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>

src/scribe/models/code_shape.py

@@ -3,6 +3,7 @@ from datetime import datetime
 from sqlalchemy import (
     BigInteger,
     DateTime,
+    Float,
     ForeignKey,
     Index,
     Integer,
@@ -19,6 +20,12 @@ from scribe.models.base import TimestampMixin
 SHAPE_STATUSES = ("canonical", "instance", "variant", "exempt", "unclassified")
 SHAPE_CLASSIFIERS = ("agent", "audit", "hook", "mechanical", "import")
 
+# How the mechanical proposer (#2792) arrived at a proposal, strongest first.
+# `derive` is the odd one out: not "this is an instance of #N" but "this
+# shape repeats with NO canon — derive one first" (note 2786's derive-first
+# rule), so it carries a group key instead of a snippet.
+PROPOSAL_BASES = ("symbol", "text", "reference", "signature", "semantic", "derive")
+
 
 class CodeShape(Base, TimestampMixin):
     """One extracted code shape and its classification against canon (#2787).
@@ -42,6 +49,20 @@ class CodeShape(Base, TimestampMixin):
     snippet_id is SET NULL on snippet deletion: the classification's target
     is gone but the judgment happened; the sync pass (step 2) re-files such
     rows as unclassified so they rejoin the todo instead of dangling.
+
+    `signature` / `body_sha` (#2792) are the shape's content fingerprint —
+    its definition line and a whitespace/comment-insensitive hash of its
+    block — refreshed by every sync. They are what the mechanical proposer
+    matches on and what a later drift recheck compares against; the ledger
+    still never stores code bodies.
+
+    The proposal columns hold the proposer's standing suggestion for an
+    UNCLASSIFIED row: `proposed_snippet_id` + `proposal_basis` + score for
+    "looks like an instance of #N", or `proposal_basis="derive"` +
+    `proposal_group` for "repeats with no canon". `proposed_sha` is the
+    body_sha the row was last examined at, so a refresh re-examines only
+    what changed. A judgment clears the proposal — the machine proposes,
+    judgment classifies.
     """
 
     __tablename__ = "code_shapes"
@@ -52,6 +73,7 @@ class CodeShape(Base, TimestampMixin):
         ),
         Index("ix_code_shapes_project_status", "project_id", "status"),
         Index("ix_code_shapes_snippet", "snippet_id"),
+        Index("ix_code_shapes_proposed", "project_id", "proposed_snippet_id"),
     )
 
     id: Mapped[int] = mapped_column(primary_key=True)
@@ -76,6 +98,31 @@ class CodeShape(Base, TimestampMixin):
     vanished_at: Mapped[datetime | None] = mapped_column(
         DateTime(timezone=True), nullable=True
     )
+    signature: Mapped[str] = mapped_column(Text, default="")
+    body_sha: Mapped[str] = mapped_column(Text, default="")
+    proposed_snippet_id: Mapped[int | None] = mapped_column(
+        BigInteger, ForeignKey("notes.id", ondelete="SET NULL"), nullable=True
+    )
+    proposal_basis: Mapped[str | None] = mapped_column(Text, nullable=True)
+    proposal_score: Mapped[float | None] = mapped_column(Float, nullable=True)
+    proposal_group: Mapped[str | None] = mapped_column(Text, nullable=True)
+    proposed_at: Mapped[datetime | None] = mapped_column(
+        DateTime(timezone=True), nullable=True
+    )
+    proposed_sha: Mapped[str] = mapped_column(Text, default="")
+
+    @property
+    def proposal(self) -> dict | None:
+        """The standing proposal as one object, or None when the proposer
+        has nothing to say about this row."""
+        if self.proposed_snippet_id is None and not self.proposal_group:
+            return None
+        out: dict = {"basis": self.proposal_basis, "score": self.proposal_score}
+        if self.proposed_snippet_id is not None:
+            out["snippet_id"] = self.proposed_snippet_id
+        if self.proposal_group:
+            out["group"] = self.proposal_group
+        return out
 
     def to_dict(self) -> dict:
         return {
@@ -93,6 +140,9 @@ class CodeShape(Base, TimestampMixin):
             "first_seen_commit": self.first_seen_commit,
             "last_seen_commit": self.last_seen_commit,
             "vanished_at": self.vanished_at.isoformat() if self.vanished_at else None,
+            "signature": self.signature,
+            "body_sha": self.body_sha,
+            "proposal": self.proposal,
             "created_at": self.created_at.isoformat(),
             "updated_at": self.updated_at.isoformat(),
         }