fix: full-suite gates — suite SoT + multi-root depth pin

- Re-export core.cli._TEST_SUITES from cli_test.TEST_SUITES so argparse
  and tests cannot drift from the runtime packs/smoke/algebra pins
  (Stage dual-pack draft boundary was only on cli_test).
- Align relational ablation multi-root metadata test with Stage 3
  fail-closed policy: ≥2 unique roots do not emit [root:] notes.

[Verification]: Smoke suite passed locally (~133s, 180 passed);
postfix targeted 5/5; full pre-fix was 4 failed / 13281 passed
(2 env dirt/flake classified separately).

core/cli.py

@@ -25,156 +25,12 @@ _CORE_RS_MANIFEST = _CORE_RS_DIR / "Cargo.toml"
 DESCRIPTION = "CORE versor engine command suite."
 EPILOG = 'Examples:\n  core chat\n  core pulse "What is truth?"\n  core pulse --no-glove --json "Compare knowledge and wisdom"\n  core bench\n  core bench --suite all\n  core bench --suite all --json --report bench_all.json\n  core bench --suite determinism --runs 50\n  core bench --suite speedup --json\n  core trace "word beginning truth"\n  core trace --output-language grc --frame-pack grc --json "logos"\n  core rust status\n  core rust build\n  core oov covenant\n  core pack list\n  core pack verify en_minimal_v1\n  core teaching audit\n  core teaching audit --json\n  core teaching gaps --top 10\n  core teaching queue --threshold 3\n  core teaching hitl-queue list\n  core teaching hitl-queue list --state all --json\n  core teaching hitl-queue show <proposal_id>\n  core teaching propose <candidate-jsonl-path>\n  core teaching propose-from-exemplars teaching/admissibility_exemplars/rate_with_currency_v1.jsonl\n  core teaching propose-from-exemplars --all\n  core teaching proposals --state pending\n  core teaching review <proposal_id> --accept --review-date 2026-05-18\n  core teaching supersede cause_light_reveals_truth --subject light --intent cause --connective grounds --object truth --review-date 2026-05-18\n  core teaching supersessions\n  core teaching supersessions --json\n  core test --suite fast -q\n  core test --suite pulse -q\n  core test --suite proof -q\n  core test --suite cognition -q\n  core test -- tests/test_alignment_graph.py -q\n  core demo audit-tour\n  core demo register-tour\n  core demo anchor-lens-tour\n  core demo orthogonality-tour\n  core demo pack-measurements\n  core demo long-context-comparison\n  core demo anti-regression\n  core demo learning-loop\n  core demo learning-arc\n  core demo articulation\n  core demo conversation\n  core demo conversation --no-stream\n  core demo all\n  core demo adr-0024-chain\n  core eval --list\n  core eval cognition\n  core eval cognition --json --save\n  core eval cognition --split dev --version v1\n  core eval cognition --split holdout\n  core eval contemplation_quality\n  core eval contemplation_quality --json --save\n  core eval math-contemplation\n  core eval math-contemplation --audit evals/gsm8k_math/train_sample/v1/audit_brief_11.json\n  core eval math-contemplation --output teaching/math_proposals/proposals.jsonl\n  core workbench api\n  core workbench api --port 9000\n  core workbench api --host 0.0.0.0 --allow-nonlocal-bind'
 
-_TEST_SUITES: dict[str, tuple[str, ...]] = {
-    "fast": (
-        "tests/test_cli_test_suites.py",
-        "tests/test_runtime_config.py",
-        "tests/test_core_semantic_seed_pack.py",
-        "tests/test_intent_proposition_graph.py",
-        "tests/test_articulation_realizer_v2.py",
-        "tests/test_reviewed_teaching_loop.py",
-        "tests/test_cognitive_eval_harness.py",
-    ),
-    "smoke": (
-        "tests/test_chat_runtime.py",
-        "tests/test_achat.py",
-        "tests/test_runtime_config.py",
-        "tests/test_cognitive_turn_pipeline.py",
-        "tests/test_architectural_invariants.py",
-        # ADR-0043 — identity falsifiability: ratified identity packs must
-        # produce distinct, directionally-correct articulations, with a
-        # pack-invariant grounding/refusal floor and zero fabrication.  Lives
-        # only under ``full`` historically, so a divergence regression cleared
-        # the PR gate and surfaced only post-merge.  Promoted into smoke so
-        # the falsifiability claim blocks-on-regression rather than
-        # detect-after-merge.
-        "tests/test_pack_measurements_phase2.py",
-    ),
-    "runtime": (
-        "tests/test_chat_runtime.py",
-        "tests/test_achat.py",
-        "tests/test_runtime_config.py",
-        "tests/test_session_coherence.py",
-    ),
-    "cognition": (
-        "tests/test_intent_proposition_graph.py",
-        "tests/test_cognitive_turn_pipeline.py",
-        "tests/test_articulation_realizer_v2.py",
-        "tests/test_semantic_realizer_integration.py",
-        "tests/test_cognitive_eval_harness.py",
-        "tests/test_deterministic_hash.py",
-        "tests/test_morphology_irregular.py",
-        "tests/test_realizer_quantifier_agreement.py",
-        "tests/test_benchmarks_profiler.py",
-        "tests/test_compose_relations.py",
-        "tests/test_replay_vs_llm_benchmark.py",
-    ),
-    "teaching": (
-        "tests/test_reviewed_teaching_loop.py",
-        "tests/test_pipeline_teaching_integration.py",
-        "tests/test_epistemic_invariants.py",
-        "tests/test_adr_0172_w2_decomposer.py",
-        "tests/test_adr_0172_w5_inference_proposal.py",
-        "tests/test_math_frame_ratification.py",
-        "tests/test_math_composition_ratification.py",
-        "tests/test_teaching_coverage_cli.py",
-    ),
-    "packs": (
-        "tests/test_core_semantic_seed_pack.py",
-        "tests/test_adr_0127_pack_ratification.py",
-        "tests/test_frame_registry_load.py",
-        "tests/test_composition_registry_load.py",
-        "tests/test_composition_consult_in_injector.py",
-        "tests/test_consumption_case_0050_hazard_pin.py",
-        "tests/test_consumption_empty_registry_no_op.py",
-        "tests/test_consumption_partition.py",
-        "tests/test_matcher_extension_currency_per_unit.py",
-        "tests/test_matcher_extension_case_0050_hazard_pin.py",
-        "tests/test_matcher_extension_end_to_end_admission.py",
-        "tests/test_me2_cross_sentence_subject.py",
-        "tests/test_me2_case_0019_admits.py",
-        "tests/test_me3_additive_composition.py",
-        "tests/test_me4_subtractive_composition.py",
-        "tests/test_me5_all_categories_integration.py",
-        "tests/test_rat1_end_to_end_admission.py",
-        "tests/test_wave_a_multiplicative_aggregation_injector.py",
-    ),
-    "algebra": (
-        "tests/test_versor_closure.py",
-        "tests/test_holonomy.py",
-        "tests/test_holonomy_resonance.py",
-        "tests/test_energy.py",
-        "tests/test_motor.py",
-        "tests/test_null_cone.py",
-        "tests/test_vault_recall.py",
-        "tests/test_vault_recall_vectorised.py",
-        "tests/test_vault_recall_rust_parity.py",
-        "tests/test_cga_inner_rust_parity.py",
-        "tests/test_geometric_product_rust_parity.py",
-        "tests/test_versor_condition_rust_parity.py",
-        "tests/test_versor_apply_rust_parity.py",
-    ),
-    "sensorium": (
-        "tests/test_sensorium_compiler_delta.py",
-        "tests/test_audio_compiler.py",
-        "tests/test_audio_crdt_merge.py",
-        "tests/test_audio_eval_gates.py",
-        "tests/test_audio_pack_manifest.py",
-        "tests/test_audio_sensorium_mount.py",
-        "tests/test_vision_compiler.py",
-        "tests/test_event_vision_compiler.py",
-        "tests/test_vision_crdt_merge.py",
-        "tests/test_vision_eval_gates.py",
-        "tests/test_vision_sensorium_mount.py",
-        "tests/test_sensorimotor_contract.py",
-        "tests/test_sensorimotor_pack_manifest.py",
-        "tests/test_observation_frame_contract.py",
-        "tests/test_observation_frame_harness.py",
-        "tests/test_environment_falsification.py",
-        "tests/test_environment_falsification_eval_cli.py",
-        "tests/test_witness_log_importer.py",
-        "tests/test_tabletop_lab_protocol.py",
-        "tests/test_sensorium_eval_cli.py",
-        "tests/test_efferent_gate.py",
-    ),
-    "pulse": (
-        "tests/test_pulse_integration.py",
-        "tests/test_graph_diffusion.py",
-    ),
-    "formation": ("tests/formation",),
-    "proof": ("tests/test_proof_properties.py",),
-    # ADR-0024 chain suites (Phases 2-6).  Each phase has its own
-    # contract tests so investors / reviewers can run them
-    # independently; ``adr-0024`` runs the full chain end-to-end.
-    "refusal": ("tests/test_refusal_contract.py",),
-    "margin": ("tests/test_margin_admissibility.py",),
-    "rotor": ("tests/test_rotor_admissibility.py",),
-    "inner-loop": (
-        "tests/test_inner_loop_admissibility.py",
-        "tests/test_inner_loop_phase2.py",
-        "tests/test_inner_loop_phase3.py",
-        "tests/test_inner_loop_phase4.py",
-    ),
-    "phase5": ("tests/test_phase5_corpus.py",),
-    "phase6": ("tests/test_phase6_demo.py",),
-    "adr-0024": (
-        "tests/test_refusal_contract.py",
-        "tests/test_margin_admissibility.py",
-        "tests/test_rotor_admissibility.py",
-        "tests/test_inner_loop_admissibility.py",
-        "tests/test_inner_loop_phase2.py",
-        "tests/test_inner_loop_phase3.py",
-        "tests/test_inner_loop_phase4.py",
-        "tests/test_phase5_corpus.py",
-        "tests/test_phase6_demo.py",
-    ),
-    # ADR-0126 P6 — measurement harness for the GSM8K candidate-graph
-    # parser exit criterion.  ``wrong == 0`` is a hard gate (Obligation
-    # #4: refuse rather than confabulate).
-    "math": ("tests/test_adr_0126_train_sample_runner.py",),
-    "deductive": ("tests/test_deductive_logic_entail.py",),
-    "full": ("tests/",),
-}
+# Canonical suite map lives in core.cli_test (runtime + --list-suites).
+# Re-export here for argparse choices and tests that import core.cli.
+# Do not maintain a second copy — Stage dual-pack / algebra pins drifted
+# when cli.py lagged cli_test.TEST_SUITES (full-suite failure 2026-07-20).
+from core.cli_test import TEST_SUITES as _TEST_SUITES  # noqa: E402
+
 
 
 def _run(*args: str, check: bool = False, cwd: Path | None = None) -> int:

tests/test_cli_test_suites.py

@@ -157,11 +157,16 @@ def test_core_test_suite_accepts_pytest_flags_without_separator(monkeypatch) ->
     # (growing) packs file list: the contract under test is that a curated
     # suite expands to its files followed by the forwarded "-q", with no "--"
     # separator needed.
+    # Assert against the runtime suite map (core.cli_test.TEST_SUITES), which
+    # cli.cmd_test actually expands. core.cli._TEST_SUITES is a re-export of
+    # the same object — do not pin a second stale list.
+    from core.cli_test import TEST_SUITES
+
     assert calls[0] == (
         cli.sys.executable,
         "-m",
         "pytest",
-        *cli._TEST_SUITES["packs"],
+        *TEST_SUITES["packs"],
         "-q",
     )
 

tests/test_relational_operator_ablation.py

@@ -269,6 +269,13 @@ def test_malformed_depth_labels_cannot_elevate_runnable() -> None:
 
 
 def test_valid_depth_metadata_on_gold_does_not_change_answer() -> None:
+    """Multi-root labels must not change the operator answer (Stage 3 fail-closed).
+
+    With ≥2 unique roots, enrichment appends AMBIGUOUS_ROOTS provenance and does
+    **not** commit a silent ``[root:…]`` first-root note. Single-root decoration
+    with ``[root:…]`` is covered by
+    ``test_metadata_only_decorates_but_does_not_change_answer``.
+    """
     depths = {
         "p0": {"language": "he", "root": "א-מ-נ"},
         "p1": {"language": "grc", "root": "λογ"},
@@ -276,7 +283,8 @@ def test_valid_depth_metadata_on_gold_does_not_change_answer() -> None:
     op = run_operator(GOLD_0001)
     meta = run_metadata_only(GOLD_0001, depth_labels=depths)
     assert answers_match(op, meta)
-    assert meta.explanation_has_root_note is True
+    # Multi-root: fail-closed — no silent first-root [root:] commit.
+    assert meta.explanation_has_root_note is False
 
 
 def test_distractor_quantity_case_refuses() -> None: