claude-bot
b9e37952e6
Replaces the previous tree entirely. The pipeline is four separable pieces, each
testable on its own:
1. leanbench/llm.py provider-neutral OpenAI-compatible connector, stdlib only,
with retries, JSON coercion and a scripted client so the
rest of the code is testable without a network.
2. leanbench/detect.py per-page detection of formalizable mathematics. Case 1 is
mathematics asserted as fact (definition/theorem/lemma/...,
deliberately not sub-classified); case 2 is a problem left
open to the reader. Hits come back as spans -- start page
and index, end page and index -- so several per page is
normal. A hit cut off by the page end makes the detector
re-read that page together with the next, repeatedly, so an
item spread over three pages is found whole.
Offsets come from verbatim quotes resolved by
leanbench/anchors.py (exact -> whitespace-insensitive ->
fuzzy), because models quote well and count badly.
3. leanbench/formalize.py + leanbench/verify.py
each span becomes one Lean 4 declaration, judged by the real
compiler: full elaboration for case 1, statement legality
only for case 2, which has no proof to check. Lean's own
diagnostics feed back for a repair attempt. "verified" (Lean
accepted it) and "proved" (accepted with no sorry) are kept
strictly apart.
4. leanbench/db.py indexed SQLite plus JSONL export. Every item is indexed by
the types of its inputs, or by its own type when it is not a
proof, and records the source book (sha256) and the page it
starts on -- so `drop --source H --pages A-B` followed by a
re-ingest redoes exactly those pages and nothing else.
Infrastructure:
- lean/ Lake project pinned to Mathlib.
- docker/ image carrying Lean 4 and a prebuilt Mathlib. The Mathlib
revision and the toolchain are resolved against each other at
build time rather than both hardcoded, so the build does not rot.
docker/smoke.py runs the whole pipeline inside the image against
the real compiler, with the LLM scripted.
- .gitea/workflows ci (lint + tests in a venv, since the runner image's Python is
Debian-managed and refuses installs into itself), docker (build,
verify, optionally push), ingest (submit a book by hand).
The docker workflow is not a throwaway build: it leaves the image, the layer cache,
an idle `lean-bench` container and the `lean-bench-data` / `lean-bench-books`
volumes in place on the runner, and never prunes, so the environment is there to be
used afterwards. Pushing to the registry is optional and cannot fail the build --
Gitea's container registry does not accept the built-in Actions token, so that needs
a REGISTRY_TOKEN secret with write:package.
58 tests; they need neither network nor Lean.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ci5T3gWDhhmqDec3e1XtYZ
82 lines
2.9 KiB
Python
82 lines
2.9 KiB
Python
from __future__ import annotations
|
||
|
||
from leanbench.typeindex import ROLE_GOAL, ROLE_INPUT, ROLE_OWN, index_types, parse_signature
|
||
|
||
|
||
def test_theorem_is_indexed_by_the_types_of_its_inputs() -> None:
|
||
code = "theorem add_dvd (a b c : Int) (h : a ∣ b) (k : a ∣ c) : a ∣ b + c := by\n sorry"
|
||
signature = parse_signature(code)
|
||
assert signature is not None
|
||
assert signature.is_proof
|
||
assert signature.name == "add_dvd"
|
||
assert "Int" in signature.inputs
|
||
pairs = index_types(code)
|
||
assert ("Int", ROLE_INPUT) in pairs
|
||
|
||
|
||
def test_definition_is_indexed_by_its_own_type() -> None:
|
||
code = "def divides (a b : Int) : Prop := ∃ k : Int, b = a * k"
|
||
signature = parse_signature(code)
|
||
assert signature is not None
|
||
assert not signature.is_proof
|
||
pairs = index_types(code)
|
||
assert ("Int", ROLE_INPUT) in pairs
|
||
assert ("Prop", ROLE_OWN) in pairs, "a predicate's own type is the point of it"
|
||
assert all(role != ROLE_GOAL for _, role in pairs)
|
||
|
||
|
||
def test_a_proof_is_not_indexed_by_Prop() -> None:
|
||
pairs = index_types("theorem t (n : Nat) : n = n := rfl")
|
||
assert all(name != "Prop" for name, _ in pairs)
|
||
|
||
|
||
def test_definition_of_a_concrete_type_records_it() -> None:
|
||
pairs = index_types("def double (n : Nat) : Nat := 2 * n")
|
||
assert ("Nat", ROLE_OWN) in pairs
|
||
|
||
|
||
def test_instance_binders_count_as_inputs() -> None:
|
||
code = "theorem foo {G : Type*} [Group G] (x : G) : x * 1 = x := by simp"
|
||
signature = parse_signature(code)
|
||
assert signature is not None
|
||
assert "Group" in signature.inputs
|
||
|
||
|
||
def test_unicode_number_types_are_normalised() -> None:
|
||
code = "theorem sq_nonneg' (n : ℤ) : 0 ≤ n ^ 2 := by positivity"
|
||
pairs = dict(index_types(code))
|
||
assert pairs.get("Int") == ROLE_INPUT
|
||
|
||
|
||
def test_structure_records_its_own_type() -> None:
|
||
code = "structure Monoid' (M : Type) : Type where\n one : M"
|
||
signature = parse_signature(code)
|
||
assert signature is not None
|
||
assert signature.keyword == "structure"
|
||
assert signature.own or signature.inputs
|
||
|
||
|
||
def test_model_supplied_types_are_merged_without_duplicates() -> None:
|
||
code = "theorem t (n : Nat) : n = n := rfl"
|
||
pairs = index_types(code, ["Nat", "Polynomial", " "])
|
||
names = [name for name, _ in pairs]
|
||
assert names.count("Nat") == 1
|
||
assert "Polynomial" in names
|
||
|
||
|
||
def test_comments_do_not_leak_into_the_index() -> None:
|
||
code = "-- about Matrix stuff\n/- Group -/\ntheorem t (n : Nat) : n = n := rfl"
|
||
names = [name for name, _ in index_types(code)]
|
||
assert "Matrix" not in names and "Group" not in names
|
||
|
||
|
||
def test_declaration_keyword_detected_after_attributes() -> None:
|
||
code = "@[simp]\nprivate theorem t (n : Nat) : n = n := rfl"
|
||
signature = parse_signature(code)
|
||
assert signature is not None and signature.keyword == "theorem"
|
||
|
||
|
||
def test_unparsable_code_yields_nothing_rather_than_nonsense() -> None:
|
||
assert parse_signature("this is not lean") is None
|
||
assert index_types("this is not lean") == []
|