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_integration_shape_classify.py

@@ -351,3 +351,145 @@ async def test_recent_pulls_reads_the_usage_stream(seeded):
     assert sid in pulls
     assert sid + 1000 not in pulls
     assert sid + 2000 not in pulls
+
+
+# --- #2792: the mechanical proposer against real rows -------------------------
+
+
+def _quiet_semantic():
+    """The semantic basis needs the embedder; these tests prove the other
+    bases and the bookkeeping, so it answers "nothing" here."""
+    from unittest.mock import AsyncMock, patch
+
+    from scribe.services import shape_ledger
+    return patch.object(shape_ledger, "_semantic_canon", AsyncMock(return_value=None))
+
+
+def _defs(*items):
+    """ArchiveShape-like records: (path, kind, name, signature, body_sha, body)."""
+    import hashlib
+    out = []
+    for path, kind, name, signature, body in items:
+        sha = hashlib.sha1(" ".join(body.split()).encode()).hexdigest()[:16]
+        out.append((path, kind, name, signature, sha, body))
+    return out
+
+
+@pytest.mark.integration
+async def test_proposer_proposes_and_confirm_classifies(seeded):
+    """Bodies in hand, the proposer records proposals on unclassified rows —
+    symbol (a second `factory` elsewhere), reference (a call site), and
+    nothing for the unrelated — skips rows whose content it already judged,
+    and a scoped confirm turns proposals into agent instances while a
+    classify on another retires its proposal."""
+    from scribe.services.shape_ledger import (
+        confirm_proposals, propose_for_repo,
+    )
+
+    owner, other, pid, sid = (
+        seeded["owner"], seeded["other"], seeded["pid"], seeded["snippet"]
+    )
+    defs = _defs(
+        ("src/app.py", "sym", "make_app", "def make_app():", "def make_app():\n    app = factory()\n    return app"),
+        ("src/app.py", "sym", "Config", "class Config:", "class Config:\n    debug = False"),
+        ("src/util.py", "sym", "helper", "def helper(x):", "def helper(x):\n    return x"),
+        ("src/dup.py", "sym", "factory", "def factory():", "def factory():\n    return 1"),
+        ("web/button.css", "css", "btn", ".btn {", ".btn {\n  color: red;\n}"),
+    )
+    await sync_repo_shapes(pid, REPO, defs, seen_marker="main")
+
+    with _quiet_semantic():
+        stats = await propose_for_repo(owner, pid, REPO, defs)
+    assert stats == {"examined": 5, "proposed": 2, "semantic_checked": 2}
+    rows, total = await list_project_shapes(owner, pid, proposal="canon")
+    by_symbol = {r.symbol: r for r in rows}
+    assert total == 2
+    assert by_symbol["factory"].proposal == {"basis": "symbol", "score": 1.0, "snippet_id": sid}
+    assert by_symbol["make_app"].proposal == {"basis": "reference", "score": 0.9, "snippet_id": sid}
+    rows, _ = await list_project_shapes(owner, pid, proposal="reference")
+    assert [r.symbol for r in rows] == ["make_app"]
+
+    # Same content again → nothing re-examined (the semantic cap would
+    # otherwise be spent on the same rows every refresh). A cap that leaves
+    # rows unreached leaves them UNexamined, so the next refresh gets them.
+    with _quiet_semantic():
+        assert (await propose_for_repo(owner, pid, REPO, defs))["examined"] == 0
+        await classify_shapes(owner, pid, [
+            {"path": "src/util.py", "symbol": "helper", "status": "unclassified"},
+        ])
+        assert (await propose_for_repo(owner, pid, REPO, defs, semantic_cap=0))["semantic_checked"] == 0
+        assert (await propose_for_repo(owner, pid, REPO, defs))["examined"] == 1
+
+    # Outsider can't confirm; the owner confirms by snippet, scoped.
+    with pytest.raises(ValueError):
+        await confirm_proposals(other, pid, snippet_id=sid)
+    assert await confirm_proposals(owner, pid, basis="symbol") == {"confirmed": 1}
+    rows, _ = await list_project_shapes(owner, pid, snippet_id=sid)
+    factory = next(r for r in rows if r.symbol == "factory")
+    assert factory.status == "instance" and factory.classified_by == "agent"
+    assert factory.reason == "confirmed symbol proposal (1.00)"
+    assert factory.proposal is None
+
+    # A judgment on a proposed row retires the proposal; withdrawing a
+    # judgment forgets the examination so the next pass proposes afresh.
+    await classify_shapes(owner, pid, [
+        {"path": "src/app.py", "symbol": "make_app", "status": "exempt", "reason": "bootstrap"},
+    ])
+    rows, _ = await list_project_shapes(owner, pid, path="src/app.py")
+    make_app = next(r for r in rows if r.symbol == "make_app")
+    assert make_app.status == "exempt" and make_app.proposal is None
+    await classify_shapes(owner, pid, [
+        {"path": "src/app.py", "symbol": "make_app", "status": "unclassified"},
+    ])
+    with _quiet_semantic():
+        assert (await propose_for_repo(owner, pid, REPO, defs))["proposed"] == 1
+    rows, _ = await list_project_shapes(owner, pid, proposal="canon")
+    assert [r.symbol for r in rows] == ["make_app"]
+
+
+@pytest.mark.integration
+async def test_derive_groups_land_on_rows_and_in_the_summary(seeded):
+    """Shapes with no canon hit that repeat — identical bodies in two files,
+    the same name in three — carry a derive proposal, and the readout ranks
+    the families. A canon proposal keeps a row out of any derive group."""
+    from scribe.services.shape_ledger import (
+        apply_derive_groups, live_rows, propose_for_repo, proposal_summary,
+    )
+
+    owner, pid, sid = seeded["owner"], seeded["pid"], seeded["snippet"]
+    defs = _defs(
+        ("a/one.py", "sym", "slug", "def slug(t):", "def slug(t):\n    return t.lower()"),
+        ("a/two.py", "sym", "slug", "def slug(t):", "def slug(t):\n    return t.lower()"),
+        ("b/x.css", "css", "card", ".card {", ".card { padding: 1px }"),
+        ("b/y.css", "css", "card", ".card {", ".card { padding: 2px }"),
+        ("b/z.css", "css", "card", ".card {", ".card { padding: 3px }"),
+        ("c/only.py", "sym", "alone", "def alone():", "def alone():\n    return 0"),
+        ("c/use.py", "sym", "boot", "def boot():", "def boot():\n    return factory()"),
+    )
+    await sync_repo_shapes(pid, REPO, defs, seen_marker="main")
+    with _quiet_semantic():
+        await propose_for_repo(owner, pid, REPO, defs)
+    assert await apply_derive_groups(pid) == 5
+
+    rows, total = await list_project_shapes(owner, pid, proposal="derive")
+    assert total == 5
+    groups = {(r.path, r.symbol): r.proposal for r in rows}
+    assert groups[("a/one.py", "slug")]["group"] == groups[("a/two.py", "slug")]["group"]
+    assert groups[("a/one.py", "slug")]["group"].startswith("dup:")
+    assert groups[("b/x.css", "card")] == {"basis": "derive", "score": 3.0, "group": "name:css:card"}
+    rows, _ = await list_project_shapes(owner, pid, proposal="any")
+    assert {r.symbol for r in rows} == {"slug", "card", "boot"}   # boot: reference proposal
+
+    summary = proposal_summary(await live_rows(pid))
+    assert summary["proposed"] == 1
+    assert [g["group"] for g in summary["derive_groups"]][0] == "name:css:card"
+    assert summary["derive_groups"][0]["label"] == ".card"
+    assert summary["derive_groups"][0]["size"] == 3
+
+    # One of the css copies gets judged → the group shrinks on the next pass.
+    await classify_shapes(owner, pid, [
+        {"path": "b/z.css", "symbol": "card", "status": "exempt", "reason": "print sheet"},
+    ])
+    await apply_derive_groups(pid)
+    rows, _ = await list_project_shapes(owner, pid, proposal="derive")
+    assert {r.symbol for r in rows} == {"slug"}                   # 2 files < the name floor