Give the agent layered context

阅读约需 103分钟 分钟,9节中含9个示例。

版次 2026.11.15 示例于 2026年11月19日 通过 78个示例中有78个通过 变化内容

AI 翻译。由人工以英文核验。 我们如何制作图书

译自英文版图书,版次 2026.11.15。 阅读原文

这部分尚未翻译,因此以英文显示。

By the end of this chapter, you can give a model that writes SQL more than the schema, in layers: notes on columns whose names mislead, a glossary of the shop's business terms, and verified queries retrieved for each question. You can fit those layers to a token budget, measure what each one adds on the dev split of the golden questions, and check the best set once on the held-out test split.

A schema can't say what its columns mean. Chapter 1 gave a model only the shop's schema and asked for net revenue in each region in March 2026. The query it wrote ran, looked right and counted cancelled orders. The rule it missed exists, in the finance team's definition of net revenue, but nothing the model was given contains it. Layered context is the most direct fix for what a schema can't say: write the rules down where the model reads them. It isn't the fix this book ends with, since chapters 5 and 6 move the definitions into a semantic layer the model can't misread. But any agent that writes SQL needs context, including the guarded one in chapter 7, and the habit this chapter teaches, adding one layer at a time and measuring each, applies to every change that follows.

这部分尚未翻译,因此以英文显示。

What the schema says, and what it doesn't

最近一次修改见于版次 2026.11.12

A schema tells a model which tables exist, what their columns are called and what type each column holds. That is a lot, and it never goes out of date, because the database produces it. What it can't tell the model is what the columns mean: which rows a table holds, which rows count toward a business number, which time zone a timestamp is in, and which of two similar tables is the one people trust. Those meanings decide whether a query returns the right number, and they live in the SQL that built the marts and in the heads of the people who own them.

The book's measure of this is the golden questions, which chapter 3 built: questions with a verified answer, scored on the dev split while context and prompts are tuned, and once on the held-out test split. Every layer in this chapter is added to the schema, so the schema is the first layer, and the place to start is what it leaves open. build_context() in lib/context.py, the shared module that builds every layer in this chapter, returns the schema layer when it's asked for nothing else.

schema-digest.py Python 3.12.15 · duckdb 2.0.0 通过
"""What the schema tells a model about revenue, and three March 2026 totals that all fit it. The three printed totalscarry the paragraph's point: they differ, and only the one that leaves out cancelled orders follows the finance definition."""from lib.context import build_contextfrom lib.warehouse import connectcon = connect()schema = build_context(con, "", layers=("schema",))      # no question, so only the schema layer is builtprint(f"tables in the schema: {schema.text.count('CREATE TABLE')}")print(f"schema tokens (estimated): {schema.tokens}")for line in schema.text.splitlines():    if "analytics.fct_orders " in line or "analytics.orders_legacy " in line:        print(line)march = "BETWEEN DATE '2026-03-01' AND DATE '2026-03-31'"   # the window of the question, on the business daycandidates = {    "orders_legacy.revenue": f"SELECT sum(revenue) FROM analytics.orders_legacy WHERE order_date {march}",    "fct_orders.net_revenue_eur, every order":        f"SELECT sum(net_revenue_eur) FROM analytics.fct_orders WHERE order_date_local {march}",    "fct_orders.net_revenue_eur, not cancelled":        f"SELECT sum(net_revenue_eur) FROM analytics.fct_orders WHERE order_date_local {march} "        "AND status <> 'cancelled'",          # net revenue leaves out cancelled orders, as the status note says}for name, sql in candidates.items():    (total,), = con.execute(sql).fetchall()    print(f"{name}: {total:,.2f}")
输出python schema-digest.py
tables in the schema: 16
schema tokens (estimated): 912
CREATE TABLE analytics.fct_orders (order_id INTEGER, customer_id INTEGER, region VARCHAR, country VARCHAR, channel VARCHAR, status VARCHAR, placed_at TIMESTAMP, order_date_local DATE, currency VARCHAR, line_count BIGINT, gross_revenue_eur DECIMAL(12,2), net_revenue_eur DECIMAL(12,2), discount_eur DECIMAL(12,2), tax_eur DECIMAL(12,2), _loaded_at TIMESTAMP);
CREATE TABLE analytics.orders_legacy (id INTEGER, cust_id INTEGER, order_date DATE, order_status VARCHAR, sales_region VARCHAR, revenue DECIMAL(12,2));
orders_legacy.revenue: 186,635.93
fct_orders.net_revenue_eur, every order: 162,542.79
fct_orders.net_revenue_eur, not cancelled: 150,082.83

The schema layer is the whole warehouse: all 16 tables, about 912 tokens. Read the two printed lines as a model would. analytics.fct_orders has a net_revenue_eur column and a status column, and analytics.orders_legacy has a revenue column and an order_date.

Each of the three totals the example computes for March 2026 is a reasonable reading of those two lines, and they disagree. The legacy table's revenue gives 186,635.93 euros, and the mart's net_revenue_eur over every order gives 162,542.79, which is what chapter 1's model computed. Only the third, 150,082.83, follows the finance team's definition, and nothing in the schema points to it rather than the other two.

The whole of the shop's warehouse fits in those 912 tokens, so there's no case for trimming it: a study of strong models on the BIRD benchmark found that passing the whole schema when it fits can beat selecting tables first, because the selection step can drop a column the query needs (Maamari et al., 2024). A warehouse with thousands of tables is a different problem, which this chapter doesn't solve. The shop's problem isn't which tables to show. It's that what the tables show doesn't say which number is right.

Working rule: Keep the whole schema in the context when it fits, and add meaning to it rather than taking tables away. Before you write any other layer, take one real question and list every reading of the schema that answers it. Each reading the schema doesn't rule out is a rule some other layer has to state.

这部分尚未翻译,因此以英文显示。

Describe columns where names mislead

最近一次修改见于版次 2026.11.15

The schema leaves open which of several readings is right, and the cheapest place to close some of them is the column itself. A column note is a sentence about one table or column that says what its name doesn't: which rows the table holds, the unit and sign of an amount, the time zone of a timestamp, the values a column takes, or that a table is deprecated. A note isn't documentation of every column. A column called product_name needs none, and a note that repeats the name costs tokens and says nothing. The notes worth writing are on the columns a careful analyst new to the warehouse would misread.

Published evidence points the same way. A study that generated column descriptions with a language model found that adding them to the prompt improved text-to-SQL accuracy and, in an ablation that replaced column names with uninformative ones, that the descriptions helped most there (Wretblad et al., 2024); it is a single preprint on the BIRD benchmark. Databricks' guidance for its Genie Agents says that "quality table and column descriptions in Unity Catalog are critical for Genie accuracy" (Databricks), which is the vendor's advice, not a measurement.

The shop's notes live in examples/data/shop/columns.toml, one entry per table with an optional note per column, and load_column_notes() in lib/context.py turns each into one line, such as analytics.fct_orders.placed_at: When the order was placed, in UTC. The notes cover the traps chapter 2 found: orders_legacy is deprecated, net_revenue_eur still holds a value for cancelled orders, placed_at is UTC while order_date_local is the business day, discount is negative in raw.order_lines and positive in the marts, and the fiscal year starts on February 1.

The recording context-layers shows what the notes do once the examples replay it. The recording holds the pinned model's SQL for every dev question of kind answer, written once with each layer set this chapter measures, using the prompt LAYERED_SQL in lib/prompts.py. The recording was made by recordings/record_context_layers.py, with the same model, sampling and seed as chapter 1's, and the examples replay it by the hash of the exact messages.

column-descriptions.py Python 3.12.15 · duckdb 2.0.0 · pyyaml 6.0.3 · sqlglot 30.31.0 通过
"""Add the column notes on columns whose names mislead, and count the dev questions they fix and break under the recordedmodel. The `fixed` and `broken` lines settle the net effect of the notes, and the broken question shows how a note misleads."""from lib.context import LAYER_SETS, build_context, grade_with_context, load_column_notesfrom lib.golden import load_goldenfrom lib.model import RecordedModelfrom lib.warehouse import connectcon = connect()notes = load_column_notes()print(f"column notes: {len(notes)}")print(f"column notes tokens (estimated): {build_context(con, '', layers=('columns',)).tokens}")for note in notes:    if note.startswith(("analytics.fct_orders.status", "analytics.fct_orders.placed_at")):        print(note)model = RecordedModel("context-layers")before, after = LAYER_SETS[0], LAYER_SETS[1]          # the sets are cumulative: [0] is the schema alone, [1] adds the notesdev = [q for q in load_golden() if q.split == "dev" and q.kind == "answer"]fixed, broken = [], []for q in dev:    was, now = grade_with_context(con, model, q, before), grade_with_context(con, model, q, after)    if was != "correct" and now == "correct":          # fixed: wrong or error without the notes, correct with them        fixed.append(q.question_id)    if was == "correct" and now != "correct":        broken.append(q.question_id)print(f"fixed by column notes: {len(fixed)} ({', '.join(fixed)})")print(f"broken by column notes: {len(broken)} ({', '.join(broken)})")
输出python column-descriptions.py
column notes: 33
column notes tokens (estimated): 1087
analytics.fct_orders.status: One of placed, shipped, delivered, cancelled, returned. Revenue leaves out cancelled orders; order and customer counts include them. Returned orders count everywhere.
analytics.fct_orders.placed_at: When the order was placed, in UTC. Don't filter or group dates on it; use order_date_local.
fixed by column notes: 7 (gq-001, gq-002, gq-003, gq-004, gq-008, gq-009, gq-011)
broken by column notes: 1 (gq-018)

The 33 notes add about 1087 tokens, more than the schema itself. On the dev questions they fix 7 (gq-001, gq-002, gq-003, gq-004, gq-008, gq-009, gq-011), among them gq-002, the March question from chapter 1, whose query now filters out cancelled orders. They also break 1 (gq-018). That question asks for the refunds on orders placed in March 2026, and with the notes the model filtered on both the order's date and refund_month, so it dropped refunds paid in a later month. The note on refund_month was accurate. The model used it on a question that didn't call for it, which is what a note can't prevent.

Working rule: Write notes only for tables and columns whose names mislead: deprecated tables, amounts with a sign or unit you wouldn't guess, timestamps in a time zone other than the business's, and columns whose values include a placeholder such as (none). Write them as facts about the column, not as instructions for one question. Expect a note to fix many questions and occasionally mislead on one, and keep the questions it broke in the golden set so you see it happen.

这部分尚未翻译,因此以英文显示。

Add the business glossary

最近一次修改见于版次 2026.11.15

Column notes describe the tables. Many questions turn on something else: what a business word means at this company. "Revenue" could be gross or net. "Orders" could include cancelled ones or not. Refunds "in March" could mean refunds paid in March or refunds on March's orders. These are choices, made by the teams that own the numbers, and no table states them. A business glossary lists the business words whose meaning a company's teams chose, and writes each meaning in terms of the warehouse's tables and columns.

Evidence for this layer comes from BIRD, a text-to-SQL benchmark whose questions come with "external knowledge evidence": hints that link a question's words to the database, such as what a term means as a formula over columns. In the benchmark's paper, adding the evidence raised GPT-4's execution accuracy on the dev set from 30.90% to 46.35%, with 2023 models and zero-shot prompts (Li et al., 2023). The hints are written per question, though, which is closer to giving the model the answer's ingredients than to giving it a glossary written once.

The shop's glossary is examples/data/shop/glossary.toml. Its entries define revenue as net revenue unless the question says gross, orders as every order including cancelled ones, average order value, fiscal periods, new customers, refunds by the month they were paid, units sold, and the two meanings of "channel". load_glossary() turns each into one line.

The glossary wasn't written blind, and the book's history shows how it changed. In the same change that recorded the model's first dev replies, with the schema alone, the entry for orders was corrected: it had said that order counts leave out cancelled orders, which disagreed with the finance team's golden SQL. The entries for units sold and for customers who ordered were added in that change too, and the column note on status was reworded to match. Later, after the test questions had been recorded with the schema alone, the refund-rate entry was changed to the book-wide definition that chapter 5 uses and that test question gq-028 also follows: refunded amount divided by gross revenue, because a refund pays back tax and only gross revenue includes it. Each change made the glossary agree with golden SQL that it was then scored against. That is how a dev score gets fitted to dev, and the check on test comes back to what it costs.

glossary-context.py Python 3.12.15 · duckdb 2.0.0 · pyyaml 6.0.3 · sqlglot 30.31.0 通过
"""Add the business glossary on top of the column notes, and count what it changes on the dev questions. The gq-002lines show the query the prose describes: with the glossary, the March query no longer filters on status."""from lib.context import LAYER_SETS, build_context, grade_with_context, load_glossaryfrom lib.golden import load_goldenfrom lib.model import RecordedModelfrom lib.prompts import layered_sql_messagesfrom lib.warehouse import connectcon = connect()terms = load_glossary()print(f"glossary terms: {len(terms)}")print(f"glossary tokens (estimated): {build_context(con, '', layers=('glossary',)).tokens}")print(next(t for t in terms if t.startswith("revenue:")))model = RecordedModel("context-layers")before, after = LAYER_SETS[1], LAYER_SETS[2]          # schema and column notes; then the glossary toodev = [q for q in load_golden() if q.split == "dev" and q.kind == "answer"]changes = {(was, now): [] for was in ("correct", "other") for now in ("correct", "other")}   # "other" is wrong or errorfor q in dev:    was, now = (grade_with_context(con, model, q, layers) for layers in (before, after))    changes["correct" if was == "correct" else "other", "correct" if now == "correct" else "other"].append(q.question_id)print(f"fixed by the glossary: {len(changes['other', 'correct'])} ({', '.join(changes['other', 'correct'])})")print(f"broken by the glossary: {len(changes['correct', 'other'])} ({', '.join(changes['correct', 'other'])})")q = next(q for q in dev if q.question_id == "gq-002")reply = model.complete(layered_sql_messages(build_context(con, q.question, after).text, q.question))filters_status = "status" in reply     # a query that filters on status has to name the columnassert not filters_status              # the chapter states it: with the glossary, gq-002 no longer filters on statusprint(f"gq-002 with the glossary filters status: {'yes' if filters_status else 'no'}")
输出python glossary-context.py
glossary terms: 13
glossary tokens (estimated): 609
revenue: Net revenue unless the question says gross: sum of analytics.fct_orders.net_revenue_eur over orders whose status isn't 'cancelled'. In EUR.
fixed by the glossary: 3 (gq-012, gq-015, gq-018)
broken by the glossary: 3 (gq-002, gq-009, gq-016)
gq-002 with the glossary filters status: no

The glossary's gains and losses cancel out: it fixes 3 (gq-012, gq-015, gq-018) dev questions and breaks 3 (gq-002, gq-009, gq-016). Its 13 terms add about 609 tokens on top of the schema and the column notes. The broken ones are the instructive part. For gq-002, the same March question, the query written with the glossary no longer filters on status, although the revenue entry and the note on status both say to leave cancelled orders out. For gq-016, the model left cancelled orders out of a customer count, applying the revenue rule where the glossary says it doesn't apply. For gq-009, the average order value, it divided the average order's net revenue by the number of orders again, although the glossary defines the measure as net revenue divided by the number of orders.

Each configuration was recorded once, with one sampled reply per question, so a change of one or two questions out of 17 is within what a second sample could undo. Chapter 10 measures that spread with repeated runs. What this result supports is narrower: the glossary didn't make this model better on these questions, and a rule stated twice was still missed. A plausible reason, which we haven't measured here, is that a longer context makes a small model use each part of it less reliably. Studies of long contexts find that models use information in the middle of a prompt worse than at its edges (Liu et al., 2024), and that accuracy falls with length when the question and the passage don't share words (Modarressi et al., 2025).

Working rule: Write a glossary entry for each business word whose meaning is a choice someone made, and state it in terms of tables and columns. Prefer one place for each rule, a column note or a glossary entry; the shop's files state the cancelled-orders rule in both, and the miss on gq-002 shows that saying it twice doesn't make it stick. Measure the glossary on your dev questions before you trust it, and keep it only if it helps there or the next layer depends on it.

这部分尚未翻译,因此以英文显示。

Retrieve verified queries as examples

最近一次修改见于版次 2026.11.15

Column notes and a glossary state rules. A verified query shows the shop's rules applied: a question someone asked, with SQL a person checked against the shop's definitions. Given a few such pairs that resemble the question, a model can copy their shape, such as the join to dim_date for a fiscal period or the filter on status, instead of inventing one. A systematic comparison of prompt designs for text-to-SQL found that the best setup chose examples by the similarity of their questions, after masking domain-specific words, and by the similarity of their SQL to a draft query written first, and showed each as a question and its SQL alone (Gao et al., 2023). Warehouse vendors build the same idea into their assistants. Snowflake's Cortex Analyst keeps a verified query repository of "questions and corresponding SQL queries to answer them" (Snowflake), and Databricks says a Genie Agent can use an example SQL query directly or learn from it, and treats parameterized ones as trusted assets (Databricks). Both are the vendors' own descriptions, not measurements.

The shop's verified queries live in examples/data/shop/verified_queries.toml. Their fields follow Snowflake's field names, name, question, sql, verified_at and verified_by, plus the role the query was checked for. Two differ in content. Snowflake's verified_at is optional and counted in seconds since 1970, and its verified_by names the person who checked the query; the shop's files give a date and name a team, never a person. None of the verified queries is a golden question. They are near neighbours of questions in both splits, such as net revenue by fiscal quarter for fiscal 2025 or average order value by region for 2024, which is how a real repository grows: from questions people asked before. A verified query that was itself a golden question would make the score measure copying.

Retrieval in lib/context.py is lexical, with no embeddings. question_terms() lowercases the question, drops common words and masks three kinds of word: numbers, month names and the shop's three region codes. Every other word stays as it is. QueryIndex scores each verified question against the masked question with TF-IDF and cosine similarity, and search() keeps at most three matches that score at least 0.4. This is a cheap stand-in for the selection in Gao et al., not a reproduction of it: it masks far fewer words, and it drops the second step, which compares draft SQL.

retrieve-similar-queries.py Python 3.12.15 · duckdb 2.0.0 通过
"""Retrieve the verified queries most like a question, by TF-IDF over the masked question's words. The matches kept at the0.4 default show that a threshold can leave a question with no example, and the masked phrases show what masking does."""from lib.context import QueryIndex, load_verified_queries, question_termsqueries = load_verified_queries()index = QueryIndex(queries)print(f"verified queries: {len(queries)}")for label, question in (("aov", "What was the average order value in each region in March 2026?"),                        ("parcels", "Which warehouse ships the most parcels?")):    print(f"question: {question}")    print(f"masked terms: {' '.join(question_terms(question))}")    for score, query in index.search(question, k=3, min_score=0.0):     # no threshold here, so the scores show the gap        print(f"  {score:.3f}  {query.name}")    print(f"{label} matches kept: {len(index.search(question))}")         # the default threshold, 0.4, is the one the book uses# Months and numbers are masked; "calendar" and "year" are not common words, and "Q3" is not masked at all.for phrase in ("March 2026", "January 2025", "calendar year 2024", "EMEA in Q3"):    print(f"masked \"{phrase}\": {' '.join(question_terms(phrase))}")
输出python retrieve-similar-queries.py
verified queries: 16
question: What was the average order value in each region in March 2026?
masked terms: average order value region <month> <number>
  0.835  average_order_value_by_region
  0.422  gross_revenue_by_region_month
  0.191  orders_of_one_customer
aov matches kept: 2
question: Which warehouse ships the most parcels?
masked terms: warehouse ships most parcels
  0.375  units_sold_by_product
  0.357  net_revenue_by_category
  0.000  average_order_value_by_region
parcels matches kept: 0
masked "March 2026": <month> <number>
masked "January 2025": <month> <number>
masked "calendar year 2024": calendar year <number>
masked "EMEA in Q3": <region> q3

For the average order value in each region in March 2026, the closest of the 16 verified queries is the same measure by region for 2024, and 2 matches pass the threshold. The second question, about which warehouse ships the most parcels, is one the shop's data can't answer at all. Its best scores come from the single shared word "most", and none passes the threshold, so 0 queries are offered. Without the threshold, the model would get three confident-looking examples, two of them about products, for a question about shipping.

The last lines of the output show what masking does and doesn't do. "March 2026" and "January 2025" both become <month> <number>, so a question about one month matches a verified query about another. "Calendar year 2024" becomes calendar year <number>, because "calendar" and "year" are neither common words nor values, and a quarter written as "Q3" isn't masked at all. That is why the March question's best match, a question about calendar year 2024, scores less than a perfect 1.

Working rule: Retrieve a few verified queries per question, chosen by similarity of the masked question, and show each as its question and SQL. Set a minimum score and check it on questions the warehouse can't answer, because lexical retrieval always returns something. Never let a golden question into the verified set. Move to embeddings only when your own measurement shows lexical retrieval missing queries that a person would call similar.

让上下文适配预算

最近一次修改见于版次 2026.11.12

有了表结构、列说明、术语表和检索到的已验证查询,这家商店的上下文所占的词元数,已是单独表结构的数倍,而且每增加一层,上下文都会更长。词元预算是智能体针对一个问题最多可以发送的上下文量。设置预算有三个原因。第一,模型的窗口是有限的:本书录制时使用的运行时为模型提供 8,192 个词元,其中最多 384 个留给回复。第二,每个提示词元在 CPU 上要花费时间,在托管模型上要花费金钱。第三,较长的上下文并不会被均匀利用,因为模型对长提示中间部分信息的利用,不如对开头或结尾部分的利用(Liu et al., 2024)。

让上下文适配预算,就是要决定舍去什么,而这个决定需要一个优先级顺序。build_context() 按优先级顺序依次取各层,逐项加入其中的条目,并舍去任何会使上下文超出预算的条目,因此后面较短的条目仍有可能放得下。表结构从不舍去,原因见第一节给出的理由:放得下的表结构应当完整发送。无论优先级如何,上下文都按一个固定顺序渲染:稳定的层在前,检索到的查询随后,问题在最后。这样可以让问题紧挨着与它最相似的示例,也能让模型运行器复用每个问题共有的那部分提示,而不必在每次调用时重新读取。录制本书所用的运行器 llama-cpp-python 0.3.36 在 Llama.generate 中做到了这一点:它把新提示的词元与上一次提示的词元作比较,只对两者最长公共前缀之后的词元进行求值(llama-cpp-python 0.3.36, llama.py)。

lib/context.py 中的词元数是估算值:estimate_tokens() 把字符数除以 3.5,因为这些示例不会加载模型的分词器。下面把这一估算值与录制提示时模型分词器报告的计数作对比,并在两种优先级下,把平均订单金额问题 gq-009 的上下文适配到 2,400 个词元的示意性预算。

context-token-budget.py Python 3.12.15 · duckdb 2.0.0 · pyyaml 6.0.3 · sqlglot 30.31.0 通过
"""Fit one question's layered context to a token budget, and check the token estimate against the model's count. Theestimate runs high, the safe side for a budget, and the dropped lines show what each priority gives up."""from lib.context import LAYERS, build_context, estimate_tokensfrom lib.golden import load_goldenfrom lib.model import RecordedModelfrom lib.prompts import layered_sql_messagesfrom lib.warehouse import connectcon = connect()question = next(q for q in load_golden() if q.question_id == "gq-009").questionfull = build_context(con, question)for layer, tokens in full.layer_tokens().items():    print(f"{layer} tokens (estimated): {tokens}")messages = layered_sql_messages(full.text, question)call = RecordedModel("context-layers").call_for(messages)print(f"prompt tokens (estimated): {estimate_tokens(''.join(m['content'] for m in messages))}")   # every message, joinedprint(f"prompt tokens (model's tokenizer): {call['prompt_tokens']}")budget = 2400          # an illustrative budget, well inside the 8,192-token window the recordings usefor name, priority in (("default", LAYERS), ("examples first", ("schema", "columns", "verified", "glossary"))):   # verified ranks above glossary    fitted = build_context(con, question, layers=priority, budget=budget)    kept = {layer: len(items) for layer, items in fitted.items.items()}    print(f"{name} priority: {fitted.tokens} tokens, kept {kept}")    print(f"{name} dropped: {len(fitted.dropped)}")print(f"render order: {', '.join(layer for layer, items in fitted.items.items() if items)}, then the question")
输出python context-token-budget.py
schema tokens (estimated): 912
columns tokens (estimated): 1087
glossary tokens (estimated): 609
verified tokens (estimated): 200
prompt tokens (estimated): 2917
prompt tokens (model's tokenizer): 2364
default priority: 2393 tokens, kept {'schema': 1, 'columns': 33, 'glossary': 9, 'verified': 0}
default dropped: 6
examples first priority: 2384 tokens, kept {'schema': 1, 'columns': 33, 'glossary': 5, 'verified': 2}
examples first dropped: 8
render order: schema, columns, glossary, verified, then the question

整个提示的估算值为 2917 个词元,而模型的分词器统计的结果为 2364 个。估算值偏高对预算而言是安全的方向:按它放行的上下文总是放得下。在默认优先级(即按各层被引入的顺序)下,预算保留了全部列说明和一部分术语表,舍去了两条检索到的查询,共舍去 6 个条目。若把已验证查询的优先级排在术语表之上,同样的预算会保留这两条查询,转而舍去 8 条术语表条目。两种顺序都不是普遍正确的。下一节会衡量在这家商店的问题上,哪些层的词元物有所值,顺序应当由此确定。

工作准则: 把词元预算设置在远小于模型窗口的范围内,并按你测量过的优先级,而不是按你编写各层的先后顺序,让每个问题的上下文适配该预算。表结构放得下时,决不舍去。无论舍去了什么,都先渲染稳定的层,最后渲染问题。把你的词元估算值与模型的真实计数核对一次,并让估算值保持在偏高一侧。

这部分尚未翻译,因此以英文显示。

Measure what each layer adds

最近一次修改见于版次 2026.11.15

Each layer so far was judged by the questions it fixed and broke. To choose which layers to keep, and in what order a budget should drop them, you need all of them measured the same way. An ablation measures every layer the same way: it scores a series of configurations that differ by one layer each, on the same questions, under the same comparison rule. The questions are the dev split of the golden questions, because choosing among configurations is tuning, and tuning on the test split would leave nothing held out to check the choice.

The shop's dev split has 24 golden questions. This chapter scores the 17 of kind answer. The other 7 should be declined, because the warehouse can't answer them or the role asking may not see the answer, and a prompt that only writes SQL can't decline, so they would score as wrong under every layer set; chapters 8 and 9 score them. Each layer set adds one layer to the one before: the schema alone, then column notes, then the glossary, then up to three retrieved verified queries. The outcomes come from grade() in lib/golden.py, as in every chapter: correct when the result matches the golden result, wrong when it runs and doesn't, error when it doesn't run. The first layer set, the schema alone, isn't chapter 3's baseline either. That baseline used the schema-only prompt and scored every question in each split, while this run uses the layered prompt LAYERED_SQL with no other layer filled in and scores the answer questions only, so its numbers differ.

layer-ablation-dev.py Python 3.12.15 · duckdb 2.0.0 · pyyaml 6.0.3 · sqlglot 30.31.0 通过
"""Score each layer set on the dev split's answer questions, replaying the recorded model's SQL for each, and print thetotals, the average token counts and the outcome grid. The correct totals and the fixed and broken lines are the numbers the prose rests on."""from collections import Counterfrom lib.context import LAYER_SETS, build_context, grade_with_context, layer_set_namefrom lib.golden import load_goldenfrom lib.model import RecordedModelfrom lib.warehouse import connectcon = connect()model = RecordedModel("context-layers")dev_split = [q for q in load_golden() if q.split == "dev"]dev = [q for q in dev_split if q.kind == "answer"]          # the other questions are declined, and are scored in chapters 8 and 9print(f"dev split questions: {len(dev_split)}")print(f"dev questions: {len(dev)}")print(f"dev questions to decline: {len(dev_split) - len(dev)}")grid = {}for layers in LAYER_SETS:    name = layer_set_name(layers)    grid[name] = [grade_with_context(con, model, q, layers) for q in dev]    counts = Counter(grid[name])    tokens = sum(build_context(con, q.question, layers).tokens for q in dev) // len(dev)   # mean over the dev questions, whole tokens    print(f"{name}: correct {counts['correct']}, wrong {counts['wrong']}, error {counts['error']}")    print(f"{name} correct: {counts['correct']}")    print(f"{name} error: {counts['error']}")    print(f"{name} tokens: {tokens}")print("question  " + "  ".join(f"{i + 1}" for i in range(len(LAYER_SETS))))for i, q in enumerate(dev):    print(f"{q.question_id}    " + "  ".join(grid[name][i][0] for name in grid))# What the verified queries changed, against the run with the glossary.before, after = grid[layer_set_name(LAYER_SETS[2])], grid[layer_set_name(LAYER_SETS[3])]   # the glossary run, then the glossary plus verified queriesfixed = [q.question_id for q, was, now in zip(dev, before, after) if was != "correct" and now == "correct"]broken = [q.question_id for q, was, now in zip(dev, before, after) if was == "correct" and now != "correct"]print(f"fixed by verified queries: {len(fixed)}")print(f"fixed by verified queries, IDs: {', '.join(fixed)}")print(f"broken by verified queries: {len(broken)}")
输出python layer-ablation-dev.py
dev split questions: 24
dev questions: 17
dev questions to decline: 7
schema: correct 3, wrong 9, error 5
schema correct: 3
schema error: 5
schema tokens: 912
schema+columns: correct 9, wrong 7, error 1
schema+columns correct: 9
schema+columns error: 1
schema+columns tokens: 1999
schema+columns+glossary: correct 9, wrong 8, error 0
schema+columns+glossary correct: 9
schema+columns+glossary error: 0
schema+columns+glossary tokens: 2608
schema+columns+glossary+verified: correct 14, wrong 2, error 1
schema+columns+glossary+verified correct: 14
schema+columns+glossary+verified error: 1
schema+columns+glossary+verified tokens: 2775
question  1  2  3  4
gq-001    e  c  c  c
gq-002    w  c  w  c
gq-003    e  c  c  c
gq-004    w  c  c  c
gq-006    e  e  w  w
gq-007    w  w  w  w
gq-008    w  c  c  c
gq-009    w  c  w  c
gq-010    e  w  w  c
gq-011    w  c  c  c
gq-012    w  w  c  c
gq-013    e  w  w  c
gq-014    c  c  c  c
gq-015    w  w  c  c
gq-016    c  c  w  c
gq-017    w  w  w  e
gq-018    c  w  c  c
fixed by verified queries: 5
fixed by verified queries, IDs: gq-002, gq-009, gq-010, gq-013, gq-016
broken by verified queries: 0

Column notes and verified queries raise the score; the glossary doesn't. The schema alone gets 3 of the dev questions right, column notes take it to 9, and the glossary leaves it at 9. Verified queries on top give 14, the best set on dev.

The grid shows where the change came from. Against the run with the glossary, retrieved examples fixed 5 questions and broke 0. Two of the fixes are new: the fiscal-quarter question gq-010 and the order count by region gq-013, whose nearest verified queries show exactly the join and the count they needed. The other three, gq-002, gq-009 and gq-016, are the questions the glossary run had lost, so there the examples won back what the glossary had cost.

The totals say how much each layer helped. The failures say what the next layer should be, so the next two examples read them, starting with the schema-only queries that don't run.

missing-columns-schema-only.py Python 3.12.15 · duckdb 2.0.0 · pyyaml 6.0.3 · sqlglot 30.31.0 通过
"""Why the dev queries written with the schema alone don't run: the column each one names, and the analytics tables that have it.The per-table counts are the evidence the prose rests on: every failure is a column on the wrong table."""import refrom collections import Counterimport duckdbfrom lib.context import LAYER_SETS, build_contextfrom lib.golden import load_goldenfrom lib.model import RecordedModelfrom lib.prompts import layered_sql_messagesfrom lib.tools import extract_sql, run_sqlfrom lib.warehouse import connectcon, model = connect(), RecordedModel("context-layers")dev = [q for q in load_golden() if q.split == "dev" and q.kind == "answer"]where = Counter()for q in dev:    context = build_context(con, q.question, LAYER_SETS[0])          # the schema alone    sql = extract_sql(model.complete(layered_sql_messages(context.text, q.question)))    try:        run_sql(con, sql)        continue    except duckdb.Error as e:        column = re.search(r'column (?:named )?"(\w+)"', str(e)).group(1)   # DuckDB says either form; take the name    (tables,), = con.execute(        "SELECT string_agg(table_schema || '.' || table_name, ', ' ORDER BY 1) FROM information_schema.columns "   # sorted, so a column in two tables lists them in a fixed order        "WHERE table_schema = 'analytics' AND column_name = ?", [column]).fetchall()   # the marts only: where the model should have looked    where[tables] += 1    print(f"{q.question_id}: no column {column}; it is in {tables}")print(f"schema-only queries that don't run: {where.total()}")for tables, n in where.items():    print(f"missing column only {tables} has: {n}")
输出python missing-columns-schema-only.py
gq-001: no column fiscal_year; it is in analytics.dim_date
gq-003: no column calendar_year; it is in analytics.dim_date
gq-006: no column quantity; it is in analytics.fct_order_lines
gq-010: no column fiscal_quarter; it is in analytics.dim_date
gq-013: no column order_date; it is in analytics.orders_legacy
schema-only queries that don't run: 5
missing column only analytics.dim_date has: 3
missing column only analytics.fct_order_lines has: 1
missing column only analytics.orders_legacy has: 1

Every failure is a column the model put on the wrong table. Of the 5, 3 ask the orders mart for a fiscal or calendar column that only dim_date has, 1 asks it for quantity, which only the order lines have, and 1 uses the legacy table's order_date.

These are the mistakes column notes are for. With the notes, 1 query in the whole dev split fails to run.

A second script prints the query for each dev question that all four layers still don't get right.

what-stays-wrong.py Python 3.12.15 · duckdb 2.0.0 · pyyaml 6.0.3 · sqlglot 30.31.0 通过
"""The dev questions that stay wrong with all four layers, each with its query, and a check of whether gq-007 fails only onthe spelling of 'tents'. The count line settles how many dev questions stay wrong, and the gq-007 line settles whether the spelling alone causes its failure."""import duckdbfrom lib.context import LAYERS, build_context, grade_with_contextfrom lib.golden import golden_result, grade, load_goldenfrom lib.model import RecordedModelfrom lib.prompts import layered_sql_messagesfrom lib.tools import extract_sql, run_sqlfrom lib.warehouse import connectcon, model = connect(), RecordedModel("context-layers")dev = [q for q in load_golden() if q.split == "dev" and q.kind == "answer"]def sql_with_all_layers(q):    return extract_sql(model.complete(layered_sql_messages(build_context(con, q.question, LAYERS).text, q.question)))unsolved = [(q, outcome) for q in dev if (outcome := grade_with_context(con, model, q, LAYERS)) != "correct"]   # LAYERS is all fourprint(f"not correct with all four layers: {len(unsolved)}")for q, outcome in unsolved:    sql = sql_with_all_layers(q)    print(f"{q.question_id} ({outcome}): {q.question}")    print("\n".join("    " + line for line in sql.strip().splitlines()))    if outcome == "error":        try:            run_sql(con, sql)        except duckdb.Error as e:            print(f"    -- {str(e).splitlines()[0]}")gq007 = next(q for q in dev if q.question_id == "gq-007")respelled = sql_with_all_layers(gq007).replace("'tents'", "'Tents'")   # change the spelling only, to see whether it is the whole failureprint(f"gq-007 with 'Tents' spelled as stored: {grade(gq007, run_sql(con, respelled), golden_result(con, gq007))}")
输出python what-stays-wrong.py
not correct with all four layers: 3
gq-006 (wrong): What were net revenue and the number of units sold in each region in 2025?
    SELECT
        o.region,
        SUM(o.net_revenue_eur) AS net_revenue,
        SUM(l.quantity) AS units_sold
    FROM analytics.fct_orders AS o
    JOIN analytics.fct_order_lines AS l USING (order_id)
    WHERE o.order_date_local >= '2025-01-01' AND o.order_date_local < '2026-01-01'
        AND o.status <> 'cancelled'
    GROUP BY o.region
    ORDER BY net_revenue DESC
gq-007 (wrong): How much net revenue came from orders that included a tent in 2025?
    SELECT
        SUM(fol.net_amount_eur) AS net_revenue
    FROM
        analytics.fct_order_lines fol
    JOIN
        analytics.fct_orders fo ON fol.order_id = fo.order_id
    JOIN
        analytics.dim_products dp ON fol.product_id = dp.product_id
    JOIN
        analytics.dim_date dd ON fo.order_date_local = dd.date_day
    WHERE
        dp.category = 'tents'
        AND dd.calendar_year = 2025
        AND fo.status != 'cancelled'
gq-017 (error): What was net revenue in each of our countries in 2025?
    SELECT d.country, round(sum(o.net_revenue_eur), 2) AS net_revenue
    FROM analytics.fct_orders AS o
    JOIN analytics.dim_date AS d ON d.date_day = o.order_date_local
    WHERE o.status <> 'cancelled'
      AND d.calendar_year = 2025
    GROUP BY d.country
    ORDER BY net_revenue DESC
    -- Binder Error: Table "d" does not have a column named "country"
gq-007 with 'Tents' spelled as stored: wrong

With all four layers, 3 questions are still not right. gq-006 asks for net revenue and units sold by region. The model joined the orders mart to its lines and summed net_revenue_eur over the joined rows, so an order's revenue counts once for every line it has. The glossary's entry for units sold says to sum the lines per order first for exactly this reason, so this is a rule the context stated and the model missed. gq-007 filters on the category 'tents' where the data says 'Tents', a value no layer lists. Spelled as stored, the answer is still wrong, because the query sums only the tent lines, where the question asks for the whole revenue of the orders that included one. gq-017 asks for "our countries", which depends on the region of the regional lead asking. No layer says who is asking, and the model's query, which takes country from dim_date, doesn't run.

This is the book's measurement on one synthetic warehouse and one 4-billion-parameter model, with one sampled reply per question, not a general result about layered context. We found no peer-reviewed study from 2025 or 2026 that measures retrieved verified queries separately from other context on business data, which is why the chapter measures it here.

Working rule: Measure context one layer at a time on the dev split, with the same questions, comparison rule and model, and keep the outcomes per question, not only the totals. Treat a difference of one or two questions on a set this size as noise until repeated runs say otherwise. Read the queries that fail, because each one names a layer you don't have yet or a rule the model still skips.

在测试集上检验所选的层

最近一次修改见于版次 2026.11.12

消融实验在开发集上选定了全部四层,开发集就是本章用来调优的那批问题。在开发集上得分最高的那一组层,仍须在留出的测试集上检验一次,并与仅使用模式(schema)的情形对照,这样比较结果就不会因为选择与调优用的是同一批问题而显得偏高。记录文件 context-layers-test 保存了模型针对 17 个类型为 answer 的测试问题所生成的 SQL,且只涉及这两组层。每个测试问题还会与其最匹配的已验证查询计算得分,供后面的段落使用。

best-layers-on-test.py Python 3.12.15 · duckdb 2.0.0 · pyyaml 6.0.3 · sqlglot 30.31.0 通过
"""Choose the best layer set on the dev split, then score it once on the held-out test split beside the schema alone. Thecorrect counts are the numbers the prose rests on, and the retrieval scores measure how close each split sits to the verified queries."""from collections import Counterfrom lib.context import LAYER_SETS, QueryIndex, grade_with_context, layer_set_name, load_verified_queriesfrom lib.golden import load_goldenfrom lib.model import RecordedModelfrom lib.warehouse import connectcon = connect()questions = [q for q in load_golden() if q.kind == "answer"]   # the answer questions only, as in the ablationdev = [q for q in questions if q.split == "dev"]test = [q for q in questions if q.split == "test"]dev_model = RecordedModel("context-layers")          # dev and test replies come from separate recordings; the test one plays no part in the choicedev_correct = {layers: sum(grade_with_context(con, dev_model, q, layers) == "correct" for q in dev)               for layers in LAYER_SETS}best = max(LAYER_SETS, key=lambda layers: (dev_correct[layers], -len(layers)))   # ties go to fewer layersprint(f"best on dev: {layer_set_name(best)}")print(f"best on dev correct: {dev_correct[best]} of {len(dev)}")test_model = RecordedModel("context-layers-test")print(f"test questions: {len(test)}")print(f"test question IDs: {', '.join(q.question_id for q in test)}")for name, layers in (("schema", LAYER_SETS[0]), ("best", best)):    counts = Counter(grade_with_context(con, test_model, q, layers) for q in test)    print(f"test {name}: correct {counts['correct']}, wrong {counts['wrong']}, error {counts['error']}")    print(f"test {name} correct: {counts['correct']}")# How close each split's questions sit to the verified queries, by the retriever's own score.index = QueryIndex(load_verified_queries())for split, qs in (("dev", dev), ("test", test)):    best_match = [(index.search(q.question, k=1, min_score=0.0)[0], q) for q in qs]   # the best match, whatever its score    print(f"{split} mean top retrieval score: {sum(score for (score, _), _ in best_match) / len(qs):.2f}")    print(f"{split} questions with no verified query kept: {sum(not index.search(q.question) for q in qs)}")    (score, query), q = max(best_match, key=lambda pair: pair[0][0])    print(f"{split} closest pair: {q.question_id} and {query.name}")    print(f"{split} closest score: {score:.3f}")
输出python best-layers-on-test.py
best on dev: schema+columns+glossary+verified
best on dev correct: 14 of 17
test questions: 17
test question IDs: gq-025, gq-026, gq-027, gq-028, gq-029, gq-030, gq-031, gq-032, gq-033, gq-034, gq-035, gq-036, gq-037, gq-038, gq-039, gq-040, gq-041
test schema: correct 4, wrong 9, error 4
test schema correct: 4
test best: correct 8, wrong 7, error 2
test best correct: 8
dev mean top retrieval score: 0.57
dev questions with no verified query kept: 2
dev closest pair: gq-001 and net_revenue_by_fiscal_quarter
dev closest score: 0.862
test mean top retrieval score: 0.63
test questions with no verified query kept: 1
test closest pair: gq-029 and new_customers_by_region
test closest score: 0.933

这些层对没有为之调优的问题仍然有帮助,而这正是关键的结果。开发集上最佳的一组层是 schema+columns+glossary+verified,在开发集上答对 14 of 17。在测试集上,仅使用模式答对 4,四层全用则答对 8。

开发集与测试集得分之间的差距是另一个结果,而本章没有测量其成因。一种解释是已验证查询更适合开发集,但检索器自身的得分与此相反:每个问题最佳匹配的平均得分,在开发集上是 0.57,在测试集上是 0.63。

最接近的一对,即一个标准问题与其已验证的匹配查询,也出现在测试集中:gq-029 and new_customers_by_region,得分为 0.933,是针对 2024 日历年提出的同一个问题。开发集中最接近的一对得分为 0.862。

有两点是已知的。第一,开发集的用途不止于选择层的组合。正如术语表一节所述,在记录最初几条开发集回复时,术语表曾被修改,以便与标准 SQL 一致;这样的修改会使上下文贴合将要据以评分的问题,无论是否有意为之。开发集就是这样被过拟合的,这也是开发集得分不宜作为报告结果的原因。第二,两个数据集所问的内容不同:测试集询问毛利率、会话数和营销支出,而开发集的问题都不涉及这些。要区分这些成因,需要比本章更多的问题和重复运行。

工作准则: 在开发集上选定一组层,然后与基线并列,在测试集上只评分一次,并报告测试集的数字。记下在读取开发集结果之后对上下文所做的每一处改动,因为每一处改动都可能使开发集得分偏高。当开发集与测试集的结果不一致时,先检查能够测量的内容,例如两个数据集各自与你的示例有多接近,然后再解释这一差距。

这部分尚未翻译,因此以英文显示。

What goes wrong in production

最近一次修改见于版次 2026.11.12

The layers raised the dev score well above the schema alone, and they stay correct only while the warehouse and its definitions stay put. Once people rely on them, the failures are quiet: a note or a verified query keeps teaching a rule its warehouse has since changed.

The notes drift away from the marts. A column note is true about the mart as it was built when someone wrote it. When the analytics engineers change fct_orders, for example to drop cancelled orders from the mart, the note that says to filter on status becomes wrong, and nothing fails. You notice by keeping the notes in the same repository as the SQL that builds the marts, reviewing them in the same pull requests, and checking in CI that every table and column a note names still exists.

A value the context never lists. The model wrote 'tents' for a category stored as 'Tents', and the query ran and returned nothing. Questions name values, such as categories, channels, regions and campaign names, and a model guesses their spelling. Reading the wrong answers whose result is empty or zero catches it. For columns with a few dozen distinct values, list them in the column note. For columns with many, retrieve the values that match the question's words, as you retrieve verified queries.

A rule stated in context is still ignored. With the glossary, the model dropped the cancelled-orders filter on gq-002 and left cancelled orders out of the customer count for gq-016. With the column notes, and again with the glossary, it left them out of the order count for gq-013. Both go against what the note on status and the glossary say. With all four layers, it summed order revenue over order lines on gq-006, which the glossary's entry for units sold warns against. Context makes a rule available. It doesn't make the model follow it. Only per-question golden scores reveal it. When a rule has to hold every time, move it out of the prompt and into code the model can't skip, which is what chapter 5's semantic layer does.

Retrieval offers the wrong example. Lexical retrieval matches words, so a question that shares only "most" with a verified query gets that query as its example unless a threshold stops it, and a question that means the same thing in other words gets nothing. Log which verified query each answer used, as Snowflake's Cortex Analyst reports it in the confidence field of its API (Snowflake), then read the logs for answers that went wrong.

A verified query is mistaken for a verified answer. A retrieved query guides the model, and the SQL it writes is new SQL that nobody checked. Databricks marks a Genie answer as verified only when the exact text of a parameterized example query is used (Databricks), which is the distinction to keep. Never show an answer as verified because a similar query was. You notice by checking what your interface says about answers that were built from examples.

Verified queries go stale. A query checked in October uses the definitions of October. When finance changes a definition, the old queries teach the old rule to every similar question. Keep a verified_at date on each query, re-run each against its golden counterpart when a definition changes, and remove queries nobody has checked since the change.

The context grows until it costs more than it gives. Each layer is cheap to add, and nobody removes one that stopped helping. On a CPU every prompt token costs time, and with a hosted model it costs money on every call. Recording the tokens of each call with its outcome, as the recordings here do, and re-running the ablation when a layer grows, shows which layer has stopped paying for its tokens.

Working rule: Version the context with the warehouse: keep it beside the marts, checked in CI against the tables it names, scored on golden questions with every change, and logged per answer with the verified queries it used. Move any rule that must always hold out of the context and into a definition the model can't skip.

这部分尚未翻译,因此以英文显示。

Decisions this chapter made

  • Context comes in four layers: the whole schema, notes on columns whose names mislead, a business glossary, and verified queries retrieved per question. Each lives in a file under examples/data/shop/, and build_context() in lib/context.py assembles them.
  • The schema is never trimmed while it fits; the budget applies to the other layers.
  • Verified queries are retrieved lexically, by TF-IDF over the question's words with numbers, months and region codes masked, at most three, each with a score of at least 0.4. None of them is a golden question, and each names the team that verified it, never a person.
  • The context is rendered stable layers first and the question last, so the question sits beside its examples and the runner can reuse the shared prefix.
  • Tokens are estimated from characters, at 3.5 characters a token, which overestimated the model's count on the prompt checked, so a context that fits the estimate should fit the model; check it on your own prompts.
  • Layers are measured by ablation on the dev split's answer questions, one layer at a time, and the best set is checked once on the test split beside the schema alone.
  • The book keeps all four layers for the chapters that write SQL, because that set scored best on dev. The glossary stays although it didn't improve the score by itself: the verified-query layer was measured on top of it, and we didn't measure verified queries without it.

本章,在本版次中

版次 2026.11.15示例于 2026年11月19日 通过本章 9个示例 个示例中有 9 个通过

译自英文版图书,版次 2026.11.15。

引用本节

格式

每种格式均引用英文原书,本译本以其为准。

每种格式都会注明该版次。其链接会打开当前版次,节标题处会说明该节文本最后一次修改的时间。访问日期和检索日期即为您打开此页的当天。

本页内容

第 4 章,共 11 章: Give the agent layered context

  1. What the schema says, and what it doesn't
  2. Describe columns where names mislead
  3. Add the business glossary
  4. Retrieve verified queries as examples
  5. 让上下文适配预算
  6. Measure what each layer adds
  7. 在测试集上检验所选的层
  8. What goes wrong in production
  9. Decisions this chapter made

返回顶部全部章节