merge(learn): advisory-fix harvest and slice 2 -- six families out-of-repo

Co-Authored-By: Claude Fable 5.1 <[email protected]>
Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo

src/openultrasast/learn/examples.py

@@ -265,8 +265,10 @@ class SideReader:
         if self._pairs is None:
             from ..pairs import load_pair_catalog
 
-            source = next(s for s in self.sources.sources if s.kind == "pairs")
-            self._pairs = {case.name: case for case in load_pair_catalog(self.root / source.files[0])}
+            # every pair-kind source (the corpus catalog and e.g. advisory-fixes): labels name both as source "pairs"
+            self._pairs = {}
+            for source in (s for s in self.sources.sources if s.kind == "pairs"):
+                self._pairs.update({case.name: case for case in load_pair_catalog(self.root / source.files[0])})
         return self._pairs
 
     def license(self, label: Mapping[str, Any]) -> str:

src/openultrasast/learn/program.py

@@ -475,7 +475,8 @@ class Program:
         target = candidate.target
         got = retrieve(target, self.memory, fold, vectors=self.vectors, n1=self.spec.n1, k=self.spec.k_ret, lam=self.spec.lam, seed=seed,
                        priors=self.spec.priors, inputs=self.spec.inputs)  # fmt: skip
-        usable = [Demo.from_dict(d) for d in demonstrations_for([d.as_dict() for d in self.spec.demos], self.index, target, fold)]
+        demos = demonstrations_for([d.as_dict() for d in self.spec.demos], self.index, target, fold, vectors=self.vectors)
+        usable = [Demo.from_dict(d) for d in demos]
         prompt = render(self.spec, candidate, got.examples, usable, self.index, self.excerpt_text)
         assert_boundary([*prompt.example_ids, *prompt.demo_ids], self.index, target, fold, vectors=self.vectors)
         return prompt, got

src/openultrasast/learn/retrieve.py

@@ -240,19 +240,32 @@ def assert_boundary(
 
 
 def demonstrations_for(
-    demos: Sequence[Mapping[str, Any]], examples: Mapping[str, Example], target: Target, fold: Fold
+    demos: Sequence[Mapping[str, Any]],
+    examples: Mapping[str, Example],
+    target: Target,
+    fold: Fold,
+    *,
+    vectors: Mapping[str, Sequence[float]] | None = None,
 ) -> list[Mapping[str, Any]]:
     """The compiled demonstrations usable for ``target``: an ineligible one is swapped for its alternate when that
-    is eligible, and dropped otherwise (leave-one-framework-out on a demonstration's framework)."""
+    is eligible, and dropped otherwise (leave-one-framework-out on a demonstration's framework; in evaluation, a
+    demonstration whose excerpt is a near-duplicate of the target's, the same rule as retrieval and
+    :func:`assert_boundary`)."""
+
+    def ok(example: Example | None) -> bool:
+        if example is None:
+            return False
+        vector = (vectors or {}).get(example.excerpt_sha)
+        cos = cosine(target.vector, vector) if target.vector is not None and vector is not None else None
+        return eligible(example, target, fold, cos=cos)
+
     out: list[Mapping[str, Any]] = []
     for demo in demos:
-        example = examples.get(str(demo["example_id"]))
-        if example is not None and eligible(example, target, fold):
+        if ok(examples.get(str(demo["example_id"]))):
             out.append(demo)
             continue
         alternate = demo.get("alternate")
-        alt = examples.get(str(alternate.get("example_id"))) if isinstance(alternate, Mapping) else None
-        if isinstance(alternate, Mapping) and alt is not None and eligible(alt, target, fold):
+        if isinstance(alternate, Mapping) and ok(examples.get(str(alternate.get("example_id")))):
             out.append(alternate)
     return out