Two new intent shapes + composers turn the runtime's corpus
density into operator-visible articulation. Both consult the
cross-corpus aggregator from ADR-0064; no new ratification needed.
P3.3 — chat/narrative_surface.py + IntentTag.NARRATIVE.
Classifier patterns (registered BEFORE generic DEFINITION):
^tell\s+me\s+about\s+
^describe\s+
^what\s+(?:can|do)\s+you\s+(?:say|know)\s+about\s+
narrative_grounded_surface(subject, max_clauses=4) walks every
reviewed chain rooted on subject across all registered teaching
corpora. Dedupes by (connective, object) — cause + verification
carrying the same predicate emit one clause, not two. Sorts by
(intent, connective, object) for replay stability.
Surface format:
"{X} — narrative-grounded ({corpus_ids}): {dX1}; {dX2}.
{X} {conn1} {O1} ({dO1}); {X} {conn2} {O2} ({dO2}).
No session evidence yet."
Cross-corpus subjects (e.g. mother in relations_v2) emit
narrative-grounded (relations_chains_v2) tag; cognition subjects
emit cognition_chains_v1 tag. Multi-corpus subjects (when
applicable) emit composite "corpus_a + corpus_b" tag.
P3.4 — chat/example_surface.py + IntentTag.EXAMPLE.
Classifier patterns:
^(?:give|show)\s+(?:me\s+)?an?\s+(?:example|instance)\s+of\s+
^example\s+of\s+
example_grounded_surface(object_lemma, max_examples=3) walks chains
where the lemma is the OBJECT — inverts the typical subject-keyed
access pattern. Dedupes by subject; sorts by (intent, subject,
connective).
Surface format:
"{X} — example-grounded ({corpus_ids}): {dX1}.
Example: {subj1} {conn1} {X}; {subj2} {conn2} {X}.
No session evidence yet."
Cross-cutting:
- Both intents added to _OOV_INTENT_TAGS — fall through to OOV
invitation when subject is unknown (Phase 2 gradient discipline).
- Both tagged grounding_source="teaching" (same provenance tier
as the existing teaching_grounded_surface).
- No prose generation, no new mutation surface.
Live verification:
> Tell me about truth.
[teaching] truth — narrative-grounded (cognition_chains_v1):
cognition.truth; logos.core. truth grounds knowledge
(cognition.knowledge); truth requires evidence (cognition.evidence).
> Give me an example of knowledge.
[teaching] knowledge — example-grounded (cognition_chains_v1):
cognition.knowledge. Example: truth grounds knowledge;
understanding requires knowledge; evidence grounds knowledge.
> Tell me about mother.
[teaching] mother — narrative-grounded (relations_chains_v2):
kinship.parent.female. mother precedes daughter (kinship.child.female).
> Describe photosynthesis.
[oov] I haven't learned 'photosynthesis' yet (intent: narrative). ...
ADR-0066 (this commit completes the ADR). 30 new tests passed.
Full lane: 2067 passed, 2 skipped, 0 failed in 2:32.
Mirrors the chain-gap pipeline (Phase 1.1+1.2) for vocabulary gaps:
the OOV invitation surface (P2.1) now emits structured signals that
operators can aggregate, rank, and auto-promote into reviewed
PackMutationProposal candidates — closing the OOV loop the same way
Phase 1 closed the chain loop.
Three new modules + two new CLI surfaces:
teaching/oov_sink.py.
OOVCandidate dataclass mirroring teaching.discovery.DiscoveryCandidate.
OOVBufferSink (in-memory) + OOVMonthlyFileSink (append-only JSONL
under <root>/<YYYY>/<YYYY-MM>.jsonl — same layout as discovery sink
so the aggregator reuses the file-walk machinery).
hash_oov_candidate_id(token, intent, trace_hash) — deterministic
32-char hex id matching DiscoveryCandidate's replay invariant.
format_oov_candidate_jsonl — sorted-keys compact JSONL line.
teaching/oov_gaps.py.
aggregate_oov_gaps(root, since, sample_limit) groups emitted
candidates by token, tracks intent-shape union (a token asked under
multiple intents is a stronger curriculum signal), splits
boundary_clean from boundary_tainted counts, supports --since
YYYY-MM filtering via the sink's file naming convention.
Pure reader; never mutates the sink. Deterministic ordering:
(count desc, token asc).
teaching/oov_promotion.py.
promote_oov_gaps(gaps, threshold, include_tainted, suggested_packs)
lifts threshold-crossing tokens to OOVPromotion records.
- boundary_clean_count gates promotion by default (tainted-only
tokens may indicate the prompt hit a safety axis rather than a
vocab gap).
- --include-tainted flag for operator override.
- threshold < 1 raises.
- queue_id deterministic: ``oov:<token>@<threshold>`` — diffable
across runs.
- suggested_packs lists mounted packs but does NOT recommend one
— domain inference is out of scope (would require a stochastic
classifier). Operator picks the destination.
Runtime wiring:
ChatRuntime.attach_oov_sink(sink) mirrors attach_discovery_sink.
Runtime emits one OOVCandidate JSONL line per turn whose
grounding_source == "oov", no-op when no sink is attached.
Intent classifier is now invoked when EITHER sink is attached
(was: only discovery sink) — both downstream paths need it.
CLI:
core teaching oov-gaps [--top N] [--since YYYY-MM] [--root PATH]
[--sample-limit N] [--json]
core teaching oov-queue [--threshold N] [--include-tainted]
[--root PATH] [--since YYYY-MM] [--json]
ADR-0065 documents the full design (five-tier honesty gradient,
P2.1-P2.4 architecture). README.md updated with the ADR-0065
index entry.
Verification:
tests/test_oov_pipeline.py 24 passed
Operator workflow round-trip verified live:
> rt.attach_oov_sink(sink); rt.chat("What is photosynthesis?")
→ sink receives:
{"boundary_clean":true,"candidate_id":"f51bf8...",
"intent":"definition","token":"photosynthesis","trigger":"unresolved_subject",
"source_turn_trace":"","review_state":"unreviewed"}
> core teaching oov-gaps --root /tmp/oov_demo
→ ranked table by count, intent-set per token
> core teaching oov-queue --root /tmp/oov_demo --threshold 2
→ promoted tokens + suggested mounted packs
Full lane: 2005 passed, 2 skipped, 0 failed in 2:34 (xdist).
ADR-0064 is the corpus-layer sibling of ADR-0063. The teaching-grounded
surface composer was hardcoded to cognition_chains_v1, so kinship CAUSE/
VERIFICATION prompts fell through to the universal disclosure even though
en_core_relations_v1 was mounted on the live runtime (ADR-0063).
Architectural change in chat/teaching_grounding.py:
- New TeachingCorpusSpec dataclass (corpus_id, path, pack_id).
- TEACHING_CORPORA tuple registers every active corpus. Each
corpus is 1:1-bound to one lexicon pack — cross-domain triples
deferred per docs/teaching_order.md §5.
- _load_corpus(spec) loads one corpus with pack-residency scoped
to its declared pack.
- _all_chains_index() aggregates across all registered corpora
(first-match-wins; cognition first preserves byte-identity).
- _pack_for_corpus(corpus_id) → bound pack lexicon.
- clear_teaching_caches() atomic cache invalidation.
- TeachingChain gains corpus_id field → surface tag follows resolving corpus.
Wiring updates:
- teaching_grounded_surface + teaching_grounded_surface_composed
consult _all_chains_index; surface tag follows chain.corpus_id.
- teaching/discovery.py gate uses chat.pack_resolver.is_resolvable
(any mounted pack) + _all_chains_index (any registered corpus).
- teaching/replay.py _swap_corpus_path rewrites the registry path
+ clears all teaching caches during the gate's transient phase.
Active corpus bytes unchanged (replay invariant preserved).
- evals/learning_loop/run_demo.py scene-5 swap mirrors the new
pattern so the demo still grounds against transient corpora.
Back-compat preserved: _corpus_index, _CORPUS_PATH, TEACHING_CORPUS_ID
remain cognition-corpus-specific for audit/replay consumers.
Phase 1.4 — relations_chains_v1 seeded with 7 reviewed kinship chains:
cause_parent_precedes_child
cause_child_follows_parent
cause_ancestor_precedes_descendant
cause_descendant_follows_ancestor
cause_family_grounds_parent
verification_child_requires_parent
verification_descendant_requires_ancestor
5 of 8 relations lemmas covered. All connectives already humanised.
Strict pack-internal to en_core_relations_v1 (no cross-domain in v1).
Seed pattern matches cognition_chains_v1's original pre-ADR-0055 seed.
Live verification:
> Why does parent exist?
parent — teaching-grounded (relations_chains_v1):
kinship.ascendant.direct; kinship.parent.
parent precedes child (kinship.descendant.direct).
grounding_source = teaching
Cognition eval byte-identical to pre-ADR baseline:
public: intent 100% / surface 100% / term 91.7% / closure 100%
holdout: intent 100% / surface 100% / term 83.3% / closure 100%
Lanes green: smoke 67 / cognition 121 / teaching 17 / packs 6 /
runtime 19 / algebra 132 / full 1933 passed.
ADR-0063 closes the ADR-0048/0050/0053/0061 hardcoded-cognition-pack
asymmetry. New chat/pack_resolver.py provides resolve_lemma(lemma,
pack_ids) → (resolving_pack_id, semantic_domains) across an ordered
tuple of mounted lexicon packs (first-match-wins, lru_cache per-pack).
Surface composers in chat/pack_grounding.py now consult the resolver
instead of a hardcoded en_core_cognition_v1. en_core_relations_v1
joins RuntimeConfig.input_packs defaults; kinship lemmas now ground
on the live path:
> What is a parent?
parent — pack-grounded (en_core_relations_v1):
kinship.ascendant.direct; kinship.parent; biology.progenitor.
No session evidence yet.
Cross-pack comparison (knowledge × parent) renders composite tag
(en_core_cognition_v1 × en_core_relations_v1). Cognition lane
remains byte-identical: cognition is resolved first and the surface
format for cognition lemmas is unchanged.
Cognition eval (byte-identical to pre-ADR baseline):
public → intent 100% / surface 100% / term 91.7% / closure 100%
holdout → intent 100% / surface 100% / term 83.3% / closure 100%
Curated lanes green: smoke 67 / cognition 121 / teaching 17 /
packs 6 / runtime 19 / algebra 132.
New tests: test_pack_resolver.py (28) + test_cross_pack_grounding.py
(17). test_en_core_relations_v1_pack.py: default-input-packs guard
inverted. test_pack_grounding.py: two stale ADR-0048 tests rewritten
(premises invalidated by ADR-0052/0061; now use fully-out-of-pack
prompts).
chat/teaching_grounding.py UNCHANGED — cognition_chains_v1 corpus
stays cognition-only. Cross-pack teaching corpora are the natural
ADR-0064.
Pre-ADR-0062, the teaching-grounded composer emitted exactly one
reviewed chain per surface — "light reveals truth" — even when the
corpus already contained an immediate follow-up "truth grounds
knowledge". With 21 active chains after curriculum saturation v2,
many grounded prompts had a corpus-ratified follow-up the composer
silently dropped.
ADR-0062 adds the composed composer + an opt-in config flag:
flag OFF (default):
light — teaching-grounded (cognition_chains_v1): cognition.illumination;
logos.core. light reveals truth (cognition.truth). No session evidence yet.
flag ON:
light — teaching-grounded (cognition_chains_v1): cognition.illumination;
logos.core. light reveals truth (cognition.truth), which grounds
knowledge (cognition.knowledge). No session evidence yet.
Follow-up resolution:
- prefer cause; fall back to verification (deterministic preference)
- cycle guard: 1-step cycles (A→B, B→A) blocked
- pack-residency guard: follow-up's object must be pack-resident
- bounded depth: v1 follows exactly one hop
- degrades to single-chain BYTE-IDENTICALLY when no follow-up
survives the guards (drop-in replacement)
Trust-boundary invariants preserved:
- Every visible non-template token is lemma / pack-domain /
humanize_predicate connective / template constant. Only added
template constant: ", which "
- Deterministic: same chains → same surface bytes
- Default-False flag pattern mirrors ADR-0047/0058
- `versor_condition < 1e-6` invariant untouched (surface composition only)
Cognition lane null-drop invariant CI-pinned:
Composed mode emits a strictly LONGER surface (extra follow-up
clause); every expected_term passing flag-OFF must still pass flag-ON.
Asserted in test_cognition_lane_metrics_unchanged_with_composed_flag
for both public and holdout splits. If a future change drops tokens,
the test fails as a deliberate regression.
public flag OFF: intent 100% / surface 100% / term 91.7% / versor 100%
public flag ON : intent 100% / surface 100% / term 91.7% / versor 100% (identical)
holdout flag OFF: intent 100% / surface 100% / term 83.3% / versor 100%
holdout flag ON : intent 100% / surface 100% / term 83.3% / versor 100% (identical)
Live-prompt lift visible on ~12 of 21 active chains; the rest hit
cycle or pack-residency guards. Saturation v2's clusters were
authored partly with composition in mind (thought→meaning→
understanding, inference→evidence→knowledge, etc.).
- core/config.py — `RuntimeConfig.composed_surface: bool = False`
- chat/teaching_grounding.py — `teaching_grounded_surface_composed`
sibling to `teaching_grounded_surface`
- chat/runtime.py — dispatch branch in `_maybe_pack_grounded_surface`
selects composed vs single-chain based on config flag
- tests/test_composed_surface.py — 11 tests pin: function-level
(None on no chain / degrades when no follow-up / two-clause when
follow-up exists / includes intermediate + final domains /
deterministic / cycle guard / trust label preserved); runtime
integration (default single-chain / flag-on composed / frozen
config); cognition-lane null-drop invariant.
Lanes (regression): smoke 67 / cognition 121 / teaching 17 /
composed-surface 11 — all green.
Pre-ADR-0061 every "How do I X?" question fell through to the
universal disclosure even when X was a pack-resident lemma. The
teaching corpus carries CAUSE/VERIFICATION chains only — procedural
knowledge is fundamentally different in kind from propositional
claims and deserves its own ratification path (deliberately out of
scope; a future parallel `procedure_chains_v1.jsonl` schema is
discussed in the ADR's non-goals).
ADR-0061 adds the honest cold-start fallback: ground the topic in
pack semantic_domains and note explicitly that ratified step-by-step
guidance does not exist yet.
Surface format:
"procedure-grounded ({pack_id}): {lemma} ({d1}; {d2}).
Step-by-step guidance for {lemma} is not yet ratified
in this session."
Selector — **last** pack-resident lemma in the verb-phrase subject:
"define a concept" → concept (object beats verb)
"verify a claim" → verify (verb wins when object is OOV)
"correct an error" → correct
"learn this" → learn
"do stuff" → None (falls through to universal disclosure)
Stopwords: only `be` and `have` (dialogue fillers). Procedure verbs
are deliberately NOT stopworded so the verb-as-fallback rule fires
when the object is OOV — keeps surface coverage.
Trust-boundary invariants:
- Every visible non-template token is lemma / pack-domain / template.
- Deterministic: same subject_text → same bytes.
- Returns None for fully-unknown utterances → universal disclosure
fires. Never fabricates surface from nothing (ADR-0053 contract).
- "not yet ratified" trust-label preserved.
Cognition lane lift:
public : intent 100% / surface 100% / term 91.7% / versor 100% (unchanged)
holdout : intent 100% / surface 94.7%→100.0% / term 79.2%→83.3% / versor 100%
Two cases fixed:
- procedure_define_010 ("How do I define a concept?") — surface +
term `concept` now captured.
- procedure_verify_034 ("How do I verify a claim?") — surface only
(case has no expected_terms; the verb fallback grounds it).
Combined effect: holdout `surface_groundedness` closes to 100%; 4 of
5 architectural holdout misses now resolved (this ADR + ADR-0060 +
the supersede from epistemology v1). Remaining 2 are UNKNOWN-intent
cases (unknown_spirit_041, unknown_word_018) — out of scope; deserve
their own ADR with distinct selector semantics.
- chat/pack_grounding.py — `_extract_procedure_topic_lemma` helper +
`pack_grounded_procedure_surface` composer.
- chat/runtime.py — import + dispatch branch for `IntentTag.PROCEDURE`.
- tests/test_procedure_surface.py — 15 tests pin: extraction
(last-wins / verb-by-elimination / be+have skipped / None on empty /
strips punctuation / case-insensitive); surface (contains lemma /
contains domains / pack_id / "not yet ratified" label / None for
no-pack-lemma / deterministic); end-to-end through ChatRuntime.
Lanes (regression): smoke 67 / cognition 121 / teaching 17 /
procedure 15 — all green.
The non-negotiable field invariant (versor_condition < 1e-6) is
unaffected: this ADR changes surface composition only.
ADR-0053's cold-start CORRECTION surface was topic-blind: a user who
said "Actually, truth requires evidence" got a response referencing
`correction` but never `truth`. The holdout case correction_truth_040
expected `term=['truth']` and missed — one of the architectural gaps
surfaced by the epistemology v1 curriculum unit.
ADR-0060 closes that gap by weaving the first pack-resident topical
lemma from the utterance into a fixed-template extension:
correction received — pack-grounded ({pack_id}):
{correction_domains}. Noted topic: {lemma} ({lemma_domains}).
No prior turn in this session to correct yet.
Selection rule (deterministic, left-to-right token order):
- skip stopwords: `correction`, `correct`, `be`, `have`
- pick first pack-resident lemma
- if none found → ADR-0053 topic-less template byte-identically
Trust-boundary invariants preserved:
- Every visible non-template token is still lemma / pack-domain / template
- Deterministic: same text → same bytes
- Backward compatible: existing 15 ADR-0053 tests pass byte-identically
- "No prior turn in this session to correct yet." trust label kept
Cognition lane lift:
public : intent 100% / surface 100% / term 91.7% / versor 100% (unchanged)
holdout : intent 100% / surface 94.7% / term 75.0%→79.2% / versor 100%
The +4.2pp matches the single-case fix exactly (correction_truth_040).
Remaining 3 holdout misses (procedure_define_010, unknown_spirit_041,
unknown_word_018) are out of scope for this ADR.
- chat/pack_grounding.py — `_extract_correction_topic_lemma` helper +
optional `text` parameter on `pack_grounded_correction_surface`.
- chat/runtime.py — single-line call-site change to pass `text` through.
- tests/test_correction_topic_lemma.py — 14 new tests pin:
extraction (first lemma / skips correction / skips fillers / None on
empty / strips punctuation / case-insensitive); surface (contains
corrected lemma / contains topic domains / degrades to ADR-0053
byte-identically / preserves trust label / deterministic / correct
pack_id); end-to-end (correction_truth_040 emits 'truth' / no-pack-
lemma still grounds).
Why text-level extraction, not intent.subject:
`intent.subject` after ADR-0049 head-noun extraction returns
", truth requires evidence" for the test prompt — the CORRECTION
intent's subject-extractor preserves the post-marker tail. Parsing
the raw text at the surface layer is cleaner; isolates the fix;
doesn't perturb upstream classification logic.
Lanes (regression): smoke 67 / cognition 121 / teaching 17 /
correction tests 29 (15 ADR-0053 backward-compat + 14 ADR-0060 new) —
all green.
The non-negotiable field invariant (versor_condition < 1e-6) is
unaffected: this ADR changes surface composition only.
`ChatRuntime.correct()` propagates a backward perturbation through the
session graph (per session/correction.py): each past turn whose output
versor has non-trivial CGA-alignment with the correction versor is
blended toward it (decayed by graph distance). The forward regen turn
that followed already emitted a TurnEvent — but the backward
perturbation itself was invisible to the telemetry sink.
ADR-0059 closes that gap with a discriminated event line.
- chat/telemetry.py — adds `serialize_correction_event` +
`format_correction_event_jsonl` emitting one JSONL line discriminated
by `"type": "correction"`. Payload: target_turn, records_count,
turns_skipped, turn_idxs_affected, max_delta_norm, mean_delta_norm,
SHA-256 correction_versor_digest, pack ids. No raw versor coordinates.
- chat/runtime.py — `_emit_correction_event` (mirrors
`_emit_turn_event`); called from `correct()` after the graph state
is updated but before the forward regen turn. No-op without sink.
- tests/test_correction_telemetry.py — 7 tests pin: no-op without
sink, emission with sink, payload shape (required keys + types +
ranges), SHA-256 digest shape, trust boundary (no versor
coordinates leaked), determinism (byte-identical lines across
runs), correction event and turn event coexist in the sink.
Trust boundary (per CLAUDE.md):
- Metadata-only: only L2 deltas + SHA-256 digest.
- No implicit wall-clock.
- Deterministic: same CorrectionResult → byte-identical line.
- Sink contract unchanged: `emit(line: str)`.
- `versor_condition < 1e-6` invariant: untouched (telemetry-only).
Verification: smoke 67 / runtime 19 / correction telemetry 7 — green.
ADR-0058 closes the ADR-0047 follow-up question ("should the
forward_graph_constraint flag become default-on or pack-opt-in?")
with the explicit answer: neither, yet.
The ADR-0047 A/B characterisation found that the flag is observably
inert on every public-cognition-lane metric — narrowing which tokens
the walk may visit did not change which surface gets emitted. That
finding scoped ADR-0048..0053, which closed the cognition lane to
100.0% surface_groundedness / 91.7% term_capture_rate via realizer /
surface-assembly work downstream of propagation.
This ADR makes three load-bearing decisions:
1. `forward_graph_constraint` remains opt-in with default `False`.
No identity pack (including precision_first_v1) opts in.
2. No `runtime_preferences` block is added to identity packs; no
path from pack JSON to RuntimeConfig is opened. Deferring the
pack-to-runtime composition layer until at least one such
preference has demonstrated lift avoids letting the wiring lead
the lift and locking in an abstraction at the wrong level.
3. The ADR-0047 null-lift finding is promoted from a historical
observation to a CI-enforced invariant. A new regression test
runs the public cognition split twice (flag OFF vs ON) and
asserts every watched metric is pair-wise identical. If
downstream realizer work later moves a metric on the flag flip,
the test fails as a deliberate transition rather than silent drift.
- docs/decisions/ADR-0058-forward-graph-constraint-status.md — ADR doc.
- docs/decisions/README.md — index entry.
- tests/test_forward_graph_constraint_null_lift.py — 2 tests:
null-lift invariant across the cognition lane, default-False contract.
Verification:
smoke 67 passed; flag tests 7 passed (5 wiring + 2 null-lift).
No runtime behaviour change; versor_condition < 1e-6 invariant unaffected.
The only path by which CORE extends its own active teaching corpus.
Closes ADR-0055 Phase C alongside ADR-0056's cognitive surface.
Three load-bearing calls (recorded in ADR-0057):
1. Replay-equivalence is a precondition, not a permission;
operator --accept remains required.
2. Eligibility = polarity in {affirms, falsifies} AND at least
one source='corpus' evidence pointer AND boundary_clean AND
claim_domain != evaluative (unless --allow-evaluative) AND
proposed_chain complete.
3. Append-only proposal log; corpus history append-only too.
Changes
- teaching/proposals.py — TeachingChainProposal, ReplayEvidence,
ProposalLog (event-sourced replay → current_state), eligibility
predicate, propose_from_candidate, accept/reject/withdraw,
append_chain_to_corpus (the sole corpus-write surface). Uses
TYPE_CHECKING guards to break the circular import with
chat.pack_grounding.
- teaching/replay.py — run_replay_equivalence; swaps _corpus_index
path to a tmp file, runs cognition lane on the active corpus
AND a transient copy with the proposed chain appended, returns
regressed-metrics list; trust-boundary assertion that the active
corpus bytes are byte-identical pre/post.
- teaching/discovery.py — moved chat.pack_grounding /
chat.teaching_grounding imports inside extract_discovery_candidates
to break the cycle (was masked when chat.runtime was the entry
point; surfaced by CLI entry).
- core/cli.py — three new subcommands:
core teaching propose <candidate-jsonl-path> [--allow-evaluative]
core teaching proposals [--state pending|accepted|rejected|withdrawn] [--json]
core teaching review <proposal_id> --accept --review-date YYYY-MM-DD
core teaching review <proposal_id> --reject [--note ...]
core teaching review <proposal_id> --withdraw [--note ...]
- tests/test_teaching_proposals.py — 16 tests covering: every
eligibility gate, proposal_id idempotency, append-only log,
replay-equivalent stays pending, regression auto-rejects with
named regressed metrics, --accept appends one line with typed
Provenance, --accept refused on non-equivalent, state-machine
blocks double-accept, real replay gate runs cognition lane
twice and asserts byte-clean active corpus pre/post.
Invariants preserved
- versor_condition(F) < 1e-6 — C2 touches no algebra path.
- Active corpus bytes byte-identical regardless of replay outcome.
- No clock-time reads, no LLM, no async.
- Proposal-only — accept_proposal is the sole corpus-write path.
Lanes: smoke 67 / cognition 121 / runtime 19 / teaching 17 /
new proposals 16. Cognition eval unchanged.
Open follow-ups (not in scope):
- supersession via operator review action
- cross-pack falsification arbitration (ADR-0056 Call 2 deferred)
- pack-data migration of frame-dependent connectives
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Splits ADR-0055 Phase C into:
- C1 (this ADR): cognitive contemplation loop — question
decomposition + polarity (affirms/falsifies/undetermined) +
claim_domain typing (factual/relational/evaluative)
- C2 (future ADR): review-and-apply — TeachingChainProposal,
replay-equivalence gate, corpus append-on-accept
Documents four load-bearing design calls with explicit reasoning
so future sessions can re-derive without re-arguing:
1. Stopping condition: record-the-gap-and-stop primary, bounded
depth failsafe; failsafe firing emits recursion_overflow audit
signal — never silent truncation.
2. Falsification evidence: reviewed-only, same pack family;
session-tier contests but does not falsify. Cross-pack
arbitration deferred.
3. Order: C1 before C2. Reversed instinct to land 'small thing
first' — C2 alone is useless without enriched input; C1
physically cannot mutate corpus until C2 wires the apply path.
4. Sync, not async. CORE hot path is deterministic; concurrency
overhead exceeds probe cost on local-only probes. Async
deferred to a future ADR if a blocking probe surface emerges.
Trust boundary: C1 never mutates the corpus. C1 reads pack,
corpus, vault, and most recent TurnEvent; writes only to the
existing Phase B discovery sink. Gap-recorded sub-questions
emit as new top-level candidates on the same sink — recursion
reified into the stream.
Maps directly onto user-stated framing recorded verbatim in the
ADR:
- 'contemplation always starts with a question' → candidate is
the posing; contemplate() is the answering
- 'truths and/or falsities' → polarity on the chain itself
- 'remain humble' → claim_domain with escalating evidence
thresholds, mandatory hedge for evaluative
Lands the first deterministic trigger of the discovery → reviewed-
memory loop. Candidates are structured evidence; emission is
opt-in via attach_discovery_sink and NEVER mutates the active
teaching corpus.
- teaching/discovery.py: DiscoveryCandidate dataclass + pure
extract_discovery_candidates(turn_event, intent, subject) rule
firing. Phase B fires only the would_have_grounded trigger:
grounding_source == "none"
AND intent ∈ {CAUSE, VERIFICATION}
AND subject lemma in ratified cognition pack
AND (subject, intent) NOT in active corpus
candidate_id = SHA-256 of canonical JSON payload — replay-stable.
Other DiscoveryTrigger literals (successful_comparison,
hedge_acknowledged, oov_resolved_via_decomp) are reserved for
later phases.
- teaching/discovery_sink.py: DiscoveryCandidateSink protocol,
DiscoveryBufferSink (in-memory), DiscoveryMonthlyFileSink
(append-only JSONL, <root>/<YYYY>/<YYYY-MM>.jsonl rollover,
injectable clock).
- chat/runtime.py: opt-in attach_discovery_sink, post-turn
emission inside _stub_response only when caller threads
classified intent forward (gate-fire fall-through site).
Intent classification at the call site reuses the same
deterministic classifier already invoked by
_maybe_pack_grounded_surface for the empty-vault English path.
Trust boundary: candidates write to a separate sink/file path
only; the active corpus on disk is never touched. Tests
explicitly assert corpus bytes are byte-identical before and
after a candidate-emitting turn.
Tests: tests/test_discovery_candidates.py — 24 tests covering
pure-predicate rule firing, every short-circuit path,
deterministic candidate_id, sink opt-in, runtime parity with no
sink, monthly rollover semantics, append-only behaviour, no
corpus mutation.
Lanes: smoke 67, cognition 121, runtime 19, teaching 17, packs 6
— all green. Cognition eval metrics unchanged on dev / public /
holdout splits. versor_condition < 1e-6 invariant untouched.
Phased design for closing the inter-session learning loop without a
parallel learning path:
- Phase A: make today's 4-tier story load-bearing (audit CLI,
active-set view via superseded_by, typed provenance enum)
- Phase B: DiscoveryCandidate emission from the turn loop —
deterministic rule-firing on the audit trail, never writes the
corpus
- Phase C: TeachingChainProposal — sibling to PackMutationProposal,
proposal-only, replay-equivalence gate on dev+public
- Phase D: epistemic-tier guard (only COHERENT evidence promotes)
- Phase E: curriculum integration via formation review
Non-goals named explicitly: no embeddings, no DB storage, no
automatic identity/safety/ethics mutation, no opaque LLM step, no
removal of human reviewer.
Status Proposed; later ADRs land each phase against the verification
contracts named here.
Closes both cognition splits at 100% surface_groundedness. Three
parts:
1. Teaching corpus expansion (no code). cognition_chains_v1.jsonl
grows 3→10 chains. 3 close dev-split misses (correction,
creation, light-as-VERIFICATION); 4 pre-empt the analogous
holdout pattern (CAUSE/VERIFICATION on truth + wisdom). Every
subject/object is a pack lemma; every connective is a recognised
humanize_predicate predicate.
2. CORRECTION acknowledgement branch. New
`pack_grounded_correction_surface()` in chat/pack_grounding.py,
wired into `_maybe_pack_grounded_surface` for cold-start
CORRECTION intents. Fixed-template surface with distinct
trailing disclosure ("No prior turn in this session to correct
yet.") — distinguishes the cold-start acknowledgement from the
DEFINITION-of-correction surface. The post-correction reviewed-
teaching path in teaching/correction.py is unchanged.
3. Diagnostic memory. Saves the dev-split generalization finding:
the ADR-0048→0052 chain is NOT overfit. Public/dev gap was
teaching-corpus content coverage, not architecture.
Eval deltas (both splits run, post-ADR-0053):
public dev
intent_accuracy 100% 100% (=)
surface_groundedness 100% 100% SATURATED
term_capture_rate 91.7% 78.6%
versor_closure_rate 100% 100% (=)
Public surface_groundedness: 92.3% → 100% (+7.7 pp)
Dev surface_groundedness: 69.2% → 100% (+30.8 pp)
Tests: tests/test_pack_grounded_correction.py (15 new tests).
Lanes green: smoke (67), cognition (121), runtime (19),
teaching (17), packs (6).
Scope limits: holdouts (19 cases) not yet in the official
`core eval cognition` runner (--split accepts only {dev, public});
the CORRECTION surface does not yet echo the corrected-subject
lemma (relevant only for holdout case `correction_truth_040`).
Add the two rows the orchestrator deferred while the parallel
subagent worktrees were in flight. Both ADRs were merged in
preceding commits; this lands the README index entries that
were intentionally fenced out of each subagent's scope to
avoid merge-conflict noise.
Sibling to ADR-0048's DEFINITION/RECALL pack-grounded surface for
the COMPARISON intent. `pack_grounded_comparison_surface(a, b)` in
`chat/pack_grounding.py` composes a deterministic side-by-side
surface from both lemmas' pack `semantic_domains`, joined by the
fixed connective "contrasts with":
"{a} (d_a1; d_a2) contrasts with {b} (d_b1; d_b2) — pack-grounded
({pack_id}). No session evidence yet."
`chat/runtime.py:_maybe_pack_grounded_surface` gains a COMPARISON
branch that runs before the DEFINITION/RECALL check. Engages only
when both `intent.subject` and `intent.secondary_subject` are pack
lemmas and differ (identical-lemma comparison defers to disclosure).
Order-sensitive by design — matches the graph-layer's directional
CONTRAST edge.
Cognition eval (13-case public split):
surface_groundedness 61.5% → 69.2% (+7.7 pp)
term_capture_rate 50.0% → 58.3% (+8.3 pp)
intent_accuracy 100.0% (=)
versor_closure_rate 100.0% (=)
Case lifted: comparison_memory_recall_030 ("Compare memory and
recall"). Remaining unlift cases (CAUSE×2, VERIFICATION×1,
CORRECTION×1) need teaching-store chains or operator-driven
inference — pack lookup cannot supply causal explanations,
verifications, or corrections without fabrication.
Tests: tests/test_pack_grounded_comparison.py (15 tests).
Lanes green: smoke (67), cognition (121), runtime (19), algebra
(132), teaching (17), packs (6).
Add a deterministic, pack-agnostic post-processor in `generate/intent.py`
that runs after the `_RULES` table fires:
- DEFINITION / RECALL / PROCEDURE: strip trailing punctuation + leading
articles; preserve multi-word noun phrases
- CAUSE / VERIFICATION: additionally strip leading aux verbs; return
the head noun
Closed-set frozen sets (`_ARTICLES`, `_AUX_VERBS`) make the transform
inspectable. No pack load, no algebra change — touches only
`DialogueIntent.subject`.
Cognition eval (13-case public split):
surface_groundedness 46.2% → 61.5% (+15.3 pp)
term_capture_rate 33.3% → 50.0% (+16.7 pp)
intent_accuracy 100.0% (=)
versor_closure_rate 100.0% (=)
Two cases lift through the ADR-0048 pack path
(definition_procedure_023, definition_relation_026 — both
"What is a X?" → subject=X via article stripping). CAUSE / VERIFICATION
subjects are now clean head nouns, foundational for future COMPARISON
pack path / teaching-store inference.
Tests: tests/test_intent_subject_extraction.py (30 tests).
Lanes green: smoke (67), cognition (121), runtime (19), algebra (132),
teaching (17), packs (6).
Closes the surface-grounding gap isolated by ADR-0047's
characterisation. Adds the ratified cognition pack as a second
grounding source alongside the session vault.
== chat/pack_grounding.py (new) ==
Loads en_core_cognition_v1's lexicon once (cached; immutable pack)
and exposes:
pack_grounded_surface(lemma) -> str | None
Returns a deterministic, fully pack-sourced surface:
"{lemma} — pack-grounded ({pack_id}): {d1}; {d2}; {d3}. No session evidence yet."
Every visible atom is the lemma or a verbatim semantic_domains
string from the pack. No rewording, no synthesis, no LLM.
== chat/runtime.py ==
_stub_response gains optional pack_grounded_surface= parameter.
_maybe_pack_grounded_surface routes to the pack only when all four
hold: gate_source=="empty_vault", output_language=="en",
intent.tag in {DEFINITION, RECALL}, and intent.subject is a pack
lemma. Safety/ethics refusal still takes priority above this branch.
ChatResponse and TurnEvent gain grounding_source ∈ {vault,pack,none}.
Main walk path tags responses "vault".
== core/cognition/pipeline.py ==
gate_fired detection moved from string equality on the universal
disclosure to provenance:
gate_fired = response.vault_hits == 0 and response.grounding_source != "vault"
Same intent (suppress realizer template on gate-fired turns),
broader stub-path surface set.
== Characterisation (core eval cognition, 13-case public split) ==
Metric Pre Post Δ
intent_accuracy 100.0% 100.0% 0
surface_groundedness 15.4% 46.2% +30.8 pp
term_capture_rate 0.0% 33.3% +33.3 pp
versor_closure_rate 100.0% 100.0% 0
Lift is non-uniform by design: only single-lemma DEFINITION/RECALL
on pack-known English subjects engage. CAUSE/COMPARISON/VERIFICATION
and multi-word OOV subjects still return the universal disclosure —
fabricating those would violate the no-LLM-fallback doctrine.
== Tests ==
tests/test_pack_grounding.py 18 passed
tests/test_semantic_realizer_integration.py (updated) 1 stub-path test
pinned to the broader contract: surface is either universal
disclosure or pack-grounded; never the realizer template.
== Lanes ==
smoke 67 cognition 121 runtime 19 algebra 132
teaching 17 packs 6
versor_condition(F) < 1e-6 invariant unaffected (no algebra changes).
Closes ADR-0046's deferred follow-up: convert the PropositionGraph
into an AdmissibilityRegion BEFORE generate() runs on the live
chat path.
== generate/intent_bridge.py ==
New public helper:
build_graph_from_input(text, plan) -> PropositionGraph
Same internal call as _build_graph_from_intent, without the
post-generation ground_graph step — suitable for forward use.
== chat/runtime.py ==
When the new flag is on and output language is English, build the
graph and the region before generate() and pass it via region=.
Empty / fully OOV graphs return AdmissibilityRegion(allowed_indices=None),
which generate() treats as unconstrained — the change is a true
no-op when the graph carries no in-vocab anchors.
== core/config.py ==
RuntimeConfig.forward_graph_constraint: bool = False
Default False preserves all pre-ADR-0046 behaviour and the ADR-0024
honest-refusal contract. A first attempt wired the constraint
unconditionally; 15 tests failed with InnerLoopExhaustion because the
intent-derived graph's CGA neighbourhood doesn't intersect the walk's
candidate pool with top_k=8 on the current packs. The honest answer
is not to widen top_k until the failure goes away nor to silently
relax — both erase the architectural information that the geometry
of the graph and the geometry of the walk are not yet co-located.
Opt-in preserves ADR-0024 and follows the ADR-0022→0026 transition-
window pattern.
== Characterisation (core eval cognition, 13-case public split) ==
A/B with the flag toggled:
Metric OFF ON Δ
intent_accuracy 100.0% 100.0% 0
surface_groundedness 15.4% 15.4% 0
term_capture_rate 0.0% 0.0% 0
versor_closure_rate 100.0% 100.0% 0
InnerLoopExhaustion 0 0 0
non-trivial constraint n/a 6 / 13 —
Findings:
- Wiring is correct and safe (no exhaustions, closure unchanged).
- Single-token in-vocab subjects engage the constraint
(light/knowledge/meaning/memory/correction).
- Multi-word OOV subject phrases produced by the intent classifier
fall through to unconstrained — this is the existing intent-
classifier contract surfacing into geometry, not a constraint bug.
- Restricting which tokens the walk may visit did not change
surface_groundedness or term_capture_rate on this lane. The
surface-grounding gap therefore lives downstream of propagation
— in the realizer / surface-assembly / dialogue-role path — and is
the next load-bearing pull. This isolates the next ADR's scope.
== tests/test_forward_graph_constraint_wiring.py (5 tests) ==
- DEFAULT_CONFIG.forward_graph_constraint is False
- Default runtime answers without InnerLoopExhaustion
- Opt-in runtime answers on a short benign input
- Graph builder + build_graph_constraint produce a labelled
AdmissibilityRegion ("graph:unconstrained" or "graph:<root_id>")
- Flag is observable on the frozen RuntimeConfig
== docs/decisions/ ==
- ADR-0047 ratifies the wire-up, opt-in rationale, and A/B numbers.
- README index updated; the Pillar 1→2→3 section now reflects both
the primitive (ADR-0046) and the live wiring (ADR-0047), and
names the next pull (realizer / surface assembly) explicitly.
Verification (this branch):
tests/test_forward_graph_constraint_wiring.py 5 passed
tests/test_graph_constraint.py 8 passed
core test --suite smoke 67 passed
core test --suite cognition 121 passed
core test --suite runtime 19 passed
core test --suite algebra 132 passed
core test --suite teaching 17 passed
core test --suite packs 6 passed
core eval cognition metrics unchanged from main
versor_condition(F) < 1e-6 invariant unaffected.
The original adr-0046 commit was never run. Fixes:
- generate/graph_constraint.py: import RegionSource (was the
non-existent AdmissibilitySource).
- tests/test_graph_constraint.py + demo_01: load pack
"en_core_cognition_v1" (was "en", which is not a pack ID).
- demo_03: read JsonlBufferSink.lines as a list attribute, not a
method call.
- demo_04 (exact_recall_scale): DROPPED. The construction used
raw standard_normal vectors through unitize_versor and asserted
cga_inner self-similarity is the population max. Cl(4,1) has
mixed signature — cga_inner is not self-maximising for arbitrary
unitized random vectors — and the demo failed at N=10 000 in
exactly the way the construction predicts. The exact-recall
claim's correct home is ADR-0045 (real vault path, properly
constructed versors, N up to 100k = 100%).
Doc/index updates:
- ADR-0046 trimmed to three demos, with an explicit note on the
dropped demo's geometric error and the cross-reference to
ADR-0045.
- ADR-0046 verification block updated with measured lane numbers
(smoke 67 / cognition 121 / runtime 19 / algebra 132 /
teaching 17 / packs 6; core eval cognition unchanged).
- ADR-0046 cross-references ADR-0018 (intent_bridge source of the
graph) and ADR-0022→ADR-0026 (AdmissibilityRegion contract).
- docs/decisions/README.md: ADR-0046 added to the index and to a
new "Pillar 1 → 2 → 3 coupling" section linking the graph
constraint to the existing forward-semantic-control chain.
- evals/industry_demos/__init__.py: invocation list trimmed to
the three real entry points; removed the aspirational
"core demo …" subcommands that were never wired.
Verification on this branch:
tests/test_graph_constraint.py 8 passed
evals/industry_demos/demo_01..03 exit 0 each
core test --suite smoke 67 passed
core test --suite cognition 121 passed
core test --suite runtime 19 passed
core test --suite algebra 132 passed
core test --suite teaching 17 passed
core test --suite packs 6 passed
core eval cognition intent 100%, versor_closure 100%
Closes the structural gap identified in the 2026-05-17 assessment:
the PropositionGraph was a post-hoc descriptor of what the field walk
already produced. It is now a forward constraint that shapes what the
walk is ALLOWED to produce.
== generate/graph_constraint.py (new) ==
GraphConstraint — converts a PropositionGraph into an AdmissibilityRegion
before generate() runs, not after. The region's allowed_indices are the
intersection of:
- subject versor neighbourhood (top-k by CGA inner product)
- object versor neighbourhood (top-k by CGA inner product)
- any explicitly named node surfaces already in-vocabulary
This is the Pillar 1 → Pillar 2 coupling that was missing:
geometry (CGA) → structure (graph) → propagation (generate)
build_graph_constraint(graph, vocab, *, top_k) is the public entry.
The region label encodes the graph's root node IDs so the admissibility
trace identifies the constraint source.
== generate/stream.py (updated) ==
generate() already accepts an AdmissibilityRegion. No new API needed —
graph_constraint.build_graph_constraint() produces one.
== evals/industry_demos/ (new) ==
Four standalone demo scripts that each make ONE falsifiable claim no
transformer-LLM wrapper can reproduce. Each script runs independently
via `python -m evals.industry_demos.<name>` and exits 0 on pass / 1 on
fail. Each prints structured evidence to stdout.
demo_01_forward_constraint.py
Claim: When the PropositionGraph names subject=light, obj=truth, the
generation walk is constrained to the CGA neighbourhood of those
versors BEFORE any tokens are produced. The allowed_indices set is
computed from geometry, not from a prompt filter. Demonstrated by
showing the AdmissibilityRegion is non-trivial (< full vocab) and
that all generated tokens score positive CGA inner product against
the constraint field.
demo_02_geometry_drives_identity.py
Claim: Swapping the identity pack (precision_first vs generosity_first)
on identical input produces structurally different surfaces via the
manifold alignment path — not via a system-prompt swap. Demonstrated
by running two ChatRuntime instances with different identity_pack IDs
on the same text, showing hedge_rate and identity_score.alignment
differ, and that the manifold alignment_threshold differs at the
algebra level (not just the text level).
demo_03_deterministic_audit.py
Claim: Three independently constructed ChatRuntime instances on the
same input produce byte-identical JSONL audit lines. Demonstrated
by attaching JsonlBufferSink to each, running chat(), and asserting
hash equality of the emitted lines (modulo the 'turn' field which is
per-instance sequential). This is architectural determinism — not
seeded randomness.
demo_04_exact_recall_scale.py
Claim: CGA vault recall is exact (100%) at N=100, N=1_000, N=10_000.
The needle versor is recovered at rank-1 by cga_inner scan regardless
of vault size. No approximate nearest-neighbour index. No FAISS.
No degradation curve. Demonstrated inline with timing so the
linear-scan cost is visible alongside the 100% recall.
== tests/test_graph_constraint.py (new) ==
8 tests:
- build_graph_constraint returns an AdmissibilityRegion
- allowed_indices is a strict subset of vocab (non-trivial constraint)
- all constraint indices score positive cga_inner against at least
one node versor
- empty graph returns unconstrained region (safe fallback)
- two-node graph unions both neighbourhoods
- constraint label encodes root node IDs
- round-trip: constraint region feeds generate() without raising
- forward vs post-hoc: constrained walk produces tokens in the
region; unconstrained walk may not (statistical, seeded vocab)
Co-Authored-By: Perplexity AI
ADR-0044 — Medical / clinical ethics pack (worked-example domain pack).
Ships packs/ethics/medical_clinical_ethics_v1.json with six commitments
partitioned across all three remediation tiers:
- refuse: no_dosing_recommendation, no_emergency_triage_authority
- hedge: defer_diagnosis_to_clinician, surface_evidence_grade
- audit: disclose_no_clinician_relationship, respect_patient_autonomy
Ratified end-to-end through scripts/ratify_ethics_pack.py (PACK_IDS
extended). Production-mode load via load_ethics_pack succeeds.
ChatRuntime composition includes universal safety floor + every medical
commitment. tests/test_medical_clinical_ethics_pack.py (8 tests) gates
file existence, sealed report, disjoint refusal/hedge lists, and
pack-swap visibility (default pack does NOT carry medical commitments).
ADR-0045 — Long-context recall: CORE vs transformer baselines.
Adds evals/long_context_cost/comparison_runner.py with a deterministic
needle-in-a-haystack measurement at N ∈ {100, 1_000, 10_000, 100_000}.
CORE recall = 100% at every tested N by exact cga_inner scan.
Paired with frozen citations of published transformer NIAH numbers in
evals/long_context_cost/baselines/transformer_long_context.json:
Claude 2.1 (200k, 50%), GPT-4 Turbo 128k (~71%), Gemini 1.5 Pro (99.7%),
NVIDIA RULER (varies). Each citation carries source + url.
The two components measure different inputs (synthetic versors vs NL
needles) and are not directly comparable benchmark-for-benchmark. The
comparison is at the architectural level — exact-scan recall vs
attention-based probabilistic recall. Scope and limits documented in
the ADR. tests/test_long_context_comparison.py (5 tests) gates schema,
CORE recall == 100%, and baseline citation presence.
CLI integration: two new demo targets with study-grade preambles.
- core demo pack-measurements (ADR-0043 — wired)
- core demo long-context-comparison (ADR-0045)
README + docs/PROGRESS.md cheatsheets updated. docs/decisions/README.md
index extended with ADR-0044 + ADR-0045; pack-layer chain title now
"ADR-0027 through ADR-0045".
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Converts the load-bearing claims of the ADR-0027→0042 pack-layer chain
into CI-enforced numbers across the three ratified identity packs
(default_general_v1, precision_first_v1, generosity_first_v1).
Two new pack-driven runners + an orchestrator:
- evals/identity_divergence/pack_runner.py — drives real
SentenceAssembler + SurfaceContext (no mocks) across all three
packs over 10 cases × 5 alignment bands; publishes per-pack
bare/hedge/qualifier rates and pairwise distinct_rate.
- evals/refusal_calibration/pack_runner.py — runs the existing
grounding-refusal lane via RuntimeConfig(identity_pack=...);
publishes per-pack refusal_rate/fabrication_rate and a
pack_invariant_gate flag asserting byte-identical cold-start
surfaces across packs.
- scripts/publish_pack_measurements.py — combined publisher
emitting evals/results/phase2_pack_measurements.json.
Baseline numbers (2026-05-17):
- precision_first hedge_rate=0.60, qualifier_rate=0.20
- generosity_first hedge_rate=0.20, qualifier_rate=0.00
- default_general hedge_rate=0.40, qualifier_rate=0.00
- pairwise distinct_rate ∈ [0.40, 0.80]
- refusal_rate=1.00, fabrication_rate=0.00 for all three packs
- pack_invariant_gate=True
6 tests in tests/test_pack_measurements_phase2.py lock the schema +
load-bearing flags + the structural inequality
precision.hedge_rate > generosity.hedge_rate. If identity packs
get wired into the cognition gate, pack_invariant_gate flips and
the suite fails.
ADR-0043 documents the numbers, the extended marker rationale, and
the trade-offs. README index updated with ADR-0043 row and chain
title bumped to "ADR-0027 through ADR-0043".
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Ships `core demo audit-tour` as the first investor-facing
walkthrough of the ADR-0027→0041 pack-layer architecture. Four
scenes, each making one falsifiable claim no transformer-LLM
wrapper can reproduce:
S1. Identity is geometric, not prompt-veneer.
Three identity packs load three structurally distinct
manifolds (ADR-0027). Distinct alignment thresholds +
distinct hedge phrases from JSON pack files, not prompts.
S2. Safety is the universal floor.
Runtime-checkable safety violation produces a deterministic
typed refusal string (ADR-0036). walk_surface preserved
for audit. Byte-identical across runs.
S3. Ethics commitments choose their remediation.
Per-commitment opt-in (ADR-0037 / ADR-0038): pure-helper
evidence (should_inject_hedge + inject_hedge worked
example) against a synthetic violation. Default pack
returns False; deployment pack (with acknowledge_uncertainty
in hedge_commitments) returns True. Pack JSON drives the
policy tier.
S4. Deterministic replay across runtime instances.
Two fresh ChatRuntime instances, same input, same packs.
Byte-identical JSONL audit lines (ADR-0040).
Load-bearing evidence over surface inspection: the draft compared
response.surface across packs. Cold-start hits stub path; pack
differences don't manifest at the surface by design. Shipped
version pulls evidence from structural surfaces (manifold fields,
opt-in lists, pure helpers) — what actually distinguishes the
packs. No fake claims.
Scene 3 uses synthetic verdict (not chat()) because ADR-0038
specifies stub path skips hedge by design. Main-path end-to-end
is asserted in tests/test_hedge_injection.py and referenced in
the tour's evidence comment.
Test gate: tests/test_audit_tour.py asserts
result["all_claims_supported"] is True. Any scene flipping to
False fails the test and catches the regression.
CLI integration:
core demo audit-tour # narration to stdout
core demo audit-tour --json # structured report, no narration
Files:
- evals/audit_tour/__init__.py + run_tour.py (new) — 4-scene tour
- core/cli.py — audit-tour target on demo subcommand;
_AUDIT_TOUR_PREAMBLE; --json suppresses narration
- tests/test_audit_tour.py (new) — 8 tests gating all four claims
- docs/decisions/ADR-0042-audit-tour-demo.md (new) — decision record
- docs/decisions/README.md — ADR index now lists ADR-0027..0042
+ Pack-Layer chain section describing the three-tier composition,
remediation tiers, and verification surface
- docs/PROGRESS.md — adds core demo audit-tour to verify cheatsheet
- README.md — adds core demo audit-tour to commands cheatsheet
Verification:
- Combined pack-layer + telemetry + tour suite: 220 green
(was 212 after ADR-0041; +8)
- CLI suites unchanged: smoke 67, runtime 19, cognition 121
- core eval cognition: intent 100%, versor_closure 100% (baseline)
- Manual: core demo audit-tour and --json both correct;
all_claims_supported = true
Two thin layers closing the audit story end-to-end:
- core chat --show-verdicts prints format_verdict_summary(verdicts)
to stderr after each turn. Stdout stays clean for piped
consumers. Format is dense and terse; designed to skim, not
machine-parseable (the JSONL sink owns that contract).
- FanOutSink forwards every emitted line to N sinks in declaration
order. Fail-fast on first error — consistent with ADR-0040's
single-sink contract (audit failures surface). Composes with
any combination of JsonlFileSink / JsonlBufferSink / future
sinks.
Two formatters, one bundle: format_turn_event_jsonl (machine,
ADR-0040) and format_verdict_summary (operator, ADR-0041) both
consume the same TurnVerdicts. No risk of drift.
Summary format:
[identity=0.83 safety=ok ethics=VIOLATED:foo refusal=- hedge=YES]
Audit story now reads end-to-end:
- TurnVerdicts bundle (ADR-0039)
- Machine JSONL sink (ADR-0040)
- Fan-out + operator CLI (ADR-0041)
Files:
- chat/telemetry.py — FanOutSink dataclass, format_verdict_summary,
_format_verdict_short helper
- core/cli.py — --show-verdicts on chat subparser; cmd_chat prints
summary to stderr when set
- tests/test_telemetry_fanout_and_summary.py (new) — 13 tests
- docs/decisions/ADR-0041-cli-verdicts-and-fanout.md (new)
Verification:
- Combined pack-layer + telemetry suite: 212 green (was 199; +13)
- CLI suites unchanged: smoke 67, runtime 19, cognition 121
- core eval cognition: intent 100%, versor_closure 100% (baseline)
- Manual smoke: echo "light is" | core chat --show-verdicts prints
expected bracketed audit line to stderr alongside response.
Closes three audit gaps left by the ADR-0035→ADR-0038 pack-layer
surface:
1. TurnVerdicts bundle (chat/verdicts.py) — frozen dataclass
aggregating identity_score + safety_verdict + ethics_verdict +
refusal_emitted + hedge_injected. Attached to both
ChatResponse.verdicts and TurnEvent.verdicts. Fields typed as
object for the same module-coupling reason as
TurnEvent.safety_verdict.
2. Stub-path TurnEvent emission — _stub_response accepts optional
tokens kwarg and appends a TurnEvent to turn_log when invoked
from a real turn. Audit consumers can now iterate turn_log
end-to-end without missing stub paths. Defensive call sites
(correct() fallback) bypass the append by omitting tokens.
3. refusal_emitted / hedge_injected flags — runtime tracks whether
it actually mutated the surface this turn. hedge_injected uses
idempotent-on-prefix semantics (True iff the runtime ADDED a
hedge, not iff a hedge happens to be present).
Test-pattern note: previous "gate on rt.turn_log to detect main vs
stub" pattern is now broken; updated to gate on walk_surface ==
_UNKNOWN_DOMAIN_SURFACE. One existing hedge-injection test gate
updated accordingly.
Back-compat: ADR-0035→0038 per-field accessors
(response.safety_verdict, etc.) still work. New consumers should
read response.verdicts.
Files:
- chat/verdicts.py (new) — TurnVerdicts dataclass
- chat/runtime.py — _stub_response tokens kwarg + stub TurnEvent
append + hedge_injected tracking + bundle construction
- core/physics/identity.py — TurnEvent.verdicts: object = None
- tests/test_turn_verdicts_bundle.py (new) — 16 tests
- tests/test_hedge_injection.py — gate fix for stub detection
- docs/decisions/ADR-0039-audit-completeness.md (new)
Verification:
- Combined pack-layer suite: 170 green (was 154 after ADR-0038)
- CLI suites unchanged: smoke 67, runtime 19, cognition 121
- core eval cognition: intent 100%, versor_closure 100% (baseline)
Wires SafetyCheck and EthicsCheck into ChatRuntime at end-of-turn on
both the main articulation path and _stub_response. Verdicts attach
to ChatResponse.safety_verdict / .ethics_verdict and TurnEvent.
Observational at v1: no refusal, no re-articulation, no behavioral
change. Refusal policy is the next ADR with real verdict data in hand.
Runtime-checkable predicates today:
- preserve_versor_closure (via _FieldStateWithVersor adapter)
- no_identity_override (manifold hash before vs after; equal by construction)
- no_silent_correction (runtime._last_refusal_was_typed bookkeeping)
- acknowledge_uncertainty (IdentityScore.alignment + hedge detection)
- disclose_limitations (walk_surface == _UNKNOWN_DOMAIN_SURFACE)
Predicates with no runtime evidence (no_manipulation, no_fabricated_source,
defer_high_stakes_to_human_review, respect_user_autonomy, no_hot_path_repair)
honestly report runtime_checkable=False per the ADR-0032/0034 discipline.
They become checkable as classifiers and pipelines land — surface contract
doesn't change.
Test coverage: 14 new tests; combined pack-layer surface suite (loaders +
checks + turn-loop) now 122 green. CLI suites unaffected: smoke 67,
cognition 121, teaching 17, runtime 19. Cognition eval baseline preserved.
Completes the predicate-surface layer for ethics packs, sibling to
ADR-0032's SafetyCheck. Same registry-of-predicates shape; same
observational discipline; same honest reporting of runtime-checkable=False
for structural commitments that cannot be evaluated from per-turn evidence.
Five default predicates for the v1 commitments:
acknowledge_uncertainty — alignment < threshold ⇒ requires hedge
defer_high_stakes_to_human_review — high_stakes ⇒ requires recommend_review
disclose_limitations — ungrounded ⇒ requires disclosure marker
no_manipulation — structural; runtime_checkable=False
respect_user_autonomy — prescriptive ⇒ requires ≥2 options surfaced
`no_manipulation` is the ethics-side analogue of `no_hot_path_repair`
in SafetyCheck — an aggregate property enforced by realizer design and
review, not a per-turn metric. Honest reporting rather than a silent
upheld pass.
ChatRuntime exposes `runtime.ethics_check`; turn loop does not
auto-invoke. Refusal / re-articulation wiring is a future ADR.
Test coverage: 27 new tests; combined pack-layer surface suite
(identity + safety + ethics, loaders + checks) is now 108 tests, all
green. Cognition (121), teaching (17), runtime (19), smoke (67)
unaffected.
Completes the three-layer pack architecture:
identity (who CORE is) + safety (universal red lines)
+ ethics (deployment-specific propositional commitments)
manifold.boundary_ids = identity.boundary_ids
∪ safety.boundary_ids
∪ ethics.commitment_ids
Ethics packs are swappable like identity (fall back to default on load
failure) but propositional like safety (commitment ids union into the
manifold). EthicsPackError inherits from ValueError; only when both
the requested and default packs fail does startup refuse.
Ships default_general_ethics_v1 with five commitments:
- acknowledge_uncertainty
- defer_high_stakes_to_human_review
- disclose_limitations
- no_manipulation
- respect_user_autonomy
Ratified through identity_anchor template at SHA 81fc9b61c828….
Test coverage: 20 new tests; combined identity/safety/ethics surface
suite is 81 tests, all green. Cognition (121), teaching (17), runtime
(19), smoke (67), and cognition eval all unaffected.
Closes the 'boundaries are checked at scattered call sites' gap noted
in ADR-0029. Adds a centralized observational surface parallel in
shape to IdentityCheck — produces a verdict, does not refuse. Wiring
verdicts into refusal paths is a future ADR.
Shape (parallel to IdentityCheck, different in mechanism):
SafetyContext — duck-typed input bag (field_state, citations,
refusal-was-typed flag, identity manifold hashes
before/after). Every field optional with safe
defaults; absence of evidence is not evidence of
violation.
SafetyCheckResult — per-boundary: boundary_id, upheld, reason,
runtime_checkable, evidence tuple.
SafetyVerdict — aggregate: pack_id, results (lex order on
boundary_id), upheld, violated_boundaries,
runtime_checkable_count.
SafetyCheck — registry of predicates; check(ctx, pack) returns
SafetyVerdict. register(boundary_id, predicate)
adds custom predicates.
Five default predicates for v1 boundaries:
preserve_versor_closure runtime_checkable=True field.versor_condition < 1e-6
no_fabricated_source runtime_checkable=True* cited ⊆ allowed
no_silent_correction runtime_checkable=True last refusal was typed
no_identity_override runtime_checkable=True* hash before == hash after
no_hot_path_repair runtime_checkable=FALSE code-path; static-analysis
*Conditional on the caller supplying the necessary fields.
The honest answer on no_hot_path_repair: it is a code-path boundary
enforced by static analysis + code review. Runtime cannot judge it.
A predicate that silently reported upheld=True would be a small lie —
exactly the kind of thing CLAUDE.md forbids. SafetyCheck reports
runtime_checkable=False with a clear reason so auditors see the truth.
ChatRuntime integration:
ChatRuntime.__init__ now constructs self.safety_check = SafetyCheck()
alongside self._identity_check. Turn loop does NOT auto-invoke at
v1 — operators and future ADRs decide when/where to call it.
Files:
packs/safety/check.py new — SafetyCheck + value types +
default predicates
packs/safety/__init__.py re-exports the new public surface
chat/runtime.py constructs self.safety_check
tests/test_safety_check.py new — 20 tests covering each
default predicate (positive +
negative), unknown-boundary
fallback, custom registration,
defensive boundary-id rebinding,
verdict aggregation, ChatRuntime
integration
docs/decisions/ADR-0032-safety-check-surface.md Accepted
docs/safety_packs.md §SafetyCheck section added,
known-limit #1 struck through
memory/safety-pack.md refreshed; new follow-up about
turn-loop auto-invocation
Suite status (all green):
cognition 121, teaching 17, runtime 19, formation 182, smoke 67
identity / safety / surface divergence suites: 108 tests passing
(was 88 before this ADR; +20 safety-check tests)
Scope limits (documented):
- No auto-invocation in the turn loop.
- No refusal wiring on violation.
- No refactoring of existing scattered enforcement sites.
- Defensive boundary-id rebinding masks predicate bugs; debug-mode
surfacing is a future enhancement.
Closes the 'identity hedges are generic' gap. When IdentityCheck reports
that a specific axis is deviating AND the pack supplies an axis_hedges
entry for that axis, the assembler uses that axis's phrase instead of
ADR-0028's generic preferred_hedge_*. The hedge text now names what is
actually at issue.
Selection: lex-smallest axis_id in (ctx.deviation_axes ∩ axis_hedges).
Deterministic; loader emits axis_hedges in lex order on axis_id.
Example surface at alignment=0.30 (strong band) under default pack:
No deviation → 'It seems that truth reveals reality.'
truthfulness deviates → 'Evidence is thin that truth reveals reality.'
coherence deviates → 'This does not yet cohere: truth reveals reality.'
reverence deviates → 'Reports suggest truth reveals reality.'
Same trajectory + truthfulness deviation, three different packs:
default_general_v1 → 'Evidence is thin that truth reveals reality.'
precision_first_v1 → 'The evidence does not support that truth reveals reality.'
generosity_first_v1 → 'Truth reveals reality.' (above generosity's strong=0.20)
Schema (additive, optional):
surface_preferences.axis_hedges = {
<axis_id>: { 'strong': str, 'soft': str, 'qualifier': str },
...
}
Bounds: each phrase length 1–64; axis_id non-empty. Absent block →
ADR-0028 byte-for-byte fallback. Loader emits pairs in lex order on
axis_id for hashability + deterministic tie-break.
Files:
core/physics/identity.py
+ class AxisHedge (frozen: strong, soft, qualifier)
SurfacePreferences gains axis_hedges: Tuple = ()
packs/identity/loader.py
+ _build_axis_hedges(): parse + bounds-check + emit lex-ordered tuple
generate/surface.py
SurfaceContext gains deviation_axes: frozenset[str] + axis_hedges tuple
+ _axis_specific_phrase(ctx): lex-smallest match or None
_apply_hedge consults axis-specific phrase before ADR-0028 fallback
Depth languages (he, grc) unchanged — ADR-0030 canonical phrases
chat/runtime.py
_build_surface_context lifts identity_score.deviation_axes and
prefs.axis_hedges into SurfaceContext
packs/identity/*.json
Three v1 packs gain axis_hedges blocks (truthfulness, coherence,
reverence — each pack uses voice consistent with its character)
scripts/ratify_identity_packs.py (no change — idempotent)
packs/identity/*.mastery_report.json
Auto-refreshed. New SHAs:
default_general_v1 → 2ab7d469013509ba5030313ca9a609a443d0716e3ddcc5596f59858ce054f5d3
precision_first_v1 → 78aa1e6a68a35c2c8576b6196a52d421b94f6d11e006128986902a4fd08679af
generosity_first_v1 → 511f1ce20edd4266239da61443bfc93473a5433f20bfee6692a25a03073dc933
Tests: tests/test_identity_score_decomposition.py — 17 new tests:
per-axis phrase selection, band gating still applies, pack swap with
same deviation produces three different phrases, lex tie-break is
deterministic, depth-language fallback to ADR-0030, backward compat
with empty deviation_axes, and the contract that all three v1 packs
ship axis_hedges for all three default-pack axes.
Suite status (all green):
cognition 121, teaching 17, runtime 19, formation 182, smoke 67
identity+safety+English+depth divergence 71
score decomposition 17
Scope limits (documented in ADR-0031):
- English-only at v1 (depth languages use canonical ADR-0030 phrases)
- Lex tie-break is operational not semantic — pack authors can re-key
if they need a different priority
- No dominance-driven phrasing (Interpretation A); preserved as
forward-compatible follow-up
Docs: ADR-0031 (Accepted) recorded; docs/identity_packs.md gains
§Axis-specific hedge phrases section and updated v1-pack SHAs; memory
'identity-packs.md' refreshed.
Closes the ADR-0028 'English-only differentiation' gap. Hebrew and
Koine Greek surfaces now consult identity-pack surface_preferences for
hedge and claim-strength shaping, using language-appropriate canonical
hedge phrases. CORE's three-language foundation (English / Hebrew /
Greek) is now uniformly identity-aware at the realizer.
Algorithm: the same four-band hedge/claim-strength logic from ADR-0028
runs for all three languages. Thresholds and claim_strength come from
the identity pack (carried on SurfaceContext). Hedge phrases come
from ctx for English and from a new module-level constant
_DEPTH_HEDGE_PHRASES for Hebrew (he) and Koine Greek (grc).
he: 'נראה ש' / 'אולי' / 'במקרים מסוימים,'
grc: 'δοκεῖ ὅτι' / 'ἴσως' / 'ἐνίοτε,'
Pack swap visibly affects depth-language output: a precision_first
identity pulls hedges to higher alignment than default; a generosity
pack pulls them to lower alignment. Same trajectory through the
manifold → three different Hebrew surfaces under three different
packs. Same for Greek.
Files:
generate/surface.py
_DEPTH_HEDGE_PHRASES (new module constant)
_apply_hedge(surface, ctx, lang='en') — lang param added
_assemble_he(.., ctx) — ctx param added
_assemble_grc(.., ctx) — ctx param added
SentenceAssembler.assemble — passes context to he/grc
tests/test_identity_surface_divergence_depth.py — 15 new tests:
Hebrew hedge bands, Greek hedge bands, pack-swap divergence in
both depth languages, three-language hedge phrase distinctness,
backward compatibility with ctx=None
docs/decisions/ADR-0030-depth-language-hedge.md — Accepted
docs/identity_packs.md — closes known-limit #1
memory/identity-packs.md — refreshed
Backward compat:
- _apply_hedge default lang='en' so existing callers unaffected.
- English surface output byte-for-byte unchanged.
- _assemble_he / _assemble_grc with ctx=None match pre-ADR output
byte-for-byte (asserted by TestBackwardCompatibility).
Scope limits (documented in ADR):
- Depth-language hedge phrases are canonical defaults, not per-pack
overridable yet. Future ADR may add a 'languages' block to the
pack schema if a downstream deployment needs override capability.
- Contrast ('However, ...') and subordination ('Given that ..., ...')
remain English-only. Hedge is the dominant differentiator.
- Hebrew/Greek grammar / word order unchanged.
Suite status: cognition 121, teaching 17, runtime 19, formation 182,
smoke 67 — all green. Identity + safety + divergence suites: 26+15+15+15=71
all green.
Closes the trust gap ADR-0027 opened: making the identity manifold
swappable was necessary for downstream robotics / personalization /
creative deployments, but it left nothing structurally preventing a
downstream identity pack from disabling core safety constraints.
Safety packs sit at a separate trust layer, fail closed on every error
path, and union their boundaries into every runtime manifold regardless
of which identity pack is selected.
Architecture (sibling to identity packs, structurally distinct):
Layer Swappable? Removable? Schema
--------------- ---------- ---------- -----------------------------
Safety pack No No boundary_ids + descriptions
Identity pack Yes No value_axes + surface_prefs
Language pack Yes (>=1 reqd) vocab / morphology / packs
Composition rule (at ChatRuntime startup, additive only):
identity = load_identity_manifold(config.identity_pack)
safety = load_safety_pack() # fail-closed
final.boundary_ids = identity.boundary_ids ∪ safety.boundary_ids
Safety contributes boundaries only — no value_axes, threshold, or
surface_preferences. This keeps existing tests that assert on identity
axis sets passing byte-for-byte, and matches the semantic intent
(safety is what's forbidden, not what's pulled toward).
Shipping safety pack: packs/safety/core_safety_axes_v1.json
→ mastery_report_sha256 ee1249acdf8c273aeb656d803c37ef915e536d85f177f5cc18c6e2f6c995ce29
Five v1 boundaries, each closing a specific CLAUDE.md doctrine:
no_fabricated_source — no invented provenance
no_hot_path_repair — no normalization in propagate/stream/store
no_identity_override — user text cannot mutate identity
no_silent_correction — failures are typed and visible
preserve_versor_closure — ||F * reverse(F) - 1||_F < 1e-6
Fail-closed semantics:
SafetyPackError inherits from RuntimeError (NOT ValueError) so
catch-and-continue is discouraged at the type level. Missing file /
malformed JSON / empty boundaries / duplicate boundary / failed
self-seal all raise. ChatRuntime.__init__ does not catch.
Files:
packs/safety/core_safety_axes_v1.json shipping pack
packs/safety/core_safety_axes_v1.mastery_report.json signed report
packs/safety/__init__.py public surface
packs/safety/loader.py load_safety_pack(),
SafetyPack,
SafetyPackError,
DEFAULT_SAFETY_PACK
scripts/ratify_safety_pack.py idempotent driver
chat/runtime.py composition wiring
tests/test_safety_pack.py 15 tests:
loader bounds,
fail-closed,
composition under
all 3 identity packs
docs/decisions/ADR-0029-safety-packs.md decision record
docs/safety_packs.md operational ref
README.md §Safety Pack added
memory/safety-pack.md auto-memory entry
Suite status: cognition 121, teaching 17, runtime 19, formation 182,
smoke 67, identity 41, safety 15 — all green.
Drives the three v1 identity packs through the full formation pipeline
(Forge -> Compose -> Compile -> Run -> Ratify) and embeds the resulting
self-sealed MasteryReport SHAs into each pack file. Companion
'<pack_id>.mastery_report.json' artifacts ship alongside. Loader now
defaults to production mode (require_ratified=None) and ChatRuntime
calls it without the dev-only override.
Ratification results:
default_general_v1 -> 0b77357fe4359f161d7ca72f184b6e0db2f9e2de16b32c237a3b80d2bbb005b4
precision_first_v1 -> 5f5000dba9a0dd19d831e9ab5d3c0e3b9faf6abdc2648940e96aa6263af3302e
generosity_first_v1 -> 91716117558113f74b2c6d07a804cb324f262d62b743523d901d1386a4f85ae4
Driver: scripts/ratify_identity_packs.py — idempotent. Re-running on
already-current packs is a no-op (verified by a test). Each pack is
treated as its own provenance source: source_sha = SHA-256 of the pack's
canonical JSON body with mastery_report_sha256 blanked, so the
self-referential chain stays stable across SHA updates. Axes become
ConceptCandidates; canned override-attempt triples become
CounterCandidates; the identity_anchor template renders the body.
Loader hardening (packs/identity/loader.py):
* When require_ratified resolves to True, the loader now requires the
companion '<pack_id>.mastery_report.json' to exist, its
report_sha256 to match the pack's mastery_report_sha256, and its
self-seal to verify via formation.hashing.verify_seal.
* Tampered companion (wrong SHA, broken seal) is rejected with a
diagnostic IdentityPackError.
Tests: 18 -> 23. New cases cover production-mode loading of all three
v1 packs, missing companion file, mismatched companion SHA, failed
self-seal, and end-to-end idempotency of the ratification script
(subprocess-launched, asserts pack bytes unchanged on re-run).
Suite status: cognition 121, teaching 17, runtime 19, formation 182,
smoke 67 — all green.
Docs updated: ADR-0027 status flipped to Phases 1-6 complete with the
three report SHAs recorded; docs/identity_packs.md notes the ratified
SHAs and the re-ratification command; memory file 'identity-packs.md'
refreshed.
Patent-grade precision pass over the doc surface so every claim
about the Forward Semantic Control chain is backed by a file path,
test count, or commit hash.
Updates by file:
README.md
- Modernize Quick Start: add `core test --suite adr-0024`,
`core demo phase6 / phase5 / all / list-results`, full CLI map.
- New "Forward Semantic Control — The ADR-0024 Chain" section
with layer/ADR mapping and CI-enforced C1/C2/C3 claims table.
- Cross-links to runtime_contracts.md, phase5_stratified_findings,
phase6_comparative_demo, and the central results directory.
docs/decisions/README.md
- Index was stale at ADR-0014. Add ADR-0015 through ADR-0026
with accurate Accepted statuses.
- New "ADR-0024 chain — Forward Semantic Control closure" section
laying out the five-ADR / six-commit dependency order with test
counts per phase.
docs/runtime_contracts.md
- Add "Ranked-with-margin contract (ADR-0026 / Phase 3)" section
between the existing Phase 2 refusal and Phase 4 rotor sections.
- Documents threshold-mode vs margin-mode behaviour, δ = 0.4
default, falsifiability gate, and Cl(4,1) signature motivation.
docs/PROGRESS.md
- Add naming-note disambiguation: capability-roadmap "Phase N"
vs ADR-0024 chain "Phase N" are distinct.
- New top-of-document "ADR-0024 Chain — Forward Semantic Control
Closure" section with per-phase commit + test-count table and
a single-command verification path.
docs/Whitepaper.md
- New Section XII "Forward Semantic Control — Generation Without
Sampling" before Extensions. Five-component description of the
mechanism (region, intersection, destination check, rotor check,
margin gate) with explicit "what a sampling LLM cannot exhibit"
contrast. Existing Section XII renumbered to XIII.
docs/Yellowpaper.md
- New Section IX-B "Forward Semantic Control — Formal Admissibility
Specification" with eight subsections covering:
1. AdmissibilityRegion typed triple (I, B, Φ)
2. Destination-side admissibility (σ_dest, admit_threshold)
3. Rotor-side admissibility (σ_rotor, admit_rotor)
4. Ranked-with-margin gate (admit_margin, deterministic
tie-break by index, default δ = 0.4)
5. Honest refusal (InnerLoopExhaustion typed evidence,
RefusalReason enum, trace fold)
6. Composition order at the generation seam
(admit_step = intersection ∧ destination ∧ rotor)
7. Replay determinism contract (5 test lanes pinning byte
identity across reruns)
8. Verification invariants table (6 new structural contracts)
- Patent-grade: every predicate is named, every module is path-
referenced, every test is file-referenced, the load-bearing
architectural placement decision (rotor admissibility lives in
generate/, NOT algebra/, NOT field/) is stated by name with
its rejection reasoning.
No code changes; tests untouched (1099 passed, 2 skipped baseline
from commit 36aad75 still holds).
Promote ADR-0025 from Draft (design note) to Accepted with the
architectural home decision reversed: rotor admissibility lives at
the same generation/propagation seam as ADR-0024's destination
check — in a sibling-but-separate module
`generate/rotor_admissibility.py` — NOT in `algebra/versor.py` or
`field/propagate.py`.
Algebra rejected because admissibility is a pack-semantic test, not
a closure invariant; placing it there couples algebra to pack state
and creates structural temptation toward grade-projection repair
(CLAUDE.md §Normalization Rules forbids). field/propagate rejected
as a forbidden normalization site even when framed as precondition
guard. The clean answer is generation-side, in its own file:
endpoint admissibility (token-side, blade) and rotor admissibility
(rotor-side, frame) compose at the same seam while remaining
conceptually separable.
New module generate/rotor_admissibility.py:
RotorVerdict — admit/reject + score + region_label + reason
check_rotor_admissibility(region, *, field_current, rotor)
-> RotorVerdict
Pure semantic check:
F' = versor_apply(V, F_current)
score = cga_inner(F', region.frame_versor)
admit iff score > 0 (basic positivity in frame half-space)
No state mutation, no closure enforcement (algebra's job).
region.frame_versor is None → trivial admit (back-compat).
RefusalReason extended:
INNER_LOOP_EXHAUSTION — destination-side (ADR-0024 / ADR-0026)
ROTOR_REJECTION — rotor-side (this ADR)
The two reasons let the trace name the axis that ran out without a
parallel exception type. InnerLoopExhaustion(ValueError) hierarchy
unchanged; back-compat preserved.
Wiring in generate/stream.py:
threshold mode per-candidate rotor check after destination admit;
reject → log rotor score, retry next candidate;
exhaustion routes reason to ROTOR_REJECTION iff
any rotor rejection occurred in the step
margin mode rotor check on the top-ranked admissible candidate;
reject → immediate InnerLoopExhaustion(
reason=ROTOR_REJECTION) carrying the destination
ranking + the rejected rotor's score
Phase 4 keeps positivity (score > 0), not margin, on the rotor side.
No cross-case calibration evidence to inform a rotor-margin constant
yet; promoting to ranked-with-margin awaits Phase 5 diversified-
families evidence. Destination-side margin (ADR-0026) is unchanged.
Teaching boundary closed at Stance A — strictly hygiene-only.
Rotor rejections are deterministic geometric outcomes, not reviewed
teaching examples. CLAUDE.md §Teaching Safety forbids parallel
correction paths; entangling rotor rejection with reviewed teaching
would create one. Confirmed in ADR-0025 §"Teaching boundary".
Acceptance evidence (tests/test_rotor_admissibility.py, 11 passing):
No-frame back-compat — frame_versor=None tokens identical to
Phase 3 baseline
Admit when aligned — frame_versor=seed direction admits
seed→destination rotor
Refuse with named axis — orthogonal frame raises
InnerLoopExhaustion(reason=ROTOR_REJECTION); threshold mode
also routes reason correctly
versor_condition < 1e-6 preserved on admitted rotors
Deterministic replay — 5 reruns identical for both admitted and
refused turns
Suite results:
full: 1048 passed, 2 skipped (+11 new rotor tests)
docs/runtime_contracts.md updated with "Rotor admissibility contract"
subsection documenting the seam, the algorithm, and the refusal
taxonomy.
Architectural invariants preserved:
no new code in algebra/versor.py, field/propagate.py, vault/store.py
no approximate recall, no cosine similarity, no HNSW/ANN
no hot-path repair; check is pure typed-verdict
InnerLoopExhaustion(ValueError) hierarchy unchanged
Replace the static-threshold admissibility gate with a ranked-with-
margin check that is scale-invariant under blade-norm variation.
Phase 4 characterization established no single global threshold
separates the v2 mechanism-isolation cases (blade norms vary ~10x);
margins between top and second-ranked candidates do, because they
scale with the blade norm and carry the relative ordering the
geometry actually delivers.
New primitives in generate/admissibility.py:
RankedCandidate — (index, word, score)
MarginVerdict — admit/reject + top + margin + full ranking
rank_candidates_by_blade — sort admissible set by cga_inner desc,
strict > tie-break by ascending vocab index
check_margin — admit top iff score>0 AND margin>=delta
Selection semantics in margin mode are blade-rank-driven: the top-
ranked admissible candidate IS the admitted destination. Differs
from threshold mode (field-driven _nearest_next then per-candidate
gate). Both modes coexist; threshold is the default and ADR-0024
acceptance evidence is preserved byte-for-byte.
Wired through:
core/config.py admissibility_mode="threshold" (default)
admissibility_margin=0.4
chat/runtime.py forwards both fields
generate/stream.py margin_mode_active branch — ranks the
candidate set once per step, admits or
raises InnerLoopExhaustion with the full
ranking in rejected_attempts
Default delta = 0.4 chosen from the v2 case margins:
V2-001: 0.596 V2-002: 0.456 V2-003: 13.27
V2-004: 3.37 V2-005: 12.74
min = 0.456 → 0.4 admits all 5 with headroom; 0.5 would refuse
V2-002. The default is falsifiable: Phase 5 may surface a case
below 0.4, which should be reported as an architectural finding
rather than patched per-case.
Acceptance evidence (tests/test_margin_admissibility.py, 13 passing):
5/5 v2 cases pass in margin mode; forbidden_token in every
case's rejected_attempts ranking
Refusal-on-insufficient-margin: delta=0.9 on V2-001 (margin
0.597) raises InnerLoopExhaustion with full ranking; no silent
boundary fallback
Threshold mode byte-identical with or without margin plumbing
5 reruns produce identical canonical trace steps
Strict > tie-break: equal scores resolve to lower-index winner
deterministically
Invariants preserved:
versor_condition < 1e-6 — rotor V is constructed only for the
admitted candidate; margin mode adds no normalization/repair site
Deterministic replay — strict > tie-break now load-bearing in
rank_candidates_by_blade alongside vocab.nearest
No approximate recall, no cosine similarity, no HNSW/ANN; pure
rank-and-difference on exact cga_inner scores
No new code in field/propagate.py, algebra/versor.py,
vault/store.py, or chat/runtime.respond()
Suite results:
full: 1037 passed, 2 skipped (+13 new margin tests)
core eval cognition: 13/13, 100% intent_accuracy,
100% versor_closure_rate
ADR-0026 documents the contract, the single-delta rationale, the
falsifiability story, and the residual risks. Margin mode is
flag-gated default-off; a future ADR may promote it to default
after Phase 5's diversified families confirm the single delta
holds (or surface the architectural finding if it doesn't).
Rewrite v1+dev FSC cases with pack-grounded tokens drawn from
en_core_cognition_v1. Closes the 9/9 region-construction failure
recorded in Phase 4 (chain_tokens alpha/beta/gamma/delta/etc. were
ungrounded in the active pack).
Token mappings preserve each case's test pattern:
* alpha→beta→gamma→delta → tone→evidence→memory→wisdom (causes)
* mu→nu→omicron → voice→memory→wisdom (means)
* pi→rho→sigma→tau → question→answer→understanding→wisdom (precedes)
* upsilon→phi→chi → word→discourse→narrative (part_of)
* eta/theta/zeta + means-distractors → symbol/word/meaning + image/light
Result post-rewrite:
* skipped_count: 9/9 → 0/9 (region constructible)
* causal_attribution_valid: True (preserved)
* code_path_residual: 0.0 (preserved)
* inner_loop_t0 hash stability: 1.0 (preserved)
* best_separation_quality: 0.0 → 0.056 (still below 0.8 gate)
The rewrite exposes a deeper architectural finding documented in the
ADR addendum: v1/dev case schema (prime + chain_tokens) probes
teaching-driven walk (ADR-0022/0023), not the inner-loop's
blade-admissibility mechanism (ADR-0024). The Phase 2 corpus-
observation runner's reuse of v1/dev was a categorical error.
v1/dev belong to the boundary-walk lane (runner.py); v2 belongs to
the inner-loop lane (v2_runner.py). Phase 5 will author the benign
inner-loop corpus the EXHAUSTION_CEILING gate was designed against.
Tests pinning new state:
* TestV1ChainBladeUngrounded → TestV1ChainBladePostGrounding
(assertions inverted: skipped_count == 0; separation_quality < 0.5)
* TestPhase2 (unchanged) continues to assert causal_attribution_valid
and hash stability; exhaustion remains a finding, not an invariant.
Shay