From 5f0b2359ac2eced796a2e51965039c35a4c50b7a Mon Sep 17 00:00:00 2001 From: ThearchyHelios Date: Wed, 4 Nov 2026 14:47:23 +0800 Subject: [PATCH] =?UTF-8?q?=E5=85=A5=E5=8F=A3=E5=8F=AA=E7=95=99=E6=AF=8F?= =?UTF-8?q?=E6=AC=A1=E9=83=BD=E4=BC=9A=E5=8F=98=E7=9A=84=E4=B8=9C=E8=A5=BF?= =?UTF-8?q?=EF=BC=8C=E5=9B=BA=E5=AE=9A=E6=9D=A1=E4=BB=B6=E5=86=99=E6=AD=BB?= =?UTF-8?q?=E5=9C=A8=20SQL=20=E9=87=8C?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 实测同一份文档：入口从 7 个（start/end/factory_code/object_id/line_code/gc_code/scx_code） 降到 2 个（start/end）。 提示词加了四条：同一维度只做一个入口（factory_code 和 gc_code 是同一件事）、编码和主键不当 必填入口、跨表编码在 SQL 里 JOIN 映射、可选维度写成空值不过滤；入口上限 4 个，超了照实报 出来但不悄悄删（删了 SQL 还引用着）。起草页多一栏「固定条件」：工厂、产线、属性组填这里， 写死在 SQL 里，不变成每次都要填的参数。 --- backend/app/api/ledger.py | 14 +++++-- backend/app/ledger/draftplan.py | 43 +++++++++++++++------ backend/tests/test_ledger_docdraft_api.py | 22 +++++++++++ backend/tests/test_ledger_draftplan.py | 18 +++++++++ frontend/src/api/caliberLedger.ts | 6 ++- frontend/src/lib/termsLedger.ts | 4 ++ frontend/src/pages/ledger/CaliberDrafts.tsx | 11 ++++++ 7 files changed, 102 insertions(+), 16 deletions(-) diff --git a/backend/app/api/ledger.py b/backend/app/api/ledger.py index a8ff99a5..116fd1e9 100644 --- a/backend/app/api/ledger.py +++ b/backend/app/api/ledger.py @@ -813,6 +813,7 @@ async def _extract_in_background(draft_id: str) -> None: datasource = {"name": source.name, "type": source.kind, "description": source.description} guidance = str(origin.get("guidance") or "") + fixed_filters = str(origin.get("fixed_filters") or "") alignment: dict[str, list[Any]] = {"new": [], "duplicate": [], "conflict": []} # 每组一组指标：{sql, entry_fields, metrics}，循环结束时拼成一张图 blocks: list[dict[str, Any]] = [] @@ -835,7 +836,8 @@ async def _extract_in_background(draft_id: str) -> None: try: for rnd in range(1, MAX_ROUNDS + 1): result = await draftplan.plan(session, docs=entries, chunks=chunks, guidance=guidance, - datasource=datasource, tables_text=tables_text, covered=covered) + datasource=datasource, tables_text=tables_text, covered=covered, + fixed=fixed_filters) plan, round_problems = draftplan.normalize_plan(result, chunks, allowed_tables=allowed_tables) fresh = _fresh_metrics(plan["metrics"], covered) if plan["sql"] and fresh: @@ -951,12 +953,17 @@ def _problems_text(problems: list[dict[str, Any]]) -> str: class DraftExtractIn(BaseModel): - """从哪几份文档起草、起草时给模型看的附加要求。数据源必须给：它的表结构和目录是 SQL 的唯一依据。""" + """从哪几份文档起草、起草时给模型看的附加要求。数据源必须给：它的表结构和目录是 SQL 的唯一依据。 + + fixed_filters 是「每次跑都不变的条件」（工厂、产线、属性组）：写死在 SQL 里，不做成入口字段。 + 入口只留「每次跑都可能不同」的东西（时间范围，最多再一个业务维度），否则每问一次数都要填一遍编码。 + """ documents: list[str] = Field(min_length=1, max_length=20) collection: str | None = Field(default=None, max_length=100) datasource_id: str | None = Field(default=None, max_length=32) guidance: str = Field(default="", max_length=2000) + fixed_filters: str = Field(default="", max_length=1000) @router.post("/drafts/extract", status_code=201) @@ -989,7 +996,8 @@ async def draft_extract(payload: DraftExtractIn, background: BackgroundTasks, draft = CaliberDraft(title=_doc_title(docs), collection=payload.collection or (docs[0].collection or "default"), datasource_id=payload.datasource_id or None, status="drafting", payload={}, - origin={"documents": doc_ids, "guidance": payload.guidance.strip()}, + origin={"documents": doc_ids, "guidance": payload.guidance.strip(), + "fixed_filters": payload.fixed_filters.strip()}, created_by=current_principal().username) session.add(draft) await session.commit() diff --git a/backend/app/ledger/draftplan.py b/backend/app/ledger/draftplan.py index 0016f975..6d9d628c 100644 --- a/backend/app/ledger/draftplan.py +++ b/backend/app/ledger/draftplan.py @@ -46,7 +46,10 @@ ENTRY_TYPES = ("string", "number", "integer", "boolean") #: 指标里固定出现的字段（顺序照接口契约） METRIC_FIELDS = ("id", "name", "synonyms", "unit", "decimals", "expression", "definition", "open_questions") -#: SQL 模板里的入口占位符：{{ input.x }}（引号内外都认） +#: 入口字段最多几个（时间范围占两个）。再多说明把「每次都不变」的条件也做成了参数， +#: 人每跑一次都要填一遍，口径就没法用了 +MAX_ENTRY_FIELDS = 4 +#: 输入里能出现的入口占位符：{{ input.x }}（引号内外都认） _INPUT = re.compile(r"\{\{\s*input\.([A-Za-z_][\w-]*)\s*\}\}") #: 口径卡的取值表达式，列名可以用单引号或双引号 _EXPRESSION = re.compile(r"^cell\(\s*nodes\.fetch\s*,\s*0\s*,\s*['\"]([^'\"]+)['\"]\s*\)$") @@ -73,6 +76,15 @@ _SYSTEM = """你是业务口径与取数模板的起草助手。读给定的业 8. **sql 要短。** 能用 GROUP BY 和聚合表达的，不要为每个属性枚举一长串 CASE WHEN 列；输出额度有限，SQL 写长了， 后面的指标就写不出来了。 9. 写不下时宁可少写几条指标、把剩下的写进 uncovered，**也不要让 JSON 半截断掉**。 +10. **同一件事只做一个入口。** 工厂、产线这类维度全图只给一个字段，不要为不同的表各造一个 + （factory_code / gc_code / scx_code 说的是同一件事）；跨表的编码差异在 sql 里用 JOIN 或子查询映射， + 不要让填参数的人重复填等价编码。 +11. **编码和主键不当必填入口。** object_id、line_code 这类字段只有业务上确实每次按它跑时才做入口， + 而且必须是可选（留空不过滤）；人填不出来才能跑的入口，等于这份口径跑不了。 +12. **可选维度要写成「空值不过滤」**：`AND ('{{ input.line_code }}' = '' OR t.line_code = '{{ input.line_code }}')`。 + 不这么写，留空会把结果筛成空。 +13. **入口最多 4 个**，时间范围占两个。再多就把不常变的条件写死在 sql 里（见第 14 条）。 +14. **不常变的条件写进 sql，不做入口**：固定筛选段里给出的取值（工厂、产线、属性组、状态）直接写成常量。 输出格式： { @@ -135,7 +147,7 @@ def _chunk_block(chunk_id: str, chunk: Any) -> str: def _human(docs: list[dict], chunks: Mapping[str, dict], guidance: str, datasource: dict | None, - tables_text: str, covered: Sequence[str] = ()) -> str: + tables_text: str, covered: Sequence[str] = (), fixed: str = "") -> str: parts = ["文档清单：", *(_doc_line(doc) for doc in docs), "", "逐段原文（引用时 chunk 写方括号里的 id，quote 逐字抄）："] parts.extend(_chunk_block(chunk_id, chunks[chunk_id]) for chunk_id in _order(chunks)) @@ -151,17 +163,20 @@ def _human(docs: list[dict], chunks: Mapping[str, dict], guidance: str, datasour names = [name.strip() for name in covered if isinstance(name, str) and name.strip()] parts.append("、".join(names) if names else "（无）") parts.append("") + parts.append("固定条件（这些写死在 sql 里，**不要**做成入口字段）：{}".format( + fixed.strip() if fixed and fixed.strip() else "（无）")) + parts.append("") parts.append("用户补充要求：{}".format(guidance.strip() if guidance and guidance.strip() else "（无）")) return "\n".join(parts) def prompt(docs: list[dict], chunks: dict[str, dict], guidance: str = "", datasource: dict | None = None, - tables_text: str = "", covered: Sequence[str] = ()) -> list[Any]: - """构造 system + human：文档原文 + 数据目录 + 已经起草过的指标。目录是 sql 的唯一依据，和原文一样原样交给模型。""" + tables_text: str = "", covered: Sequence[str] = (), fixed: str = "") -> list[Any]: + """构造 system + human：文档原文 + 数据目录 + 已经起草过的指标 + 固定条件。目录是 sql 的唯一依据。""" from langchain_core.messages import HumanMessage, SystemMessage return [SystemMessage(content=_SYSTEM), - HumanMessage(content=_human(docs, chunks, guidance, datasource, tables_text, covered))] + HumanMessage(content=_human(docs, chunks, guidance, datasource, tables_text, covered, fixed))] def _chars(messages: list[Any]) -> int: @@ -170,7 +185,7 @@ def _chars(messages: list[Any]) -> int: def _fit(docs: list[dict], chunks: dict[str, dict], guidance: str, datasource: dict | None, tables_text: str, - covered: Sequence[str] = ()) -> tuple[dict[str, dict], str, bool, bool]: + covered: Sequence[str] = (), fixed: str = "") -> tuple[dict[str, dict], str, bool, bool]: """把材料压到 MAX_INPUT_CHARS 以内：先截表目录尾部，再从后往前按 chunk 边界丢，最后截仅剩的那一段。 表目录先截：SQL 必须写在目录里的表上，目录比文档的细枝末节更硬；被截掉的是表详情，表名索引还在最前面。 @@ -187,7 +202,7 @@ def _fit(docs: list[dict], chunks: dict[str, dict], guidance: str, catalog_truncated = True def size() -> int: - return _chars(prompt(docs, kept, guidance, datasource, tables, covered)) + return _chars(prompt(docs, kept, guidance, datasource, tables, covered, fixed)) order = _order(kept) while size() > MAX_INPUT_CHARS and len(order) > 1: @@ -243,11 +258,12 @@ def _salvage_reply(text: str) -> dict: async def plan(session: Any, *, docs: list[dict], chunks: dict[str, dict], guidance: str = "", datasource: dict | None = None, tables_text: str = "", model: Any = None, - covered: Sequence[str] = ()) -> dict: + covered: Sequence[str] = (), fixed: str = "") -> dict: """一次模型调用，返回 {entry_fields, sql, metrics, open_questions, model_id, doc_truncated, catalog_truncated, truncated}（未校验）。 - covered 是前几轮已经起草过的指标名，写进提示词让模型不要重复；调用方按 uncovered 续跑，直到 covered 不再增长。 + covered 是前几轮已经起草过的指标名，写进提示词让模型不要重复；fixed 是「每次都不变的条件」（工厂、产线、 + 属性组），提示词要求它写死在 sql 里、不做成入口字段。调用方按 uncovered 续跑，直到 covered 不再增长。 truncated 仍是两者的「或」，老前端只认这一个键。不落库。model 可注入（测试用假对象：有 async ainvoke(messages)， 回复有 .content）；不给就按设置解析，模型不可用时抛 docdraft.DraftUnavailable。SQL 的对错、引用能不能核对，交给 normalize_plan。 @@ -265,8 +281,8 @@ async def plan(session: Any, *, docs: list[dict], chunks: dict[str, dict], guida model_id = named if isinstance(named, str) else "" kept, tables, doc_truncated, catalog_truncated = _fit(docs, chunks, guidance, datasource, tables_text, - covered) - reply = await model.ainvoke(prompt(docs, kept, guidance, datasource, tables, covered)) + covered, fixed) + reply = await model.ainvoke(prompt(docs, kept, guidance, datasource, tables, covered, fixed)) text = message_text(reply) salvaged = False try: @@ -435,6 +451,11 @@ def normalize_plan(raw: Any, chunks: Mapping[str, dict], *, allowed_tables: set[ body = raw if isinstance(raw, Mapping) else {} problems: list[dict] = [] entry_fields = _entry_fields(body.get("entry_fields"), problems) + if len(entry_fields) > MAX_ENTRY_FIELDS: + # 不自动删：入口删了 SQL 还引用着，跑不通。照实说清楚，让人把不常变的条件写成固定条件重起一份 + problems.append({"name": "入口字段", + "reason": f"入口有 {len(entry_fields)} 个（上限 {MAX_ENTRY_FIELDS}）：同一维度只该有一个，" + f"不常变的条件应当写死在 sql 里（用「固定条件」重起一份）"}) sql = body.get("sql") sql_text = sql.strip() if isinstance(sql, str) else "" diff --git a/backend/tests/test_ledger_docdraft_api.py b/backend/tests/test_ledger_docdraft_api.py index 80113427..85292c83 100644 --- a/backend/tests/test_ledger_docdraft_api.py +++ b/backend/tests/test_ledger_docdraft_api.py @@ -736,3 +736,25 @@ async def test_running_the_trial_with_inputs_typed_on_the_page(client, documents res = await client.post(f"/api/ledger/drafts/{body['draft_id']}/trial", json={"inputs": {"start": "2026-01-01"}}) assert res.status_code == 200, res.text assert seen["start"] == "2026-01-01" + + +async def test_extract_hands_the_fixed_filters_to_every_round(client, documents, datasource, monkeypatch): + """固定条件（工厂、产线、属性组）要交给模型写死在 SQL 里，不做成入口字段。""" + from app.ledger import draftplan + + doc = await documents("dd-fixed") + source_id = await datasource() + fake_model(monkeypatch, plan_reply(f"{doc}-2")) + seen: dict[str, object] = {} + real_plan = draftplan.plan + + async def spy(session, **kwargs): + seen.update(kwargs) + return await real_plan(session, **kwargs) + + monkeypatch.setattr(draftplan, "plan", spy) + body = await client.post("/api/ledger/drafts/extract", json={ + "documents": [doc], "datasource_id": source_id, "fixed_filters": "line_code = 'FOAM01'"}) + made = (await client.get(f"/api/ledger/drafts/{body.json()['draft_id']}")).json() + assert made["workflow_id"] + assert seen["fixed"] == "line_code = 'FOAM01'" diff --git a/backend/tests/test_ledger_draftplan.py b/backend/tests/test_ledger_draftplan.py index ecb01e3e..dee6f7b0 100644 --- a/backend/tests/test_ledger_draftplan.py +++ b/backend/tests/test_ledger_draftplan.py @@ -346,3 +346,21 @@ async def test_plan_reports_document_and_catalog_truncation_separately(): assert result["doc_truncated"] is False assert result["catalog_truncated"] is False assert result["truncated"] is False + + +async def test_plan_tells_the_model_which_conditions_are_fixed(): + """固定条件要原样交到模型手里，并明确说「写死在 SQL 里、不要做成入口」。""" + model = FakeModel(json.dumps(raw(), ensure_ascii=False)) + await draftplan.plan(None, docs=[], chunks={}, model=model, fixed="line_code = 'FOAM01'") + human = model.messages[-1].content + assert "固定条件" in human and "FOAM01" in human + assert "不要" in human and "入口" in human + + +def test_too_many_entry_fields_is_reported_not_silently_trimmed(): + """入口超过 4 个说明把不常变的条件也做成了参数：照实报出来，但不悄悄删（删了 SQL 还引用着）。""" + fields = [{"name": "start", "type": "string", "required": True, "default": "2026-09-01"}] + fields += [{"name": f"dim{i}", "type": "string", "required": False} for i in range(4)] + plan, problems = draftplan.normalize_plan(raw(entry_fields=fields), CHUNKS, allowed_tables={"orders"}) + assert len(plan["entry_fields"]) == 5 + assert any(p["name"] == "入口字段" and "上限" in p["reason"] for p in problems) diff --git a/frontend/src/api/caliberLedger.ts b/frontend/src/api/caliberLedger.ts index 85c3643e..391831fb 100644 --- a/frontend/src/api/caliberLedger.ts +++ b/frontend/src/api/caliberLedger.ts @@ -64,8 +64,10 @@ export const caliberLedger = { */ runDraftTrial: (draftId: string, inputs: Record) => post(`${draftAt(draftId)}/trial`, { inputs }), - /** 选文档发起起草：documents 是要用的知识库文档 id，guidance 是给模型看的附加要求 */ - extractDraft: (body: { documents: string[]; collection?: string; datasource_id?: string; guidance?: string }) => + /** 选文档发起起草：documents 是要用的知识库文档 id，guidance 是给模型看的附加要求， + * fixed_filters 是每次跑都不变的条件（工厂、产线、属性组），服务端要求写死在 SQL 里、不做成入口字段 */ + extractDraft: (body: { documents: string[]; collection?: string; datasource_id?: string; guidance?: string; + fixed_filters?: string }) => post<{ draft_id: string; status: string }>('/ledger/drafts/extract', body), /** * 改标题、整体换掉指标、或把答清的问题消掉（resolved 是问题原文）。服务端据此重算状态：还有问题 → questions_open， diff --git a/frontend/src/lib/termsLedger.ts b/frontend/src/lib/termsLedger.ts index 1ba980b3..fd079826 100644 --- a/frontend/src/lib/termsLedger.ts +++ b/frontend/src/lib/termsLedger.ts @@ -269,6 +269,10 @@ export const LEDGER_UI = { datasourceHint: '取数 SQL 对照这个库的真实表和列写，先探查过表结构才能起草', guidance: '起草要求（可选）', guidancePlaceholder: '例如：只整理和月度结算有关的指标', + fixedFilters: '固定条件（可选）', + fixedFiltersHint: '每次运行都不变的条件写死在 SQL 里，不变成入口字段：工厂、产线、属性组这类编码都放这里。' + + '入口只留时间范围，最多再一个业务维度', + fixedFiltersPlaceholder: "例如：line_code = 'FOAM01'、attribute_group = 'OEE'", submit: '开始起草', submitting: '正在发起…', needDoc: '请至少选一份文档', diff --git a/frontend/src/pages/ledger/CaliberDrafts.tsx b/frontend/src/pages/ledger/CaliberDrafts.tsx index 8df94b12..db793035 100644 --- a/frontend/src/pages/ledger/CaliberDrafts.tsx +++ b/frontend/src/pages/ledger/CaliberDrafts.tsx @@ -188,6 +188,8 @@ export function CaliberDrafts() { const [pickedDocs, setPickedDocs] = useState([]) const [datasourceId, setDatasourceId] = useState('') const [guidance, setGuidance] = useState('') + /** 每次跑都不变的条件（工厂、产线、属性组）：要求写死在 SQL 里，不做成入口字段 */ + const [fixedFilters, setFixedFilters] = useState('') const [submitting, setSubmitting] = useState(false) const [pickedQuestions, setPickedQuestions] = useState([]) @@ -404,10 +406,12 @@ export function CaliberDrafts() { documents: pickedDocs, ...(datasourceId ? { datasource_id: datasourceId } : {}), ...(guidance.trim() ? { guidance: guidance.trim() } : {}), + ...(fixedFilters.trim() ? { fixed_filters: fixedFilters.trim() } : {}), }) toast.ok(D.started) setPickedDocs([]) setGuidance('') + setFixedFilters('') setDatasourceId('') setFilter('') loadList() @@ -978,6 +982,13 @@ export function CaliberDrafts() {