esh-pfi-infrastructure/persistent-memory.d/2026-10-12-decision-seat-h2o-rollbacks-and-cutover.md

# [2026-10-12] Decision seat: h2o tried, rolled back twice, then production on Prime's fix-forward

`[2026-10-12]` **Decision seat: h2o-lightning-4b served 1311–1403, then ROLLED BACK to INC** on albok-dev's word, with brokkr concurring (Prime's plan made the swap conditional on the judge's sign-off). Every eval-set check had passed (JevBench 205/231, 422 refusal, 16q@32k ~2.1 s, seat peak 16,164/16,847), but albok's full walk over 10,841 same texts (both verdicts, same prompt and policy) found h2o flags 242 adult at 0.5 against INC's 88, with 154 extra at 0.80–0.90 that no threshold separates; for personal, 5 vs 11 with only 2 in common. **Lesson: a passing benchmark plus a small borderline set (9 entries, 2 → 5) could not resolve a 2× shift in a production classifier; only the same-text fleet comparison did.** albok's re-stamp walk on INC (1406–1408) put the hidden set back exactly to its pre-cutover counts (fleet/memory 86, agent-feedback 21, nonfiction 0). Prime's inline-images-only order (via brokkr) is carried in the staged h2o compose. h2o returns only after a judge re-fit. Threads `01M4RSFC9J2R0J07EEBD4N04W3` (brokkr), `01M4RYSMP3DV9HZHJ0KNBH2S96` (albok). **Then:** the round 2 eval seat on GPU 3 (1428–1619, Prime 1420) found the cause. The judge's v1 note question asked two things at once: INC answered it inconsistently, h2o literally. The shim floor is ruled out (identical verdicts on and off). Prime ruled "text itself", and albok-nemi 0.1.18 (judge v2) re-fitted the question. Both seats agree under v2 (work notes INC 0/22, h2o 1/22 at 0.52). **Prime ruled the cutover at 1640 ("do it", via albok-dev): h2o LIVE again since 1704** (`switch-to-h2o.sh` 170223, healthy 170454, probes clean). **The v2 walk on h2o (1705–1745) moved two margins past albok-dev's named line**: nonfiction adult 0 → 79 (the Schell chapter at 0.531 on the book profile) and memory personal 6 → 18. Notes held at 0 adult. **Rolled back to INC at 1748 on albok-dev's word.** The 1749–1751 re-stamp walk restored the counts (memory 0 adult / 6 personal, feedback 0 / 2, nonfiction 0 / 0), and the timer was back at 1751. **Then Prime, 1805 (via albok-dev): "go to h2o, and fix forward. do not fall back to inc."** albok-dev declared the two published nonfiction titles `visibility: public` (the chapter margin cannot recur). **h2o has been production since 1807** (`switch-to-h2o.sh` 180513, healthy 180740, all checks clean). The cutover walk (1809–1813, 0 degraded) left memory 0 adult / 18 personal, feedback 2 / 0, nonfiction 0 / 0 and fiction 0 / 0, and the timer is back. **The one open margin is the personal reading (18 vs INC's 6).** albok-dev is re-fitting it forward on the live seat in small batches. Threads `01M4S026GWS354WZGXZ5E34F31`, `01M4S91WPPPN0B17JBNX98K5CY`.
		`# [2026-10-12] Decision seat: h2o tried, rolled back twice, then production on Prime's fix-forward`

		`[2026-10-12]` Decision seat: h2o-lightning-4b served 1311–1403, then ROLLED BACK to INC on albok-dev's word, with brokkr concurring (Prime's plan made the swap conditional on the judge's sign-off). Every eval-set check had passed (JevBench 205/231, 422 refusal, 16q@32k ~2.1 s, seat peak 16,164/16,847), but albok's full walk over 10,841 same texts (both verdicts, same prompt and policy) found h2o flags 242 adult at 0.5 against INC's 88, with 154 extra at 0.80–0.90 that no threshold separates; for personal, 5 vs 11 with only 2 in common. Lesson: a passing benchmark plus a small borderline set (9 entries, 2 → 5) could not resolve a 2× shift in a production classifier; only the same-text fleet comparison did. albok's re-stamp walk on INC (1406–1408) put the hidden set back exactly to its pre-cutover counts (fleet/memory 86, agent-feedback 21, nonfiction 0). Prime's inline-images-only order (via brokkr) is carried in the staged h2o compose. h2o returns only after a judge re-fit. Threads `01M4RSFC9J2R0J07EEBD4N04W3` (brokkr), `01M4RYSMP3DV9HZHJ0KNBH2S96` (albok). Then: the round 2 eval seat on GPU 3 (1428–1619, Prime 1420) found the cause. The judge's v1 note question asked two things at once: INC answered it inconsistently, h2o literally. The shim floor is ruled out (identical verdicts on and off). Prime ruled "text itself", and albok-nemi 0.1.18 (judge v2) re-fitted the question. Both seats agree under v2 (work notes INC 0/22, h2o 1/22 at 0.52). Prime ruled the cutover at 1640 ("do it", via albok-dev): h2o LIVE again since 1704 (`switch-to-h2o.sh` 170223, healthy 170454, probes clean). The v2 walk on h2o (1705–1745) moved two margins past albok-dev's named line: nonfiction adult 0 → 79 (the Schell chapter at 0.531 on the book profile) and memory personal 6 → 18. Notes held at 0 adult. Rolled back to INC at 1748 on albok-dev's word. The 1749–1751 re-stamp walk restored the counts (memory 0 adult / 6 personal, feedback 0 / 2, nonfiction 0 / 0), and the timer was back at 1751. Then Prime, 1805 (via albok-dev): "go to h2o, and fix forward. do not fall back to inc." albok-dev declared the two published nonfiction titles `visibility: public` (the chapter margin cannot recur). h2o has been production since 1807 (`switch-to-h2o.sh` 180513, healthy 180740, all checks clean). The cutover walk (1809–1813, 0 degraded) left memory 0 adult / 18 personal, feedback 2 / 0, nonfiction 0 / 0 and fiction 0 / 0, and the timer is back. The one open margin is the personal reading (18 vs INC's 6). albok-dev is re-fitting it forward on the live seat in small batches. Threads `01M4S026GWS354WZGXZ5E34F31`, `01M4S91WPPPN0B17JBNX98K5CY`.