mirror of
https://github.com/we-promise/sure.git
synced 2026-04-07 14:31:25 +00:00
88952e4714
* Initial implementation * FIX keys * Add langfuse evals support * FIX trace upload * Delete .claude/settings.local.json Signed-off-by: soky srm <sokysrm@gmail.com> * Update client.rb * Small LLMs improvements * Keep batch size normal * Update categorizer * FIX json mode * Add reasonable alternative to matching * FIX thinking blocks for llms * Implement json mode support with AUTO mode * Make auto default for everyone * FIX linter * Address review * Allow export manual categories * FIX user export * FIX oneshot example pollution * Update categorization_golden_v1.yml * Update categorization_golden_v1.yml * Trim to 100 items * Update auto_categorizer.rb * FIX for auto retry in auto mode * Separate the Eval Logic from the Auto-Categorizer The expected_null_count parameter conflates eval-specific logic with production categorization logic. * Force json mode on evals * Introduce a more mixed dataset 150 items, performance from a local model: By Difficulty: easy: 93.22% accuracy (55/59) medium: 93.33% accuracy (42/45) hard: 92.86% accuracy (26/28) edge_case: 100.0% accuracy (18/18) * Improve datasets Remove Data leakage from prompts * Create eval runs as "pending" --------- Signed-off-by: soky srm <sokysrm@gmail.com> Signed-off-by: Juan José Mata <juanjo.mata@gmail.com> Co-authored-by: Juan José Mata <juanjo.mata@gmail.com>
826 lines
19 KiB
YAML
826 lines
19 KiB
YAML
---
|
|
name: chat_golden_v1
|
|
description: Golden dataset for chat/assistant function calling evaluation
|
|
eval_type: chat
|
|
version: "1.0"
|
|
metadata:
|
|
created_at: "2024-12-01"
|
|
source: manual_curation
|
|
|
|
samples:
|
|
# ===== EASY - Simple single function calls =====
|
|
- id: chat_easy_001
|
|
difficulty: easy
|
|
tags: [get_accounts, simple]
|
|
input:
|
|
prompt: "What accounts do I have?"
|
|
expected:
|
|
functions:
|
|
- name: "get_accounts"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_002
|
|
difficulty: easy
|
|
tags: [get_accounts, simple]
|
|
input:
|
|
prompt: "Show me my accounts"
|
|
expected:
|
|
functions:
|
|
- name: "get_accounts"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_003
|
|
difficulty: easy
|
|
tags: [get_accounts, balance]
|
|
input:
|
|
prompt: "What's my account balance?"
|
|
expected:
|
|
functions:
|
|
- name: "get_accounts"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_004
|
|
difficulty: easy
|
|
tags: [get_transactions, simple]
|
|
input:
|
|
prompt: "Show me my recent transactions"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_005
|
|
difficulty: easy
|
|
tags: [get_transactions, simple]
|
|
input:
|
|
prompt: "What are my latest transactions?"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_006
|
|
difficulty: easy
|
|
tags: [get_balance_sheet, simple]
|
|
input:
|
|
prompt: "What's my net worth?"
|
|
expected:
|
|
functions:
|
|
- name: "get_balance_sheet"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_007
|
|
difficulty: easy
|
|
tags: [get_balance_sheet, simple]
|
|
input:
|
|
prompt: "Show me my assets and liabilities"
|
|
expected:
|
|
functions:
|
|
- name: "get_balance_sheet"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_008
|
|
difficulty: easy
|
|
tags: [get_income_statement, simple]
|
|
input:
|
|
prompt: "What were my expenses last month?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_009
|
|
difficulty: easy
|
|
tags: [get_income_statement, simple]
|
|
input:
|
|
prompt: "How much income did I make this month?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_010
|
|
difficulty: easy
|
|
tags: [get_accounts, simple]
|
|
input:
|
|
prompt: "How many accounts do I have?"
|
|
expected:
|
|
functions:
|
|
- name: "get_accounts"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_011
|
|
difficulty: easy
|
|
tags: [get_transactions, simple]
|
|
input:
|
|
prompt: "List my transactions"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_012
|
|
difficulty: easy
|
|
tags: [get_balance_sheet, simple]
|
|
input:
|
|
prompt: "How much do I owe?"
|
|
expected:
|
|
functions:
|
|
- name: "get_balance_sheet"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_013
|
|
difficulty: easy
|
|
tags: [get_balance_sheet, simple]
|
|
input:
|
|
prompt: "What are my total assets?"
|
|
expected:
|
|
functions:
|
|
- name: "get_balance_sheet"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_014
|
|
difficulty: easy
|
|
tags: [get_income_statement, simple]
|
|
input:
|
|
prompt: "Show my spending"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_015
|
|
difficulty: easy
|
|
tags: [get_income_statement, simple]
|
|
input:
|
|
prompt: "How much did I spend?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
# ===== MEDIUM - With filtering or specific parameters =====
|
|
- id: chat_medium_001
|
|
difficulty: medium
|
|
tags: [get_transactions, filtering]
|
|
input:
|
|
prompt: "Show me my restaurant spending"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_002
|
|
difficulty: medium
|
|
tags: [get_transactions, filtering]
|
|
input:
|
|
prompt: "What did I spend on groceries?"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_003
|
|
difficulty: medium
|
|
tags: [get_transactions, filtering]
|
|
input:
|
|
prompt: "Show transactions over $100"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_004
|
|
difficulty: medium
|
|
tags: [get_transactions, filtering]
|
|
input:
|
|
prompt: "What did I spend at Amazon?"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_005
|
|
difficulty: medium
|
|
tags: [get_transactions, date_range]
|
|
input:
|
|
prompt: "Show me last week's transactions"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_006
|
|
difficulty: medium
|
|
tags: [get_income_statement, date_range]
|
|
input:
|
|
prompt: "What was my income in January?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_007
|
|
difficulty: medium
|
|
tags: [get_income_statement, comparison]
|
|
input:
|
|
prompt: "How much did I save last month?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_008
|
|
difficulty: medium
|
|
tags: [get_accounts, specific]
|
|
input:
|
|
prompt: "What's the balance in my checking account?"
|
|
expected:
|
|
functions:
|
|
- name: "get_accounts"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_009
|
|
difficulty: medium
|
|
tags: [get_accounts, specific]
|
|
input:
|
|
prompt: "How much do I have in savings?"
|
|
expected:
|
|
functions:
|
|
- name: "get_accounts"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_010
|
|
difficulty: medium
|
|
tags: [get_transactions, category]
|
|
input:
|
|
prompt: "Show me all my subscription payments"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_011
|
|
difficulty: medium
|
|
tags: [get_transactions, search]
|
|
input:
|
|
prompt: "Find transactions from Uber"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_012
|
|
difficulty: medium
|
|
tags: [get_income_statement, category]
|
|
input:
|
|
prompt: "How much do I spend on entertainment?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_013
|
|
difficulty: medium
|
|
tags: [get_balance_sheet, trend]
|
|
input:
|
|
prompt: "How has my net worth changed over time?"
|
|
expected:
|
|
functions:
|
|
- name: "get_balance_sheet"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_014
|
|
difficulty: medium
|
|
tags: [get_transactions, amount]
|
|
input:
|
|
prompt: "What's my largest expense this month?"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_015
|
|
difficulty: medium
|
|
tags: [get_income_statement, breakdown]
|
|
input:
|
|
prompt: "Break down my expenses by category"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_016
|
|
difficulty: medium
|
|
tags: [get_transactions, recurring]
|
|
input:
|
|
prompt: "Show me my recurring payments"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_017
|
|
difficulty: medium
|
|
tags: [get_accounts, credit]
|
|
input:
|
|
prompt: "What's my credit card balance?"
|
|
expected:
|
|
functions:
|
|
- name: "get_accounts"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_018
|
|
difficulty: medium
|
|
tags: [get_income_statement, specific]
|
|
input:
|
|
prompt: "How much did I spend on food last month?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_019
|
|
difficulty: medium
|
|
tags: [get_transactions, date]
|
|
input:
|
|
prompt: "Show transactions from December"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_020
|
|
difficulty: medium
|
|
tags: [get_balance_sheet, liability]
|
|
input:
|
|
prompt: "What are my debts?"
|
|
expected:
|
|
functions:
|
|
- name: "get_balance_sheet"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
# ===== HARD - Analysis, comparisons, insights =====
|
|
- id: chat_hard_001
|
|
difficulty: hard
|
|
tags: [analysis, spending_trend]
|
|
input:
|
|
prompt: "Am I spending more than I make?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_002
|
|
difficulty: hard
|
|
tags: [comparison, month_over_month]
|
|
input:
|
|
prompt: "How does my spending this month compare to last month?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_003
|
|
difficulty: hard
|
|
tags: [analysis, budget]
|
|
input:
|
|
prompt: "Where can I cut expenses?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_004
|
|
difficulty: hard
|
|
tags: [analysis, savings]
|
|
input:
|
|
prompt: "What's my savings rate?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_005
|
|
difficulty: hard
|
|
tags: [analysis, trend]
|
|
input:
|
|
prompt: "Are my expenses trending up or down?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_006
|
|
difficulty: hard
|
|
tags: [analysis, category]
|
|
input:
|
|
prompt: "What category do I spend the most on?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_007
|
|
difficulty: hard
|
|
tags: [analysis, unusual]
|
|
input:
|
|
prompt: "Are there any unusual transactions this month?"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_008
|
|
difficulty: hard
|
|
tags: [analysis, debt]
|
|
input:
|
|
prompt: "How long will it take to pay off my credit card?"
|
|
expected:
|
|
functions:
|
|
- name: "get_accounts"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_009
|
|
difficulty: hard
|
|
tags: [analysis, financial_health]
|
|
input:
|
|
prompt: "What's my debt-to-income ratio?"
|
|
expected:
|
|
functions:
|
|
- name: "get_balance_sheet"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_010
|
|
difficulty: hard
|
|
tags: [analysis, goals]
|
|
input:
|
|
prompt: "Can I afford to save $500 more per month?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_011
|
|
difficulty: hard
|
|
tags: [comparison, year_over_year]
|
|
input:
|
|
prompt: "How does this year compare to last year?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_012
|
|
difficulty: hard
|
|
tags: [analysis, pattern]
|
|
input:
|
|
prompt: "Do I have any spending patterns I should know about?"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_013
|
|
difficulty: hard
|
|
tags: [advice, budget]
|
|
input:
|
|
prompt: "How should I allocate my income?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_014
|
|
difficulty: hard
|
|
tags: [analysis, efficiency]
|
|
input:
|
|
prompt: "Am I overspending on subscriptions?"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_015
|
|
difficulty: hard
|
|
tags: [forecast, projection]
|
|
input:
|
|
prompt: "At this rate, how much will I have saved by year end?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
# ===== EDGE CASES - Unclear intent, no function needed =====
|
|
- id: chat_edge_001
|
|
difficulty: edge_case
|
|
tags: [no_function, greeting]
|
|
input:
|
|
prompt: "Hello"
|
|
expected:
|
|
functions: []
|
|
response_contains: []
|
|
|
|
- id: chat_edge_002
|
|
difficulty: edge_case
|
|
tags: [no_function, thanks]
|
|
input:
|
|
prompt: "Thank you!"
|
|
expected:
|
|
functions: []
|
|
response_contains: []
|
|
|
|
- id: chat_edge_003
|
|
difficulty: edge_case
|
|
tags: [no_function, general]
|
|
input:
|
|
prompt: "What can you help me with?"
|
|
expected:
|
|
functions: []
|
|
response_contains: []
|
|
|
|
- id: chat_edge_004
|
|
difficulty: edge_case
|
|
tags: [no_function, advice]
|
|
input:
|
|
prompt: "Should I invest in stocks?"
|
|
expected:
|
|
functions: []
|
|
response_contains: []
|
|
|
|
- id: chat_edge_005
|
|
difficulty: edge_case
|
|
tags: [no_function, external]
|
|
input:
|
|
prompt: "What's the weather like?"
|
|
expected:
|
|
functions: []
|
|
response_contains: []
|
|
|
|
- id: chat_edge_006
|
|
difficulty: edge_case
|
|
tags: [ambiguous]
|
|
input:
|
|
prompt: "Tell me about my money"
|
|
expected:
|
|
functions:
|
|
- name: "get_balance_sheet"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_edge_007
|
|
difficulty: edge_case
|
|
tags: [ambiguous]
|
|
input:
|
|
prompt: "How am I doing financially?"
|
|
expected:
|
|
functions:
|
|
- name: "get_balance_sheet"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_edge_008
|
|
difficulty: edge_case
|
|
tags: [ambiguous]
|
|
input:
|
|
prompt: "Give me a summary"
|
|
expected:
|
|
functions:
|
|
- name: "get_balance_sheet"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_edge_009
|
|
difficulty: edge_case
|
|
tags: [no_function, off_topic]
|
|
input:
|
|
prompt: "What's 2 + 2?"
|
|
expected:
|
|
functions: []
|
|
response_contains: []
|
|
|
|
- id: chat_edge_010
|
|
difficulty: edge_case
|
|
tags: [no_function, general]
|
|
input:
|
|
prompt: "Who are you?"
|
|
expected:
|
|
functions: []
|
|
response_contains: []
|
|
|
|
# Additional samples
|
|
- id: chat_easy_016
|
|
difficulty: easy
|
|
tags: [get_transactions]
|
|
input:
|
|
prompt: "Pull up my transactions"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_017
|
|
difficulty: easy
|
|
tags: [get_accounts]
|
|
input:
|
|
prompt: "Show all my bank accounts"
|
|
expected:
|
|
functions:
|
|
- name: "get_accounts"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_018
|
|
difficulty: easy
|
|
tags: [get_balance_sheet]
|
|
input:
|
|
prompt: "What do I own?"
|
|
expected:
|
|
functions:
|
|
- name: "get_balance_sheet"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_019
|
|
difficulty: easy
|
|
tags: [get_income_statement]
|
|
input:
|
|
prompt: "What's my income?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_easy_020
|
|
difficulty: easy
|
|
tags: [get_transactions]
|
|
input:
|
|
prompt: "Recent purchases"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_021
|
|
difficulty: medium
|
|
tags: [get_transactions, merchant]
|
|
input:
|
|
prompt: "How much have I spent at Starbucks?"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_022
|
|
difficulty: medium
|
|
tags: [get_transactions, category]
|
|
input:
|
|
prompt: "Show transportation expenses"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_023
|
|
difficulty: medium
|
|
tags: [get_income_statement, period]
|
|
input:
|
|
prompt: "Quarterly expense report"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_024
|
|
difficulty: medium
|
|
tags: [get_accounts, type]
|
|
input:
|
|
prompt: "Show my investment accounts"
|
|
expected:
|
|
functions:
|
|
- name: "get_accounts"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_medium_025
|
|
difficulty: medium
|
|
tags: [get_transactions, amount]
|
|
input:
|
|
prompt: "Transactions under $50"
|
|
expected:
|
|
functions:
|
|
- name: "get_transactions"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_016
|
|
difficulty: hard
|
|
tags: [analysis, discretionary]
|
|
input:
|
|
prompt: "How much discretionary spending do I have?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_017
|
|
difficulty: hard
|
|
tags: [analysis, fixed_vs_variable]
|
|
input:
|
|
prompt: "What are my fixed vs variable expenses?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_018
|
|
difficulty: hard
|
|
tags: [analysis, emergency_fund]
|
|
input:
|
|
prompt: "Do I have enough for an emergency fund?"
|
|
expected:
|
|
functions:
|
|
- name: "get_balance_sheet"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_019
|
|
difficulty: hard
|
|
tags: [analysis, liquidity]
|
|
input:
|
|
prompt: "How liquid are my assets?"
|
|
expected:
|
|
functions:
|
|
- name: "get_accounts"
|
|
params: {}
|
|
response_contains: []
|
|
|
|
- id: chat_hard_020
|
|
difficulty: hard
|
|
tags: [comparison, benchmark]
|
|
input:
|
|
prompt: "Am I spending too much on housing?"
|
|
expected:
|
|
functions:
|
|
- name: "get_income_statement"
|
|
params: {}
|
|
response_contains: []
|