LLM updates

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "kiroAgent.configureMCP": "Disabled"
+}

AGENTS.md

@@ -0,0 +1,22 @@
+# Repository Guidelines
+
+## Project Structure & Module Organization
+Core package lives under `tradingagents/` with agent roles in `tradingagents/agents`, data acquisition in `tradingagents/dataflows`, and LangGraph orchestration in `tradingagents/graph`. CLI entry points sit in `cli/`; run `python -m cli.main` for the interactive workflow, and see `main.py` for a scripted example. Reference material (images, CLI captures) belongs in `assets/`, while experiment output should land in `results/`. Avoid committing local virtual environments—`tradingagents/python=3.13/` is legacy and should stay untracked. Update shared configs through `tradingagents/default_config.py` and keep per-developer overrides outside the repo.
+
+## Build, Test, and Development Commands
+- `python -m venv .venv && source .venv/bin/activate`: create and activate a clean Python ≥3.10 environment.
+- `pip install -r requirements.txt && pip install -e .`: install runtime dependencies and link the package for local development.
+- `python -m cli.main`: launch the console UI to step through ticker selection and agent runs.
+- `python main.py`: execute a minimal graph run using `DEFAULT_CONFIG` for smoke-testing pipeline changes.
+
+## Coding Style & Naming Conventions
+Follow standard PEP 8: 4-space indentation, lowercase `snake_case` functions, and `CamelCase` classes. Preserve typing hints where present (`Dict[str, Any]` patterns are common) and keep docstrings focused on side effects and arguments. Prefer module-level constants for configuration keys rather than magic strings scattered across functions.
+
+## Testing Guidelines
+`test.py` currently exercises the Yahoo Finance dataflow; extend it or add new scripts under `tests/` when introducing features, keeping names aligned with the module under test (`test_<module>.py`). When you add high-impact functionality, capture CLI or graph outputs in the PR description and include deterministic test cases where possible.
+
+## Commit & Pull Request Guidelines
+Recent history uses short, present-tense summaries (“Latest changes applied”, “utf8 encoding fixed…”). Mirror that tone, lead with the primary change, and keep messages under ~70 characters when feasible. PRs should include a concise summary, configuration considerations, and before/after evidence (logs, screenshots) plus linked issue IDs where applicable.
+
+## Security & Configuration Tips
+Load API keys through the environment (`FINNHUB_API_KEY`, `OPENAI_API_KEY`) and never hard-code real secrets; scrub `DEFAULT_CONFIG` before publishing. Regenerate cached data under `tradingagents/dataflows/data_cache` rather than checking large blobs into git. If you script new agents, document required permissions and expected rate limits in the PR to help reviewers assess operational impact.

package-lock.json

@@ -0,0 +1,6 @@
+{
+  "name": "TradingAgents",
+  "lockfileVersion": 3,
+  "requires": true,
+  "packages": {}
+}

tradingagents/agents/utils/memory.py

@@ -13,9 +13,9 @@ class FinancialSituationMemory:
         if config["backend_url"] == "http://localhost:11434/v1":
             self.embedding = "nomic-embed-text"
         elif config["backend_url"] == "http://192.168.0.20:1234/v1":
-            self.embedding = "text-embedding-nomic-embed-text-v1.5"
+            self.embedding = "text-embedding-nomic-embed-text-v2-moe"
         else:
-            self.embedding = "ttext-embedding-nomic-embed-text-v1.5"
+            self.embedding = "text-embedding-nomic-embed-text-v2-moe"
                 
         self.client = OpenAI(base_url=config["backend_url"])
         self.chroma_client = chromadb.Client(Settings(allow_reset=True))

tradingagents/default_config.py

@@ -22,8 +22,8 @@ DEFAULT_CONFIG = {
     
     # Default LLM is set to local LMStudio instance
     "llm_provider": "lmstudio",
-    "deep_think_llm": "qwen/qwen3-4b-thinking-2507",
-    "quick_think_llm": "openai/gpt-oss-20b",
+    "deep_think_llm": "glm-4.7-reap-50-mixed-3-4-bits",
+    "quick_think_llm": "qwen/qwen3-vl-30b",
     "backend_url": "http://192.168.0.20/v1",
     "api_key": "blablabla",
     

updated_files/default_config.py

@@ -16,8 +16,8 @@ DEFAULT_CONFIG = {
     
     # Default LLM is set to local LMStudio instance
     "llm_provider": "lmstudio",
-    "deep_think_llm": "qwen/qwen3-4b-thinking-2507",
-    "quick_think_llm": "openai/gpt-oss-20b",
+    "deep_think_llm": "glm-4.7-reap-50-mixed-3-4-bits",
+    "quick_think_llm": "qwen/qwen3-vl-30b",
     "backend_url": "http://192.168.0.20/v1",
     "api_key": "blablabla",
     

updated_files/memory.py

@@ -5,12 +5,12 @@ from openai import OpenAI
 
 class FinancialSituationMemory:
     def __init__(self, name, config):
-        if config["backend_url"] == "http://192.168.0.20:11434/v1":
-            self.embedding = "nomic-embed-text"
+        if config["backend_url"] == "http://192.168.0.20:1234/v1":
+            self.embedding = "text-embedding-nomic-embed-text-v2-moe"
         elif config["backend_url"] == "http://192.168.0.20:1234/v1":
-            self.embedding = "text-embedding-nomic-embed-text-v1.5"
+            self.embedding = "text-embedding-nomic-embed-text-v2-moe"
         else:
-            self.embedding = "ttext-embedding-nomic-embed-text-v1.5"
+            self.embedding = "text-embedding-nomic-embed-text-v2-moe"
             
         self.client = OpenAI(base_url=config["backend_url"], api_key=config["api_key"])
         self.chroma_client = chromadb.Client(Settings(allow_reset=True))

updated_files/utils.py

@@ -0,0 +1,291 @@
+import questionary
+from typing import List, Optional, Tuple, Dict
+
+from cli.models import AnalystType
+
+ANALYST_ORDER = [
+    ("Market Analyst", AnalystType.MARKET),
+    ("Social Media Analyst", AnalystType.SOCIAL),
+    ("News Analyst", AnalystType.NEWS),
+    ("Fundamentals Analyst", AnalystType.FUNDAMENTALS),
+]
+
+
+def get_ticker() -> str:
+    """Prompt the user to enter a ticker symbol."""
+    ticker = questionary.text(
+        "Enter the ticker symbol to analyze:",
+        validate=lambda x: len(x.strip()) > 0 or "Please enter a valid ticker symbol.",
+        style=questionary.Style(
+            [
+                ("text", "fg:green"),
+                ("highlighted", "noinherit"),
+            ]
+        ),
+    ).ask()
+
+    if not ticker:
+        console.print("\n[red]No ticker symbol provided. Exiting...[/red]")
+        exit(1)
+
+    return ticker.strip().upper()
+
+
+def get_analysis_date() -> str:
+    """Prompt the user to enter a date in YYYY-MM-DD format."""
+    import re
+    from datetime import datetime
+
+    def validate_date(date_str: str) -> bool:
+        if not re.match(r"^\d{4}-\d{2}-\d{2}$", date_str):
+            return False
+        try:
+            datetime.strptime(date_str, "%Y-%m-%d")
+            return True
+        except ValueError:
+            return False
+
+    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.",
+        style=questionary.Style(
+            [
+                ("text", "fg:green"),
+                ("highlighted", "noinherit"),
+            ]
+        ),
+    ).ask()
+
+    if not date:
+        console.print("\n[red]No date provided. Exiting...[/red]")
+        exit(1)
+
+    return date.strip()
+
+
+def select_analysts() -> List[AnalystType]:
+    """Select analysts using an interactive checkbox."""
+    choices = questionary.checkbox(
+        "Select Your [Analysts Team]:",
+        choices=[
+            questionary.Choice(display, value=value) for display, value in ANALYST_ORDER
+        ],
+        instruction="\n- Press Space to select/unselect analysts\n- Press 'a' to select/unselect all\n- Press Enter when done",
+        validate=lambda x: len(x) > 0 or "You must select at least one analyst.",
+        style=questionary.Style(
+            [
+                ("checkbox-selected", "fg:green"),
+                ("selected", "fg:green noinherit"),
+                ("highlighted", "noinherit"),
+                ("pointer", "noinherit"),
+            ]
+        ),
+    ).ask()
+
+    if not choices:
+        console.print("\n[red]No analysts selected. Exiting...[/red]")
+        exit(1)
+
+    return choices
+
+
+def select_research_depth() -> int:
+    """Select research depth using an interactive selection."""
+
+    # Define research depth options with their corresponding values
+    DEPTH_OPTIONS = [
+        ("Shallow - Quick research, few debate and strategy discussion rounds", 1),
+        ("Medium - Middle ground, moderate debate rounds and strategy discussion", 3),
+        ("Deep - Comprehensive research, in depth debate and strategy discussion", 5),
+    ]
+
+    choice = questionary.select(
+        "Select Your [Research Depth]:",
+        choices=[
+            questionary.Choice(display, value=value) for display, value in DEPTH_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 research depth selected. Exiting...[/red]")
+        exit(1)
+
+    return choice
+
+
+def select_shallow_thinking_agent(provider) -> str:
+    """Select shallow thinking llm engine using an interactive selection."""
+
+    # Define shallow thinking llm engine options with their corresponding model names
+    SHALLOW_AGENT_OPTIONS = {
+        "openai": [
+            ("GPT-4o-mini - Fast and efficient for quick tasks", "gpt-4o-mini"),
+            ("GPT-4.1-nano - Ultra-lightweight model for basic operations", "gpt-4.1-nano"),
+            ("GPT-4.1-mini - Compact model with good performance", "gpt-4.1-mini"),
+            ("GPT-4o - Standard model with solid capabilities", "gpt-4o"),
+        ],
+        "anthropic": [
+            ("Claude Haiku 3.5 - Fast inference and standard capabilities", "claude-3-5-haiku-latest"),
+            ("Claude Sonnet 3.5 - Highly capable standard model", "claude-3-5-sonnet-latest"),
+            ("Claude Sonnet 3.7 - Exceptional hybrid reasoning and agentic capabilities", "claude-3-7-sonnet-latest"),
+            ("Claude Sonnet 4 - High performance and excellent reasoning", "claude-sonnet-4-0"),
+            ("CCR", "openai/gpt-oss-20b"),
+        ],
+        "google": [
+            ("Gemini 2.0 Flash-Lite - Cost efficiency and low latency", "gemini-2.0-flash-lite"),
+            ("Gemini 2.0 Flash - Next generation features, speed, and thinking", "gemini-2.0-flash"),
+            ("Gemini 2.5 Flash - Adaptive thinking, cost efficiency", "gemini-2.5-flash-preview-05-20"),
+        ],
+        "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"),
+        ],
+        "ollama": [
+            ("llama3.1 local", "llama3.1"),
+            ("llama3.2 local", "llama3.2"),
+        ],
+        "lmstudio": [
+            ("LMStudio Qwen 4b Thinking","qwen/qwen3-4b-thinking-2507"),
+            ("LMStudio GLM", "glm-4.5-air-mlx"),
+            ("LMStudio OSS 120b","openai/gpt-oss-120b"),
+            ("LMStudio Kimi","kimi-dev-72b-dwq"),
+        ]
+    }
+
+    choice = questionary.select(
+        "Select Your [Quick-Thinking LLM Engine]:",
+        choices=[
+            questionary.Choice(display, value=value)
+            for display, value in SHALLOW_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 shallow thinking llm engine selected. Exiting...[/red]"
+        )
+        exit(1)
+
+    return choice
+
+
+def select_deep_thinking_agent(provider) -> str:
+    """Select deep thinking llm engine using an interactive selection."""
+
+    # Define deep thinking llm engine options with their corresponding model names
+    DEEP_AGENT_OPTIONS = {
+        "openai": [
+            ("GPT-4.1-nano - Ultra-lightweight model for basic operations", "gpt-4.1-nano"),
+            ("GPT-4.1-mini - Compact model with good performance", "gpt-4.1-mini"),
+            ("GPT-4o - Standard model with solid capabilities", "gpt-4o"),
+            ("o4-mini - Specialized reasoning model (compact)", "o4-mini"),
+            ("o3-mini - Advanced reasoning model (lightweight)", "o3-mini"),
+            ("o3 - Full advanced reasoning model", "o3"),
+            ("o1 - Premier reasoning and problem-solving model", "o1"),
+        ],
+        "anthropic": [
+            ("Claude Haiku 3.5 - Fast inference and standard capabilities", "claude-3-5-haiku-latest"),
+            ("Claude Sonnet 3.5 - Highly capable standard model", "claude-3-5-sonnet-latest"),
+            ("Claude Sonnet 3.7 - Exceptional hybrid reasoning and agentic capabilities", "claude-3-7-sonnet-latest"),
+            ("Claude Sonnet 4 - High performance and excellent reasoning", "claude-sonnet-4-0"),
+            ("Claude Opus 4 - Most powerful Anthropic model", "	claude-opus-4-0"),
+        ],
+        "google": [
+            ("Gemini 2.0 Flash-Lite - Cost efficiency and low latency", "gemini-2.0-flash-lite"),
+            ("Gemini 2.0 Flash - Next generation features, speed, and thinking", "gemini-2.0-flash"),
+            ("Gemini 2.5 Flash - Adaptive thinking, cost efficiency", "gemini-2.5-flash-preview-05-20"),
+            ("Gemini 2.5 Pro", "gemini-2.5-pro-preview-06-05"),
+        ],
+        "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"),
+        ],
+        "ollama": [
+            ("llama3.1 local", "llama3.1"),
+            ("qwen3", "qwen3"),
+        ],
+        "lmstudio": [
+            ("LMStudio Qwen 4b Thinking","qwen/qwen3-4b-thinking-2507"),
+            ("LMStudio GLM", "glm-4.5-air-mlx"),
+            ("LMStudio OSS 20b","openai/gpt-oss-20b"),
+            ("LMStudio Kimi","kimi-dev-72b-dwq"),
+        ]
+    }
+    
+    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 = [
+        ("LMStudio", "http://192.168.0.20:1234/v1"),
+        ("OpenAI Local", "http://192.168.0.20:1234/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"),
+    ]
+    
+    choice = questionary.select(
+        "Select your LLM Provider:",
+        choices=[
+            questionary.Choice(display, value=(display, value))
+            for display, value in BASE_URLS
+        ],
+        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 OpenAI backend selected. Exiting...[/red]")
+        exit(1)
+    
+    display_name, url = choice
+    print(f"You selected: {display_name}\tURL: {url}")
+    
+    return display_name, url