Pilot prep: simplex schema, projection, alignment, lint, stats, pilot scripts, protocol v1

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FYqwNMyPUHeTbFWg83GQq6

tests/test_project.py

@@ -0,0 +1,94 @@
+from leanbench.project import classify, project
+from leanbench.schema import KIND_FACT, KIND_GOAL, KIND_OBJECT, KIND_OWN
+
+
+def roles(code):
+    return {r.name: r for r in project(code).roles}
+
+
+def test_objects_instances_and_goal():
+    p = project(
+        "theorem t (G : Type*) [Group G] [Fintype G] (g : G) : g ^ Fintype.card G = 1 := by sorry"
+    )
+    got = {r.name: r for r in p.roles}
+    assert list(got) == ["G", "g", "goal"]
+    assert got["G"].kind == KIND_OBJECT
+    assert got["G"].attrs["instances"] == ["Group G", "Fintype G"]
+    assert got["goal"].kind == KIND_GOAL
+    assert not p.degenerate
+    assert p.simplex is not None and len(p.simplex.roles) == 3
+
+
+def test_hypothesis_binders_become_facts():
+    got = roles("theorem t (n : ℕ) (a : ℤ) (h : Nat.Coprime a n) : a ≡ 1 [ZMOD n] := by sorry")
+    assert got["h"].kind == KIND_FACT
+    assert got["h"].attrs["classified_by"] == "predicate"
+    assert got["n"].kind == KIND_OBJECT
+
+
+def test_relation_symbols_mark_a_fact():
+    got = roles("theorem t (a b : ℤ) (hab : a ∣ b) (hpos : 0 < a) : a ≤ b := by sorry")
+    assert got["hab"].kind == KIND_FACT and got["hpos"].kind == KIND_FACT
+    assert got["a"].kind == KIND_OBJECT
+
+
+def test_function_type_is_data_not_a_fact():
+    kind, how = classify("ℕ → ℕ", ["f"], set())
+    assert kind == KIND_OBJECT and how == "default"
+    assert classify("Type*", ["G"], set()) == (KIND_OBJECT, "sort")
+
+
+def test_leading_forall_is_lifted_so_both_spellings_agree():
+    a = project("theorem t (n : ℕ) : n = n := by rfl")
+    b = project("theorem t : ∀ n : ℕ, n = n := by rfl")
+    assert [(r.name, r.kind) for r in a.roles] == [(r.name, r.kind) for r in b.roles]
+    assert {r.attrs.get("origin") for r in b.roles if r.name == "n"} == {"forall_in_goal"}
+
+
+def test_goal_implication_splits_into_premises():
+    got = roles("theorem t : ∀ n m : ℕ, n < m → m < 10 → n < 10 := by omega")
+    assert [n for n in got if n.startswith("premise")] == ["premise1", "premise2"]
+    assert got["goal"].type_text == "n < 10"
+
+
+def test_bounded_forall_adds_an_object_and_a_fact():
+    got = roles("theorem t : ∀ x ∈ S, f x = 0 := by sorry")
+    assert got["x"].kind == KIND_OBJECT and got["h_x"].kind == KIND_FACT
+
+
+def test_definition_has_an_own_role():
+    p = project("def divides (a b : Int) : Prop := ∃ k, b = a * k")
+    assert p.by_kind(KIND_OWN)[0].type_text == "Prop"
+    assert [r.name for r in p.roles] == ["a", "b", "own"]
+
+
+def test_structure_stops_at_where_and_ignores_extends():
+    p = project("structure Ring (R : Type*) extends AddCommGroup R, Mul R where\n  x : R")
+    assert [r.name for r in p.roles] == ["R", "own"]
+
+
+def test_bare_statement_is_degenerate_not_an_error():
+    p = project("theorem t : 2 + 2 = 4 := by norm_num")
+    assert p.degenerate and p.simplex is None
+    assert [r.name for r in p.roles] == ["goal"]
+
+
+def test_no_declaration():
+    p = project("-- just a comment")
+    assert p.degenerate and p.notes == ["no declaration found"]
+
+
+def test_instance_without_target_is_noted():
+    p = project("theorem t (n : ℕ) [Fact (1 < 2)] : n = n := by rfl")
+    assert any("constrains no named object" in n for n in p.notes)
+
+
+def test_duplicate_names_are_aliased():
+    p = project("theorem t (h : 0 < 1) (h : 1 < 2) : True := by trivial")
+    assert p.simplex is not None
+    assert "h" in p.simplex.roles and "h_2" in p.simplex.roles
+
+
+def test_comments_and_proof_body_are_ignored():
+    code = "/- doc -/\ntheorem t (n : ℕ) : n = n := by\n  -- (x : T) here is noise\n  rfl"
+    assert [r.name for r in project(code).roles] == ["n", "goal"]