feat(ledger): mechanical proposer — every refresh proposes instances against canon and groups derive-first candidates; agents confirm in batches (#2792, milestone 294 step 6)

Shapes now carry a content fingerprint (signature + whitespace/comment-
insensitive body_sha; migration 0080) and the proposer runs inside the
coverage refresh, the one moment bodies exist: symbol elsewhere → textual
containment → body references the canon → signature resemblance → semantic
(capped per refresh, unreached rows stay unexamined for the next). A hit is
a proposal on the row (proposed_snippet_id/basis/score), never a
classification; rows with no canon hit group by the derive-first rule
(identical body in ≥2 places, same name in ≥3 files) as proposal_basis=
derive + a group key. list_shapes(proposal=any|canon|derive|<basis>) is the
queue; confirm_shape_proposals(project_id, snippet_id|path|basis) confirms
in batches as agent instances; any classify_shapes/hook stamp retires the
proposal. Readout carries proposed + derive_groups (line, payload, card).
Plugin 0.1.35 (skill: the machine proposes, judgment classifies).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

tests/test_shape_ledger.py

@@ -5,6 +5,8 @@ token-free serialisation. The sync pass (step 2) and the classification
 surface (step 3) grow their tests here; DB-backed behavior lands in the
 integration lane once there is behavior to exercise.
 """
+import pytest
+
 from scribe.models import Base
 from scribe.models.code_shape import SHAPE_CLASSIFIERS, SHAPE_STATUSES, CodeShape
 
@@ -135,3 +137,142 @@ def test_hook_is_a_server_internal_classifier():
 
     assert "hook" in SHAPE_CLASSIFIERS
     assert "hook" not in _CALLER_VIAS
+
+
+# --- step 6: the mechanical proposer (pure) ---------------------------------
+
+
+def test_proposal_columns_and_vocabulary_are_pinned():
+    """Fingerprints + the proposer's standing suggestion live on the row; the
+    basis vocabulary is fixed, with `derive` the odd one out (a group, not a
+    snippet)."""
+    from scribe.models.code_shape import PROPOSAL_BASES
+
+    cols = CodeShape.__table__.c
+    for name in ("signature", "body_sha", "proposed_snippet_id", "proposal_basis",
+                 "proposal_score", "proposal_group", "proposed_at", "proposed_sha"):
+        assert name in cols, name
+    fk = next(iter(cols.proposed_snippet_id.foreign_keys))
+    assert fk.ondelete == "SET NULL" and fk.column.table.name == "notes"
+    assert "ix_code_shapes_proposed" in {ix.name for ix in CodeShape.__table__.indexes}
+    assert PROPOSAL_BASES == ("symbol", "text", "reference", "signature", "semantic", "derive")
+
+
+def test_row_proposal_property_is_one_object_or_none():
+    row = CodeShape(project_id=1, repo_key="r", path="a.py", symbol="f", kind="sym")
+    assert row.proposal is None
+    row.proposed_snippet_id, row.proposal_basis, row.proposal_score = 9, "symbol", 1.0
+    assert row.proposal == {"basis": "symbol", "score": 1.0, "snippet_id": 9}
+    row.proposed_snippet_id = None
+    row.proposal_basis, row.proposal_group, row.proposal_score = "derive", "dup:abc", 3.0
+    assert row.proposal == {"basis": "derive", "score": 3.0, "group": "dup:abc"}
+
+
+def test_signature_similarity_blanks_the_names():
+    from scribe.services.shape_ledger import signature_similarity as sim
+
+    a = "def move_event(project_id: int, event_id: int, after_id: int | None):"
+    b = "def move_beat(project_id: int, beat_id: int, after_id: int | None):"
+    assert sim(a, "move_event", b, "move_beat") > 0.85
+    assert sim(a, "move_event", "def export_pdf(manuscript, design, fonts):", "export_pdf") < 0.6
+    assert sim("", "x", b, "move_beat") == 0.0
+    # Trivial signatures resemble everything and mean nothing — floored out.
+    assert sim("def helper(x):", "helper", "def make_app():", "make_app") == 0.0
+
+
+def test_text_containment_is_whitespace_insensitive_with_a_floor():
+    from scribe.services.shape_ledger import text_contains
+
+    code = "const ok = await confirmed({ title: 'Delete?', confirmLabel: 'Delete' });\nif (!ok) return;"
+    body = "async function onDelete() {\n  const ok = await confirmed({\n    title: 'Delete?',\n    confirmLabel: 'Delete'\n  });\n  if (!ok) return;\n}"
+    assert text_contains(body, code)
+    assert text_contains(code, body)
+    assert not text_contains("x = 1", "x = 1")          # below the substance floor
+
+
+def _canon(sid, kind="sym", symbol="", locations=(), signature="", code=""):
+    from scribe.services.shape_ledger import Canon, _norm_text
+    return Canon(sid, kind, symbol, tuple(locations), signature, _norm_text(code))
+
+
+def test_match_canon_orders_bases_strongest_first_and_respects_kind():
+    from scribe.services.shape_ledger import match_canon
+
+    confirmed = _canon(
+        7, "sym", "confirmed", [("frontend/src/composables/useConfirm.ts", "confirmed")],
+        "export async function confirmed(opts: ConfirmOptions): Promise<boolean> {",
+        "export async function confirmed(opts: ConfirmOptions): Promise<boolean> { /* singleton */ }",
+    )
+    mover = _canon(
+        8, "sym", "move_beat", [("src/forge/plot.py", "move_beat")],
+        "def move_beat(project_id: int, beat_id: int, after_id: int | None) -> None:",
+    )
+    btn = _canon(9, "css", ".btn-primary", [("web/buttons.css", ".btn-primary")],
+                 ".btn-primary {", ".btn-primary { color: var(--action-primary); padding: 4px 8px; border-radius: 4px; }")
+    canons = [confirmed, mover, btn]
+
+    # symbol: a second `confirmed` defined elsewhere answers to #7 — but the
+    # canon's own location never does (that row is canonical, not a proposal).
+    assert match_canon("sym", "src/other.ts", "confirmed", "function confirmed() {", "", canons) == (7, "symbol", 1.0)
+    assert match_canon("sym", "frontend/src/composables/useConfirm.ts", "confirmed",
+                       "export async function confirmed(", "", canons) is None
+    # reference: a call site of the canon.
+    body = "async function onTrash() {\n  const ok = await confirmed({ title: 'x' });\n  if (!ok) return;\n}"
+    assert match_canon("sym", "c.vue", "onTrash", "async function onTrash() {", body, canons) == (7, "reference", 0.9)
+    # signature: the family shape, names blanked.
+    hit = match_canon("sym", "src/forge/timeline.py", "move_event",
+                      "def move_event(project_id: int, event_id: int, after_id: int | None) -> None:",
+                      "    pass", canons)
+    assert hit and hit[0] == 8 and hit[1] == "signature" and hit[2] >= 0.8
+    # text: the canon's code contains the shape's body (a css copy), kind-matched —
+    # the same text as a `sym` shape matches no css canon.
+    css_body = ".btn-primary { color: var(--action-primary); padding: 4px 8px; border-radius: 4px; }"
+    assert match_canon("css", "web/other.css", "btn-big", ".btn-big {", css_body, canons) == (9, "text", 0.95)
+    assert match_canon("sym", "web/other.css", "btn-big", ".btn-big {", css_body, canons) is None
+    # nothing in play
+    assert match_canon("sym", "x.py", "unrelated", "def unrelated(a, b, c, d, e):", "return 1", canons) is None
+
+
+def test_match_canon_symbol_beats_everything_including_css_copies():
+    """The previous test's css `btn-primary`-elsewhere case, stated plainly:
+    a second definition of the canon's own name is the symbol basis."""
+    from scribe.services.shape_ledger import match_canon
+    btn = _canon(9, "css", ".btn-primary", [("web/buttons.css", ".btn-primary")], ".btn-primary {", ".btn-primary { color: red; padding: 4px 8px; border-radius: 4px; }")
+    assert match_canon("css", "web/other.css", "btn-primary", ".btn-primary {", ".btn-primary { color: blue }", [btn]) == (9, "symbol", 1.0)
+
+
+def test_derive_groups_copy_before_name_with_floors():
+    from scribe.services.shape_ledger import derive_groups
+
+    rows = [
+        ("a.py", "sym", "helper", "sha1"), ("b.py", "sym", "helper", "sha1"),   # identical copies
+        ("c.py", "sym", "helper", "sha9"),                                        # same name, 3rd file
+        ("d.css", "css", "btn", "s1"), ("e.css", "css", "btn", "s2"), ("f.css", "css", "btn", "s3"),
+        ("g.py", "sym", "main", "s4"), ("h.py", "sym", "main", "s5"),            # only 2 files → no name group
+        ("i.py", "sym", "one", "s6"),
+    ]
+    g = derive_groups(rows)
+    assert g[("a.py", "sym", "helper")] == "dup:sha1" == g[("b.py", "sym", "helper")]
+    assert g[("c.py", "sym", "helper")] == "name:sym:helper"
+    assert g[("d.css", "css", "btn")] == "name:css:btn"
+    assert ("g.py", "sym", "main") not in g
+    assert ("i.py", "sym", "one") not in g
+
+
+def test_confirm_requires_a_named_scope():
+    import asyncio
+
+    from scribe.services.shape_ledger import confirm_proposals
+
+    with pytest.raises(ValueError) as err:
+        asyncio.run(confirm_proposals(1, 2))
+    assert "name what you reviewed" in str(err.value)
+
+
+def test_proposer_tools_are_mounted():
+    from scribe.mcp.server import build_mcp_server
+
+    mcp = build_mcp_server()
+    assert mcp._tool_manager.get_tool("confirm_shape_proposals") is not None
+    tool = mcp._tool_manager.get_tool("list_shapes")
+    assert "proposal" in tool.parameters.get("properties", {})