swift15 cutover: AGENTS.md + runbook + log + fleet probes + KLD gate shape fix

- AGENTS.md: fleet table row + frank-primary section rewritten for the
  GPTQ w4 chain (1.0.13 serve/convert, 1.2.0 calib, int8 KV, vram pair).
- runbook: throughput gate PASS (136.0 t/s median @ 44.5k, 4.5x bar),
  fleet probes PASS, control baselines recorded.
- log.md: 2026-10-08 campaign entry with the four measured engine laws.
- kld-gate: shape matched to the reference recording, then reshaped for
  the w4 MNBT<=2048 file-tier law (pool 40960).
- fleet-probes-swift15.sh: tools/reasoning/response_format/vision walk.

serverAppConfigs-docs/LLM/frank-primary-radiance-swift15-w4dn8.md

@@ -105,9 +105,6 @@ v22.5 template override. `MODEL_FILE` points at
 `/home/dank/models/rad/qwen4exp-swift15-w4dn8-i8-hc8m.rad` (**116,416
 MiB measured**); the serve size floor `FRANK_PRIMARY_RAD_MIN_MIB` moves
 177000 → **110000**.
-`/home/dank/models/rad/qwen4exp-swift15-w4dn8.rad`; the serve size floor
-`FRANK_PRIMARY_RAD_MIN_MIB` moves 177000 → (real output size, set at
-cutover from `rad-info`, MEASURED@cutover).
 
 ## Gates (measured at cutover)
 
@@ -121,11 +118,26 @@ cutover from `rad-info`, MEASURED@cutover).
   refused), KV 2048, headroom 512, no speculation. The engine ran rank 0
   fully on card 0 (25.88 GiB) with rank 1 host-side in this shape —
   scoring is placement-invariant; scored at 28 positions/s.
-- **Throughput gate**: decode ≥ 30.8 t/s at the 43.6k greedy probe
-  (control: 1.0.13 + fp8-native drew 30.08 / accept 0.7549). Fail →
-  fall back to the w4 down tier (Q35).
-- MEASURED@cutover: decode t/s, acceptance, prefill, boot ledger, KV pool,
-  KLD numbers.
+- **Throughput gate: PASS (2026-10-08 05:40)** — decode at 44.5k depth
+  (streamed chat probe, temp 0, 512 tokens, salted): arm A (main serve
+  shape, EVC 0.82) **146–173 t/s**, engine timings **121.9 t/s**,
+  draft accept **0.7246** (350/483); arm C (deployed vram-pair shape
+  26071/3543) median **136.0 t/s**, warm TTFT 9.45 s. Control
+  (fp8-native 1.0.13): 30.08 / accept 0.7549. Prefill ~4.7k t/s warm.
+  The w4 expert table is resident — the fp8-native era's NVMe expert
+  streaming (the 3.5 GB/s wall) is gone; the MTP ×3 head rides a 45–60
+  t/s base decode. Conversation battery (short context): geomean
+  172 t/s (min 100 / max 208), mean ttft 0.09 s. The EVC ladder is moot:
+  the w4 resident set fits fully inside the 40 GiB pool at 0.82
+  (ledger: mover full fill). Depth-output audit: the 44.5k-depth
+  summary is a coherent ordered index of the concatenated corpus
+  (no repetition, no NaN-token garbage) — the depth-corruption class
+  of 2026-10-04 is clean.
+- Fleet probes: PASS — vision (solid-red 512 px → "Red"), tool_calls
+  (`{"expr":"23 * 47"}`), reasoning_effort xhigh/medium/low/high all
+  200 (the Swift1.5 template accepts the full set), reasoning_content
+  present, response_format json_object honoured.
+
 
 
 ## Deploy + verify