": 1,

tradingagents/llm_clients/openai_client.py

@@ -74,8 +74,9 @@ class OpenAIClient(BaseLLMClient):
                 llm_kwargs[key] = self.kwargs[key]
 
         # Native OpenAI: use Responses API for consistent behavior across
-        # all model families. Third-party providers use Chat Completions.
-        if self.provider == "openai":
+        # all model families. Third-party compatible providers with a custom
+        # base_url (e.g. mimo, local proxies) use standard Chat Completions.
+        if self.provider == "openai" and not self.base_url:
             llm_kwargs["use_responses_api"] = True
 
         return NormalizedChatOpenAI(**llm_kwargs)