4f9e00a6a5
Closes audit Finding 5 (2026-05-20).
Pre-fix ``CognitiveTurnPipeline._speculative_subjects`` was a bare
``set[str]`` that only grew over a session. Two correctness gaps:
* A subject promoted to ``EpistemicStatus.COHERENT`` via the teaching
review loop kept appearing with the "(speculative, not yet
reviewed)" marker forever, contaminating reviewed material on
later probes.
* Long teaching sessions widened the per-turn substring scan in
``_should_mark_speculative`` without bound.
Fix:
* Back the cache with ``OrderedDict[str, None]`` (LRU) capped at
``_MAX_SPECULATIVE_SUBJECTS = 64``.
* Introduce ``_remember_speculative_subject`` (insert / refresh) and
``_forget_speculative_subject`` (evict) helpers; route all
SPECULATIVE inserts through them.
* When a proposal lands as ``EpistemicStatus.COHERENT``, evict the
subject and every long-enough non-stopword token derived from it,
so the marker stops appearing on reviewed material.
Iteration order in ``_should_mark_speculative`` is unchanged (keys
view); lookups remain O(1). No surface change for any case the prior
behavior didn't already mishandle, so byte-identical eval surfaces
stay stable (verified locally against ``core eval cognition`` public /
holdout / dev splits — all unchanged from MEMORY baseline).
Tests (7 new, ``tests/test_speculative_subject_lifecycle.py``):
* storage is an OrderedDict and the cap is 64
* remember normalizes (lower+strip) and drops empty input
* remember refreshes LRU position on re-insert
* cache caps at 64 with insertion-order eviction
* forget is case-insensitive and removes the entry
* forget on a missing / empty subject is a no-op
* ``_should_mark_speculative`` triggers after remember and stops
triggering after forget
Audit findings referenced:
https://github.com/AssetOverflow/core/pull/76 (Finding 5, "Unbounded
``_speculative_subjects``")
93 lines
3.6 KiB
Python
93 lines
3.6 KiB
Python
"""Speculative-subject cache lifecycle (Finding 5, audit 2026-05-20).
|
|
|
|
Pre-fix ``CognitiveTurnPipeline._speculative_subjects`` was an unbounded
|
|
``set[str]`` that only grew over a session. Two correctness gaps:
|
|
|
|
* A subject promoted to ``EpistemicStatus.COHERENT`` via the teaching
|
|
review loop kept appearing with the "(speculative, not yet reviewed)"
|
|
marker forever.
|
|
* Long teaching sessions widened the per-turn substring scan inside
|
|
``_should_mark_speculative`` without bound.
|
|
|
|
These tests pin the lifecycle so the fix cannot silently regress.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from collections import OrderedDict
|
|
|
|
import pytest
|
|
|
|
from chat.runtime import ChatRuntime
|
|
from core.cognition import CognitiveTurnPipeline
|
|
from core.cognition.pipeline import _MAX_SPECULATIVE_SUBJECTS
|
|
|
|
|
|
@pytest.fixture()
|
|
def pipeline() -> CognitiveTurnPipeline:
|
|
return CognitiveTurnPipeline(runtime=ChatRuntime())
|
|
|
|
|
|
def test_storage_is_bounded_ordereddict(pipeline: CognitiveTurnPipeline) -> None:
|
|
assert isinstance(pipeline._speculative_subjects, OrderedDict)
|
|
assert _MAX_SPECULATIVE_SUBJECTS == 64
|
|
|
|
|
|
def test_remember_inserts_and_normalizes(pipeline: CognitiveTurnPipeline) -> None:
|
|
pipeline._remember_speculative_subject(" TRUTH ")
|
|
assert "truth" in pipeline._speculative_subjects
|
|
pipeline._remember_speculative_subject("")
|
|
pipeline._remember_speculative_subject(" ")
|
|
# Empty / whitespace inputs are silently dropped
|
|
assert list(pipeline._speculative_subjects) == ["truth"]
|
|
|
|
|
|
def test_remember_refreshes_lru_position(pipeline: CognitiveTurnPipeline) -> None:
|
|
pipeline._remember_speculative_subject("alpha")
|
|
pipeline._remember_speculative_subject("beta")
|
|
pipeline._remember_speculative_subject("alpha")
|
|
# alpha was re-touched after beta, so alpha is now the MRU entry
|
|
assert list(pipeline._speculative_subjects) == ["beta", "alpha"]
|
|
|
|
|
|
def test_cache_caps_at_max(pipeline: CognitiveTurnPipeline) -> None:
|
|
for i in range(_MAX_SPECULATIVE_SUBJECTS + 10):
|
|
pipeline._remember_speculative_subject(f"subj{i:03d}")
|
|
assert len(pipeline._speculative_subjects) == _MAX_SPECULATIVE_SUBJECTS
|
|
# Oldest 10 entries (subj000..subj009) evicted; newest survive
|
|
keys = list(pipeline._speculative_subjects)
|
|
assert "subj000" not in keys
|
|
assert "subj009" not in keys
|
|
assert "subj010" in keys
|
|
assert keys[-1] == f"subj{_MAX_SPECULATIVE_SUBJECTS + 9:03d}"
|
|
|
|
|
|
def test_forget_removes(pipeline: CognitiveTurnPipeline) -> None:
|
|
pipeline._remember_speculative_subject("truth")
|
|
pipeline._remember_speculative_subject("light")
|
|
pipeline._forget_speculative_subject("Truth") # case-insensitive
|
|
assert "truth" not in pipeline._speculative_subjects
|
|
assert "light" in pipeline._speculative_subjects
|
|
|
|
|
|
def test_forget_missing_is_noop(pipeline: CognitiveTurnPipeline) -> None:
|
|
pipeline._remember_speculative_subject("truth")
|
|
pipeline._forget_speculative_subject("never-added")
|
|
pipeline._forget_speculative_subject("")
|
|
assert list(pipeline._speculative_subjects) == ["truth"]
|
|
|
|
|
|
def test_should_mark_speculative_still_iterates_correctly(
|
|
pipeline: CognitiveTurnPipeline,
|
|
) -> None:
|
|
"""The marker decision still triggers on stored subjects."""
|
|
pipeline._remember_speculative_subject("wisdom")
|
|
assert pipeline._should_mark_speculative(
|
|
text="Tell me about wisdom",
|
|
surface="Wisdom is the application of knowledge.",
|
|
)
|
|
pipeline._forget_speculative_subject("wisdom")
|
|
assert not pipeline._should_mark_speculative(
|
|
text="Tell me about wisdom",
|
|
surface="Wisdom is the application of knowledge.",
|
|
)
|