{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "d:\\ankelodon_multiagent_system\\.venv\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "from agent import build_workflow\n",
    "from config import config\n",
    "from tools.code_interpreter import safe_code_run"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "graph = build_workflow()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "💡 ════════════════════\n",
      "💡  USER QUERY \n",
      "💡 ════════════════════\n",
      "   • files: none provided\n",
      "=== COMPLEXITY ASSESSMENT ===\n",
      "Complexity: simple\n",
      "Needs planning: False\n",
      "Reasoning: This is a single-step arithmetic question (2+2). Although calculations technically require a tool per the special considerations, this is trivial and requires only one immediate operation, so it is SIMPLE.\n",
      "=== SIMPLE EXECUTION ===\n",
      "Response generated for simple query.\n",
      "=== GENERATING EXECUTION REPORT ===\n",
      "Report generated - Confidence: high\n",
      "Key findings: 3\n",
      "Data sources: 2\n",
      "query_summary=\"User asked for the numeric result of the arithmetic expression '2+2'.\" approach_used=\"Direct evaluation using basic arithmetic: interpreted '+' as standard integer addition and computed the sum mentally without invoking external tools or files.\" tools_executed=[] key_findings=[\"The expression '2+2' was interpreted as standard integer addition.\", 'Computed result is 4.', 'No external tools or data were required to compute the result.'] data_sources=['Basic arithmetic rules (internal knowledge)', 'Conversation history confirming the query and an earlier direct answer'] assumptions_made=[\"The '+' operator denotes standard arithmetic addition on integers.\", 'Numbers are in the usual base-10 system and no special context (e.g., modular arithmetic or symbolic manipulation) was intended.'] confidence_level='high' limitations=['If the user intended a nonstandard context (modulo arithmetic, different base, or overloaded operator semantics), the answer could differ.', 'Extremely simple query; few realistic limitations beyond contextual ambiguity.'] final_answer='4'\n",
      "=== ENHANCED ANSWER CRITIQUE ===\n",
      "Quality Score: 8/10\n",
      "Complete: True\n",
      "Accurate: True\n",
      "Issues found: [\"Performed the calculation mentally rather than using an external computational tool (triggers the evaluation framework's manual-calculation penalty).\"]\n",
      "=== REPLAN DECISION ===\n",
      "Iteration: 1/10\n",
      "Quality score: 8\n",
      "Needs replanning: False\n",
      "Quality acceptable, ending execution\n"
     ]
    }
   ],
   "source": [
    "query = \"What is 2+2\"\n",
    "result = graph.invoke({\"query\" : query, \"current_step\": 0, \"reasoning_done\": False, \"files\" : [], \"files_contents\" : {}, \"iteration_count\" : 0, \"max_iterations\" : 10, \"plan\" : None} , config = config)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "FINAL ANSWER: 4\n"
     ]
    }
   ],
   "source": [
    "print(result[\"final_answer\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'messages': [SystemMessage(content='You are a COMPLEXITY ASSESSOR for a multi-tool agent system.\\nYour job is to analyze user queries and determine their complexity level and processing requirements.\\n\\nCOMPLEXITY LEVELS:\\n1. SIMPLE: Direct questions that can be answered immediately without tools or with single tool use\\n   - Examples: \"What is photosynthesis?\", \"Define machine learning\", \"What\\'s the capital of France?\"\\n   - NOTE: Simple math like \"2+2\" still requires calculator tool but counts as SIMPLE\\n\\n   !ALSO: It can be a logical reasoning or explanation task that does not require tools.\\n   \\n2. MODERATE: Questions requiring 2-4 tool calls or basic multi-step analysis\\n   - Examples: \"Search for recent news about AI\", \"Analyze this CSV file for trends\", \"Calculate ROI from this data\"\\n   - \"Compare two datasets\", \"Summarize multiple documents\"\\n   \\n3. COMPLEX: Multi-step problems requiring planning, multiple tools, and sophisticated reasoning\\n   - Examples: \"Research market trends and create investment strategy\", \"Analyze multiple data sources and predict outcomes\"\\n   - \"Build comprehensive report from various inputs\", \"Multi-stage data processing with validation\"\\n\\nMOST OF THE LOGICAL TASKS ARE SIMPLE, UNLESS THEY REQUIRE TOOLS.\\n\\nASSESSMENT CRITERIA:\\n- Number of distinct steps likely needed (1 = Simple, 2-4 = Moderate, 5+ = Complex)\\n- Tool complexity and dependencies between steps\\n- Data processing requirements and validation needs\\n- Need for intermediate reasoning and synthesis\\n- Risk of failure without proper step-by-step planning\\n- Presence of calculations (automatically requires tool usage)\\n\\nSPECIAL CONSIDERATIONS:\\n- Any calculation/counting task requires tools (affects complexity assessment)\\n- File analysis tasks usually need multiple steps (load + analyze + calculate)\\n- Research tasks typically need search + fetch + synthesis steps\\n- Comparison tasks need separate analysis steps for each item being compared\\n\\nRULES:\\n- SIMPLE queries may bypass planning for non-calculation tasks\\n- MODERATE queries benefit from lightweight planning\\n- COMPLEX queries require full planning with fallbacks\\n- When in doubt, err toward higher complexity\\n- Calculation tasks are never truly \"simple\" due to mandatory tool usage\\n\\nAnalyze the query and respond with your assessment.', additional_kwargs={}, response_metadata={}, id='db109164-6e6e-4c1f-82bb-93d6d9b64e6a'),\n",
       "  HumanMessage(content='Query: What is 2+2', additional_kwargs={}, response_metadata={}, id='6b9afadb-3463-40a2-989b-19f8a237f7fc'),\n",
       "  AIMessage(content='2 + 2 = 4', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 80, 'prompt_tokens': 1638, 'total_tokens': 1718, 'completion_tokens_details': {'accepted_prediction_tokens': 0, 'audio_tokens': 0, 'reasoning_tokens': 64, 'rejected_prediction_tokens': 0}, 'prompt_tokens_details': {'audio_tokens': 0, 'cached_tokens': 0}}, 'model_name': 'gpt-5-mini-2025-08-07', 'system_fingerprint': None, 'id': 'chatcmpl-CId3zSwgGIoDxYMuwG2xJfCLDiVuM', 'service_tier': 'default', 'finish_reason': 'stop', 'logprobs': None}, id='run--210d298d-a542-4458-8933-93ebf4c7bac0-0', usage_metadata={'input_tokens': 1638, 'output_tokens': 80, 'total_tokens': 1718, 'input_token_details': {'audio': 0, 'cache_read': 0}, 'output_token_details': {'audio': 0, 'reasoning': 64}})],\n",
       " 'query': 'What is 2+2',\n",
       " 'final_answer': 'FINAL ANSWER: 4',\n",
       " 'plan': None,\n",
       " 'complexity_assessment': ComplexityLevel(level='simple', reasoning='This is a single-step arithmetic question (2+2). Although calculations technically require a tool per the special considerations, this is trivial and requires only one immediate operation, so it is SIMPLE.', needs_planning=False, suggested_approach='Perform the basic arithmetic (2+2) and return the result (4). No detailed planning or multi-step processing needed.'),\n",
       " 'current_step': 0,\n",
       " 'reasoning_done': False,\n",
       " 'files': [],\n",
       " 'critique_feedback': CritiqueFeedback(quality_score=8, is_complete=True, is_accurate=True, missing_elements=[], errors_found=[\"Performed the calculation mentally rather than using an external computational tool (triggers the evaluation framework's manual-calculation penalty).\"], suggested_improvements=['Use a computational tool or explicitly show the calculation steps even for trivial arithmetic to avoid the manual-calculation policy violation (e.g., evaluate with a calculator tool or print the operation and result).', \"Explicitly state assumptions up front (that '+' is standard integer addition in base 10) and, when relevant, ask a clarifying question if the user might have meant a nonstandard interpretation (modular arithmetic, different base, operator overloading).\", 'For transparency, include a short note citing the arithmetic rule used (e.g., basic integer addition) when delivering the result, even though the operation is trivial.'], needs_replanning=False, replan_instructions=None),\n",
       " 'iteration_count': 1,\n",
       " 'max_iterations': 10,\n",
       " 'execution_report': ExecutionReport(query_summary=\"User asked for the numeric result of the arithmetic expression '2+2'.\", approach_used=\"Direct evaluation using basic arithmetic: interpreted '+' as standard integer addition and computed the sum mentally without invoking external tools or files.\", tools_executed=[], key_findings=[\"The expression '2+2' was interpreted as standard integer addition.\", 'Computed result is 4.', 'No external tools or data were required to compute the result.'], data_sources=['Basic arithmetic rules (internal knowledge)', 'Conversation history confirming the query and an earlier direct answer'], assumptions_made=[\"The '+' operator denotes standard arithmetic addition on integers.\", 'Numbers are in the usual base-10 system and no special context (e.g., modular arithmetic or symbolic manipulation) was intended.'], confidence_level='high', limitations=['If the user intended a nonstandard context (modulo arithmetic, different base, or overloaded operator semantics), the answer could differ.', 'Extremely simple query; few realistic limitations beyond contextual ambiguity.'], final_answer='4')}"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "#TO-DO\n",
    "#1. Check routing with REPLANNER -> может придумывать несуществующие инструменты -> PARTIALLY COMPLETED\n",
    "#2. Add crawling tool \n",
    "#3. Enhance description of coder tool and прописать более четко в промпте важность вывода через print() или return или result/_ -> COMPLETED?\n",
    "#4. Смягчить критика COMPLETED"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}