报告里单元格的 ISO 日期时间显示成「2026-06-30 08:21:39」,只改显示

报告表格里的时间以前照快照原样显示成 2026-06-30T08:21:39,读起来费劲。[[v:]] 和 [[table:]] 渲染出来的 ISO 日期时间改成用空格隔开(小数秒、时区照留),写作目录和流式输出同一套写法。快照里的值、引用记下的 value、eid、证据下钻都不变。

复核按文档生成时的规则:老文档存的是带 T 的字,拿新规则重新渲染会对不上、被当成文档被改过。所以显示规则也记版本:新文档里真有日期时间被改写时在顶层记 cell_display: 2(参与内容哈希),没有被改写的文档和以前一字不差;没有这个字段的按 1 版(原样)复核,记了认不出的值报 bad_schema。出口复核、期 4 的金样(test_provenance_unchanged)都照旧通过;裁判摘录是给模型看的,不改
This commit is contained in:
ThearchyHelios
2026-10-04 11:33:09 +08:00
parent 799c80b97e
commit 470f8b6641
2 changed files with 165 additions and 13 deletions
+47 -13
View File
@@ -72,6 +72,15 @@ DOC_SCHEMA = "agentlab.report/1"
#: 和记下的状态对不上,会被当成文档被改过(state_mismatch)。
ENTITY_SYNTAX = 2
ENTITY_SYNTAXES = frozenset({1, 2})
#: 单元格显示规则的版本(文档顶层 cell_display):
#: - 1:照快照里的原样显示,ISO 日期时间带 T(2026-06-30T08:21:39)。没有这个字段的老文档按它复核
#: - 2:ISO 日期时间显示成「2026-06-30 08:21:39」(小数秒、时区照留)。只改显示:快照里的值、引用记下的 value、
#: eid、证据下钻都不变
#: 新组装的文档里真有日期时间被改写时才记 cell_display: 2(参与内容哈希),没有的文档和以前一字不差。复核必须按
#: 文档生成时的那一版:老文档存的是带 T 的字,拿新规则重新渲染对不上,会被当成文档被改过(render_mismatch)
CELL_DISPLAY = 2
CELL_DISPLAYS = frozenset({1, 2})
_ISO_DATETIME = re.compile(r"^(\d{4}-\d{2}-\d{2})T(\d{2}:\d{2}(?::\d{2}(?:\.\d+)?)?(?:Z|[+-]\d{2}:?\d{2})?)$")
# --------------------------------------------------------------------------
@@ -1273,7 +1282,8 @@ class _Snapshots:
compose / verify / 流式渲染里:出口复核是另一次调用,照样重新取、重新验。
"""
def __init__(self, loader: Loader | None = None, *, entities: bool = True, syntax: int | None = None) -> None:
def __init__(self, loader: Loader | None = None, *, entities: bool = True, syntax: int | None = None,
display: int | None = None) -> None:
self.loader = loader or load_artifact
self.memo: dict[str, tuple[Any, str | None]] = {}
self._index: tuple[dict[str, Any], _EntityIndex] | None = None
@@ -1281,6 +1291,17 @@ class _Snapshots:
self.entities_on = entities
#: 这一次解析按哪一版实体语法:组装、流式渲染用当前版,复核按文档记下的版本(verify_doc)
self.syntax = ENTITY_SYNTAX if syntax is None else syntax
#: 单元格按哪一版显示规则渲染(CELL_DISPLAY):组装、流式渲染用当前版,复核按文档记下的版本
self.display = CELL_DISPLAY if display is None else display
#: 这一次解析里有没有哪一格因为显示规则改了写法:组装时据此决定文档记不记 cell_display
self.reformatted = False
def shown(self, raw: Any) -> Any:
"""按显示规则要显示的原值:2 版起 ISO 日期时间的 T 换成空格。没改就是原值本身。"""
if self.display >= 2 and isinstance(raw, str) and (m := _ISO_DATETIME.match(raw.strip())):
self.reformatted = True
return f"{m.group(1)} {m.group(2)}"
return raw
def entities(self, catalog: dict[str, Any]) -> _EntityIndex:
if self._index is None or self._index[0] is not catalog:
@@ -1289,11 +1310,12 @@ class _Snapshots:
self._index = (catalog, _EntityIndex(shown, syntax=self.syntax))
return self._index[1]
def with_syntax(self, syntax: int) -> "_Snapshots":
"""换一版实体语法的同一次解析。取过的快照共用:快照内容和语法版本无关,不必再取、再验一遍。"""
if syntax == self.syntax:
def with_syntax(self, syntax: int, display: int | None = None) -> "_Snapshots":
"""换一版实体语法(和单元格显示规则)的同一次解析。取过的快照共用:快照内容和版本无关,不必再取、再验一遍。"""
display = self.display if display is None else display
if syntax == self.syntax and display == self.display:
return self
twin = _Snapshots(self.loader, entities=self.entities_on, syntax=syntax)
twin = _Snapshots(self.loader, entities=self.entities_on, syntax=syntax, display=display)
twin.memo = self.memo
return twin
@@ -1339,11 +1361,11 @@ class _Snapshots:
def _snapshots(loader: Loader | _Snapshots | None, *, entities: bool = True,
syntax: int | None = None) -> _Snapshots:
"""loader 已经是 _Snapshots 时沿用它(entities 不看);给了 syntax 就换成那一版。"""
syntax: int | None = None, display: int | None = None) -> _Snapshots:
"""loader 已经是 _Snapshots 时沿用它(entities 不看);给了 syntax、display 就换成那一版。"""
if isinstance(loader, _Snapshots):
return loader if syntax is None else loader.with_syntax(syntax)
return _Snapshots(loader, entities=entities, syntax=syntax)
return loader if syntax is None and display is None else loader.with_syntax(syntax or loader.syntax, display)
return _Snapshots(loader, entities=entities, syntax=syntax, display=display)
_CELL_REF = re.compile(r"^(?P<alias>[QK]\d+)\.r(?P<row>\d+)\.(?P<column>.+)$")
@@ -1393,7 +1415,7 @@ def _resolve_cell(marker: dict[str, Any], catalog: dict[str, Any], snaps: _Snaps
try:
raw, column = locate_cell(snapshot, parsed["row"], parsed["column"])
kind = column_kind(snapshot, column)
rendered = render_cell(raw, conv, kind=kind)
rendered = render_cell(snaps.shown(raw), conv, kind=kind)
except CellError as e:
return _unresolved(marker, alias, "cell", f"{alias} {e}")
except RenderError as e:
@@ -2630,8 +2652,10 @@ def compose_doc(
# entity_syntax:这份文档按哪一版实体语法组装,复核照它走(verify_doc)。在文档顶层,参与内容哈希
# provenance:期 4 的文档标记(P4-SPEC 1.4)。带它的文档才有查询步骤的提示字段、推断来源、裁判摘录的新行;
# 没有它的(期 4 之前组装的)一律按原样展示。写在顶层、参与内容哈希,事后补不上:补了哈希就变,封存链就断
# cell_display:有单元格因为显示规则改了写法(ISO 日期时间)才记,复核照它渲染;没有的文档和以前一字不差
doc: dict[str, Any] = {
"schema": DOC_SCHEMA, "entity_syntax": snaps.syntax, "provenance": DOC_PROVENANCE,
**({"cell_display": snaps.display} if snaps.reformatted and snaps.display != 1 else {}),
"run_id": run_id, "node_id": node_id,
"markdown": markdown, "source": source, "catalog": kept, "blocks": out_blocks,
}
@@ -2785,7 +2809,8 @@ def verify_doc(
有知识库检索时才有(它们才可能不是 0):升级前的运行统计的键和以前一模一样。
"""
entity_syntax = doc_entity_syntax(doc)
snaps = _snapshots(loader, entities=entities, syntax=entity_syntax or ENTITY_SYNTAX)
display = doc_cell_display(doc)
snaps = _snapshots(loader, entities=entities, syntax=entity_syntax or ENTITY_SYNTAX, display=display or CELL_DISPLAY)
index = snaps.entities(catalog)
violations: list[dict[str, Any]] = []
uncited: list[dict[str, Any]] = []
@@ -2803,6 +2828,8 @@ def verify_doc(
if entity_syntax is None:
violations.append(_violation("bad_schema",
f"报告文档记录的表名、字段名规则版本「{doc.get('entity_syntax')}」无法识别"))
if display is None:
violations.append(_violation("bad_schema", f"报告文档记录的单元格显示规则版本「{doc.get('cell_display')}」无法识别"))
markdown = str(doc.get("markdown") or "")
masks: list[tuple[int, int]] = [] # 引用渲染出来的字
@@ -2949,6 +2976,13 @@ def verify_doc(
return {"ok": not violations, "violations": violations, "stats": stats, "uncited": uncited}
def doc_cell_display(doc: Any) -> int | None:
"""文档按哪一版单元格显示规则组装:没有 cell_display 字段的是 1 版(老文档、没有日期时间被改写的文档),
记了认不出的值返回 None。"""
raw = doc.get("cell_display", 1) if isinstance(doc, dict) else 1
return raw if type(raw) is int and raw in CELL_DISPLAYS else None
def doc_entity_syntax(doc: Any) -> int | None:
"""文档按哪一版实体语法组装:没有 entity_syntax 字段的是老文档(1 版),记了认不出的值返回 None。"""
raw = doc.get("entity_syntax", 1) if isinstance(doc, dict) else 1
@@ -3182,7 +3216,7 @@ def _query_prompt(entry: dict[str, Any], snaps: _Snapshots, cells_allowed: bool,
try:
raw, _ = locate_cell(snapshot, r, c)
kind = column_kind(snapshot, c)
shown, numeric = render_cell(raw, kind=kind), is_number(cell_value(raw, kind))
shown, numeric = render_cell(snaps.shown(raw), kind=kind), is_number(cell_value(raw, kind))
except (CellError, RenderError):
shown, numeric = MISSING, False
cells.append(f"{c}={shown}")
@@ -3327,7 +3361,7 @@ def _field_prompt(path: str, value: Any, ev: dict[str, Any], aliases: dict[str,
if why:
raise CellError(why)
raw, column = locate_cell(snapshot, row, column)
shown = render_cell(raw, kind=column_kind(snapshot, column))
shown = render_cell(snaps.shown(raw), kind=column_kind(snapshot, column))
except (CellError, RenderError):
try:
shown = render_cell(value)
@@ -0,0 +1,118 @@
"""报告里单元格的 ISO 日期时间显示成「2026-06-30 08:21:39」,不再是「2026-06-30T08:21:39」。
只改显示:快照里的值、引用记下的 value、eid、证据下钻都不变。复核要按文档生成时的规则:老文档里存的是带 T 的字,
拿新规则重新渲染会对不上,被当成文档被改过(render_mismatch)——所以新文档在顶层记 cell_display: 2(只在真有日期
时间被改写时记,没有的文档和以前一字不差),没有这个字段的老文档按 1 版(原样)复核。期 4 的金样
(test_provenance_unchanged)照旧逐字不变。
夹具合成:门店、卡券。
"""
from __future__ import annotations
import pytest
from app.core.artifact_store import canonical_json
from app.engine import evidence as ev
from app.engine.evidence import (
CELL_DISPLAY,
StreamRenderer,
build_catalog,
cell_eid,
compose_doc,
doc_cell_display,
iter_segments,
verify_doc,
writer_catalog,
)
ART = "d" * 64
SNAP = {"columns": ["store_name", "redeemed_at", "biz_date", "amount", "note"],
"column_types": {"store_name": "text", "redeemed_at": "datetime", "biz_date": "date", "amount": "number",
"note": "text"},
"rows": [["门店01", "2026-06-30T08:21:39", "2026-06-30", 120, "T 开头的备注"],
["门店02", "2026-06-29T23:05:00.250000+08:00", "2026-06-29", 80, "2026-06-29T10:00:00Z"]],
"truncated": False}
STORE = {ART: SNAP}
def load(artifact):
return STORE.get(artifact)
@pytest.fixture
def catalog():
ledger = [{"kind": "query", "node_id": "fetch", "exec": 1, "artifact": ART, "tool": "db_query__shop",
"columns": SNAP["columns"], "rows": 2, "truncated": False}]
return build_catalog(nodes={}, ledger=ledger)
def cells(doc):
return [s for s in iter_segments(doc) if s.get("ref", "").startswith("v:")]
def test_iso_datetimes_read_with_a_space(catalog):
doc = compose_doc("最近一笔核销在 [[v:Q1.r0.redeemed_at]],门店 [[v:Q1.r0.store_name]]。[[see:Q1]]", catalog, loader=load)
[when, store] = cells(doc)
assert when["text"] == "2026-06-30 08:21:39" and "2026-06-30 08:21:39" in doc["markdown"]
# 只改显示:引用记下的值、证据标识照旧
assert when["cite"]["value"] == "2026-06-30T08:21:39"
assert when["cite"]["eid"] == cell_eid(ART, 0, "redeemed_at")
assert store["text"] == "门店01"
assert doc["cell_display"] == CELL_DISPLAY == 2 and doc_cell_display(doc) == 2
assert '"cell_display":2' in canonical_json(doc), "在文档顶层,参与内容哈希"
assert verify_doc(doc, catalog, loader=load)["ok"]
def test_fractions_and_offsets_are_kept_and_dates_are_untouched(catalog):
doc = compose_doc("时间 [[v:Q1.r1.redeemed_at]],日期 [[v:Q1.r1.biz_date]],备注 [[v:Q1.r1.note]]。", catalog,
loader=load)
assert [s["text"] for s in cells(doc)] == ["2026-06-29 23:05:00.250000+08:00", "2026-06-29", "2026-06-29 10:00:00Z"]
assert verify_doc(doc, catalog, loader=load)["ok"]
def test_tables_read_the_same_way(catalog):
doc = compose_doc("[[table:Q1 cols=store_name,redeemed_at]]", catalog, loader=load)
assert "| 门店01 | 2026-06-30 08:21:39 |" in doc["markdown"]
assert "T08:21:39" not in doc["markdown"]
assert verify_doc(doc, catalog, loader=load)["ok"]
def test_documents_without_datetimes_are_unchanged(catalog):
doc = compose_doc("门店 [[v:Q1.r0.store_name]],金额 [[v:Q1.r0.amount]]。", catalog, loader=load)
assert "cell_display" not in doc, "没有被改写的日期时间:文档和以前一字不差"
assert doc_cell_display(doc) == 1
def test_old_documents_still_verify_as_they_were(catalog, monkeypatch):
"""改动前组装的文档:存的是带 T 的字、没有 cell_display。按 1 版复核,不报 render_mismatch。"""
monkeypatch.setattr(ev, "CELL_DISPLAY", 1)
old = compose_doc("最近一笔核销在 [[v:Q1.r0.redeemed_at]]。", catalog, loader=load)
monkeypatch.undo()
assert "cell_display" not in old and "2026-06-30T08:21:39" in old["markdown"]
checked = verify_doc(old, catalog, loader=load)
assert checked["ok"], checked["violations"]
def test_a_document_edited_back_is_caught(catalog):
doc = compose_doc("最近一笔核销在 [[v:Q1.r0.redeemed_at]]。", catalog, loader=load)
[seg] = cells(doc)
start = seg["span"][0]
doc["markdown"] = doc["markdown"].replace("2026-06-30 08:21:39", "2026-06-30T08:21:39")
seg["text"] = "2026-06-30T08:21:39"
seg["span"] = [start, start + len(seg["text"])]
codes = {v["code"] for v in verify_doc(doc, catalog, loader=load)["violations"]}
assert "render_mismatch" in codes
def test_an_unknown_display_version_is_reported(catalog):
doc = compose_doc("最近一笔核销在 [[v:Q1.r0.redeemed_at]]。", catalog, loader=load)
doc["cell_display"] = 9
assert "bad_schema" in {v["code"] for v in verify_doc(doc, catalog, loader=load)["violations"]}
def test_the_writer_and_the_stream_see_what_the_report_will_show(catalog):
text = writer_catalog(catalog, loader=load).text
assert "redeemed_at=2026-06-30 08:21:39" in text and "T08:21:39" not in text
stream = StreamRenderer(catalog, loader=load)
shown = stream.feed("最近一笔在 [[v:Q1.r0.redeemed_at]]。") + stream.flush()
assert "2026-06-30 08:21:39" in shown