1 line
7.9 KiB
JSON
1 line
7.9 KiB
JSON
{"repo": "blackeagle686/myagent", "files": {"config.py": {"2a5f664cc0b5873ffaef267c28f3706888581ae8": {"t": 1785604524.5906994, "n": 1632, "h": "3b25b1085d6ec5d2", "c": "from dataclasses import dataclass\n\n@dataclass\nclass Config:\n # OpenRouter API config\n # api_key: str = \"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\"\n api_key: str = \"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\"\n base_url: str = \"https://openrouter.ai/api/v1\"\n \n # LLMs \n embedding_model: str = \"nvidia/llama-nemotron-embed-vl-1b-v2:free\"\n search_model: str = \"nousresearch/hermes-3-llama-3.1-405b:free\"\n # model: str = \"qwen/qwen3-vl-30b-a3b-thinking\"\n # model: str = \"z-ai/glm-4.5-air:free\"\n # model : str = \"google/gemini-2.0-flash-lite-preview-02-05:free\"\n \n # model -> for thinking and planning \n # coder_model -> for coding and heavy code tasks\n # vdb_model -> for vector database operations and embbedings \n model : str = \"nvidia/nemotron-3-super-120b-a12b:free\"\n coder_model: str = \"nvidia/nemotron-3-super-120b-a12b:free\"\n vdb_model: str = \"all-MiniLM-L6-v2\"\n \n # Local LLMs\n local_thinker_model: str = \"Qwen/Qwen2.5-3B-Instruct-GGUF\"\n local_planner_model: str = \"Qwen/Qwen2.5-Coder-3B-Instruct-GGUF\"\n local_embedding_model: str = \"sentence-transformers/all-MiniLM-L6-v2\"\n \n # Agent config\n top_k: int = 3\n similarity_threshold: float = 0.55\n max_memory_cells: int = 1000\n experience_reward_decay: float = 0.9\n enable_emotions: bool = True\n \n # Rate Limit & Caching\n enable_cache: bool = True\n semantic_cache_threshold: float = 0.92\n max_retries: int = 3\n backoff_factor: float = 2.0\n \n # Rust Accelerator\n use_rust_accelerator: bool = True\n "}}, "execute_tasks.py": {"0d220bcded59523ce20750f865326ecb17685c0c": {"t": 1785604526.2659905, "n": 456, "h": "04ccd951f877bbd8", "c": "import subprocess, sys\nwith open(\"./heavy_tasks.txt\", \"r\") as f:\n for line in f:\n line = line.strip()\n if not line or line.startswith(\"#\"):\n continue\n print(f\"Running: {line}\")\n result = subprocess.run(line, shell=True, check=False)\n if result.returncode != 0:\n print(f\"Failed: {line} (exit {result.returncode})\")\n sys.exit(result.returncode)\nprint(\"All tasks completed successfully.\")"}}, "generate_test_csv.py": {"7592d4b95c696184b99518154fc1302075309999": {"t": 1785604528.5896454, "n": 985, "h": "6eb9e026ca4b82f1", "c": "import pandas as pd\nimport numpy as np\n\n# Set seed for reproducibility\nnp.random.seed(42)\n\n# Generate 1000 rows\nn_rows = 1000\n\ndata = {\n \"id\": np.arange(1, n_rows + 1),\n \"category\": np.random.choice([\"Electronics\", \"Clothing\", \"Home\", \"Toys\"], size=n_rows),\n \"ad_spend\": np.random.uniform(100, 5000, size=n_rows),\n \"website_visits\": np.random.randint(50, 10000, size=n_rows),\n \"sales\": np.zeros(n_rows)\n}\n\n# Create a relationship for sales\n# sales = 50 + 0.5 * ad_spend + 0.01 * website_visits + noise\ndata[\"sales\"] = 50 + (0.5 * data[\"ad_spend\"]) + (0.01 * data[\"website_visits\"]) + np.random.normal(0, 100, size=n_rows)\n\n# Create a target for classification (high_sales = 1 if sales > median)\nmedian_sales = np.median(data[\"sales\"])\ndata[\"high_performance\"] = (data[\"sales\"] > median_sales).astype(int)\n\ndf = pd.DataFrame(data)\n\n# Save to CSV\ndf.to_csv(\"test_data.csv\", index=False)\nprint(f\"Created 'test_data.csv' with {len(df)} rows and {len(df.columns)} columns.\")\n"}}, "run_agent.py": {"0378114053e052cb6cbc96ac69bcb2506c46b6fa": {"t": 1785604529.8133166, "n": 3132, "h": "0e0b2c6f155b1f53", "c": "#!/usr/bin/env python3\nimport argparse\nimport sys\nimport logging\nimport os\nfrom unittest.mock import MagicMock\n\ndef setup_mocks():\n \"\"\"Mocks heavy dependencies to allow running without full environment setup.\"\"\"\n print(\"⚠️ Warning: Running in MOCK mode. Heavy dependencies will be mocked.\")\n for module_name in [\n \"openai\", \"sentence_transformers\", \"torch\", \"torch.nn\", \"torch.nn.functional\", \n \"numpy\", \"chromadb\", \"chromadb.utils\", \"chromadb.config\", \"chromadb.errors\"\n ]:\n if module_name not in sys.modules:\n sys.modules[module_name] = MagicMock()\n\n\nimport os\n\ndef print_banner():\n\n os.system(r'''\n(\necho \"\"\necho \" ,~.\"\necho \" (o o)\"\necho \" ----( V )----\"\necho \" U U\"\necho \"\"\necho \" >>> MyAgent <<<\"\necho \"\"\n) | lolcat -a -d 7\n''')\n\n os.system('toilet -f mono12 -F metal \"MY AGENT\" | lolcat -a')\n\n print()\n\n\ndef main():\n print_banner()\n parser = argparse.ArgumentParser(description=\"Run the BrainAgent Loop\")\n parser.add_argument(\"prompt\", type=str, help=\"The user prompt to send to the agent\")\n parser.add_argument(\"--mock\", action=\"store_true\", help=\"Run with mocked dependencies (no API keys required)\")\n parser.add_argument(\"--steps\", type=int, default=10, help=\"Maximum number of steps in the agent loop\")\n parser.add_argument(\"--verbose\", action=\"store_true\", help=\"Enable verbose logging\")\n \n args = parser.parse_args()\n\n # Configure logging\n log_level = logging.INFO if args.verbose else logging.WARNING\n logging.basicConfig(level=log_level, format='%(levelname)s: %(message)s')\n\n if args.mock:\n setup_mocks()\n # setup mock side effects for the LLM if mocking\n # This is just a basic example for mock mode\n from core.services.llm_service import client\n client.generate = MagicMock() \n client.generate.side_effect = [\n \"problem_type: general\\ndifficulty: easy\\nneeds_tools: no\\nstrategy: direct_answer\", # Thinker analysis\n \"[]\", # Thinker tasks\n \"FINAL_ANSWER: Hello! I am running in mock mode. You asked: \" + args.prompt, # Planner/Summary\n \"Mock memory summary\" # Learning\n ]\n\n # Import agent components\n try:\n from core.agent import BrainAgent\n from core.agent.agent_loop import agent_loop\n except ImportError as e:\n print(f\"❌ Error: Could not import agent components. Ensure you are in the project root. {e}\")\n sys.exit(1)\n\n print(f\"\\n😇 Initializing BrainAgent...\")\n agent = BrainAgent(sys_prompt=\"You are a helpful and intelligent AI assistant.\")\n \n print(f\"🐥 Agent is thinking about: '{args.prompt}'\")\n print(\"-\" * 40)\n \n try:\n final_answer = agent_loop(agent, args.prompt, max_steps=args.steps)\n print(\"\\n\" + \"=\"*60)\n print(\"🐣 FINAL ANSWER:\")\n print(final_answer)\n print(\"=\"*60 + \"\\n\")\n except Exception as e:\n print(f\"💔 Error during agent execution: {e}\")\n if args.verbose:\n import traceback\n traceback.print_exc()\n\nif __name__ == \"__main__\":\n main()\n"}}, "run_gui.py": {"ce30a687cbe998bb15610afe691b9cc166751fd2": {"t": 1785604530.9726226, "n": 406, "h": "e9ac163224846a1e", "c": "import sys\nimport logging\nfrom PySide6.QtWidgets import QApplication\nfrom gui.main_window import MainWindow\n\n# Configure logging\nlogging.basicConfig(\n level=logging.INFO,\n format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'\n)\n\ndef main():\n app = QApplication(sys.argv)\n \n window = MainWindow()\n window.show()\n \n sys.exit(app.exec())\n\nif __name__ == \"__main__\":\n main()\n"}}, "run_irym1.sh": {"4dcb9a711b02803193dde66366ad4d7d58517a49": {"t": 1785604532.6758816, "n": 215, "h": "a017a7780d6bd2b0", "c": "#!/bin/bash\nexport PYTHONPATH=$(pwd)\nsource .venv/bin/activate\necho \"Starting IRYM1 FastAPI Server on http://127.0.0.1:8000/irym1/ ...\"\npython -m uvicorn apps.irym_1.irym_1:app --host 127.0.0.1 --port 8000 --reload\n"}}}} |