mcp-servers/nadlan-mcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
34 Commits 1 Branch 0 Tags
fe0a96ab83b530b950aac59d5ee97c991d448121
Commit Graph

6 Commits

Author SHA1 Message Date
Nitzan Pomerantz fe0a96ab83 Fix: Address E2E bugs from real-world MCP testing 
Fixes three critical bugs discovered during live testing with Claude:

Bug #1: Same building detection always returned 0
- Root cause: deal.get('address') returned empty string
- Fix: Construct address from streetNameHeb + houseNum fields
- Added test: test_same_building_detection_with_api_fields

Bug #2: Property type filter too strict
- Root cause: Exact match failed for variants like 'דירת גג'
- Fix: Use flexible substring matching with normalization

Bug #3: Deal deduplication used non-existent field
- Root cause: Deduplication key referenced deal.get('address')
- Fix: Removed non-existent field from deduplication key

Also added _calculate_distance() helper for future radius filtering.

Test results: 26/28 passing (2 pre-existing failures unrelated)
References: .cursor/plans/MCP-E2E-TEST-SUMMARY.md

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-10-24 23:47:07 +03:00
Nitzan Pomerantz 56ed1029e0 Fix tests for time_period_months filtering implementation 
Update tests to pass time_period_months=None for tests using old dates
(2022-2023) to disable time filtering. This is necessary because the
time_period_months parameter is now properly implemented and filters
out old deals by default.

Tests fixed:
- test_calculate_market_activity_score_success
- test_calculate_market_activity_score_high_activity
- test_get_market_liquidity_success
- test_get_market_liquidity_quarterly_breakdown

All market analysis tests now pass (25/27 tests passing, 2 pre-existing
failures unrelated to our changes).

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-10-24 19:36:04 +03:00
Nitzan Pomerantz 943a03ae5a Improve test assertion specificity and formatting 
Replace broad assertion (mean > 0) with specific expected value using
pytest.approx for floating-point comparison. This makes the test more
robust and prevents future regressions.

Changes:
- Change area_stats mean assertion from > 0 to == pytest.approx(80.0)
- Add final newline to file per convention

Expected mean: (80 + 90 + 70) / 3 = 80.0

Addresses PR #2 review comments on line 527.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-10-24 19:27:32 +03:00
Nitzan Pomerantz 2968711307 Complete Phase 2: Market Analysis, Filtering & Documentation 
This commit implements all Phase 2 functionality with architectural
improvements over the original plan.

## Phase 2.1: Property Valuation Data ✅
- filter_deals_by_criteria() with comprehensive filtering
- calculate_deal_statistics() for statistical aggregations
- _extract_floor_number() for Hebrew floor parsing
- _calculate_std_dev() helper function
- MCP tools: get_valuation_comparables, get_deal_statistics

## Phase 2.2: Market Activity & Investment Analysis ✅
- calculate_market_activity_score() - deal frequency & velocity
  * Activity score (0-100), trend analysis, monthly distribution
  * Classifies markets: very_high, high, moderate, low, very_low
- analyze_investment_potential() - price trends & stability
  * Price appreciation rate via linear regression
  * Volatility score using coefficient of variation
  * Investment score combining appreciation & stability
- get_market_liquidity() - turnover & liquidity metrics
  * Quarterly/monthly breakdowns, velocity scoring
  * Trend direction, most active periods
- MCP tool: get_market_activity_metrics (unified tool)

## Phase 2.3: Enhanced Deal Filtering ✅
- Property type, room count, price, area, floor filtering
- All integrated into existing tools
- Hebrew floor number parsing support

## Testing ✅
- Added 15 comprehensive unit tests (all passing)
- Coverage: market activity, investment analysis, liquidity, filtering
- Edge cases: empty data, invalid dates, insufficient data

## Documentation ✅
- Created CLAUDE.md (~250 lines) - AI agent guidance
  * Development commands, architecture overview
  * Product vision from USECASES.md
  * Available tools with status indicators
- Updated TASKS.md - Phase 2 marked 100% complete

## Architectural Improvements
- 1 unified MCP tool instead of 6 separate tools (simpler API)
- 1 flexible filtering function instead of 3 (more composable)
- All logic in govmap.py (no new files, better cohesion)
- ~955 lines added with comprehensive documentation

## Design Principles Followed
✅ MCP provides data, LLM provides intelligence
✅ No predictions - only statistical calculations
✅ Comprehensive error handling & input validation
✅ Well-documented with detailed docstrings

Phase 2 Progress: 100% complete (60% overall project completion)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-10-24 18:51:50 +03:00
Nitzan Pomerantz dd6d78b48b Refactor govmap 2025-07-13 01:03:15 +03:00
Nitzan Pomerantz 1f1f4fc0ec Added tests 2025-07-12 17:48:50 +03:00