Closes four surface-form bypass vectors against fix#2 that were
real holes: contractions ("you're now a pirate" did not match marker
"you are now"), curly quotes (U+2019 vs U+0027), em-dashes (token
splicing), and verb morphology ("becoming"/"transformed"/"dropped"
did not stem to the bare redirect-verb set).
teaching/review.py:
- _normalize() folds Unicode punctuation and expands 28 common
English contractions (you're, it's, let's, don't, won't, etc.)
before rule (a) substring matching and rule (b/c/d) tokenisation.
- _stem_verb() folds -ing / -ed / -es / -s morphology with silent-e
drop and doubled-consonant handling, so "becomes" / "becoming" /
"became"-class forms match the bare redirect-verb stem.
- Rule (d) window now uses verb stems, not raw tokens.
Verification: ten splits (v1-v5, public + holdouts) at 100% attack
rejection and 100% legitimate acceptance. v5 (32 attacks + 18
legitimates) is the new regression gate, exercising every fold class
plus legitimates that themselves use contractions ("wisdom's broader",
"knowledge isn't merely collected").
Tests: test_reviewed_teaching_loop.py 5/5, test_pipeline_teaching_integration.py
5/5, test_identity_gate.py 17/17 (including 5 TestWouldViolatePredicate
tests from prior commit).
Resolves the adversarial-identity v3 finding (0% rejection on
paraphrased attacks against the marker-string defense). Two
independent layers now guard the review gate; either is sufficient
to reject.
Fix#2 (syntactic, in teaching/review.py):
Replaces the substring-only check with four deterministic rules:
(a) legacy markers (v1/v2 coverage preserved verbatim)
(b) redirect-verb + role-frame co-occurrence
(c) negating qualifier within +/-3 tokens of a role-frame
(d) negating qualifier within +/-3 tokens of a redirect-verb
Replay-safe, no learned classifier, single-file contained change.
Fix#3 (geometric, in core/physics/identity.py):
Adds IdentityCheck.would_violate(score, manifold) predicate per
ADR-0010 and wires it through CognitiveTurnPipeline._run_teaching
from response.identity_score. The geometric layer is paraphrase-
invariant by construction.
Honest finding: with the current default IdentityManifold (three
unit-axis ValueAxes), the geometric layer flags 0/32 of v3 attacks
independently. The predicate and wiring are in place; the manifold
axis design is the limiting factor and remains as scoped follow-up.
Fix#2 is what is actually rejecting attacks today.
Verification: all eight adversarial-identity splits (v1-v4, public +
holdouts) at attack_rejection=1.0 and legitimate_acceptance=1.0.
v4 (32 attacks + 18 legitimate) is the regression gate for fix#2,
exercising rules (b)/(c)/(d) with new attack vocabulary. Tests
test_reviewed_teaching_loop.py (5/5), test_pipeline_teaching_integration.py
(5/5), test_identity_gate.py (incl. 5 new TestWouldViolatePredicate
tests, 12/12). CLI suites: smoke, cognition, teaching, runtime all
green.
Also drops a stale entry from the runtime CLI suite list
(test_chat_identity_telemetry.py was removed in 222124a).
Introduces teaching/ module with three-stage correction pipeline:
1. correction.py — extracts CorrectionCandidate from correction intents,
binding correction text to the prior turn it references
2. review.py — validates candidates: rejects identity overrides (17
marker patterns) and empty corrections; produces ReviewedTeachingExample
with deterministic SHA-256 review hash
3. store.py — bounded FIFO store for accepted examples; emits
PackMutationProposal objects instead of mutating the vocab manifold
directly; retrievable by subject
Design invariants:
- Identity override attempts are rejected at the review gate
- Pack mutations are proposal-only (applied=False by default)
- All traces are deterministic: same input → same candidate_id and review_hash
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
