在無法回答時要說出來

閱讀約需 90 分鐘 分鐘,7 節 中共有 5 個範例。

版次 2026.11.15 範例於 2026年11 月 19 通過測試 78 個範例中有 78 個通過 變更內容

由 AI 翻譯。經人工以英文驗證。 我們如何製作書籍

譯自英文書,版次 2026.11.15。 閱讀原文

讀完本章,你可以把拒答當成一種正式的回答:區分倉儲能回答與不能回答的問題,以已知類型的理由拒答,檢查所問期間的資料是否已經到齊,為每個答案呈現其出處,並用精確率與召回率衡量拒答,使代理既不亂猜,也不過度拒絕。

商店的資料止於 2026 年 6 月的最後一天,而它的代理必須知道自己何時無法回答。第 6 章建立了一個代理:模型選擇指標、維度與篩選條件,再由語意層撰寫 SQL。在黃金問題的開發集上,該代理答對了大部分可回答的問題,其中兩個失敗案例正是本章的主題。對於「哪個地區表現最好?」,它回傳了各地區的歷史總營收,由小到大排列,為一個沒有單一答案的問題給出了一個數字。對於下一季的淨營收,它反問對方指的是曆年季度還是會計季度,彷彿這兩種解讀都能從那份資料中得到答案。

這兩個失敗看起來都像是答案,而來自倉儲的錯誤數字比沒有數字更糟,因為它會被貼進簡報裡。文字轉 SQL 的研究也指出同樣的問題:無法回答的問題可能產生能執行、卻給出誤導結果的 SQL(Ren et al.)。本章讓代理有說不的方法,並提供衡量方式,用來區分良好的拒答與不願工作的拒絕。本章建立在第 6 章以指標為先的代理之上,而不是第 7 章受防護的 SQL 路徑,因此沒有任何指標涵蓋的問題在這裡仍會被拒答,而衡量時會把每一次這類拒答都計為成本。

此部分尚未翻譯,因此以英文呈現。

Kinds of questions the warehouse can't answer

最近一次變動於第 2026.11.15 版

A question that shouldn't get a single number is one of two kinds, and they need different replies. An ambiguous question has several valid answers: the words fit more than one metric, period or filter, and the right reply is a question back to the person or a stated assumption. An unanswerable question has no valid answer in the warehouse: the data doesn't hold what it needs, or it asks for something SQL can't do, such as a forecast.

The research gives both kinds names you can use. PRACTIQ, a conversational text-to-SQL dataset, sorts them into four ambiguous categories, such as an ambiguous SELECT column, where several valid SQLs differ in the columns they select, and four unanswerable ones, such as a nonexistent SELECT column, where "The column that contains the results asked in the question do not exist in the database" (Dong et al.). TrustSQL adds questions that fail because the schema is incompatible or because they need something SQL can't do (Lee et al.). Knowing the schema doesn't remove the ambiguity: AMBROSIA's authors found that the ambiguity persists even when the database context is provided (Saparina and Lapata).

We can audit each golden decline against the warehouse before trusting its label. The shop's golden questions, from chapter 3, include eight whose right answer is a decline, four in each split, and each carries a decline_type: two ambiguous and two unanswerable per split. The audit prints each one with its category in PRACTIQ's terms, or TrustSQL's for the forecast, and searches both schemas for a column whose name matches the words the question needs. Then it answers two ambiguous questions in each of their readings, from the semantic layer. One of the ambiguous questions has no reading to answer: "Who are our best customers?", gq-019, is ambiguous in PRACTIQ's terms, but no metric or dimension ranks customers, so its right reply is a decline, not a question back.

unanswerable-cases.py Python 3.12.15 · duckdb 2.0.0 · pyyaml 6.0.3 · sqlglot 30.31.0 通過
"""The golden questions whose right answer is a decline: which are ambiguous, which are unanswerable, and why.The point that unanswerable questions have nothing to compute from rests on the "columns matching" lines, and the pointthat ambiguous ones have too many answers rests on the "best region" and "net revenue" lines."""from lib.golden import load_goldenfrom lib.semantic import MetricRequest, loadfrom lib.warehouse import connectcon, layer = connect(), load()# Each decline question's category: PRACTIQ's names, and TrustSQL's for the forecast. Words to look for in the schema.CATEGORIES = {"gq-005": ("beyond SQL: a forecast", "forecast|predict"), "gq-019": ("ambiguous SELECT column", None),              "gq-020": ("ambiguous SELECT column", None), "gq-021": ("nonexistent SELECT column", "ship"),              "gq-042": ("ambiguous filter criteria", None), "gq-043": ("ambiguous values within a column", None),              "gq-044": ("unsupported join", "view|page"), "gq-045": ("nonexistent WHERE column", "deliver|promise")}for q in load_golden():    if q.kind == "decline":        category, words = CATEGORIES[q.question_id]        print(f"{q.question_id} ({q.split}, {q.decline_type}): {category}")        if words:            # raw and analytics are the only schemas with data; the layer reads from both            found = con.execute("""SELECT string_agg(table_name || '.' || column_name, ', ') FROM information_schema.columns                                   WHERE table_schema IN ('raw', 'analytics') AND regexp_matches(column_name, ?)""",                                [words]).fetchall()[0][0]            print(f"  columns matching {words!r}: {found or 'none'}")# the match is on the name: a column named for cost is the product's unit cost, which is not the shipping the question asks forcost = con.execute("""SELECT string_agg(table_name || '.' || column_name, ', ') FROM information_schema.columns                      WHERE table_schema IN ('raw', 'analytics') AND regexp_matches(column_name, 'cost')""").fetchall()print(f"columns named for cost: {cost[0][0] or 'none'}")reasons = [r for (r,) in con.execute("SELECT DISTINCT reason FROM analytics.fct_refunds ORDER BY 1").fetchall()]print(f"refund reasons: {', '.join(reasons)}")print(f"last order day: {con.execute('SELECT max(order_date_local) FROM analytics.fct_orders').fetchall()[0][0]}")# "Which region is doing best?" in fiscal 2026, by three metrics the layer defines.fiscal_2026 = {"metric_time__fiscal_year": 2026}for metric, order in (("net_revenue", "-net_revenue"), ("orders", "-orders"), ("refund_rate", "refund_rate")):    # a leading minus sorts descending, so net revenue and orders put the largest first; refund_rate sorts ascending,    # so its first row is the lowest rate; the limit of 1 keeps that one row    answer = layer.query(con, MetricRequest((metric,), ("order__region",), fiscal_2026, (order,), 1))    print(f"best region by {order.lstrip('-')}{' (lowest)' if order == metric else ''}: {answer.rows[0][0]}")# Q2 read as a calendar quarter and as a fiscal quarter: calendar Q2 starts on April 1, fiscal Q2 2026 runs May to July.for name, value in (("metric_time__quarter", "2025-04-01"), ("metric_time__fiscal_quarter", "2026-Q2")):    # one row with one column, so the unpacking gives the revenue total for the period    (revenue,), = layer.query(con, MetricRequest(("net_revenue",), (), {name: value})).rows    print(f"net revenue, {name.removeprefix('metric_time__')} {value}: {revenue:,.2f}")
輸出python unanswerable-cases.py
gq-005 (dev, unanswerable): beyond SQL: a forecast
  columns matching 'forecast|predict': none
gq-019 (dev, ambiguous): ambiguous SELECT column
gq-020 (dev, ambiguous): ambiguous SELECT column
gq-021 (dev, unanswerable): nonexistent SELECT column
  columns matching 'ship': none
gq-042 (test, ambiguous): ambiguous filter criteria
gq-043 (test, ambiguous): ambiguous values within a column
gq-044 (test, unanswerable): unsupported join
  columns matching 'view|page': none
gq-045 (test, unanswerable): nonexistent WHERE column
  columns matching 'deliver|promise': none
columns named for cost: dim_products.unit_cost, products.unit_cost
refund reasons: changed_mind, damaged, late_delivery, other, wrong_size
last order day: 2026-06-30
best region by net_revenue: EMEA
best region by orders: EMEA
best region by refund_rate (lowest): APAC
net revenue, quarter 2025-04-01: 415,495.84
net revenue, fiscal_quarter 2026-Q2: 467,081.90

No column in raw or analytics is named for shipping, product views, delivery promises or forecasts, and the last order day is 2026-06-30. So the four unanswerable questions have nothing to compute from, but each has something nearby that a model could reach for. The products table has unit_cost (dim_products.unit_cost, products.unit_cost), which is the product's cost, not shipping. The refunds table has a reason called late_delivery, which counts refunds, not late deliveries. A model that trusts the question's premise will write runnable SQL against those columns: PremiseSQL's authors found that models "are strongly premise-trusting by default and rarely critique flawed premises" (Lin et al.).

The ambiguous questions have answers, too many of them. For "Which region is doing best?" in fiscal 2026, the layer names EMEA by net revenue and by orders, and APAC by the lowest refund rate. For revenue in Q2 of 2025, it gives 415,495.84 euros of net revenue for the calendar quarter, and 467,081.90 for the fiscal one, which runs from May to July. Each of those numbers is right for one reading and wrong for the others, and nothing in the result says which reading produced it.

A third kind looks unanswerable and isn't: a nonexistent filter value, in PRACTIQ's terms, is a filter value no row holds, such as a region called Europe. In the shop, chapter 6's validation refuses it and names the regions that exist, so the model can correct its request instead of declining.

Working rule: Sort every question your golden set marks as a decline into ambiguous or unanswerable, and name its category, so you know which reply it needs. Ask back on an ambiguous question only when every reading is answerable, and decline an unanswerable one with what's missing. For each unanswerable question, find the column or value nearby that a model could mistake for the answer, because that's the wrong number you're guarding against.

此部分尚未翻譯,因此以英文呈現。

Decline with a reason

最近一次變動於第 2026.11.15 版

The two kinds of question need a reply that isn't a number, and a reply the code can read. A decline is an answer: it ends the run, it says why, and the person can act on it. The reason has two parts. One is a sentence for the person, naming what's missing. A decline's kind, the reason's other part, comes from a fixed list, for the code, so declines can be counted, routed and scored by kind instead of read one at a time. In chapter 6, the forecast's question back about the calendar or the fiscal quarter scored as correct because it returned no number, and only its trace showed that the reason was wrong.

This chapter's agent, which we call the declining agent, lives in lib/declining.py, a module this chapter adds. Its DecliningToolbox keeps chapter 6's five metric tools and changes what two of them do. cannot_answer takes a kind as well as a reason, and refuses a kind outside the list. query_metric runs two checks in code before it answers: chapter 6's ranking check, which refuses a request that ranks its result over no period, and the freshness check that the section on freshness builds. The prompt, DECLINING in lib/prompts.py, differs from chapter 6's in three places. It lists the kinds the model may give; it allows ask_back only when every option is a request the metrics can answer, chapter 6's working rule; and it states what a wrong number costs, in the form Kalai and colleagues propose: "Answer only if you are >t confident, since mistakes are penalized t/(1-t) points" (Kalai et al.). With t at 0.75, the formula makes a wrong number cost 0.75/0.25 = 3 points and a decline 0.

The recording decline-runs holds the pinned model's replies to that prompt for the dev split's answer and decline questions, 21 of them. It was made by recordings/record_decline_runs.py with the same model file, sampling and seed as every recording in this book, and at most four model calls a run, as in chapter 6. The three forbidden questions on dev aren't recorded, because their decline belongs below the model, in chapter 9. We chose the prompt's changes by reading chapter 6's dev traces, so the dev split informed them. We recorded the dev split once, after writing the prompt, and changed nothing afterwards. The recording's manifest says so in its tuning field, and every replay checks it in part: a reply is found by a hash of the messages that produced it, prompt included, so a changed prompt finds no reply.

A kind helps only when the agent picks it, so we print the kinds and who decides each, send cannot_answer a call without one, and replay the four dev decline questions and one answerable question the agent declined.

cannot-answer-tool.py Python 3.12.15 · duckdb 2.0.0 · pyyaml 6.0.3 · sqlglot 30.31.0 通過
"""Decline with a kind from a fixed list and a reason, so declines can be checked and counted like answers.The prose's point about "Which region is doing best?" rests on the gq-020 request and the ranking check's reply to it."""from lib.agent import run_agentfrom lib.declining import DECLINE_KINDS, MODEL_KINDS, DecliningToolbox, decline_kindfrom lib.golden import load_goldenfrom lib.metric_tools import catalogfrom lib.model import RecordedModelfrom lib.prompts import declining_promptfrom lib.warehouse import connectcon = connect()toolbox = DecliningToolbox(con)for kind, meaning in DECLINE_KINDS.items():    print(f"{kind}{' (model)' if kind in MODEL_KINDS else ' (code)'}: {meaning}")# without a kind the call is refused, and the error lists the kinds the model may giveprint(toolbox.call("cannot_answer", {"reason": "no shipping costs"}).content)print(toolbox.call("cannot_answer", {"kind": "not_in_data", "reason": "no shipping costs"}).answer.show())system, model = declining_prompt(catalog(toolbox.layer)), RecordedModel("decline-runs")for q in load_golden():    # gq-016 is answerable; it is replayed too, to show the agent declining it    if q.split == "dev" and q.kind == "decline" or q.question_id == "gq-016":        trace = run_agent(q.question, system, model, DecliningToolbox(con, toolbox.layer, role=q.role), max_steps=4)        calls = [step for step in trace.steps if step.kind == "model"]        print(f"{q.question_id} ({q.decline_type or q.kind}): {q.question}")        print(f"{q.question_id} ended with: {calls[-1].tool}, kind {decline_kind(trace.answer)}")        print(f"{q.question_id} model calls: {len(calls)}")        label = "asks" if trace.answer.provenance.source == "ask_back" else "reason"        print(f"  {label}: {trace.answer.reason.splitlines()[0]}")        if q.question_id == "gq-021":            # the first model call is the reply that lacked the tool's name, which the loop answered with an error            print(f"  first reply: {calls[0].content}")        if q.question_id == "gq-020":            asked = next(i for i, step in enumerate(trace.steps) if step.tool == "query_metric")            request = trace.steps[asked].arguments            print(f"gq-020 request: {', '.join(request['metrics'])} by {', '.join(request['group_by'])}, ordered by "                  f"{', '.join(request['order_by'])}, period: {request.get('filters') or 'none'}")            # the step right after the request is the ranking check's refusal of it, so the offset of one is the reply            print(f"gq-020 check: {trace.steps[asked + 1].content}")            # the options sit in the arguments of the ask_back call, the step before the run's last step            print(f"gq-020 options: {', '.join(trace.steps[-2].arguments['options'])}")
輸出python cannot-answer-tool.py
not_in_data (model): no metric or dimension holds what the question needs
forecast (model): the question asks about a period that hasn't happened, or for a prediction
no_definition (model): the question uses a term the shop hasn't defined, and no metric settles it
stale (code): the data for the period hasn't all arrived: not loaded yet, or not happened yet
forbidden (code): the role asking may not see the answer (chapter 9)
error: kind must be one of not_in_data, forecast, no_definition; got ''
cannot answer: not_in_data: no shipping costs
gq-005 (unanswerable): What will our net revenue be next quarter?
gq-005 ended with: cannot_answer, kind forecast
gq-005 model calls: 1
  reason: forecast: The question asks about a future period that hasn't happened yet, and no data is available for forecasting.
gq-016 (answer): How many customers placed at least one order in 2025?
gq-016 ended with: cannot_answer, kind not_in_data
gq-016 model calls: 2
  reason: not_in_data: The metric 'new_customers' cannot use 'order__order_date' as a filter, and no alternative metric or dimension is available to answer the question about customers placing at least one order in 2025.
gq-019 (ambiguous): Who are our best customers?
gq-019 ended with: cannot_answer, kind no_definition
gq-019 model calls: 1
  reason: no_definition: The term 'best' is not defined in the available metrics or dimensions, and no metric or dimension can determine customer performance based on this vague criterion.
gq-020 (ambiguous): Which region is doing best?
gq-020 ended with: ask_back, kind None
gq-020 model calls: 3
  asks: Which time period are you interested in? For example, the most recent month, the last quarter, or a specific year?
gq-020 request: net_revenue by customer__region, ordered by net_revenue, period: none
gq-020 check: error: request rejected: the request ranks its result but names no period; filter or group by a metric_time grain; or ask the person which period they mean
gq-020 options: last month, last quarter, 2026
gq-021 (unanswerable): How much did shipping cost us in fiscal year 2026?
gq-021 ended with: cannot_answer, kind not_in_data
gq-021 model calls: 2
  reason: not_in_data: The shop's data does not include a metric for shipping costs.
  first reply: {"kind": "not_in_data", "reason": "The shop's data does not include a metric for shipping costs."}

The model may give three kinds: not_in_data, forecast and no_definition. Code gives the other two: stale, when the data for the period hasn't arrived, and forbidden, which chapter 9's access rules will give. A call without a kind comes back as an error that lists the allowed kinds, so the model can correct it in its next call.

In the declining agent's run, the forecast, gq-005, ends in a decline of kind forecast, in 1 model call. "Who are our best customers?", gq-019, is declined with kind no_definition, which is the honest reply chapter 6 said was due: the shop's metrics don't rank customers, so no option could have been answered. The shipping question, gq-021, took 2 calls. The model's first reply was the decline's arguments without the tool's name, the loop sent back an error, and the second reply declined with kind not_in_data.

"Which region is doing best?", gq-020, is the one to read closely. The model asked for net revenue by region, ordered, with no period (net_revenue by customer__region, ordered by net_revenue, period: none), the request chapter 6's agent ran. The ranking check refused it because it ranks its result but names no period, and the model then asked back which period the person meant, offering last month, last quarter, 2026. That counts as a correct reply, and it settles half the question. A period doesn't say what "best" means, and the readings give different regions.

The last question, gq-016, asks how many customers placed at least one order in 2025. The warehouse can answer it, but no metric in the layer counts customers who ordered, and chapter 6's agent answered it with the count of new customers, a wrong number. The declining agent declined it as not_in_data, which is honest about the layer, and gave a reason about a filter the metric can't use, which is beside the point.

Working rule: Make declining a tool that ends the run with a kind from a fixed list and a sentence for the person. Let the model choose among the kinds it can judge, such as missing data, a forecast or an undefined term, and let code decide the kinds code can check, such as stale data or a forbidden role. Count declines by kind, and read the reasons in traces, because a decline of the right kind can still give the wrong reason.

此部分尚未翻譯,因此以英文呈現。

Check freshness before answering

最近一次變動於第 2026.11.15 版

A decline the model chooses covers questions the data can't answer at all. A subtler case is data that can answer the question but hasn't all arrived. A partial total looks complete: the SQL runs, the number has the right shape, and it's too small. Freshness is how far a source's events have arrived, read from when its rows were loaded. dbt's source freshness check works that way: it reads the newest load time from a loaded_at_field, or from a loaded_at_query, which is "A SQL expression that returns the most recent loaded timestamp", and compares it with thresholds such as warn_after, the age the newest data can reach before a warning (dbt). dbt can also read the warehouse's own metadata when you give it neither; we don't, for the reason below.

Freshness has to come from the data, not from the warehouse's table metadata. Snowflake's LAST_ALTERED records the "Date and time the object was last altered by a DML, DDL, or background metadata operation" (Snowflake), so maintenance moves it too. DuckDB's table catalog, duckdb_tables(), has no time column at all (duckdb_tables() time columns: none).

The shop's generator gives every raw table a _loaded_at column, the time the nightly load brought the row in, at 02:00 UTC the day after the event, and the marts carry it through. Its refunds feed stopped after June 26, 2026, while orders run to June 30. Some metrics keep changing after their period ends. The refund rate, refund_rate, divides refunded euros by the gross revenue of the same orders, and counts each refund on its order's day. A refund comes weeks after its order, so a month's rate keeps rising until every refund on its orders has come. A metric's settling window, as we call it, is the time until every event it counts for a period has come. The freshness check in lib/declining.py compares each feed's newest load with the end of the period a request filters on, plus the settling window of the metrics that read the feed. FEEDS names, for each table a metric reads, the feed whose loads decide its freshness, and SETTLING_DAYS gives the window of each metric counted on an earlier date than its events; every other metric's is zero. Loads are in UTC and the shop's days are local, so the period ends when its last local day ends in the region furthest behind UTC. We measure the window from the data, run the check with it, and estimate why May and June fall short.

stale-refunds.py Python 3.12.15 · duckdb 2.0.0 · pyyaml 6.0.3 · sqlglot 30.31.0 通過
"""Check freshness before answering: refunds stopped loading after June 26, 2026, and arrive weeks after the order.The prose's point rests on the unchecked June rate, the shortfall lines that split June's gap, and the 'stale' decline."""from datetime import datefrom lib.declining import (FEEDS, SETTLING_DAYS, DecliningToolbox, check_freshness, refund_delays, refund_shortfall,                           settled_refund_rate)from lib.semantic import MetricRequest, loadfrom lib.warehouse import connect, data_as_ofcon, layer = connect(), load()# the catalog's column types, filtered for any type containing TIME: DuckDB's catalog has none, so the list is emptycatalog = [c for (c, t, *_) in con.execute("DESCRIBE SELECT * FROM duckdb_tables()").fetchall() if "TIME" in t]print(f"duckdb_tables() time columns: {', '.join(catalog) or 'none'}")for table in ("analytics.fct_orders", "analytics.fct_refunds", "analytics.dim_customers"):    print(f"data as of, {table}: {data_as_of(con, table)}")delays = refund_delays(con)                # the longest delay on settled orders is what SETTLING_DAYS usesprint(f"refunds per day: {delays['per day']:.1f}\nmedian days from order to refund: {delays['median']}\n"      f"refunds within 30 days of the order: {delays['within 30']:.0%}\n"      f"refunds within 45 days of the order: {delays['within 45']:.0%}\n"      f"longest days from order to refund: {delays['longest']}\n"      f"settling window, order_refunds: {SETTLING_DAYS['order_refunds']} days")for month in ("2026-04", "2026-05", "2026-06"):           # without a check, the layer answers for any month    (rate,), = layer.query(con, MetricRequest(("refund_rate",), (), {"metric_time__month": month})).rows    print(f"refund rate, {month}, unchecked: {rate:.2%}")# Why May and June are short, estimated from the twelve months whose refunds have all come.print(f"refund rate, settled months: {settled_refund_rate(con):.2%}")for month, end in (("2026-05", date(2026, 6, 1)), ("2026-06", date(2026, 7, 1))):    # refund_shortfall takes the first day after the month, so the month's events are all before it    short = refund_shortfall(con, end)    print(f"{month}, settled months' rate with refunds as loaded: {short['as loaded']:.2%}\n"          f"{month}, points short, refunds not loaded: {short['not loaded'] * 100:.2f}\n"          f"{month}, points short, refunds not happened yet: {short['not happened'] * 100:.2f}\n"          f"{month}, share of the shortfall not loaded: {short['share not loaded']:.0%}")print(f"new customers, feed for dim_customers: {FEEDS['analytics.dim_customers']}")  # customers load at sign-upfor name, metric in (("refund rate", "refund_rate"), ("new customers", "new_customers")):    for check in check_freshness(con, layer, MetricRequest((metric,), (), {"metric_time__month": "2026-06"})):        print(f"{name}, 2026-06: {check.describe()}")for month in ("2026-06", "2026-05", "2026-04"):    query = {"metrics": ["refund_rate"], "filters": {"metric_time__month": month}}    # r keeps the tool's result, so a declined call can print its reason in place of a number    a = (r := DecliningToolbox(con, layer).call("query_metric", query)).answer    print(f"refund rate, {month}, checked: "          + (f"{a.rows[0][0]:.2%}, data as of {a.provenance.data_as_of}" if a.answered else r.content))
輸出python stale-refunds.py
duckdb_tables() time columns: none
data as of, analytics.fct_orders: 2026-07-02 02:00:00
data as of, analytics.fct_refunds: 2026-06-27 02:00:00
data as of, analytics.dim_customers: 2026-06-15 02:00:00
refunds per day: 1.2
median days from order to refund: 27.5
refunds within 30 days of the order: 56%
refunds within 45 days of the order: 93%
longest days from order to refund: 49
settling window, order_refunds: 49 days
refund rate, 2026-04, unchecked: 6.74%
refund rate, 2026-05, unchecked: 6.85%
refund rate, 2026-06, unchecked: 0.54%
refund rate, settled months: 7.21%
2026-05, settled months' rate with refunds as loaded: 5.78%
2026-05, points short, refunds not loaded: 0.48
2026-05, points short, refunds not happened yet: 0.95
2026-05, share of the shortfall not loaded: 33%
2026-06, settled months' rate with refunds as loaded: 1.17%
2026-06, points short, refunds not loaded: 0.46
2026-06, points short, refunds not happened yet: 5.57
2026-06, share of the shortfall not loaded: 8%
new customers, feed for dim_customers: analytics.fct_orders
refund rate, 2026-06: analytics.fct_orders last loaded 2026-07-02 02:00, period ends 2026-06-30: complete
refund rate, 2026-06: analytics.fct_refunds last loaded 2026-06-27 02:00, period ends 2026-06-30, its rows can arrive through 2026-08-18 (49 days later): STALE (not loaded, not happened yet)
new customers, 2026-06: analytics.fct_orders last loaded 2026-07-02 02:00, period ends 2026-06-30: complete
refund rate, 2026-06, checked: declined: stale: analytics.fct_refunds was last loaded at 2026-06-27 02:00, and rows for the period ending 2026-06-30 can arrive through 2026-08-18, 49 days later (not loaded, not happened yet), so the answer would be missing rows
refund rate, 2026-05, checked: declined: stale: analytics.fct_refunds was last loaded at 2026-06-27 02:00, and rows for the period ending 2026-05-31 can arrive through 2026-07-19, 49 days later (not loaded, not happened yet), so the answer would be missing rows
refund rate, 2026-04, checked: 6.74%, data as of 2026-06-27 02:00:00

On orders placed before March 2026, old enough for all their refunds to have come, 56% of refunds came within 30 days of the order and 93% within 45, and the longest took 49 days. So the refund rate's window is 49 days, the longest delay the shop has seen.

Without a check, the layer reports June's refund rate as 0.54%, against 6.85% for May, which looks normal. June's fall has two causes: some of June's refunds were made but never loaded, and most haven't been made yet. The twelve settled months, May 2025 to April 2026, estimate each. Their refund rate is 7.21%, and with each month's refunds counted only to the point the refunds feed's last load reaches for June, they give 1.17%.

Most of June's shortfall is refunds not yet made: the stale feed explains only 8% of it. May is short too, for the same two reasons, and the stale feed explains 33% of its shortfall. These are estimates from other months, not measurements.

The check finds June's orders complete and its refunds short for both causes, and the tool declines May and June with kind stale and a reason that names the feed, its last load and the last day the period's refunds can come. The model never sees a number to report. April's window ended before the refunds' last load, so its rate is answered, with the refunds' load time in its provenance.

The naive version of the check misfires. The customers table was last loaded at 2026-06-15 02:00:00, because a customer's row loads when they sign up, and nobody signed up after mid-June. Checked against its own loads, June's new customers would be declined. But a customer's first order date comes from the orders, so FEEDS maps the customers table to the orders feed, and June's new customers pass. Which feed decides a table's freshness is a fact about your pipeline, and it belongs in a mapping a person writes, as dbt sources declare their own loaded_at_field.

We decline a period that hasn't settled rather than answer with a warning, as a rule of thumb. A warning travels with the answer only until someone copies the number. A decline that names the last load and the last day the period's events can come lets the person ask for a period that has settled.

Working rule: Check freshness in code before every answer that names a period: compare the newest load of each feed the answer reads with the end of the period plus the metric's settling window, and decline as stale when the feed stops short, whether its rows haven't loaded or haven't happened. Measure each window from your own data, as the delay that covers the events you've seen. Read load times from your own load columns or a load log, never from table metadata, and map each table to the feed that decides its freshness. Answer a question with no period, and show its data as of in the provenance.

此部分尚未翻譯,因此以英文呈現。

Show the provenance with every answer

最近一次變動於第 2026.11.12 版

A decline tells the person why there's no number. An answer owes them the same: where the number came from. An answer's provenance is the metric or SQL behind it, the filters, the role it was computed for and how fresh the data was. The shop's Answer has carried answer.provenance since chapter 1. This section is about showing it. We found no study that measures whether showing provenance makes people catch more wrong numbers, so this is our design choice, not a measured effect. The reasoning is that a person checks a metric's definition in seconds, and a query in minutes.

provenance_card() in lib/declining.py prints an answer with its provenance: the result, each metric's name and the definition its owner wrote in the semantic layer, the filters, the role, the data as of, the freshness check for each feed and, optionally, the SQL. A decline's card is its kind, its reason and the role. Three of the declining agent's runs, replayed with their cards, show what a card catches: net revenue by region in March 2026, which it got right; total revenue by sales region in 2025, which it got wrong; and the cost of shipping, which it declined.

answer-with-provenance.py Python 3.12.15 · duckdb 2.0.0 · pyyaml 6.0.3 · sqlglot 30.31.0 通過
"""Show the provenance with every answer: the metric's definition, filters, role, freshness and the SQL that ran.The prose's point rests on the first card's SQL and the second card's definition line, which names the tax."""from lib.agent import run_agentfrom lib.declining import DecliningToolbox, provenance_cardfrom lib.golden import golden_result, grade, load_goldenfrom lib.metric_tools import catalogfrom lib.model import RecordedModelfrom lib.prompts import declining_promptfrom lib.semantic import loadfrom lib.warehouse import connectcon, layer = connect(), load()system, model = declining_prompt(catalog(layer)), RecordedModel("decline-runs")golden = {q.question_id: q for q in load_golden()}# one right answer, one near-miss metric, one declinefor question_id in ("gq-002", "gq-012", "gq-021"):    q = golden[question_id]    toolbox = DecliningToolbox(con, layer, role=q.role)    trace = run_agent(q.question, system, model, toolbox, max_steps=4)    print(f"{question_id}: {q.question}")    # only the first card shows its SQL, which the prose walks through    print(provenance_card(trace.answer, layer, toolbox.freshness, sql=question_id == "gq-002"))    print(f"{question_id} outcome: {grade(q, trace.answer, golden_result(con, q))}")    print()
輸出python answer-with-provenance.py
gq-002: What was net revenue in each region in March 2026?
order__region  net_revenue
AMER           51,762.14
APAC           35,296.93
EMEA           63,023.76
metric: net_revenue: Revenue in EUR after discounts and before tax, from real orders that weren't cancelled, counted on the order's local business day. Returned orders count; refunds are not subtracted.
filters: {'metric_time__month': '2026-03'}
role: analyst
data as of: 2026-07-02 02:00:00
freshness: analytics.fct_orders last loaded 2026-07-02 02:00, period ends 2026-03-31: complete
sql:
SELECT
  orders.region AS order__region,
  SUM(orders.net_revenue_eur) AS net_revenue
FROM analytics.fct_orders AS orders
WHERE
  orders.status <> 'cancelled'
  AND CAST(DATE_TRUNC('MONTH', CAST(orders.order_date_local AS DATE)) AS DATE) = CAST('2026-03-01' AS DATE)
GROUP BY
  orders.region
ORDER BY
  order__region ASC
gq-002 outcome: correct

gq-012: What was total revenue for each sales region in 2025?
order__region  gross_revenue
AMER           538,429.66
APAC           444,472.81
EMEA           897,698.19
metric: gross_revenue: Revenue in EUR including tax, before refunds, from real orders that weren't cancelled.
filters: {'metric_time__year': 2025}
role: analyst
data as of: 2026-07-02 02:00:00
freshness: analytics.fct_orders last loaded 2026-07-02 02:00, period ends 2025-12-31: complete
gq-012 outcome: wrong

gq-021: How much did shipping cost us in fiscal year 2026?
declined: not_in_data: The shop's data does not include a metric for shipping costs.
role: finance
gq-021 outcome: correct

The first card, gq-002, is the answer with everything behind it. Net revenue's definition says what the number includes, the filter says March 2026, the freshness line says the orders feed was complete for that period, and the SQL shows the cancelled orders left out. Its outcome is correct.

The second card, gq-012, is why the card exists. The question asks for total revenue, and the shop's finance team means net revenue by it. The agent chose gross_revenue, and the card's definition line says "Revenue in EUR including tax". A person who reads only the numbers sees three plausible regional totals. A person who reads the first line under them sees that tax is included and asks again. The outcome is wrong, and the card made the mistake visible without the SQL.

The third card is a decline with its kind and its reason, not_in_data, and the role it was computed for, finance. A decline needs no SQL, but it needs the role: when chapter 9 adds access rules, the same question can be answered for one role and declined for another.

Working rule: Show every answer with its provenance, and put the metric's name and definition first, since that's where a near-miss metric shows. Then show the filters, the period, the role and the data as of, and keep the SQL one step away for the people who check it. Show declines the same way, with their kind, reason and role.

此部分尚未翻譯,因此以英文呈現。

Measure declines, not only accuracy

最近一次變動於第 2026.11.15 版

Declines, the freshness check and provenance change how the agent fails, and a score has to show which way. Accuracy doesn't. It counts a decline on an answerable question as a miss, the same as a wrong number, so an agent that guesses scores no worse than one that declines. Kalai and colleagues argue that grading this way rewards guessing (Kalai et al.). Two pairs of measures separate the cases, and one score weighs them.

Decline precision and recall treat a question whose right answer is a decline as a positive, and a run that ended without a number, by a decline or a question back, as a predicted positive. Decline precision asks how many of the agent's declines were due; decline recall asks how many of the due declines the agent made. Coverage and selective risk come from selective prediction. Coverage is the share of questions the system doesn't reject, and selective risk is the error rate on the questions the system answers (Geifman and El-Yaniv). Lowering the bar for answering raises coverage and usually risk. TrustSQL's penalty score weighs them. In the penalty score, each question scores one point for a right answer or a right decline, nothing for declining an answerable question, and minus c for a wrong number, including an answer to a question it should have declined; the score is the mean over the questions (Lee et al.). TrustSQL's questions to decline are unanswerable ones only, and it leaves resolving ambiguity out of its scope. We score the ambiguous questions too, as questions to decline, and count a question back on one as a right decline, so our score is TrustSQL's adapted to the shop's golden set. With c at 0 it is the share of correct replies, as accuracy is; with c large, one wrong number cancels many right ones. As formulas, where a wrong number includes any number given for a question that should be declined:

decline precision = correct declines / all declines
decline recall    = correct declines / questions whose right answer is a decline
coverage          = questions answered with a number / questions asked
selective risk    = wrong numbers / questions answered with a number
penalty score     = (right answers + correct declines − c × wrong numbers) / questions asked

A run that hit the step limit is neither a decline nor an answer: it adds nothing to the score and counts as unanswered for coverage. Tally in lib/declining.py computes all five. We run chapter 6's metrics-first agent and the declining agent on the same 21 dev questions, 17 answerable and 4 to decline, so the measures compare like with like, and print each one with c at 3, the cost the prompt states, and at 10, a value TrustSQL uses. Choosing c is a judgement about what a wrong number costs, not a measurement.

decline-precision-recall.py Python 3.12.15 · duckdb 2.0.0 · pyyaml 6.0.3 · sqlglot 30.31.0 通過
"""Measure declines, not only accuracy: precision, recall, coverage, selective risk and a penalty score, on dev.The prose's point rests on each agent's decline recall, decline precision and penalty score lines."""from lib.agent import run_agentfrom lib.declining import DecliningToolbox, Tallyfrom lib.golden import golden_result, grade, load_goldenfrom lib.metric_tools import MetricToolbox, catalogfrom lib.model import RecordedModelfrom lib.prompts import declining_prompt, metrics_first_promptfrom lib.semantic import loadfrom lib.warehouse import connectcon, layer = connect(), load()agents = {"metrics-first": (metrics_first_prompt(catalog(layer)), RecordedModel("metric-agent-runs"), MetricToolbox),          "declining": (declining_prompt(catalog(layer)), RecordedModel("decline-runs"), DecliningToolbox)}# The dev split's answer and decline questions; forbidden questions are decided below the model, in chapter 9.questions = [q for q in load_golden() if q.split == "dev" and q.kind in ("answer", "decline")]for name, (system, model, Toolbox) in agents.items():    tally, by_type = Tally(), {"ambiguous": Tally(), "unanswerable": Tally()}    for q in questions:        answer = run_agent(q.question, system, model, Toolbox(con, layer, role=q.role), max_steps=4).answer        outcome = grade(q, answer, golden_result(con, q))        tally.add(q.question_id, q.kind, answer, outcome)        if q.kind == "decline":            by_type[q.decline_type].add(q.question_id, q.kind, answer, outcome)    for ending in ("right", "wrong", "abstained", "step limit"):        print(f"{name} {ending}: {tally.count(ending=ending)} of {len(questions)}")    # None for the kind means every question counts, so the wrong numbers include a number given for any question    for label, kind, ending in (("wrong numbers", None, "wrong"), ("declined answerable", "answer", "abstained")):        ids = [i for i, k, e in tally.rows if kind in (None, k) and e == ending]        print(f"{name} {label}: {', '.join(ids) or 'none'}")    print(f"{name} decline precision: {tally.precision:.2f}")    print(f"{name} decline recall: {tally.recall:.2f}")    for kind, part in by_type.items():        # an abstention is a decline or a question back; this counts those on the questions whose right answer is a decline        print(f"{name} recall, {kind}: {part.count('decline', 'abstained')} of {part.count('decline')}")    print(f"{name} coverage: {tally.coverage:.2f}")    print(f"{name} selective risk: {tally.selective_risk:.2f}")    # c is the penalty for a wrong number, in points: 3 is the cost the prompt states, 10 is one of the penalties TrustSQL reports    for c in (3, 10):        print(f"{name} penalty score, c={c}: {tally.penalty_score(c):.2f}")
輸出python decline-precision-recall.py
metrics-first right: 12 of 21
metrics-first wrong: 5 of 21
metrics-first abstained: 3 of 21
metrics-first step limit: 1 of 21
metrics-first wrong numbers: gq-012, gq-016, gq-017, gq-018, gq-020
metrics-first declined answerable: none
metrics-first decline precision: 1.00
metrics-first decline recall: 0.75
metrics-first recall, ambiguous: 1 of 2
metrics-first recall, unanswerable: 2 of 2
metrics-first coverage: 0.81
metrics-first selective risk: 0.29
metrics-first penalty score, c=3: 0.00
metrics-first penalty score, c=10: -1.67
declining right: 11 of 21
declining wrong: 4 of 21
declining abstained: 5 of 21
declining step limit: 1 of 21
declining wrong numbers: gq-008, gq-012, gq-017, gq-018
declining declined answerable: gq-016
declining decline precision: 0.80
declining decline recall: 1.00
declining recall, ambiguous: 2 of 2
declining recall, unanswerable: 2 of 2
declining coverage: 0.71
declining selective risk: 0.27
declining penalty score, c=3: 0.14
declining penalty score, c=10: -1.19

The declining agent declines more and answers less, and the decline measures show the trade. Decline recall rose from 0.75 to 1.00: the declining agent declined or asked back on all four questions, where chapter 6's agent answered "Which region is doing best?". Decline precision fell from 1.00 to 0.80, because it declined one answerable question, gq-016, the count of customers who ordered.

Coverage fell from 0.81 to 0.71, and selective risk moved from 0.29 to 0.27.

The penalty score at c = 3 went from 0.00 to 0.14, and at c = 10 from -1.67 to -1.19.

The wrong numbers tell the rest. Chapter 6's agent gave gq-012, gq-016, gq-017, gq-018, gq-020; the declining agent gave gq-008, gq-012, gq-017, gq-018. Two left the list by the routes this chapter built: gq-020 through the ranking check and a question back, and gq-016 through a decline. One joined it: gq-008, total revenue in 2025, which chapter 6's agent answered with net revenue and this one with gross revenue, the near-miss pair chapter 6 described. The prompt's sentence that a metric with a similar name isn't the same metric didn't prevent it, though with one sample per call, a single flip such as gq-008 may be chance. The rest are the near-miss metrics of gq-012 and gq-018, and gq-017, which needs the asker's region, chapter 9's work. Both agents score below zero at c = 10: a handful of wrong numbers outweighs every right one, which matches TrustSQL's own finding, that "achieving high scores under severe penalties requires significant effort".

Read these as small numbers. The dev split has four questions to decline, so recall moves in steps of a quarter, and one question of 21 changes coverage by about five points. The dev numbers are optimistic for the reason given in Decline with a reason, and this chapter records nothing on the test split. The direction agrees with larger studies: prompting helps abstention but doesn't fix it (Kirichenko et al.), and prompts that push models to critique questions also raise "false invalid judgments" on valid ones (Lin et al.).

Working rule: Score an agent on declines as well as answers: report decline precision and recall, coverage and selective risk, and a penalty score with a c your stakeholders agree to, stated as a judgement. Compare agents on the same questions, and list the wrong numbers each gave, because a change that removes one wrong number can add another. When the decline questions number in single digits, read the runs, not only the rates.

正式環境中會出什麼問題

最近一次變動於第 2026.11.12 版

商店的拒答代理會拒答它該拒答的開發問題,卻也因此多拒答了一個本來可以回答的問題。對真實資料倉儲採用拒答機制的代理,會以下列方式失敗,而每一種都有察覺的辦法。

**安靜的資料來源看起來像過期。**新鮮度檢查會讀取資料中最新的 _loaded_at,而某天沒有任何事件的資料來源,當天就不會載入任何資料列。商店的退款每天大約有 1.2 筆,因此一個安靜的週末就會讓完整的期間看起來已經過期。若有一份載入紀錄,記下每次執行及其資料列數,就能解決這個問題;dbt 的 loaded_at_query 就是為這類資料來源而設。你可以依資料來源統計過期拒答的次數來察覺:一個大多數日子都被拒答的資料來源,是安靜,而不是遲到。

**沈澱視窗會過時。**商店有一半的退款,是在訂單後超過 27.5 天才發生,而這個視窗是迄今所見的最長延遲。較長的退貨期限,或較慢的付款服務商,都會讓視窗太短,使檢查放行仍在上升的月份。應定期重新測量每個視窗,所用的訂單要夠舊,已經收齊所有事件,並留意晚於視窗才到達的事件所占的比例。

**時間序列的最後一個期間逃過檢查。**檢查讀取的是請求所篩選的期間。一個依月份分組、沒有期間篩選的請求,會回傳每一個月,其中最後一個月只有部分資料,卻能通過檢查。應將任何時間序列的最後一組與資料來源比對,或要求每個依時間分組的請求都必須指定期間。

**拒答會在語意層停下之處增加。**拒答代理拒答了 gq-016,是因為沒有任何指標計算下過訂單的顧客。每一次對倉儲本來能回答的問題做出類別為 not_in_data 的拒答,都是語意層的缺口:請把它們當作待辦清單,用來決定要撰寫的指標,或要交給第 7 章的受防護 SQL處理的問題。

類別可能正確,理由卻錯誤。gq-016 的理由談的是篩選條件,而第 6 章的預測回覆問錯了事情。類別用於計數;那句話是寫給人看的,由模型撰寫。每週應讀一批理由樣本,並讓類別少到人能分辨它們。

**提示中的信心目標不等於校準。**提示要求模型只在信心高於 75% 時才回答,但模型沒有可靠的方法得知自己的信心:大型語言模型以言語表達信心時「往往過度自信」(Xiong et al.),而一項未經審查的研究指出,包括「查詢可執行性」在內的訊號,區分正確與錯誤 SQL 的 AUROC 僅約 0.61 至 0.68(Richardson)。應優先採用程式碼中的檢查,例如未知的指標、沒有期間的排名,或過期的資料來源,並把提示中的目標視為一種提醒而已。

反問可能只釐清了問題的一半。gq-020 問了期間,卻沒有定義「最好」,而評分把它算作正確。應在追蹤紀錄中檢視反問,並讓反問工具提供指名各個指標的選項,使人選擇一個定義。

**實用原則:**在更多人使用這個代理之前,應為新鮮度檢查加上載入紀錄,定期重新測量每個指標的沈澱視窗,檢查每個時間序列的最後一個期間,依類別與資料來源統計拒答,並讀取一批理由與反問的樣本。先從對可回答問題的 not_in_data 拒答著手,因為每一個都指向一個該撰寫的指標。

本章做出的決定

  • 拒答是一個會結束執行的工具,帶有取自固定清單的類別,以及一句給使用者看的說明。模型在 not_in_data、forecast 與 no_definition 之間選擇;stale 由程式碼給出,而 forbidden 則從第 9 章起由程式碼給出。
  • 有歧義的問題與無法回答的問題要分開看待,各自以 PRACTIQ 或 TrustSQL 的用語命名。只有在每一種解讀都能回答時,才反問使用者。
  • **程式碼中的檢查先於模型的判斷:**排名檢查會拒絕未指定期間的排名問題;新鮮度檢查則會拒答這樣的期間:其資料來源的載入進度,未達期間結束日加上該指標穩定期之後的日期。
  • 新鮮度來自資料中的載入時間,由每個資料表對應到決定它的資料來源,絕不取自資料表的中繼資料。
  • 尚未穩定的期間會被拒答,而不是附上警告後作答,這是依經驗法則而定;拒答時附上的理由會指出該資料來源最後一次載入的時間,以及其事件最晚可能到達的日期。退款率的穩定期取該商店退款所呈現的最長延遲。
  • 每個答案都會呈現其出處,先列出指標與定義,接著是篩選條件、角色、資料截止時間與新鮮度,SQL 則只需再一步操作即可查看。
  • 拒答以精確率與召回率、覆蓋率與選擇性風險,以及懲罰分數來衡量,懲罰分數取 c = 3 與 c = 10,採用 TrustSQL 的平均值,並將有歧義的問題計為拒答;評測使用開發集中 21 個作答與拒答的問題,並與第 6 章的代理並列比較。被禁止的問題留待第 9 章處理。
  • 提示詞依據第 6 章的開發集軌跡撰寫,並只記錄一次,本章沒有記錄測試集。

本章,於本版次中

版次 2026.11.15範例於 2026年11 月 19 通過測試本章 5 個範例 個範例中有 5 個通過

譯自英文書,版次 2026.11.15。

引用本節

格式

各種格式皆引用英文原書,本譯本即依循該原書。

每種格式都會標示本版。其連結會開啟目前版次,節標題會說明該節內文最後一次變動的時間。存取日期與擷取日期即為你開啟此頁的當日。

本頁內容

第 8 章,共 11 章: 在無法回答時要說出來

  1. Kinds of questions the warehouse can't answer
  2. Decline with a reason
  3. Check freshness before answering
  4. Show the provenance with every answer
  5. Measure declines, not only accuracy
  6. 正式環境中會出什麼問題
  7. 本章做出的決定

返回頂端所有章節