fix(ledger): the proposer prefers a same-project canon on a tie — family canon elsewhere is the fallback, not the first hit

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

src/scribe/services/shape_ledger.py

@@ -685,6 +685,7 @@ class Canon(NamedTuple):
     locations: tuple[tuple[str, str], ...]
     signature: str
     code_norm: str
+    project_id: int = 0
 
 
 def _norm_text(text: str) -> str:
@@ -718,17 +719,20 @@ def text_contains(body: str, code: str) -> bool:
 
 def match_canon(
     kind: str, path: str, symbol: str, signature: str, body: str,
-    canons: Iterable[Canon],
+    canons: Iterable[Canon], *, project_id: int = 0,
 ) -> tuple[int, str, float] | None:
     """The strongest (snippet_id, basis, score) a shape earns against the
     canon catalog, by the non-semantic bases — or None. Strongest by
-    basis order, then by score within the basis."""
-    best: dict[str, tuple[float, int]] = {}
+    basis order, then by score within the basis; on a tie, a canon recorded
+    in the shape's own project beats family canon from another (the same
+    helper recorded in two projects is the shape's own first)."""
+    best: dict[str, tuple[float, bool, int]] = {}
 
-    def offer(basis: str, score: float, sid: int) -> None:
+    def offer(basis: str, score: float, canon: Canon) -> None:
         cur = best.get(basis)
-        if cur is None or score > cur[0]:
-            best[basis] = (score, sid)
+        same = bool(project_id) and canon.project_id == project_id
+        if cur is None or (score, same) > (cur[0], cur[1]):
+            best[basis] = (score, same, canon.snippet_id)
 
     norm_sym = _norm_symbol(symbol)
     for c in canons:
@@ -736,19 +740,19 @@ def match_canon(
             continue
         if c.symbol and _norm_symbol(c.symbol) == norm_sym:
             if not any(location_covers(lp, ls, path, symbol) for lp, ls in c.locations):
-                offer("symbol", 1.0, c.snippet_id)
+                offer("symbol", 1.0, c)
             continue  # its own location is canonical territory, not a proposal
         if c.symbol and references_symbol(body, c.symbol, kind):
-            offer("reference", 0.9, c.snippet_id)
+            offer("reference", 0.9, c)
         if c.code_norm and text_contains(body, c.code_norm):
-            offer("text", 0.95, c.snippet_id)
+            offer("text", 0.95, c)
         if kind == "sym" and c.signature:
             ratio = signature_similarity(signature, symbol, c.signature, c.symbol)
             if ratio >= _SIGNATURE_FLOOR:
-                offer("signature", round(ratio, 3), c.snippet_id)
+                offer("signature", round(ratio, 3), c)
     for basis in _BASIS_ORDER:
         if basis in best:
-            score, sid = best[basis]
+            score, _same, sid = best[basis]
             return (sid, basis, score)
     return None
 
@@ -790,7 +794,7 @@ async def canon_catalog(user_id: int) -> list[Canon]:
                 ((loc.get("path") or ""), (loc.get("symbol") or ""))
                 for loc in fields.get("locations") or []
             ),
-            signature, _norm_text(code),
+            signature, _norm_text(code), int(note.project_id or 0),
         ))
     return out
 
@@ -872,7 +876,10 @@ async def propose_for_repo(
                 continue
             examined += 1
             group = row.proposal_group  # derive grouping is reassigned below
-            hit = match_canon(row.kind, row.path, row.symbol, signature, body, canons)
+            hit = match_canon(
+                row.kind, row.path, row.symbol, signature, body, canons,
+                project_id=project_id,
+            )
             _clear_proposal(row)
             row.proposal_group = group
             row.proposed_at = now

tests/test_shape_ledger.py

@@ -190,9 +190,24 @@ def test_text_containment_is_whitespace_insensitive_with_a_floor():
     assert not text_contains("x = 1", "x = 1")          # below the substance floor
 
 
-def _canon(sid, kind="sym", symbol="", locations=(), signature="", code=""):
+def _canon(sid, kind="sym", symbol="", locations=(), signature="", code="", project_id=0):
     from scribe.services.shape_ledger import Canon, _norm_text
-    return Canon(sid, kind, symbol, tuple(locations), signature, _norm_text(code))
+    return Canon(sid, kind, symbol, tuple(locations), signature, _norm_text(code), project_id)
+
+
+def test_match_canon_prefers_the_shapes_own_project_on_a_tie():
+    """The same helper recorded in two projects: the shape's own project's
+    record is its canon; family canon elsewhere is the fallback."""
+    from scribe.services.shape_ledger import match_canon
+    family = _canon(3, "sym", "slugify", [("lib/text.py", "slugify")], project_id=1)
+    own = _canon(4, "sym", "slugify", [("src/util/text.py", "slugify")], project_id=2)
+    assert match_canon("sym", "src/other.py", "slugify", "def slugify(t):", "",
+                       [family, own], project_id=2) == (4, "symbol", 1.0)
+    assert match_canon("sym", "src/other.py", "slugify", "def slugify(t):", "",
+                       [family, own], project_id=1) == (3, "symbol", 1.0)
+    # No project given → first-best stands; nothing breaks.
+    assert match_canon("sym", "src/other.py", "slugify", "def slugify(t):", "",
+                       [family, own])[1] == "symbol"
 
 
 def test_match_canon_orders_bases_strongest_first_and_respects_kind():