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.
First end-to-end curriculum unit through the production
propose / review --accept / supersede operator surfaces against the
active teaching corpus. Replay-equivalence gate passed for every
proposal; public split byte-identical; holdout term_capture lifted
exactly as predicted.
- Supersede `verification_wisdom_grounds_judgment` →
`verification_wisdom_requires_knowledge`. Fixes the only corpus-
fixable holdout miss: `verification_wisdom_036`
("Is wisdom the same as knowledge?") now grounds with both
expected terms. Provenance carries
`:supersede(verification_wisdom_grounds_judgment)`.
- Propose + accept four new chains closing epistemology subgraph
cells:
cause_understanding_requires_knowledge
cause_judgment_requires_wisdom
verification_evidence_grounds_knowledge
cause_inference_requires_evidence
Each chain is pack-consistent, uses canonical predicates, and opens
a previously-empty (subject, intent) cell. Replay gate confirmed
no metric regression on the public split before each accept.
Lift (cognition eval):
public : intent 100% / surface 100% / term 91.7% / versor 100% (unchanged)
holdout : intent 100% / surface 94.7% / term 70.8%→75.0% / versor 100%
The remaining four holdout misses (correction_truth_040,
procedure_define_010, unknown_spirit_041, unknown_word_018) are
architectural — surface-composition gaps in the correction-
acknowledgment template, procedure-intent routing, and unknown-
intent surface — and out of scope for corpus surgery.
- teaching/cognition_chains/cognition_chains_v1.jsonl — 10 → 15 lines
(4 appends + 1 supersession marker; 1 retired chain still on disk
per the audit doctrine of append-only at the file level).
- teaching/proposals/proposals.jsonl — new append-only proposal log
with `created` / `replay` / `transition` / `accepted_corpus_append`
events for every accepted proposal.
- docs/curriculum/epistemology_v1.md — full curriculum log:
rationale per chain, prediction-vs-result on the holdout lift,
reproducibility commands, architectural-gap analysis.
Lanes (regression check):
core test --suite smoke 67 passed
core test --suite cognition 121 passed
core test --suite teaching 17 passed
tests/test_eval_holdout_split 10 passed
The first curriculum unit that *measurably moves a cognition-lane
metric* through the operator surfaces, with full provenance from
operator note back to corpus append.
`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.
Three shareable demo / benchmark writeups modeled on the existing
`docs/evals/phase6_comparative_demo.md` treatment, each accompanied
by an asciinema-rendered GIF for at-a-glance viewing on the repo page.
- docs/evals/anti_regression_demo.md — three-gate defense; per-gate
table; honesty paragraph about the synthetic regression in S2 (real
ReplayEvidence shape via documented run_replay= kwarg); sample run
output; falsifiable claims index.
- docs/evals/learning_loop_demo.md — headline before/after; CORE-vs-
pretraining comparison table; trust-boundary code snippet showing
the _CORPUS_PATH swap; per-scene table; full sample run; subject-
selection rationale (pack-resident ∧ no active chain ∧ deterministic
intent classification).
- docs/evals/teaching_loop_bench.md — what's byte-identical and why
it matters per artifact; 100-run reference numbers (unique=1 across
all five artifacts; mean=1.849s p50=1.838s p95=1.851s); pairing
paragraph with ADR-0045 (read vs write determinism).
GIF captures (rendered with asciinema 3.2.0 + agg 1.8.1, github-dark
theme, JetBrains Mono):
- docs/evals/assets/anti_regression.gif (120K, 944x843)
- docs/evals/assets/learning_loop.gif (332K, 944x1039)
- docs/evals/assets/teaching_loop_bench.gif (64K, 860x1000)
Raw .cast files preserved alongside the GIFs for re-rendering at
different themes / speeds / sizes without re-recording.
README.md — added writeup-link column to the Inter-Session Memory
three-demo table.
Three external-facing demos / benchmarks now match the existing
audit-tour / pack-measurements / long-context-comparison treatment:
preamble printed before the run, README index entries, claims table.
- core/cli.py — _ANTI_REGRESSION_PREAMBLE, _LEARNING_LOOP_PREAMBLE,
_TEACHING_LOOP_BENCH_PREAMBLE. Each lists reference ADRs, what to
expect, trust boundary, test gate, and machine-readable invocation.
Wired through _print_preamble in the demo dispatch + bench dispatch
(suppressed under --json).
- README.md — new "Inter-Session Memory — Reviewed Learning" section
between Teaching Order and Architecture: the three-gate trust
property table, the three live-demo table, and the operator-surface
command list. Quick-start block lists `core demo anti-regression`,
`core demo learning-loop`, and `core bench --suite teaching-loop
--runs 100` alongside the existing demos.
No code paths changed — preambles are stdout-only when not under JSON.
Tests unchanged; 17/17 green (5 anti-regression + 7 learning-loop + 5 bench).
`core bench --suite teaching-loop [--runs N]` runs the full reviewed-
corpus extension pipeline (propose → real replay-equivalence gate →
operator accept) N times against an identical input and asserts
byte-identical artifacts every run:
- proposal_id (SHA-256 of canonical-JSON payload)
- replay_baseline (cognition lane metrics on active corpus)
- replay_candidate (cognition lane metrics on transient corpus)
- regressed_metrics (sorted tuple)
- chain_id_written
Also reports per-iteration latency (mean / p50 / p95) and total wall.
100-run result against today's main:
unique(proposal_id)=1 unique(baseline)=1 unique(candidate)=1
unique(chain_id)=1 active_corpus_byte_eq=True
mean=1.849s p50=1.838s p95=1.851s
The full learning loop is replayable bit-identically across N
independent invocations. Pairs naturally with ADR-0045's 100% exact-
NIAH recall numbers — same epistemic class of guarantee, applied to
the *learning loop* itself rather than only to retrieval. No LLM
provider can publish equivalent numbers on a learning path.
- benchmarks/teaching_loop.py — `run_teaching_loop_determinism(runs)`
returns a typed `TeachingLoopBenchReport` with uniqueness counts,
determinism flag, byte-identical-active-corpus flag, and latency
distribution (mean / p50 / p95 / total). Pure-stdlib percentile —
no numpy dep on this path.
- benchmarks/run_benchmarks.py — `bench_teaching_loop_determinism`
shim + `_SUITES["teaching-loop"]` registration + runs= passthrough.
- core/cli.py — `--suite teaching-loop` choice added to bench parser.
- tests/test_teaching_loop_bench.py — 5 tests pin determinism at
small N, proposal_id SHA-256 shape, canonical chain_id layout,
latency stats well-formedness, JSON serialisation.
Trust boundary: every write is confined to a tempdir created inside
the bench loop; the active corpus is read once at start, once at end,
and any byte difference would fail the bench.
`core demo learning-loop` (+ `--json`) walks a single prompt through the
full ADR-0055..0057 inter-session-memory architecture:
S1. Cold turn → universal disclosure, grounding_source=none
S2. Discovery emission → DiscoveryCandidate to attached sink
S3. Operator proposal → real replay-equivalence gate, no regression
S4. Operator accept → TRANSIENT corpus only; active untouched
S5. Same prompt → teaching-grounded surface with the new chain
Before / after on the deterministic prompt "Why does thought exist?":
before: [none] I don't know — insufficient grounding for that yet.
after: [teaching] thought — teaching-grounded (cognition_chains_v1):
cognition.thought; logos.internal. thought reveals meaning
(cognition.meaning). No session evidence yet.
The active corpus on disk is byte-identical pre/post. The demo writes
only to a transient corpus, then swaps `_CORPUS_PATH` for the after
turn — the same pattern the replay-equivalence gate uses.
- evals/learning_loop/run_demo.py — `run_demo(emit_json=False)` returns
a structured `DemoReport` with both surfaces and per-scene detail.
- core/cli.py — `core demo learning-loop` target wired.
- tests/test_learning_loop_demo.py — 7 tests pin: full loop closes,
before is ungrounded, after contains new chain atoms (thought /
reveal / meaning), discovery emits ≥1, replay gate reports no
regression, S4 byte-identical active + 1 line on transient, same
prompt drives both surfaces.
Lane state: learning-loop-demo 7 new — green. Demo runs in ~15s
end-to-end (cognition lane runs twice via replay gate).
No LLM provider has a published equivalent of this loop: per-fact
provenance from operator accept to surface, replay-equivalence gate
proving non-regression, byte-identical active state regardless of
outcome, full audit trail back to the originating cold turn.
`core demo anti-regression` (+ `--json`) is a self-contained walkthrough of
the three independent gates that every reviewed-corpus extension must pass.
Designed for showcasing CORE's epistemic discipline to reviewers / industry
observers — no LLM provider has a published equivalent.
Scenes:
- S1. Eligibility predicate refuses an undetermined-polarity candidate
before any replay is invoked. ProposalError raised; no log row.
- S2. Replay-equivalence gate auto-rejects a regressing candidate with
the named regressed metrics in the operator note. Uses the documented
`run_replay=` kwarg of `propose_from_candidate` to inject a controlled
regression of the same `ReplayEvidence` shape the real gate produces.
- S3. Real `teaching.replay.run_replay_equivalence` runs the cognition
public lane. A replay-equivalent candidate reaches 'pending' — operator
`--accept` is still required to write.
Each scene asserts the active corpus is byte-identical pre/post.
- evals/anti_regression/run_demo.py — `run_demo(emit_json=False)` returns
a structured `DemoReport`; verbose human output by default, JSON on flag.
- core/cli.py — `core demo anti-regression` target wired alongside
audit-tour / pack-measurements / long-context-comparison.
- tests/test_anti_regression_demo.py — 5 tests pin each scene's
load-bearing claim + the corpus-byte-identical invariant.
Lane state: anti-regression-demo 5 new — green. Demo runs in ~10s end-to-end.
`core teaching supersessions` (+ `--json`) pairs each retired chain with its
active replacement. Derived view over `audit_corpus()`; pure, read-only.
- teaching/audit.py — `SupersessionRecord` + `supersession_history(report)`
returns retired→replacement pairs ordered by retired-line (disk order,
oldest first). Orphan supersessions (retired with no live entry carrying
the matching `superseded_by` — e.g. chained retirements where the middle
link itself was retired) surface as `replacement=None` so silent corpus
drift is inspectable.
- core/cli.py — `core teaching supersessions [--json]`. Exit 1 if any
orphan is detected (catches silent drift in CI); 0 otherwise.
- tests/test_supersession_history.py — 7 tests pin empty-history,
single-pair shape, chained-supersession surfaces both pairs, line-no
ordering, orphan detection, JSON round-trip, no corpus mutation.
Lane state: smoke 67 / cognition 121 / supersession-history 7 new / supersede 13 /
audit 23 — green. `core eval cognition`: unchanged (intent 100% / surface 100% /
term 91.7% / versor 100%). Real corpus today reports `(no supersessions)`.
`core teaching supersede <old_chain_id> --subject ... --intent ... --connective ...
--object ... --review-date YYYY-MM-DD` is the second corpus mutation surface
(alongside accept_proposal). No replay gate — it's a deliberate operator action
that replaces a hand-authored or previously discovery-promoted chain.
- teaching/supersede.py — `supersede_chain()` orchestrator with pre-checks
(review_date format, intent whitelist, pack-consistency via re-audit,
no double-supersede, no self-supersede, no new-chain-id collision) and
byte-identical rollback on post-audit failure.
- teaching/proposals.py — extended `append_chain_to_corpus` with optional
`superseded_by` kwarg; remains the only function in the codebase that
writes to the active teaching corpus.
- core/cli.py — `core teaching supersede` subcommand wired to the live
`_CORPUS_PATH`; EPILOG updated with example.
- tests/test_supersede.py — 13 tests pin every gate, byte-identical
rollback on rejection, append-only at disk level, audit-and-runtime
parity after supersession, hand_authored provenance with
`supersede(<old_chain_id>)` tag.
Lane state: smoke 67 / cognition 121 / teaching 17 / supersede 13 / audit 23 /
proposals 16 / contemplation 16 / contemplation-wiring 6 / discovery 24 — green.
`core eval cognition`: intent 100% / surface 100% / term 91.7% / versor 100% — unchanged.
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>
ChatRuntime.attach_contemplation(enabled=True) flips an opt-in
flag; when on, each emitted DiscoveryCandidate runs through
teaching.contemplation.contemplate before the sink writes the
JSONL line. Default off ⇒ Phase B raw output preserved byte-
identical.
Trust boundary
- Contemplation is read-only over pack + corpus.
- Without an attached discovery sink the flag is inert (no hidden
work — emission requires an observable destination).
- Active teaching corpus on disk byte-identical pre/post.
Lanes: smoke 67 / runtime 19 / cognition 121 / contemplation-
wiring 6 — all green. Cognition eval unchanged.
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.
Lands the three load-bearing pieces of ADR-0055 Phase A so later
phases (DiscoveryCandidate, TeachingChainProposal) have a safe
substrate to write into.
- teaching/audit.py: pure, deterministic re-parse of the reviewed
corpus with same gates as the runtime loader but keeps drop
reasons (invalid_json, missing_required_field:*, unsupported_intent,
pack_missing_subject, pack_missing_object, superseded_by:*).
- teaching/provenance.py: typed Provenance(adr_id, source,
review_date, raw); legacy "reviewed" maps to "hand_authored" so
current corpus reports the canonical enum without a file rewrite.
- chat/teaching_grounding._corpus_index honors superseded_by —
active view drops superseded entries while disk preserves history.
- core teaching audit CLI subcommand (--json optional); exits 1 on
any drop so CI catches silent corpus shrinkage from pack swaps.
Observable behaviour unchanged: corpus is 10/10 loaded, all five
core lanes green (smoke 67, cognition 121, runtime 19, teaching 17,
packs 6), cognition eval metrics identical on dev / public /
holdout splits. versor_condition < 1e-6 invariant untouched.
Tests: tests/test_teaching_audit.py — 23 tests covering provenance
parser, real-corpus determinism, every drop-reason path,
supersession semantics, runtime/audit parity, read-only contract.
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. Opt-in via
RuntimeConfig.forward_graph_constraint (default False).
A/B characterisation on the 13-case cognition lane shows wiring is
correct and safe, six cases produce a non-trivial constraint, and
the lane's surface_groundedness / term_capture_rate gap is downstream
of propagation — isolating the next ADR's scope to realizer / surface
assembly.
Lanes green: smoke 67 / cognition 121 / runtime 19 / algebra 132 /
teaching 17 / packs 6. core eval cognition unchanged with the flag
off (default), unchanged with the flag on (constraint engages but
does not alter surface for this lane).
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.
Brings in the original ADR-0046 work (Perplexity-coauthored) plus the
mergeability fix. The merge preserves both commits so the history
records what was tried, what broke, and what fixed it.
Lanes green on the merged tree:
smoke 67 cognition 121 runtime 19 algebra 132 teaching 17 packs 6
core eval cognition intent_accuracy=100% versor_closure_rate=100%
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.
