fix(synthesis): make coverage-map gaps opt-in (audit R-8)

find_gaps defaulted its probe topics to paper titles, so a title — which
retrieves mostly its own single bibkey — fell below synthesis_gap_min_coverage
and flagged almost every paper as a 'gap'. Coverage-map gaps now run only for
explicitly-requested topics; the CLI gains a repeatable --topic option. The
code-vs-corpus gap path (precise) is unchanged and still default.

Tests: the two cases that relied on default-title coverage gaps now pass explicit
topics; added a regression that no coverage gaps appear without --topic.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Tarik Moussa
2026-06-15 16:32:01 +02:00
parent cfbfa53398
commit c4106b0f51
4 changed files with 46 additions and 11 deletions

View File

@@ -112,10 +112,35 @@ def test_find_gaps_coverage_map_low_coverage_triggers_llm(
"For an ideal tetrahedron with dihedral angles the hyperbolic volume is "
"V = L(gamma1) + L(gamma2) + L(gamma3). [Springborn2008 #chunk 16]\n"
)
leads = find_gaps(llm=StubLLM(grounded_body))
# Coverage gaps are opt-in (audit R-8): pass the topic explicitly.
leads = find_gaps(llm=StubLLM(grounded_body), topics=["hyperbolic volume formula"])
assert any(lead.kind == "gap" for lead in leads)
def test_find_gaps_no_coverage_gaps_without_explicit_topics(
monkeypatch: pytest.MonkeyPatch,
mock_paper_titles: None,
mock_settings: Path,
) -> None:
"""Without explicit topics, paper titles do NOT auto-generate coverage gaps (R-8)."""
sparse_chunks: list[dict[str, Any]] = [
{
"id": 10,
"paper_id": "springborn-2008",
"ord": 16,
"content": "the hyperbolic volume is V = L(gamma1) + L(gamma2) + L(gamma3)",
"bibkey": "Springborn2008",
},
]
monkeypatch.setattr(
"codex.synthesis._retrieve_chunks",
lambda queries, top_k: [dict(c) for c in sparse_chunks],
)
# No lib_path, no topics → the coverage map must not run despite sparse coverage.
leads = find_gaps(llm=StubLLM("a gap. [Springborn2008 #chunk 16]"))
assert leads == []
def test_find_gaps_explicit_topics_override_default(
monkeypatch: pytest.MonkeyPatch,
mock_paper_titles: None,

View File

@@ -148,7 +148,8 @@ def test_find_gaps_topic_with_no_chunks(
) -> None:
"""When retrieval returns no chunks, a gap lead is emitted directly."""
monkeypatch.setattr("codex.synthesis._retrieve_chunks", lambda queries, top_k: [])
leads = find_gaps(llm=StubLLM(""))
# Coverage gaps are opt-in now (audit R-8): pass an explicit topic.
leads = find_gaps(llm=StubLLM(""), topics=["nonexistent topic"])
assert len(leads) >= 1
assert all(lead.kind == "gap" for lead in leads)
# Direct gap leads carry a validation hint (re-ingest)