"""写作者的出处清单:预算按写作模型的上下文窗口定;超出预算时分优先级、按来源均衡,省略了什么照实说。 2026-10 一次运行:证据台账里上百次查询(4 个 Agent 查询次数悬殊),出处清单写死 12000 字,十万字以上的目录 被截到一万两千字以内,只有前二十来次查询进了写作者的视野,后面只有一句「目录太长,后面的省略了」。查询按编号排,前面的 Agent 占满了预算,有的 Agent 一次都没露面;写作者于是写出「本轮没有查到任何核销结果」,可那个 Agent 查到了上百条。 - 预算:写作模型上下文窗口的 40%(字数按 1 字 ≈ 1 token 保守算),拿不到窗口按 128K;下限 12000、上限 160000 - 第一优先:各 Agent 经按出处核对交来的结构化字段、口径卡指标,一律列出 - 查询按产出它的节点分组、轮流取:先给每次查询前几行,再补到 20 行;每个节点都有代表 - 没展开的查询列出编号和一行摘要(表、行数);约定只能写 [[see:Qn]] 作依据,数字照样逐字核对 - 清单开头明说「目录有省略」,各节点各省略了多少条 夹具全部合成(tests/fixtures/evidence/store_run.py)。 """ from __future__ import annotations import re import pytest import app.db.models # noqa: F401 - 建表(conftest 的 create_all)前要先登记模型 from app.engine.evidence import ( CATALOG_MAX_CHARS, CATALOG_MIN_CHARS, DEFAULT_CATALOG_BUDGET, build_catalog, catalog_budget, catalog_prompt, writer_catalog, ) from tests.fixtures.evidence import store_run LEDGER, STORE, NODES, TITLES = store_run.build() def load(artifact): return STORE.get(artifact) @pytest.fixture def catalog(): return build_catalog(nodes=NODES, ledger=LEDGER) def sources(): return [{"node_id": nid, "title": TITLES[nid], "data": NODES[nid]["data"], "evidence": NODES[nid]["data_evidence"]} for nid, *_ in store_run.AGENTS] def written(catalog, budget=DEFAULT_CATALOG_BUDGET, **kw): return writer_catalog(catalog, budget=budget, loader=load, fields=sources(), titles=TITLES, **kw) def group_of(text: str, title: str) -> str: """清单里「来自「<名字>」的查询」那一段(到下一个来源或下一节为止)。""" start = text.index(f"来自「{title}」的查询") rest = text[start + 1:] ends = [m.start() for m in re.finditer(r"\n(?:来自「|\n)", rest)] return text[start:start + 1 + (ends[0] if ends else len(rest))] # -------------------------------------------------------------------------- # 预算 # -------------------------------------------------------------------------- def test_budget_follows_the_model_window(): assert DEFAULT_CATALOG_BUDGET == catalog_budget(None) == 51_200, "拿不到窗口按 128K 的 40%" assert catalog_budget(128_000) == 51_200 assert catalog_budget(200_000) == 80_000 assert catalog_budget(32_000) == 12_800 assert catalog_budget(8_000) == CATALOG_MIN_CHARS == 12_000, "很小的窗口维持原来的篇幅" assert catalog_budget(1_000_000) == CATALOG_MAX_CHARS == 160_000, "百万窗口也有上限:每写一稿都要重发整份目录" assert catalog_budget(0) == catalog_budget(-5) == DEFAULT_CATALOG_BUDGET def test_the_default_is_far_above_the_old_cut(): assert DEFAULT_CATALOG_BUDGET >= 4 * 12_000 # -------------------------------------------------------------------------- # 放得下:照旧 # -------------------------------------------------------------------------- def test_a_catalog_that_fits_is_not_trimmed(): small = build_catalog(nodes={}, ledger=[e for e in LEDGER if e.get("node_id") == "agent_store"]) got = writer_catalog(small, loader=load) assert not got.trimmed and not got.omitted assert "目录有省略" not in got.text assert got.text == catalog_prompt(small, loader=load), "没有结构化字段时和 catalog_prompt 一字不差" assert "Q17:" in got.text and " r19:" in got.text # -------------------------------------------------------------------------- # 放不下:分优先级、按来源均衡(那次运行同样形状的场景) # -------------------------------------------------------------------------- @pytest.mark.parametrize("budget", [DEFAULT_CATALOG_BUDGET, 12_000]) def test_every_agent_stays_in_view_within_the_budget(catalog, budget): got = written(catalog, budget) text = got.text assert got.trimmed and len(text) <= budget, len(text) for nid, title, count, table in store_run.AGENTS: group = group_of(text, title) assert f"共 {count} 次" in group assert re.search(r"\n {2}r0:", group), f"「{title}」一次查询都没展开" # 每次查询都在清单里:展开的有行,没展开的有编号和摘要 total = sum(c for *_, c, _ in store_run.AGENTS) for n in range(1, total + 1): assert re.search(rf"(?:^|\n)\s*- Q{n}:", text), f"Q{n} 不见了" def test_omitted_queries_are_listed_with_a_summary(catalog): got = written(catalog) assert got.omitted, "这个场景放不下全部展开" for alias in got.omitted: node = catalog[alias]["node_id"] table = next(t for nid, _, _, t in store_run.AGENTS if nid == node) assert re.search(rf"\n {{2}}- {alias}:{table},30 行", got.text), alias # 没展开的查询没有行 first = got.omitted[0] block = got.text[got.text.index(f"- {first}:"):].split("\n", 2) assert not block[1].lstrip().startswith("r0:") def test_the_head_says_what_was_left_out_per_source(catalog): got = written(catalog) head = got.text[:800] assert "目录有省略" in head for row in got.nodes: assert f"{row['title']} {row['total']} 次" in head and f"省略 {row['omitted']} 次" in head, row assert sum(r["omitted"] for r in got.nodes) == len(got.omitted) assert [r["node_id"] for r in got.nodes] == [nid for nid, *_ in store_run.AGENTS] def test_how_to_use_an_omitted_query_is_spelled_out(catalog): text = written(catalog).text assert "[[see:Qn]]" in text and "本报告未覆盖" in text assert "不要凭摘要写" in text and "数字照样逐字核对" in text for phrase in ("没有查到", "不存在", "缺失", "没有数据"): assert phrase in text def test_structured_fields_come_first_and_point_at_global_cells(catalog): got = written(catalog, 12_000) text = got.text fields_at = text.index("各 Agent 交来的结构化结论") assert fields_at < text.index("来自「"), "结构化结论排在查询前面" member_q3 = store_run.global_alias("agent_member", 3) store_q3 = store_run.global_alias("agent_store", 3) campaign_q5 = store_run.global_alias("agent_campaign", 5) assert f"[[v:{member_q3}.r0.cnt]]" in text and f"[[v:{store_q3}.r0.store_name]]" in text assert f"[[table:{campaign_q5} cols=store_name rows=0-4]]" in text assert "churn_rate:抽取时没有找到这个值" in text # 抽取失败的那个 Agent:结构化结论为空,不能据此断言没有数据 block = text[text.index("「卡券核销」:", fields_at):] assert block.startswith("「卡券核销」:结构化结论为空") and "本报告未覆盖" in block.split("\n", 1)[0] assert got.empty_sources == ["卡券核销"] def test_queries_the_fields_cite_are_expanded_first(catalog): """结构化字段引用到的那几次查询先展开:写作者照抄字段的引用标记时,看得到那几行。""" got = written(catalog, 12_000) for nid in ("agent_member", "agent_store", "agent_campaign"): for local in (3, 5): alias = store_run.global_alias(nid, local) assert alias not in got.omitted, alias assert re.search(rf"\n- {alias}:.*\n {{2}}r0:", got.text), alias def test_a_field_value_reads_like_the_cell_it_cites(catalog): """字段后面写的值和引用之后报告里显示的一样([[v:]] 的渲染规则)。""" text = written(catalog).text q3 = STORE[store_run.artifact_of("agent_member", 3)] assert f"total_cnt = {q3['rows'][0][2]:,}:[[v:Q3.r0.cnt]]" in text # -------------------------------------------------------------------------- # 报告节点:窗口从哪来 # -------------------------------------------------------------------------- async def test_the_window_comes_from_the_provider_entry_then_the_catalog(): """模型接入里给这个模型登记的 context 优先,其次模型目录;都没有返回 None(预算按保守值)。""" from sqlalchemy import delete from app.db.base import SessionLocal from app.db.models import Provider from app.engine.nodes.report import model_window from app.providers.factory import ModelSpec async with SessionLocal() as session: row = Provider(name="fa-window-test", kind="mock", enabled=True, default_model="mock-wide", models=[{"id": "mock-wide", "context": 64_000}, {"id": "mock-text", "context": "96000"}, {"id": "mock-bare"}]) session.add(row) await session.commit() try: assert await model_window(session, ModelSpec(model="mock-wide"), "mock-wide") == 64_000 assert await model_window(session, ModelSpec(model="mock-text"), "mock-text") == 96_000 # 接入里没登记窗口:按模型目录(deepseek-chat 登记了 128K);目录里也没有就是 None assert await model_window(session, ModelSpec(model="deepseek-chat"), "deepseek-chat") == 128_000 assert await model_window(session, ModelSpec(model="mock-bare"), "mock-bare") is None assert catalog_budget(await model_window(session, ModelSpec(model="mock-wide"), "mock-wide")) == 25_600 finally: await session.execute(delete(Provider).where(Provider.id == row.id)) await session.commit() # ---------------------------------------------------------------- 警告说的是实情 def _writer(nodes, omitted=()): from app.engine.evidence import WriterCatalog return WriterCatalog(text="", budget=51200, queries=sum(r["total"] for r in nodes), trimmed=True, nodes=nodes, omitted=list(omitted)) def _row(title, total, *, full=0, compact=0, omitted=0): return {"node_id": title, "title": title, "total": total, "full": full, "compact": compact, "omitted": omitted} def test_the_warning_names_omitted_queries_when_there_are_some(): from app.engine.nodes.report import _trimmed_message text = _trimmed_message(_writer([_row("会员专项", 26, full=26), _row("卡券核销", 79, full=20, omitted=59)], omitted=[f"Q{i}" for i in range(1, 60)])) assert "105 次查询中 46 次列出了数据,59 次只列编号和摘要(卡券核销省略 59 次)" in text assert "看不到这些查询的明细" in text def test_all_queries_listed_but_some_only_first_rows_is_not_called_omitted(): """放不下但查询全都列出,只是有的只列前几行:不写「0 次只列编号和摘要()」,写清是行数有省略。""" from app.engine.nodes.report import _trimmed_message writer = _writer([_row("会员专项", 26, full=26), _row("卡券核销", 79, full=30, compact=49)]) text = _trimmed_message(writer) assert writer.compact == 49 assert f"105 次查询都列出了数据,其中 49 次只列前 {writer.compact_rows} 行(卡券核销 49 次)" in text assert "看不到这些查询其余的行" in text assert "只列编号和摘要" not in text and "()" not in text def test_only_the_table_notes_were_cut(): from app.engine.nodes.report import _trimmed_message text = _trimmed_message(_writer([_row("会员专项", 26, full=26)])) assert "26 次查询都列出了数据,表和字段、知识库检索的说明有省略" in text and "()" not in text