#!/usr/bin/env python3 """ Step 6: Report Context Preparation Aggregates all analysis results, figure paths, and thesis points into a single structured JSON file for the downstream report generation workflow. """ import json import os from pathlib import Path from datetime import datetime # Define paths SESSION_DIR = Path("/app/sandbox/session_20260203_085912_030e6e80a419") RESULTS_DIR = SESSION_DIR / "results" FIGURES_DIR = SESSION_DIR / "figures" print("=" * 60) print("STEP 6: REPORT CONTEXT PREPARATION") print("=" * 60) print(f"Timestamp: {datetime.now().isoformat()}") print() # 1. Read all summary files print("1. Reading summary files...") def read_file_content(filepath): """Read file content safely.""" try: with open(filepath, 'r', encoding='utf-8') as f: return f.read() except Exception as e: print(f" WARNING: Could not read {filepath}: {e}") return "" # Read summary files financial_summary = read_file_content(RESULTS_DIR / "financial_health_summary.txt") print(f" - financial_health_summary.txt: {len(financial_summary)} chars") valuation_summary = read_file_content(RESULTS_DIR / "valuation_summary.txt") print(f" - valuation_summary.txt: {len(valuation_summary)} chars") sentiment_analysis = read_file_content(RESULTS_DIR / "sentiment_analysis.txt") print(f" - sentiment_analysis.txt: {len(sentiment_analysis)} chars") investment_thesis = read_file_content(RESULTS_DIR / "investment_thesis_synthesis.txt") print(f" - investment_thesis_synthesis.txt: {len(investment_thesis)} chars") # Read thesis summary JSON print("\n2. Reading thesis_summary.json...") try: with open(RESULTS_DIR / "thesis_summary.json", 'r') as f: thesis_summary_json = json.load(f) print(f" - Loaded {len(thesis_summary_json)} key metrics") except Exception as e: print(f" WARNING: Could not read thesis_summary.json: {e}") thesis_summary_json = {} # 3. Scan figures directory print("\n3. Scanning figures/ directory...") figures_list = [] figure_mapping = { "revenue_profit_trend.png": { "caption": "Revenue vs Net Income Trend (2021-2024)", "relevance": "Shows accelerating revenue decline and profit margin collapse", "section": "financial" }, "margin_erosion.png": { "caption": "Operating and Net Profit Margin Erosion", "relevance": "Illustrates margin compression from +10% to -135%", "section": "financial" }, "cash_vs_debt.png": { "caption": "Cash Position vs Total Debt Evolution", "relevance": "Demonstrates aggressive deleveraging despite revenue decline", "section": "financial" }, "projected_revenue_scenarios.png": { "caption": "DCF Revenue Projections: Bull/Base/Bear Scenarios", "relevance": "Visual comparison of valuation scenario outcomes", "section": "valuation" }, "valuation_sensitivity.png": { "caption": "Valuation Sensitivity to WACC and Growth Assumptions", "relevance": "Shows fair value range across different assumptions", "section": "valuation" }, "technical_chart.png": { "caption": "Technical Analysis: Price, Moving Averages, and Volume", "relevance": "Confirms strong downtrend with price below key SMAs", "section": "valuation" }, "ownership_structure.png": { "caption": "Ownership Structure and Short Interest Breakdown", "relevance": "Shows 5.9% short interest - trade not crowded", "section": "sentiment" } } if FIGURES_DIR.exists(): for fig_file in sorted(FIGURES_DIR.iterdir()): if fig_file.suffix in ['.png', '.jpg', '.jpeg', '.pdf', '.svg']: fig_name = fig_file.name fig_info = figure_mapping.get(fig_name, { "caption": fig_name.replace('_', ' ').replace('.png', '').title(), "relevance": "Analysis visualization", "section": "general" }) figures_list.append({ "path": f"figures/{fig_name}", "filename": fig_name, "caption": fig_info["caption"], "relevance": fig_info["relevance"], "section": fig_info["section"] }) print(f" - {fig_name}: {fig_info['caption']}") else: print(" WARNING: figures/ directory not found") print(f"\n Total figures found: {len(figures_list)}") # 4. Build structured JSON object print("\n4. Building structured JSON report context...") report_context = { "metadata": { "generated_at": datetime.now().isoformat(), "ticker": "CHGG", "company": "Chegg, Inc.", "analysis_type": "Investment Thesis - Short Position", "workflow_status": "Analysis Complete - Ready for Writing Agent", "steps_completed": [ "Step 1: Environment Setup & Data Inventory", "Step 2: Financial Health Analysis", "Step 3: Valuation Modeling", "Step 4: Sentiment & Short Interest Analysis", "Step 5: Investment Thesis Synthesis", "Step 6: Report Context Preparation" ] }, "thesis_core": investment_thesis, "key_metrics": thesis_summary_json, "section_summaries": { "financial_health": { "title": "Financial Health Analysis", "content": financial_summary, "key_findings": [ "Revenue declined 42% from 2021 peak ($776M) to TTM ($448M)", "Net profit margin collapsed to -135.5% in 2024", "$677M goodwill impairment acknowledges permanent AI disruption", "Current ratio < 1.0 indicates short-term liquidity stress", "Aggressive debt reduction from $1.7B to $504M" ] }, "valuation": { "title": "Valuation Analysis", "content": valuation_summary, "key_findings": [ "Probability-weighted fair value: $0.94 (+34% vs current)", "Liquidation value floor: $0.50/share", "Bear case (35% probability): $0.12/share", "Reverse DCF implies -35% perpetual growth expectation", "Trading at 0.52x book, 0.17x sales (distressed multiples)" ] }, "sentiment": { "title": "Short Interest & Market Sentiment", "content": sentiment_analysis, "key_findings": [ "Short interest at 5.9% - trade NOT crowded", "Days to cover: 5.5 days - orderly exit possible", "Squeeze risk: MODERATE (score 50/100)", "Stock transitioning from 'hated' to 'ignored'", "Institutional ownership: ~38% (limited forced selling)" ] } }, "figures": figures_list, "investment_recommendation": { "position": "MAINTAIN SHORT", "conviction": "HIGH", "entry_zone": { "low": 0.70, "high": 0.90, "optimal": 0.89 }, "stop_loss": 1.03, "price_targets": { "base_case": {"price": 0.50, "probability": 0.50, "return_pct": -32}, "bear_case": {"price": 0.25, "probability": 0.35, "return_pct": -66}, "extreme_bear": {"price": 0.12, "probability": 0.15, "return_pct": -84} }, "risk_reward_ratio": "1:0.8", "position_sizing": "2-3% of portfolio", "time_horizon": "6-18 months" }, "key_catalysts": { "negative_for_stock": [ "Q4 2025 / Q1 2026 Earnings: Continued subscriber losses", "Guidance Reduction: Management admits further deterioration", "Cash Burn Acceleration: If cost cuts fail", "AI Competition Intensifies: ChatGPT, Gemini, Claude improvements", "Debt Maturity / Refinancing Issues" ], "cover_triggers": [ "Strategic Review / M&A Rumor announcement", "Short Squeeze (limited potential with 6% SI)" ] }, "file_references": { "results": [ "results/financial_health_summary.txt", "results/valuation_summary.txt", "results/sentiment_analysis.txt", "results/investment_thesis_synthesis.txt", "results/thesis_summary.json", "results/financial_metrics_history.csv", "results/valuation_scenarios.csv", "results/technical_indicators.csv" ], "figures": [f["path"] for f in figures_list], "data": [ "data/chegg_cleaned.csv" ] } } # 5. Save the report context JSON print("\n5. Saving report_context.json...") output_path = RESULTS_DIR / "report_context.json" with open(output_path, 'w', encoding='utf-8') as f: json.dump(report_context, f, indent=2, ensure_ascii=False) print(f" Saved to: {output_path}") print(f" File size: {output_path.stat().st_size / 1024:.1f} KB") # Validate JSON print("\n6. Validating JSON structure...") with open(output_path, 'r') as f: validated = json.load(f) required_keys = ['metadata', 'thesis_core', 'key_metrics', 'section_summaries', 'figures'] all_present = all(k in validated for k in required_keys) print(f" Required keys present: {all_present}") print(f" Total keys: {len(validated)}") print(f" Thesis core length: {len(validated['thesis_core'])} chars") print(f" Key metrics count: {len(validated['key_metrics'])}") print(f" Section summaries: {list(validated['section_summaries'].keys())}") print(f" Figures count: {len(validated['figures'])}") print("\n" + "=" * 60) print("REPORT CONTEXT PREPARATION COMPLETE") print("=" * 60) print(f"\nOutput: results/report_context.json") print("Status: Ready for Writing Agent ingestion")