core/generate
Shay 1adf4f5de5 feat(contemplation): contemplation v0 pass manager (N6) + boundary-first growth fix
generate/contemplation/{findings,pass_manager}.py: a single bounded pass — route (N3) -> classify+enrich (N4) -> terminal -> maybe emit proposal-only (N5). No loops/daemon/L10. Seven terminals: SOLVED_VERIFIED / REFUSED_KNOWN_BOUNDARY / REFUSED_UNSUPPORTED_FAMILY / CONTRADICTION_DETECTED / PROPOSAL_EMITTED / AMBIGUOUS_ORGAN / NO_PROGRESS. R2 solved+verified end-to-end; R1 routed setup is SOLVED_VERIFIED (numeric answer stays the eval lane in v0).

Hazard found+fixed: N6 exposed that category_pair_not_found fires on ANY non-R2 text, so mapping it to a growth surface made gibberish falsely PROPOSAL_EMITTED. Reclassified it to input_shape and made missing_category_pair reserved — only the PRECISE missing_total_count/missing_weighted_total remain reachable growth surfaces. Classification is boundary-first (input_shape non-blocking), so a problem one organ recognizes as a substantive boundary never proposes against the other's broad refusal.

Acceptance proven: known correct refusal -> no proposal; unsupported gap -> proposal-only artifact (exactly the 2 missing_* gaps over the gold); answer-key contradiction -> CONTRADICTION_DETECTED; organ conflict -> AMBIGUOUS_ORGAN. 188 tests green incl. architectural invariants; R1 7/0/3 + R2 reader 10/0/0 unchanged; off-serving.
2026-06-07 08:59:47 -07:00
..
answer_choices feat(answer-choices): multiple-choice verifier with contradiction flag (R2 C4) 2026-06-07 07:26:00 -07:00
binding_graph feat(comprehension): the divisive comparative frame — "half as many" as exact integer division (PR-6c) 2026-06-06 20:18:39 -07:00
comprehension
constraint_comprehension feat(constraint): two-category reader — prose to ConstraintProblem (R2 C5-C9) 2026-06-07 07:34:55 -07:00
contemplation feat(contemplation): contemplation v0 pass manager (N6) + boundary-first growth fix 2026-06-07 08:59:47 -07:00
cue_precision
derivation feat(derivation): math-serving reach seam — select_self_verified is policy-aware (ADR-0206 §5) 2026-06-06 15:46:14 -07:00
determine feat(determine): calibrated disclosed estimation — the engine earns the right to guess (Step E) 2026-06-06 13:49:07 -07:00
meaning_graph fix(comprehend): relational reader fail-closed on leftover relational structure 2026-06-06 09:45:10 -07:00
proof_chain feat: add deductive proof evidence gates 2026-06-04 08:37:51 -07:00
realize refactor(comprehension): drop QuantQuery — consumers read the target from graph.unknowns (PR-3) 2026-06-06 16:49:09 -07:00
__init__.py
admissibility.py
articulation.py
articulation_legality.py
attention.py
bridge_trace.py
dialogue.py feat(persistence): Shape B+ Phase C — SessionContext.snapshot/restore (full lived state) 2026-06-05 12:13:46 -07:00
discourse_planner.py
exhaustion.py
graph_constraint.py
graph_planner.py
grounding_accessors.py
intent.py
intent_bridge.py
intent_ratifier.py
logic_canonical.py feat: modus_ponens + disagreement rule — proof_chain wrong=0 mechanism (ADR-0205) 2026-06-02 20:56:57 -07:00
logic_equivalence.py feat: principled out-of-regime detector — typed out_of_decidable_regime (ADR-0201.1) 2026-06-02 19:12:41 -07:00
math_candidate_graph.py feat: add gsm8k r1 reconstruction 2026-06-04 13:25:11 -07:00
math_candidate_parser.py fix(ADR-0136.S.3): expose both consumed tokens to completeness guard 2026-06-03 01:01:50 -07:00
math_completeness.py fix(adr-0191): candidate-graph completeness guard — real-corpus wrong 5→0 (#496) 2026-05-30 15:45:07 -07:00
math_parser.py
math_problem_graph.py
math_realizer.py
math_roundtrip.py
math_solver.py
math_symbolic_equivalence.py
math_symbolic_normalizer.py
math_verifier.py
morphology.py
ood_surface_generator.py
operators.py
perturbation_suite.py
proposition.py feat(persistence): Shape B+ Phase C — SessionContext.snapshot/restore (full lived state) 2026-06-05 12:13:46 -07:00
quantitative_comprehension.py feat(comprehension): inverse reader frame — base of a more/fewer-than (PR-7b / R2 C0) 2026-06-07 07:06:26 -07:00
quantitative_expr.py feat(comprehension): the divisive comparative frame — "half as many" as exact integer division (PR-6c) 2026-06-06 20:18:39 -07:00
realizer.py
realizer_guard.py
recognizer_anchor_inject.py Harden no-reference n-times comparative guard 2026-06-03 15:22:42 -07:00
recognizer_match.py fix(math): restore WAVE-A multiplicative aggregate completeness provenance 2026-05-31 16:36:44 -07:00
recognizer_registry.py
relational_field_reader.py feat(field-wedge): geometric field reader — relational-metric lane wrong=0 (Phase W.1) 2026-06-04 19:34:43 -07:00
relational_symbolic_reader.py feat(field-wedge): ablation verdict — field is decoration on additive (C3) (Phase W.2) 2026-06-04 19:44:22 -07:00
result.py
rotor_admissibility.py
salience.py
semantic_templates.py
stream.py refactor(generate): remove redundant forbidden-site _close_final_state; rename "Drift fix 2" 2026-06-05 08:17:17 -07:00
surface.py
templates.py