chore(config): RATIFY deduction_serving_enabled — default ON (ADR-0256)

Ratified by Shay 2026-07-24. Default flipped False -> True.

Evidence at ratification:
- 25 shape-bands, each holding SERVE at 720/720 wrong=0 on the SHA-sealed
  ratified ledger (theta_SERVE=0.99, n >= 657 committed per band);
- deduction-serve lane 166/166 wrong=0 across six hand-authored splits;
- commit gate narrow by construction — a sentence-initial "therefore" IS an
  argument, so the composer cannot claim turns that are not one;
- an unearned shape is still served DISCLOSED, never asserted.

Blast radius verified, not assumed: core test --suite deductive 268 passed
with the flag ON by default; a live default-config ChatRuntime decides real
English and existential arguments through grounding_source="deduction" while
ordinary turns still fall through to pack grounding; lane pins 10/11 match —
unchanged by the flip (the single miss is the pre-existing public_demo drift
documented for Tier S).

Rollback is flipping this back: flag-off remains byte-identical to pre-arc
dispatch and leaves no residue, pinned by
test_flag_off_preserves_pack_token_gloss_byte_identity.

curriculum_serving_enabled stays OFF — every curriculum band is unearned, and
the Sonnet brief now records the explicit bar for revisiting it.

core/config.py

@@ -383,8 +383,18 @@ class RuntimeConfig:
     # argument is served AUTHORITATIVELY only when its shape-band holds a SERVE
     # license on the committed, SHA-sealed reliability ledger
     # (chat/deduction_serve_license); an unearned band is served DISCLOSED
-    # (hedged). OFF by default: flag-off is byte-identical to pre-arc dispatch.
-    deduction_serving_enabled: bool = False
+    # (hedged).
+    #
+    # RATIFIED ON 2026-07-24 by Shay — default flipped False -> True. The
+    # evidence at ratification: 25 shape-bands each holding SERVE at 720/720
+    # wrong=0 on the SHA-sealed ledger (theta_SERVE=0.99, n >= 657 committed),
+    # the deduction-serve lane at 166/166 wrong=0 across six hand-authored
+    # splits, and a commit gate (`looks_like_deductive_argument`) narrow by
+    # construction — a sentence-initial "therefore" IS an argument, so the
+    # composer cannot claim turns that are not. Rollback is flipping this back:
+    # flag-off remains byte-identical to pre-arc dispatch and leaves no residue
+    # (pinned by ``test_flag_off_preserves_pack_token_gloss_byte_identity``).
+    deduction_serving_enabled: bool = True
 
     # Generalization arc, Phase 2 (ADR-0262) — when on, ``chat/curriculum_surface.py``
     # answers exam-shaped polar questions ("Does force cause acceleration?") from the

docs/handoff/generalization-2026-07/BRIEF-S-sonnet-low-tier.md

@@ -56,7 +56,18 @@ commit; push when the server is repaired.
    `docs/research/math-reader-phase-4-1-status-2026-07-24.md`. Phase 4 should
    be re-pointed at the reader arc's own live recommendation (increment-2
    case-first on cases 0000/0001/0148/0082).
-3. **No curriculum band can earn a SERVE license from present data.** A band
+3. **`deduction_serving_enabled` is RATIFIED and ON** (2026-07-24). Flag-off
+   byte-identity is still pinned, so rollback stays one line with no residue.
+   S1's packet is now a *record* of that decision plus the standing evidence,
+   not an input to it.
+   **`curriculum_serving_enabled` stays OFF until verified.** The bar is
+   explicit: a `(subject × relation family)` band earning SERVE on the sealed
+   ledger — n≥657 committed with a genuine outcome mix. NOTHING in Tier S
+   closes that; it closes only when ratified curriculum content grows (see
+   S6). Do not flip it, and do not propose flipping it on "almost verified"
+   grounds — the bands are at ZERO earned, not near a threshold.
+
+4. **No curriculum band can earn a SERVE license from present data.** A band
    needs n≥657 with a real outcome mix; physics teaches 7 causal + 9 modal
    relations, so at most 16 questions in the whole subject can ever come back
    ENTAILED. A balanced band needs ≈219 taught relations per subject × family.

tests/test_deduction_surface.py

@@ -2,9 +2,11 @@
 
 The contract these tests pin:
 
-  - ``deduction_serving_enabled`` is OFF by default; flag-off ``chat()``
-    output is byte-identical to pre-arc behavior for argument-shaped text
-    (the pack-token-gloss fallback, unchanged).
+  - ``deduction_serving_enabled`` is ON by default since its ratification
+    (2026-07-24); flag-OFF ``chat()`` output remains byte-identical to
+    pre-arc behavior for argument-shaped text (the pack-token-gloss
+    fallback, unchanged), which is what keeps rollback a one-line, no-residue
+    operation.
   - Flag-on: a sentence-initial "therefore" conclusion clause commits the
     turn to ``chat/deduction_surface.py``; every committed turn returns a
     surface (never a silent fall-through to a different composer).
@@ -310,8 +312,12 @@ def test_flag_off_preserves_pack_token_gloss_byte_identity() -> None:
     assert "Pack-resident tokens" in resp.surface
 
 
-def test_flag_is_off_by_default() -> None:
-    assert RuntimeConfig().deduction_serving_enabled is False
+def test_flag_is_on_by_default_after_ratification() -> None:
+    """RATIFIED 2026-07-24 (ADR-0256): the default flipped False -> True on 25
+    bands at 720/720 wrong=0 and a 166/166 serve lane. The off-path above stays
+    pinned because rollback must remain byte-identical, not because it is the
+    default."""
+    assert RuntimeConfig().deduction_serving_enabled is True
 
 
 # ---------------------------------------------------------------------------