fix(shapes): weak stamps elect no canon; the arrival line names the review; Svelte scopes by default (#4608)
CI & Build / Python lint (push) Successful in 8s
CI & Build / Plugin hooks (push) Successful in 16s
CI & Build / TypeScript typecheck (push) Successful in 54s
CI & Build / integration (push) Successful in 1m3s
CI & Build / Python tests (push) Successful in 1m44s
CI & Build / Build & push image (push) Successful in 1m5s

Librarian and Stash had 132 and 488 write-path stamps written at 0.68-0.72,
before the 0.80 floor (#4204). Nothing re-judged them, and dominant_canon
counted them, so a YAML CI snippet (#3410) "dominated" Librarian's web
directory and every write there was told it diverged from it — 1408 flags
on one project, 902 on the other, all skimmed past.

- is_weak_stamp: one predicate for "hook-stamped below today's floor".
  dominant_canon and canon_form skip such rows; stamps_to_review lists them
  by the same predicate. No stored row changes — they stay for judgment.
- flag_divergence withdraws a standing flag whose canon no longer dominates
  its directory. A flag is a mechanical prompt, not a judgment.
- The coverage line ends "N weak stamps · M incoherent canons to judge —
  stamps_to_review" when either is nonzero, so a project's own session sees
  the queue on arrival. The shape-accounting skill says what to do with it.
- scoped_definitions handles .svelte: every <style> is component-scoped
  unless <style global> or :global(...); instance-script syms are scoped,
  module-script ones stay ordinary.

Plugin version minted for the skill change.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-09-30 23:27:07 -04:00
co-authored by Claude Opus 5.5
parent 3270fe90c1
commit eb5cc6d3a7
7 changed files with 291 additions and 12 deletions
+78
View File
@@ -889,6 +889,84 @@ async def test_a_second_confirm_dialog_is_detected_and_named(seeded):
assert total == 0
@pytest.mark.integration
async def test_weak_stamps_elect_no_canon_and_their_flags_are_withdrawn(seeded):
"""#4608, the poisoned-ledger case as it stood on two projects: a
directory's "dominant canon" was elected entirely by hook stamps written
at 0.68-0.72, before the 0.80 floor, so every new shape there was told it
diverged from a YAML CI snippet. The same fixture as the acceptance case
above, with one difference — the four instances are weak hook stamps
rather than an audit — and the prompt must fall silent: at refresh (the
standing flag is withdrawn) and at write time. The stamps themselves are
left exactly as they were, for `stamps_to_review` to put before a judge."""
from datetime import datetime, timedelta, timezone
from sqlalchemy import update
from scribe.services import snippets as snippets_svc
from scribe.services.shape_ledger import (
_RESEMBLE_REASON, flag_divergence, propose_for_repo, write_time_divergence,
)
owner, pid = seeded["owner"], seeded["pid"]
canon = await snippets_svc.create_snippet(
owner, name="cls_confirm_factory",
code="export async function factory(): Promise<boolean> {\n return true;\n}\n",
language="typescript", repo="Widget",
path="frontend/src/composables/useConfirm.ts", symbol="factory",
project_id=pid,
)
sid = int(canon.id)
comp = "frontend/src/components"
names = ("Trash", "Delete", "Remove", "Restore")
base = _defs(
*[(f"{comp}/{n}.vue", "sym", f"on{n}", f"async function on{n}() {{",
f"async function on{n}() {{\n const ok = await factory();\n if (!ok) return;\n}}")
for n in names],
)
await sync_repo_shapes(pid, REPO, base, seen_marker="aaa111")
await classify_shapes(owner, pid, [
{"path": f"{comp}/{n}.vue", "symbol": f"on{n}", "status": "instance", "snippet_id": sid}
for n in names
], via="audit")
previous = datetime.now(timezone.utc)
later = base + _defs(
(f"{comp}/Danger.vue", "sym", "confirmDanger", "function confirmDanger() {",
"function confirmDanger() {\n return window.confirm('Really?');\n}"),
)
await sync_repo_shapes(pid, REPO, later, seen_marker="bbb222")
with _quiet_semantic():
await propose_for_repo(owner, pid, REPO, later)
since = previous - timedelta(seconds=1)
# Judged by an audit, the canon dominates and the new shape is flagged.
assert await flag_divergence(pid, since=since) == 1
# Now make the four what the poisoned ledgers held: unattended stamps
# below today's floor.
weak = _RESEMBLE_REASON.format(sid=sid, score=0.72)
async with async_session() as session:
await session.execute(
update(CodeShape)
.where(CodeShape.project_id == pid, CodeShape.snippet_id == sid)
.values(classified_by="hook", reason=weak)
)
await session.commit()
assert await flag_divergence(pid, since=since) == 0
rows, total = await list_project_shapes(owner, pid, flag="divergence")
assert total == 0, "a flag whose canon no longer dominates is withdrawn"
assert await write_time_divergence(
pid, f"{comp}/Danger.vue", [("sym", "confirmDanger")], stamped=[]
) == []
# Nothing was un-judged: the stamps stand until someone reads them.
async with async_session() as session:
kept = (await session.execute(
select(CodeShape).where(CodeShape.project_id == pid, CodeShape.snippet_id == sid)
)).scalars().all()
assert len(kept) == 4
assert all(r.status == "instance" and r.classified_by == "hook" for r in kept)
@pytest.mark.integration
async def test_a_semantic_miss_does_not_silence_the_prompt(seeded):
"""#4208, reversed on measurement: a semantic miss is not evidence.
+43
View File
@@ -823,6 +823,49 @@ def test_scoped_definitions_are_vue_script_setup_and_scoped_style_only():
assert scoped_definitions("src/a.py", "def load():\n pass\n", extract_definitions("def load():\n pass\n")) == set()
def test_svelte_scopes_by_default_and_its_module_script_stays_importable():
"""#4608: Svelte scopes the other way round from Vue — every <style> is
the component's own unless it opts out, and only <script module> /
<script context="module"> can be imported elsewhere. Without this a
Svelte project's every `.card` and `.title` sat in the human todo."""
from scribe.services.coverage import extract_definitions, scoped_definitions
svelte = (
"<script module lang=\"ts\">\n"
"export function stageOf(x: number) {\n return x;\n}\n"
"</script>\n\n"
"<script lang=\"ts\">\n"
"function toggle() {\n open = !open;\n}\n"
"</script>\n\n"
"<div class=\"card\"></div>\n\n"
"<style>\n.card {\n padding: 1rem;\n}\n:global(.toast) {\n color: red;\n}\n</style>\n"
)
defs = extract_definitions(svelte)
names = {(d.kind, d.name) for d in defs}
assert {("sym", "stageOf"), ("sym", "toggle"), ("css", "card")} <= names
scoped = scoped_definitions("web/src/lib/A.svelte", svelte, defs)
assert ("sym", "toggle") in scoped and ("css", "card") in scoped
assert ("sym", "stageOf") not in scoped, "a module script's export is importable"
assert not any(n == "toast" for _, n in scoped), ":global(...) opts a selector out"
# The legacy spelling of the module block, and a whole global style block.
legacy = (
"<script context=\"module\">\nexport function shared() {\n return 1;\n}\n</script>\n"
"<style global>\n.page {\n margin: 0;\n}\n</style>\n"
)
assert scoped_definitions("web/src/lib/B.svelte", legacy, extract_definitions(legacy)) == set()
def test_the_line_names_the_review_queue_and_the_tool_that_holds_it():
"""#4608: `stamps_to_review` existed and two projects never called it,
because nothing on arrival said there was anything to review."""
from scribe.services.coverage import coverage_line
base = {"accounted": 10, "total": 10, "counts": {"exempt": 10},
"unclassified": 0, "computed_at": "2026-09-30T00:00:00"}
assert "stamps_to_review" not in coverage_line(base)
line = coverage_line({**base, "weak_stamps": 132, "incoherent_canons": 3})
assert line.endswith("; 132 weak stamps · 3 incoherent canons to judge — stamps_to_review")
assert coverage_line({**base, "weak_stamps": 1}).endswith("; 1 weak stamp to judge — stamps_to_review")
@pytest.mark.integration
async def test_binding_ref_is_the_branch_the_ledger_follows(seeded):
"""#2873: a binding that names a ref is read at that ref (not the forge's
+50
View File
@@ -350,3 +350,53 @@ def test_the_coherence_verdict_reads_rows_and_writes_nothing() -> None:
canon_coherence(rows)
assert [(r.path, r.symbol, r.status, r.snippet_id, r.signature)
for r in rows] == before
# ── a weak stamp is listed for judgment and counted by nobody (#4608) ─────
#
# The floor guarded new writes; the rows written before it went on electing
# canons. On two projects a YAML CI snippet "dominated" a Svelte directory on
# the strength of 0.68-0.72 stamps, and every write there was told it
# diverged from it. The readers below must agree with the review surface
# about what "weak" means — one predicate, so they cannot drift apart.
def test_one_predicate_says_what_weak_is() -> None:
from scribe.services.shape_ledger import is_weak_stamp
assert is_weak_stamp(_stamped(0.72))
assert not is_weak_stamp(_stamped(_RESEMBLE_MIN))
# A by-name stamp carries no score: it is not resemblance evidence at all.
assert not is_weak_stamp(_Row(reason="hook: pulled #1; payload references `f`"))
for by in ("agent", "audit", "mechanical"):
assert not is_weak_stamp(_stamped(0.5, classified_by=by)), by
def test_weak_stamps_do_not_elect_a_dominant_canon() -> None:
from scribe.services.shape_ledger import dominant_canon
weak = [_stamped(0.72, path=f"web/src/lib/{i}.ts", symbol=f"f{i}") for i in range(5)]
assert dominant_canon(weak) is None
# The same rows judged by an agent do — the kind of evidence is the point.
judged = [_stamped(0.72, path=f"web/src/lib/{i}.ts", symbol=f"f{i}", classified_by="agent")
for i in range(5)]
assert dominant_canon(judged) == (1, 5, 5)
# And weak rows do not dilute a real majority either: they are not counted
# as judged at all.
mixed = judged[:3] + [_stamped(0.7, snippet_id=2, symbol=f"g{i}") for i in range(4)]
assert dominant_canon(mixed) == (1, 3, 3)
def test_weak_stamps_do_not_say_what_form_a_canon_is() -> None:
from scribe.services.shape_ledger import FORM_UNKNOWN, canon_form
weak = [_stamped(0.7, symbol=f"T{i}", signature=f"class T{i}:") for i in range(5)]
assert canon_form(weak, 1) == FORM_UNKNOWN
judged = [_stamped(0.7, symbol=f"T{i}", signature=f"class T{i}:", classified_by="audit")
for i in range(5)]
assert canon_form(judged + weak, 1) == canon_form(judged, 1) != FORM_UNKNOWN
def test_counting_them_out_leaves_them_listed() -> None:
"""Not counted is not withdrawn: the review still lists every one."""
rows = [_stamped(0.7, symbol=f"f{i}") for i in range(3)]
assert stamps_to_review(rows)["weak_count"] == 3