3092f1814e
Each stage (find_connections/gaps/improvements/propose_conjectures) numbered its leads from seq=1, so connection L-0001, gap L-0001 and improvement L-0001 all resolved to grounded/L-0001.md. The CLI concatenates them (connections + gaps + improvements) and write_leads writes in order, so later kinds silently overwrote earlier ones — survivors = max(per-kind count), not the sum. Reproduced: 4 distinct leads -> 2 files. _make_lead_id now takes the kind and emits L-C-/L-G-/L-I-/L-X- prefixes, keeping same-seq ids distinct across stages. Regression tests cover the format and the no-collision invariant. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
113 lines
3.6 KiB
Python
113 lines
3.6 KiB
Python
"""Tests for the Lead / Provenance datamodel (F-13)."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import get_args
|
|
|
|
import pytest
|
|
|
|
from codex.synthesis import Lead, LeadKind, LeadStatus, Provenance
|
|
|
|
|
|
def test_provenance_requires_bibkey_and_locator() -> None:
|
|
"""Provenance has two required positional fields."""
|
|
p = Provenance(bibkey="Smith2020", locator="chunk 7")
|
|
assert p.bibkey == "Smith2020"
|
|
assert p.locator == "chunk 7"
|
|
|
|
|
|
def test_provenance_missing_field_raises() -> None:
|
|
"""Provenance without locator must fail to construct (TypeError)."""
|
|
with pytest.raises(TypeError):
|
|
Provenance(bibkey="Smith2020") # type: ignore[call-arg]
|
|
|
|
|
|
def test_lead_required_fields() -> None:
|
|
"""Lead requires id, kind, title, body, provenance, confidence."""
|
|
lead = Lead(
|
|
id="L-0001",
|
|
kind="connection",
|
|
title="A connection",
|
|
body="Some body text.",
|
|
provenance=[Provenance(bibkey="X2020", locator="chunk 1")],
|
|
confidence=0.8,
|
|
)
|
|
assert lead.id == "L-0001"
|
|
assert lead.kind == "connection"
|
|
assert lead.status == "unverified" # default
|
|
assert lead.suggested_validation == "" # default
|
|
assert lead.claims == [] # default factory
|
|
|
|
|
|
def test_lead_kind_literals_exact() -> None:
|
|
"""Lead kinds are exactly: connection, gap, improvement, conjecture."""
|
|
assert set(get_args(LeadKind)) == {"connection", "gap", "improvement", "conjecture"}
|
|
|
|
|
|
def test_lead_status_literals_exact() -> None:
|
|
"""Lead statuses are exactly: unverified, spiking, go, no-go."""
|
|
assert set(get_args(LeadStatus)) == {"unverified", "spiking", "go", "no-go"}
|
|
|
|
|
|
def test_lead_provenance_can_be_multiple() -> None:
|
|
"""A Lead may carry multiple provenance pointers."""
|
|
provs = [
|
|
Provenance(bibkey="A2020", locator="chunk 1"),
|
|
Provenance(bibkey="B2021", locator="chunk 7"),
|
|
]
|
|
lead = Lead(
|
|
id="L-0002",
|
|
kind="gap",
|
|
title="t",
|
|
body="b",
|
|
provenance=provs,
|
|
confidence=0.5,
|
|
)
|
|
assert len(lead.provenance) == 2
|
|
|
|
|
|
def test_lead_missing_provenance_field_raises() -> None:
|
|
"""Constructing Lead without provenance is a TypeError."""
|
|
with pytest.raises(TypeError):
|
|
Lead( # type: ignore[call-arg]
|
|
id="L-0003",
|
|
kind="connection",
|
|
title="x",
|
|
body="y",
|
|
confidence=0.5,
|
|
)
|
|
|
|
|
|
def test_lead_empty_provenance_raises() -> None:
|
|
"""Constructing Lead with empty provenance list raises ValueError."""
|
|
with pytest.raises(ValueError, match="at least one Provenance"):
|
|
Lead(
|
|
id="L-0004",
|
|
kind="connection",
|
|
title="x",
|
|
body="y",
|
|
provenance=[],
|
|
confidence=0.5,
|
|
)
|
|
|
|
|
|
def test_lead_id_format_helper() -> None:
|
|
"""_make_lead_id produces a kind-prefixed, zero-padded L-<K>-XXXX string."""
|
|
from codex.synthesis import _make_lead_id
|
|
|
|
assert _make_lead_id(1, "connection") == "L-C-0001"
|
|
assert _make_lead_id(42, "gap") == "L-G-0042"
|
|
assert _make_lead_id(9999, "improvement") == "L-I-9999"
|
|
assert _make_lead_id(1, "conjecture") == "L-X-0001"
|
|
|
|
|
|
def test_lead_id_namespaced_per_kind_no_collision() -> None:
|
|
"""Regression for audit C-11: each stage numbers from 1, so without a kind
|
|
prefix connection/gap/improvement all collide on L-0001 and overwrite one
|
|
another in grounded/. The prefix must keep same-seq ids distinct.
|
|
"""
|
|
from codex.synthesis import _make_lead_id
|
|
|
|
ids = {_make_lead_id(1, k) for k in ("connection", "gap", "improvement", "conjecture")}
|
|
assert len(ids) == 4, f"same-seq ids must stay distinct across kinds, got {ids}"
|