Using data returned by get_visit_info and get_store_info, Generate a detailed, comprehensive store visit performance report using the pre-calculated metrics.

## 1. Basic Store Information
- **Store ID:** store_id
- **Store Name:** store_name
- **Store Address:** store_address
- **Most recent Visit:** use latest_visit_date from get_visit_info
- **Most recent visitor:** use visitor_name from get_visit_info
- **Current Weather:** Uses `openweather_tool` to get current weather information for the store's location.
- **Foot Traffic:** Use `get_foot_traffic` to get foot traffic data for the store, for every day of the week and average of daily foot traffic.
  - Compare the Foot Traffic with day of visits to detect deviations.


## 2. Executive Summary
- **Average Duration of Visits:** use the column visit_duration
- **Average Visit Length Comparison:** compare the visit_duration with the duration previous visits.
- **Variance in Average Visit Length:** compare visit_length changes across all visits.
- **Total Visits:** use number_of_visits
- **Total Unique Stores Visited:** use visited_stores
- **Median Per-Store visits:** use median_visits_per_store
- **Median Duration of Visits:** use median_visit_duration

## 3. Summary of Insights
- **Summary of Visits:** Use the information extracted to summarize the employee's behavior based on last answers.
- **Key Findings:** Summarize the most impactful insights from the analysis.
• **Work for today's visit:** What were the key wins or successes from today's visit?
• **Challenges and Opportunities:** What challenges or opportunities did you observe during your visit?
  - Highlight major issues identified in the visits.
  - Areas where performance can be enhanced.
  - include anything that could be improved or leveraged for future success.
• **Next Steps:**
    - What specific actions or focus areas should be prioritized for your next visit to this location?.
    - what are your recommendations for improving Hisense's visibility and positioning?.

## 4. Visit Performance Metrics
Store ID: {store_id}

You are given a JSON data where each object is **one visit**.

### **IMPORTANT PRE-PROCESSING STEP**
Each object in `visit_data` will have:
  • column_name
  • question
  • answer

### Task
For each of the four key questions (column_name: '9730', '9731', '9732', '9733'), extract and analyze the data.
- Question 9730 (Key Wins): Summarize positive outcomes and successes.
- Question 9731 (Challenges/Opportunities): Identify recurring issues and improvement areas.
- Question 9732 (Next Visit Focus): Analyze follow-up priorities and action items.
- Question 9733 (Competitive Landscape): Evaluate market positioning and visibility concerns.

#### Extraction rules
1. Work **only** with the literal text inside each `answer`.
2. A phrase, theme or issue is valid **only if that exact substring appears** in an answer.
3. If none are found, output an empty list [].
4. After each list item, add “(#row_index)” indicating the first visit row where it occurs.

### For each Question (9730, 9731, 9732, 9733) provide:
• **Top Phrases:** up to 5 frequent key phrases present in `answer` (lower-cased, stemmed/lemmatized).
• **Themes:** Identify business-relevant terms like product names, competitor names, specific issues, store features, customer behaviors referenced in `answer`.
• **Key Issues:** Identify the most frequently mentioned issues or challenges.
    * up to 5 issues/challenges ranked by frequency.
• **Sentiment Counts:** evaluate all `answer` for every VisitAnswer in `visit_data`
    - Positive: X, Negative: Y, Neutral: Z
    *Positive > 0, Negative < 0, Neutral ≈ 0 (TextBlob polarity scale).*
• **Sentiment Analysis:**
    - Extract one sample answer for positive, negative and neutral from `answer`.
• **"Most Relevant Answer":** the answer that best exemplifies the key issues (highest phrase overlap).
• **Insights:** Identify any actionable insights based exclusively on phrases.

**Do NOT** aggregate multiple questions together. **Do NOT** summarize across questions. **Do NOT** omit any of the seven bullets above.

## 5. Visit Comparison – Visit_1 vs. (Visit_2 & Visit_3)

### Visits to analyze
Rank the rows by visit_timestamp DESC and label them:
  • Visit_1  = most-recent
  • Visit_2  = previous-1
  • Visit_3  = previous-2

For **each** question `column_name` produce:

### Question column_name
• **Sentiment Trend:** ↑ / ↓ / →  (based on net-positive – net-negative)
• **New Issues:** issues appearing **only** in Visit_1
• **Resolved Issues:** issues present earlier but **absent** in Visit_1
• **Persisting Issues:** issues that appear in all three visits
• **Notable Phrase Shifts:** any big change in Top Phrases frequency
• **Overall Assessment:** “Better / Worse / No Material Change” with one-sentence rationale

IMPORTANT INSTRUCTIONS:
- Strictly follow this markdown format without exception.
- Always return EVERY section and sub-section EXACTLY as formatted above.
- NEVER omit, summarize briefly, or indicate additional details elsewhere.
- DO NOT include any introductory summaries, concluding remarks, end notes, or additional text beyond the specified structure.
- NEVER include any disclaimers, warnings, or notes about the data or analysis or phrases as "... from the provided ...".
