merge upstream main into crypto-analysis-mvp

cli/main.py

@@ -6,8 +6,9 @@ from functools import wraps
 from rich.console import Console
 from dotenv import load_dotenv
 
-# Load environment variables from .env file
+# Load environment variables
 load_dotenv()
+load_dotenv(".env.enterprise", override=False)
 from rich.panel import Panel
 from rich.spinner import Spinner
 from rich.live import Live
@@ -79,7 +80,7 @@ class MessageBuffer:
         self.current_agent = None
         self.report_sections = {}
         self.selected_analysts = []
-        self._last_message_id = None
+        self._processed_message_ids = set()
 
     def init_for_analysis(self, selected_analysts):
         """Initialize agent status and report sections based on selected analysts.
@@ -114,7 +115,7 @@ class MessageBuffer:
         self.current_agent = None
         self.messages.clear()
         self.tool_calls.clear()
-        self._last_message_id = None
+        self._processed_message_ids.clear()
 
     def get_completed_reports_count(self):
         """Count reports that are finalized (their finalizing agent is completed).
@@ -462,7 +463,7 @@ def update_display(layout, spinner_text=None, stats_handler=None, start_time=Non
 def get_user_selections():
     """Get all user selections before starting the analysis display."""
     # Display ASCII art welcome message
-    with open("./cli/static/welcome.txt", "r", encoding="utf-8") as f:
+    with open(Path(__file__).parent / "static" / "welcome.txt", "r") as f:
         welcome_ascii = f.read()
 
     # Create welcome box content
@@ -501,7 +502,9 @@ def get_user_selections():
     # Step 1: Ticker symbol
     console.print(
         create_question_box(
-            "Step 1: Ticker Symbol", "Enter the ticker symbol to analyze", "SPY"
+            "Step 1: Ticker Symbol",
+            "Enter the exact ticker symbol to analyze, including exchange suffix when needed (examples: SPY, CNC.TO, 7203.T, 0700.HK)",
+            "SPY",
         )
     )
     selected_ticker = get_ticker()
@@ -521,10 +524,19 @@ def get_user_selections():
     )
     analysis_date = get_analysis_date()
 
-    # Step 3: Select analysts
+    # Step 3: Output language
     console.print(
         create_question_box(
-            "Step 3: Analysts Team", "Select your LLM analyst agents for the analysis"
+            "Step 3: Output Language",
+            "Select the language for analyst reports and final decision"
+        )
+    )
+    output_language = ask_output_language()
+
+    # Step 4: Select analysts
+    console.print(
+        create_question_box(
+            "Step 4: Analysts Team", "Select your LLM analyst agents for the analysis"
         )
     )
     selected_analysts = select_analysts(asset_type)
@@ -532,40 +544,41 @@ def get_user_selections():
         f"[green]Selected analysts:[/green] {', '.join(analyst.value for analyst in selected_analysts)}"
     )
 
-    # Step 4: Research depth
+    # Step 5: Research depth
     console.print(
         create_question_box(
-            "Step 4: Research Depth", "Select your research depth level"
+            "Step 5: Research Depth", "Select your research depth level"
         )
     )
     selected_research_depth = select_research_depth()
 
-    # Step 5: OpenAI backend
+    # Step 6: LLM Provider
     console.print(
         create_question_box(
-            "Step 5: OpenAI backend", "Select which service to talk to"
+            "Step 6: LLM Provider", "Select your LLM provider"
         )
     )
     selected_llm_provider, backend_url = select_llm_provider()
-    
-    # Step 6: Thinking agents
+
+    # Step 7: Thinking agents
     console.print(
         create_question_box(
-            "Step 6: Thinking Agents", "Select your thinking agents for analysis"
+            "Step 7: Thinking Agents", "Select your thinking agents for analysis"
         )
     )
     selected_shallow_thinker = select_shallow_thinking_agent(selected_llm_provider)
     selected_deep_thinker = select_deep_thinking_agent(selected_llm_provider)
 
-    # Step 7: Provider-specific thinking configuration
+    # Step 8: Provider-specific thinking configuration
     thinking_level = None
     reasoning_effort = None
+    anthropic_effort = None
 
     provider_lower = selected_llm_provider.lower()
     if provider_lower == "google":
         console.print(
             create_question_box(
-                "Step 7: Thinking Mode",
+                "Step 8: Thinking Mode",
                 "Configure Gemini thinking mode"
             )
         )
@@ -573,11 +586,19 @@ def get_user_selections():
     elif provider_lower == "openai":
         console.print(
             create_question_box(
-                "Step 7: Reasoning Effort",
+                "Step 8: Reasoning Effort",
                 "Configure OpenAI reasoning effort level"
             )
         )
         reasoning_effort = ask_openai_reasoning_effort()
+    elif provider_lower == "anthropic":
+        console.print(
+            create_question_box(
+                "Step 8: Effort Level",
+                "Configure Claude effort level"
+            )
+        )
+        anthropic_effort = ask_anthropic_effort()
 
     return {
         "ticker": selected_ticker,
@@ -591,6 +612,8 @@ def get_user_selections():
         "deep_thinker": selected_deep_thinker,
         "google_thinking_level": thinking_level,
         "openai_reasoning_effort": reasoning_effort,
+        "anthropic_effort": anthropic_effort,
+        "output_language": output_language,
     }
 
 
@@ -793,9 +816,11 @@ ANALYST_REPORT_MAP = {
 
 
 def update_analyst_statuses(message_buffer, chunk):
-    """Update all analyst statuses based on current report state.
+    """Update analyst statuses based on accumulated report state.
 
     Logic:
+    - Store new report content from the current chunk if present
+    - Check accumulated report_sections (not just current chunk) for status
     - Analysts with reports = completed
     - First analyst without report = in_progress
     - Remaining analysts without reports = pending
@@ -810,11 +835,16 @@ def update_analyst_statuses(message_buffer, chunk):
 
         agent_name = ANALYST_AGENT_NAMES[analyst_key]
         report_key = ANALYST_REPORT_MAP[analyst_key]
-        has_report = bool(chunk.get(report_key))
+
+        # Capture new report content from current chunk
+        if chunk.get(report_key):
+            message_buffer.update_report_section(report_key, chunk[report_key])
+
+        # Determine status from accumulated sections, not just current chunk
+        has_report = bool(message_buffer.report_sections.get(report_key))
 
         if has_report:
             message_buffer.update_agent_status(agent_name, "completed")
-            message_buffer.update_report_section(report_key, chunk[report_key])
         elif not found_active:
             message_buffer.update_agent_status(agent_name, "in_progress")
             found_active = True
@@ -916,6 +946,8 @@ def run_analysis():
     # Provider-specific thinking configuration
     config["google_thinking_level"] = selections.get("google_thinking_level")
     config["openai_reasoning_effort"] = selections.get("openai_reasoning_effort")
+    config["anthropic_effort"] = selections.get("anthropic_effort")
+    config["output_language"] = selections.get("output_language", "English")
 
     # Create stats callback handler for tracking LLM/tool calls
     stats_handler = StatsCallbackHandler()
@@ -953,7 +985,7 @@ def run_analysis():
             func(*args, **kwargs)
             timestamp, message_type, content = obj.messages[-1]
             content = content.replace("\n", " ")  # Replace newlines with spaces
-            with open(log_file, "a", encoding="utf-8") as f:
+            with open(log_file, "a") as f:
                 f.write(f"{timestamp} [{message_type}] {content}\n")
         return wrapper
     
@@ -964,7 +996,7 @@ def run_analysis():
             func(*args, **kwargs)
             timestamp, tool_name, args = obj.tool_calls[-1]
             args_str = ", ".join(f"{k}={v}" for k, v in args.items())
-            with open(log_file, "a", encoding="utf-8") as f:
+            with open(log_file, "a") as f:
                 f.write(f"{timestamp} [Tool Call] {tool_name}({args_str})\n")
         return wrapper
 
@@ -977,8 +1009,9 @@ def run_analysis():
                 content = obj.report_sections[section_name]
                 if content:
                     file_name = f"{section_name}.md"
-                    with open(report_dir / file_name, "w", encoding="utf-8") as f:
-                        f.write(content)
+                    text = "\n".join(str(item) for item in content) if isinstance(content, list) else content
+                    with open(report_dir / file_name, "w") as f:
+                        f.write(text)
         return wrapper
 
     message_buffer.add_message = save_message_decorator(message_buffer, "add_message")
@@ -1028,28 +1061,24 @@ def run_analysis():
         # Stream the analysis
         trace = []
         for chunk in graph.graph.stream(init_agent_state, **args):
-            # Process messages if present (skip duplicates via message ID)
-            if len(chunk["messages"]) > 0:
-                last_message = chunk["messages"][-1]
-                msg_id = getattr(last_message, "id", None)
+            # Process all messages in chunk, deduplicating by message ID
+            for message in chunk.get("messages", []):
+                msg_id = getattr(message, "id", None)
+                if msg_id is not None:
+                    if msg_id in message_buffer._processed_message_ids:
+                        continue
+                    message_buffer._processed_message_ids.add(msg_id)
 
-                if msg_id != message_buffer._last_message_id:
-                    message_buffer._last_message_id = msg_id
+                msg_type, content = classify_message_type(message)
+                if content and content.strip():
+                    message_buffer.add_message(msg_type, content)
 
-                    # Add message to buffer
-                    msg_type, content = classify_message_type(last_message)
-                    if content and content.strip():
-                        message_buffer.add_message(msg_type, content)
-
-                    # Handle tool calls
-                    if hasattr(last_message, "tool_calls") and last_message.tool_calls:
-                        for tool_call in last_message.tool_calls:
-                            if isinstance(tool_call, dict):
-                                message_buffer.add_tool_call(
-                                    tool_call["name"], tool_call["args"]
-                                )
-                            else:
-                                message_buffer.add_tool_call(tool_call.name, tool_call.args)
+                if hasattr(message, "tool_calls") and message.tool_calls:
+                    for tool_call in message.tool_calls:
+                        if isinstance(tool_call, dict):
+                            message_buffer.add_tool_call(tool_call["name"], tool_call["args"])
+                        else:
+                            message_buffer.add_tool_call(tool_call.name, tool_call.args)
 
             # Update analyst statuses based on report state (runs on every chunk)
             update_analyst_statuses(message_buffer, chunk)

cli/utils.py

@@ -4,9 +4,12 @@ from typing import List, Optional, Tuple, Dict
 from rich.console import Console
 
 from cli.models import AnalystType, AssetType
+from tradingagents.llm_clients.model_catalog import get_model_options
 
 console = Console()
 
+TICKER_INPUT_EXAMPLES = "Examples: SPY, CNC.TO, 7203.T, 0700.HK"
+
 ANALYST_ORDER = [
     ("Market Analyst", AnalystType.MARKET),
     ("Social Media Analyst", AnalystType.SOCIAL),
@@ -20,7 +23,7 @@ CRYPTO_SUFFIXES = ("-USD", "-USDT", "-USDC", "-BTC", "-ETH")
 def get_ticker() -> str:
     """Prompt the user to enter a ticker symbol."""
     ticker = questionary.text(
-        "Enter the ticker symbol to analyze:",
+        f"Enter the exact ticker symbol to analyze ({TICKER_INPUT_EXAMPLES}):",
         validate=lambda x: len(x.strip()) > 0 or "Please enter a valid ticker symbol.",
         style=questionary.Style(
             [
@@ -34,6 +37,11 @@ def get_ticker() -> str:
         console.print("\n[red]No ticker symbol provided. Exiting...[/red]")
         exit(1)
 
+    return normalize_ticker_symbol(ticker)
+
+
+def normalize_ticker_symbol(ticker: str) -> str:
+    """Normalize ticker input while preserving exchange suffixes."""
     return ticker.strip().upper()
 
 
@@ -153,51 +161,70 @@ def select_research_depth() -> int:
     return choice
 
 
-def select_shallow_thinking_agent(provider) -> str:
-    """Select shallow thinking llm engine using an interactive selection."""
+def _fetch_openrouter_models() -> List[Tuple[str, str]]:
+    """Fetch available models from the OpenRouter API."""
+    import requests
+    try:
+        resp = requests.get("https://openrouter.ai/api/v1/models", timeout=10)
+        resp.raise_for_status()
+        models = resp.json().get("data", [])
+        return [(m.get("name") or m["id"], m["id"]) for m in models]
+    except Exception as e:
+        console.print(f"\n[yellow]Could not fetch OpenRouter models: {e}[/yellow]")
+        return []
 
-    # Define shallow thinking llm engine options with their corresponding model names
-    # Ordering: medium → light → heavy (balanced first for quick tasks)
-    # Within same tier, newer models first
-    SHALLOW_AGENT_OPTIONS = {
-        "openai": [
-            ("GPT-5 Mini - Balanced speed, cost, and capability", "gpt-5-mini"),
-            ("GPT-5 Nano - High-throughput, simple tasks", "gpt-5-nano"),
-            ("GPT-5.4 - Latest frontier, 1M context", "gpt-5.4"),
-            ("GPT-4.1 - Smartest non-reasoning model", "gpt-4.1"),
-        ],
-        "anthropic": [
-            ("Claude Sonnet 4.6 - Best speed and intelligence balance", "claude-sonnet-4-6"),
-            ("Claude Haiku 4.5 - Fast, near-instant responses", "claude-haiku-4-5"),
-            ("Claude Sonnet 4.5 - Agents and coding", "claude-sonnet-4-5"),
-        ],
-        "google": [
-            ("Gemini 3 Flash - Next-gen fast", "gemini-3-flash-preview"),
-            ("Gemini 2.5 Flash - Balanced, stable", "gemini-2.5-flash"),
-            ("Gemini 3.1 Flash Lite - Most cost-efficient", "gemini-3.1-flash-lite-preview"),
-            ("Gemini 2.5 Flash Lite - Fast, low-cost", "gemini-2.5-flash-lite"),
-        ],
-        "xai": [
-            ("Grok 4.1 Fast (Non-Reasoning) - Speed optimized, 2M ctx", "grok-4-1-fast-non-reasoning"),
-            ("Grok 4 Fast (Non-Reasoning) - Speed optimized", "grok-4-fast-non-reasoning"),
-            ("Grok 4.1 Fast (Reasoning) - High-performance, 2M ctx", "grok-4-1-fast-reasoning"),
-        ],
-        "openrouter": [
-            ("NVIDIA Nemotron 3 Nano 30B (free)", "nvidia/nemotron-3-nano-30b-a3b:free"),
-            ("Z.AI GLM 4.5 Air (free)", "z-ai/glm-4.5-air:free"),
-        ],
-        "ollama": [
-            ("Qwen3:latest (8B, local)", "qwen3:latest"),
-            ("GPT-OSS:latest (20B, local)", "gpt-oss:latest"),
-            ("GLM-4.7-Flash:latest (30B, local)", "glm-4.7-flash:latest"),
-        ],
-    }
+
+def select_openrouter_model() -> str:
+    """Select an OpenRouter model from the newest available, or enter a custom ID."""
+    models = _fetch_openrouter_models()
+
+    choices = [questionary.Choice(name, value=mid) for name, mid in models[:5]]
+    choices.append(questionary.Choice("Custom model ID", value="custom"))
 
     choice = questionary.select(
-        "Select Your [Quick-Thinking LLM Engine]:",
+        "Select OpenRouter Model (latest available):",
+        choices=choices,
+        instruction="\n- Use arrow keys to navigate\n- Press Enter to select",
+        style=questionary.Style([
+            ("selected", "fg:magenta noinherit"),
+            ("highlighted", "fg:magenta noinherit"),
+            ("pointer", "fg:magenta noinherit"),
+        ]),
+    ).ask()
+
+    if choice is None or choice == "custom":
+        return questionary.text(
+            "Enter OpenRouter model ID (e.g. google/gemma-4-26b-a4b-it):",
+            validate=lambda x: len(x.strip()) > 0 or "Please enter a model ID.",
+        ).ask().strip()
+
+    return choice
+
+
+def _prompt_custom_model_id() -> str:
+    """Prompt user to type a custom model ID."""
+    return questionary.text(
+        "Enter model ID:",
+        validate=lambda x: len(x.strip()) > 0 or "Please enter a model ID.",
+    ).ask().strip()
+
+
+def _select_model(provider: str, mode: str) -> str:
+    """Select a model for the given provider and mode (quick/deep)."""
+    if provider.lower() == "openrouter":
+        return select_openrouter_model()
+
+    if provider.lower() == "azure":
+        return questionary.text(
+            f"Enter Azure deployment name ({mode}-thinking):",
+            validate=lambda x: len(x.strip()) > 0 or "Please enter a deployment name.",
+        ).ask().strip()
+
+    choice = questionary.select(
+        f"Select Your [{mode.title()}-Thinking LLM Engine]:",
         choices=[
             questionary.Choice(display, value=value)
-            for display, value in SHALLOW_AGENT_OPTIONS[provider.lower()]
+            for display, value in get_model_options(provider, mode)
         ],
         instruction="\n- Use arrow keys to navigate\n- Press Enter to select",
         style=questionary.Style(
@@ -210,95 +237,45 @@ def select_shallow_thinking_agent(provider) -> str:
     ).ask()
 
     if choice is None:
-        console.print(
-            "\n[red]No shallow thinking llm engine selected. Exiting...[/red]"
-        )
+        console.print(f"\n[red]No {mode} thinking llm engine selected. Exiting...[/red]")
         exit(1)
 
+    if choice == "custom":
+        return _prompt_custom_model_id()
+
     return choice
 
 
+def select_shallow_thinking_agent(provider) -> str:
+    """Select shallow thinking llm engine using an interactive selection."""
+    return _select_model(provider, "quick")
+
+
 def select_deep_thinking_agent(provider) -> str:
     """Select deep thinking llm engine using an interactive selection."""
+    return _select_model(provider, "deep")
 
-    # Define deep thinking llm engine options with their corresponding model names
-    # Ordering: heavy → medium → light (most capable first for deep tasks)
-    # Within same tier, newer models first
-    DEEP_AGENT_OPTIONS = {
-        "openai": [
-            ("GPT-5.4 - Latest frontier, 1M context", "gpt-5.4"),
-            ("GPT-5.2 - Strong reasoning, cost-effective", "gpt-5.2"),
-            ("GPT-5 Mini - Balanced speed, cost, and capability", "gpt-5-mini"),
-            ("GPT-5.4 Pro - Most capable, expensive ($30/$180 per 1M tokens)", "gpt-5.4-pro"),
-        ],
-        "anthropic": [
-            ("Claude Opus 4.6 - Most intelligent, agents and coding", "claude-opus-4-6"),
-            ("Claude Opus 4.5 - Premium, max intelligence", "claude-opus-4-5"),
-            ("Claude Sonnet 4.6 - Best speed and intelligence balance", "claude-sonnet-4-6"),
-            ("Claude Sonnet 4.5 - Agents and coding", "claude-sonnet-4-5"),
-        ],
-        "google": [
-            ("Gemini 3.1 Pro - Reasoning-first, complex workflows", "gemini-3.1-pro-preview"),
-            ("Gemini 3 Flash - Next-gen fast", "gemini-3-flash-preview"),
-            ("Gemini 2.5 Pro - Stable pro model", "gemini-2.5-pro"),
-            ("Gemini 2.5 Flash - Balanced, stable", "gemini-2.5-flash"),
-        ],
-        "xai": [
-            ("Grok 4 - Flagship model", "grok-4-0709"),
-            ("Grok 4.1 Fast (Reasoning) - High-performance, 2M ctx", "grok-4-1-fast-reasoning"),
-            ("Grok 4 Fast (Reasoning) - High-performance", "grok-4-fast-reasoning"),
-            ("Grok 4.1 Fast (Non-Reasoning) - Speed optimized, 2M ctx", "grok-4-1-fast-non-reasoning"),
-        ],
-        "openrouter": [
-            ("Z.AI GLM 4.5 Air (free)", "z-ai/glm-4.5-air:free"),
-            ("NVIDIA Nemotron 3 Nano 30B (free)", "nvidia/nemotron-3-nano-30b-a3b:free"),
-        ],
-        "ollama": [
-            ("GLM-4.7-Flash:latest (30B, local)", "glm-4.7-flash:latest"),
-            ("GPT-OSS:latest (20B, local)", "gpt-oss:latest"),
-            ("Qwen3:latest (8B, local)", "qwen3:latest"),
-        ],
-    }
-
-    choice = questionary.select(
-        "Select Your [Deep-Thinking LLM Engine]:",
-        choices=[
-            questionary.Choice(display, value=value)
-            for display, value in DEEP_AGENT_OPTIONS[provider.lower()]
-        ],
-        instruction="\n- Use arrow keys to navigate\n- Press Enter to select",
-        style=questionary.Style(
-            [
-                ("selected", "fg:magenta noinherit"),
-                ("highlighted", "fg:magenta noinherit"),
-                ("pointer", "fg:magenta noinherit"),
-            ]
-        ),
-    ).ask()
-
-    if choice is None:
-        console.print("\n[red]No deep thinking llm engine selected. Exiting...[/red]")
-        exit(1)
-
-    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 = [
-        ("OpenAI", "https://api.openai.com/v1"),
-        ("Google", "https://generativelanguage.googleapis.com/v1"),
-        ("Anthropic", "https://api.anthropic.com/"),
-        ("xAI", "https://api.x.ai/v1"),
-        ("Openrouter", "https://openrouter.ai/api/v1"),
-        ("Ollama", "http://localhost:11434/v1"),
+def select_llm_provider() -> tuple[str, str | None]:
+    """Select the LLM provider and its API endpoint."""
+    # (display_name, provider_key, base_url)
+    PROVIDERS = [
+        ("OpenAI", "openai", "https://api.openai.com/v1"),
+        ("Google", "google", None),
+        ("Anthropic", "anthropic", "https://api.anthropic.com/"),
+        ("xAI", "xai", "https://api.x.ai/v1"),
+        ("DeepSeek", "deepseek", "https://api.deepseek.com"),
+        ("Qwen", "qwen", "https://dashscope.aliyuncs.com/compatible-mode/v1"),
+        ("GLM", "glm", "https://open.bigmodel.cn/api/paas/v4/"),
+        ("OpenRouter", "openrouter", "https://openrouter.ai/api/v1"),
+        ("Azure OpenAI", "azure", None),
+        ("Ollama", "ollama", "http://localhost:11434/v1"),
     ]
-    
+
     choice = questionary.select(
         "Select your LLM Provider:",
         choices=[
-            questionary.Choice(display, value=(display, value))
-            for display, value in BASE_URLS
+            questionary.Choice(display, value=(provider_key, url))
+            for display, provider_key, url in PROVIDERS
         ],
         instruction="\n- Use arrow keys to navigate\n- Press Enter to select",
         style=questionary.Style(
@@ -311,13 +288,11 @@ def select_llm_provider() -> tuple[str, str]:
     ).ask()
     
     if choice is None:
-        console.print("\n[red]no OpenAI backend selected. Exiting...[/red]")
+        console.print("\n[red]No LLM provider selected. Exiting...[/red]")
         exit(1)
-    
-    display_name, url = choice
-    print(f"You selected: {display_name}\tURL: {url}")
 
-    return display_name, url
+    provider, url = choice
+    return provider, url
 
 
 def ask_openai_reasoning_effort() -> str:
@@ -338,6 +313,26 @@ def ask_openai_reasoning_effort() -> str:
     ).ask()
 
 
+def ask_anthropic_effort() -> str | None:
+    """Ask for Anthropic effort level.
+
+    Controls token usage and response thoroughness on Claude 4.5+ and 4.6 models.
+    """
+    return questionary.select(
+        "Select Effort Level:",
+        choices=[
+            questionary.Choice("High (recommended)", "high"),
+            questionary.Choice("Medium (balanced)", "medium"),
+            questionary.Choice("Low (faster, cheaper)", "low"),
+        ],
+        style=questionary.Style([
+            ("selected", "fg:cyan noinherit"),
+            ("highlighted", "fg:cyan noinherit"),
+            ("pointer", "fg:cyan noinherit"),
+        ]),
+    ).ask()
+
+
 def ask_gemini_thinking_config() -> str | None:
     """Ask for Gemini thinking configuration.
 
@@ -356,3 +351,37 @@ def ask_gemini_thinking_config() -> str | None:
             ("pointer", "fg:green noinherit"),
         ]),
     ).ask()
+
+
+def ask_output_language() -> str:
+    """Ask for report output language."""
+    choice = questionary.select(
+        "Select Output Language:",
+        choices=[
+            questionary.Choice("English (default)", "English"),
+            questionary.Choice("Chinese (中文)", "Chinese"),
+            questionary.Choice("Japanese (日本語)", "Japanese"),
+            questionary.Choice("Korean (한국어)", "Korean"),
+            questionary.Choice("Hindi (हिन्दी)", "Hindi"),
+            questionary.Choice("Spanish (Español)", "Spanish"),
+            questionary.Choice("Portuguese (Português)", "Portuguese"),
+            questionary.Choice("French (Français)", "French"),
+            questionary.Choice("German (Deutsch)", "German"),
+            questionary.Choice("Arabic (العربية)", "Arabic"),
+            questionary.Choice("Russian (Русский)", "Russian"),
+            questionary.Choice("Custom language", "custom"),
+        ],
+        style=questionary.Style([
+            ("selected", "fg:yellow noinherit"),
+            ("highlighted", "fg:yellow noinherit"),
+            ("pointer", "fg:yellow noinherit"),
+        ]),
+    ).ask()
+
+    if choice == "custom":
+        return questionary.text(
+            "Enter language name (e.g. Turkish, Vietnamese, Thai, Indonesian):",
+            validate=lambda x: len(x.strip()) > 0 or "Please enter a language name.",
+        ).ask().strip()
+
+    return choice