Create gemini_report.py

gemini_report.py

@@ -0,0 +1,90 @@
+import json
+import google.generativeai as genai
+from config import GEMINI_API_KEY
+from models import PageSpeedRequest
+
+def generate_report_with_gemini(pagespeed_data: dict) -> str:
+    genai.configure(api_key=GEMINI_API_KEY)
+    model = genai.GenerativeModel("gemini-2.0-flash")
+
+    prompt = (
+        "**Role:** You are an **Expert Web Performance Optimization Analyst and Senior Full-Stack Engineer** "
+        "with deep expertise in interpreting Google PageSpeed Insights data, diagnosing frontend and "
+        "backend bottlenecks, and devising actionable, high-impact optimization strategies.\n\n"
+        "**Objective:**\n"
+        "Analyze the provided Google PageSpeed Insights JSON data for the analyzed website. "
+        "Your primary goal is to generate a comprehensive, prioritized, and actionable set of strategies "
+        "to significantly improve its performance. These strategies must directly address the specific "
+        "metrics and audit findings within the report, aiming to elevate both Core Web Vitals "
+        "(LCP, INP, CLS) and other key performance indicators (FCP, TTFB, TBT), and ultimately "
+        "improve the `overall_category` to 'FAST' where possible.\n\n"
+        "**Input Data:**\n"
+        "The following JSON object contains the complete PageSpeed Insights report:\n"
+        f"```json\n{json.dumps(pagespeed_data, indent=2)}\n```\n\n"
+        "**Analysis and Strategy Formulation - Instructions:**\n\n"
+        "1.  **Executive Performance Summary:**\n"
+        "    * Begin with a concise overview of the website's current performance status based on the provided data.\n"
+        "    * Highlight the `overall_category` for both `loadingExperience` (specific URL) and `originLoadingExperience` (entire origin).\n"
+        "    * Pinpoint the current values and `category` (e.g., FAST, AVERAGE, SLOW) for each key metric:\n"
+        "        * `CUMULATIVE_LAYOUT_SHIFT_SCORE` (CLS)\n"
+        "        * `EXPERIMENTAL_TIME_TO_FIRST_BYTE` (TTFB)\n"
+        "        * `FIRST_CONTENTFUL_PAINT_MS` (FCP)\n"
+        "        * `INTERACTION_TO_NEXT_PAINT` (INP)\n"
+        "        * `LARGEST_CONTENTFUL_PAINT_MS` (LCP)\n"
+        "        * `total-blocking-time` (TBT) from Lighthouse.\n"
+        "    * Identify any significant `metricSavings` opportunities highlighted in the Lighthouse `audits`.\n\n"
+        "2.  **Deep-Dive into Bottlenecks & Audit Failures:**\n"
+        "    * Systematically go through the `loadingExperience`, `originLoadingExperience`, and `lighthouseResult` (especially the `audits` section).\n"
+        "    * For each underperforming metric or failed/suboptimal audit (e.g., Lighthouse scores less than 1, or `notApplicable` audits with clear improvement paths like `lcp-lazy-loaded`, `critical-request-chains`, `dom-size`, `non-composited-animations`), extract the relevant details, display values, and numeric values.\n\n"
+        "3.  **Develop Prioritized, Actionable Optimization Strategies:**\n"
+        "    For *each* identified performance issue or opportunity, provide the following:\n"
+        "    * **A. Issue & Evidence:** Clearly state the problem (e.g., \"High Total Blocking Time,\" \"Suboptimal Largest Contentful Paint due to unoptimized image,\" \"Excessive DOM Size,\" \"Render-blocking resources in critical request chain\"). Refer directly to the JSON data points and audit IDs that support this finding (e.g., `audits['total-blocking-time'].numericValue`, `audits['critical-request-chains'].details.longestChain`).\n"
+        "    * **B. Root Cause Analysis (Inferred):** Briefly explain the likely technical reasons behind the issue based on the data.\n"
+        "    * **C. Specific, Technical Recommendation(s):** Provide detailed, actionable steps a development team can take. Be specific.\n"
+        "    * **D. Targeted Metric Improvement:** Specify which primary and secondary metrics this strategy will positively impact (e.g., \"This will directly reduce LCP and improve FCP,\" or \"This will significantly lower TBT and improve INP.\").\n"
+        "    * **E. Priority Level:** Assign a priority (High, Medium, Low) based on:\n"
+        "        * Impact on Core Web Vitals.\n"
+        "        * Potential for overall score improvement (consider `metricSavings`).\n"
+        "        * Severity of the issue (e.g., 'SLOW' or 'AVERAGE' categories).\n"
+        "        * Estimated implementation effort (favor high-impact, low/medium-effort tasks for higher priority).\n"
+        "    * **F. Justification for Priority:** Briefly explain why this priority was assigned.\n\n"
+        "4.  **Strategic Grouping (Optional but Recommended):**\n"
+        "    If applicable, group recommendations by area (e.g., Asset Optimization, JavaScript Optimization, Server-Side Improvements, Rendering Path Optimization, CSS Enhancements).\n\n"
+        "5.  **Anticipated Overall Impact:**\n"
+        "    Conclude with a statement on the anticipated overall improvement in performance and user experience if the high and medium-priority recommendations are implemented.\n\n"
+        "**Output Format:**\n"
+        "Please structure your response clearly. Use headings, subheadings, and bullet points to enhance readability and actionability. For example:\n\n"
+        "---\n"
+        "## Executive Performance Summary\n"
+        "* **Overall URL Loading Experience Category:** [e.g., AVERAGE]\n"
+        "* **Overall Origin Loading Experience Category:** [e.g., AVERAGE]\n"
+        "* **Key Metrics:**\n"
+        "    * LCP: [Value] ms ([Category])\n"
+        "    * INP: [Value] ms ([Category])\n"
+        "    * ...etc.\n\n"
+        "---\n"
+        "## Prioritized Optimization Strategies\n\n"
+        "### High Priority\n"
+        "**1. Issue & Evidence:** [e.g., High Total Blocking Time (TBT) of 1200 ms - `audits['total-blocking-time'].numericValue`]\n"
+        "    * **Root Cause Analysis:** [e.g., Long JavaScript tasks on the main thread during page load, likely from unoptimized third-party scripts or complex component rendering.]\n"
+        "    * **Specific, Technical Recommendation(s):**\n"
+        "        * [Action 1]\n"
+        "        * [Action 2]\n"
+        "    * **Targeted Metric Improvement:** [e.g., TBT, INP, FCP]\n"
+        "    * **Justification for Priority:** [e.g., Directly impacts interactivity (INP) and is a significant contributor to a poor lab score.]\n\n"
+        "**(Continue with other High, Medium, and Low priority items)**\n"
+        "---\n\n"
+        "**Ensure your analysis is based *solely* on the provided JSON data and your expert interpretation of it. "
+        "Avoid generic advice; all recommendations must be tied to specific findings within the report. "
+        "Do not add anything irrelevant in the report.**"
+    )
+    try:
+        response = model.generate_content(prompt)
+        if response and hasattr(response, "text"):
+            return response.text
+        elif response and getattr(response, "candidates", None):
+            if response.candidates[0].finish_reason == "SAFETY":
+                return "Report generation was blocked due to safety settings."
+        return "Report generation failed or returned an incomplete response."
+    except Exception as e:
+        return f"An error occurred during report generation: {str(e)}"