- Fix HP007/HP013: add 'drawdown', 'biggest holding', 'top holdings' to
performance keyword lists so these queries route to portfolio_analysis
- Fix MS005: use word-boundary regex for short city tokens (sf, atx, dfw)
to prevent 'sf' substring-matching inside ticker symbols like 'MSFT',
which was incorrectly routing to real_estate_snapshot
- Fix MS010: route full_report_kws to performance+compliance+activity
(was 'compliance' only, missing transaction_query for 'recent activity')
- Fix sc-004: add common 'portfolio' typos (portflio, porfolio, etc.) to
natural_performance_kws for robustness against misspellings
- Fix MS005 (part 2): add 'worth today', 'worth now', 'currently worth'
to market_kws so cost-basis-vs-current-price queries trigger both
portfolio_analysis and market_data
All eval suites now pass: 182/182 pytest, 60/60 run_evals, 25/25 golden sets
Made-with: Cursor
- Created agent/evals/conftest.py: autouse fixture patches teleport_api._fetch_from_teleport
and search_city_slug to bypass all live HTTP calls during tests
- Tests now use HARDCODED_FALLBACK data for all cities (deterministic, instant)
- Created agent/pytest.ini with asyncio_mode=strict and testpaths=evals
- All 126 tests collected and passing: 0 failures, 0 skips
Made-with: Cursor
Create realestate_strategy.py with simulate_real_estate_strategy().
All rate parameters (appreciation, rent_yield, mortgage_rate,
market_return) default to None — sensible fallbacks applied inside
the function body, clearly labeled as starting points not predictions.
Adds disclaimer, how_to_adjust, and user_provided flag in assumptions.
Adds test_realestate_strategy.py with 7 passing tests.
Made-with: Cursor
property_tracker.py:
- Full SQLite backing at agent/data/properties.db (PROPERTIES_DB_PATH for tests)
- :memory: support: module-level _MEMORY_CONN so data persists across calls in tests
- add_property(), get_properties(), list_properties() (alias), update_property(),
remove_property() (soft-delete), get_real_estate_equity(), get_total_net_worth()
- _row_to_dict() computes equity/appreciation and backward-compat added_at alias
- property_store_clear() does DELETE FROM (test reset)
test_wealth_bridge.py (8 new tests, total now 89):
- test_down_payment_austin_portfolio_94k: $94k covers Caldwell/Hays counties
- test_down_payment_small_portfolio: $20k cannot afford safe 20% down anywhere
- test_job_offer_seattle_not_real_raise: $180k Seattle < $120k Austin purchasing power
- test_job_offer_sf_genuine_raise: $250k SF > $80k Austin purchasing power
- test_job_offer_global_city_london: required fields present for any global city
- test_property_crud_full_cycle: CREATE→READ→UPDATE→DELETE all verified
- test_net_worth_combines_portfolio_and_property: equity + portfolio = correct total
- test_teleport_fallback_works_when_api_unavailable: always returns usable data
Made-with: Cursor
- test_search_listings_bedroom_filter: min_beds=3 returns only 3+ bed
listings and records the filter in result.filters_applied.
- test_search_listings_price_filter: max_price=400000 excludes listings
above threshold and records filter in result.filters_applied.
- test_structured_error_code: all error paths return nested
{code, message} dict with a REAL_ESTATE_* code.
- Updated test_feature_flag_disabled: assert nested error dict with
REAL_ESTATE_FEATURE_DISABLED code.
- Updated test_unknown_location_graceful_error: assert nested error
dict with REAL_ESTATE_PROVIDER_UNAVAILABLE code.
All 8 tests pass in < 1s.
Made-with: Cursor
- eval runner: add retry logic (2 attempts) for transient connection drops
- gs-001: accept 'percent' as well as '%' (LLM formatting variance)
- gs-002: use must_contain_one_of for ticker/company name variance
- gs-008/sc-014: fix expected_tools for conditionally-triggered compliance
- graph.py: route 'health check'/'full report' queries to compliance path
so compliance_check always runs for full portfolio report requests
Co-authored-by: Cursor <cursoragent@cursor.com>
Source tags [tool_result_id] were appearing after every individual figure,
making responses unreadable. Rules 1 and 10 in SYSTEM_PROMPT and the
format_node user prompt now enforce one citation per sentence placed at
the end, not inline after each value.
Co-authored-by: Cursor <cursoragent@cursor.com>
Priyanka Punukollu