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.

scripts/kld-gate-swift15.sh

@@ -5,9 +5,14 @@
 # Same engine (1.0.13) and same boot shape as the reference RECORD
 # (run-swift15-bf16.sh kld): disk-tier, no speculation, deterministic, fp8 KV.
 # --kld-ref reads its tokens from the reference (no --kld-corpus here — the
-# engine rejects the pair); --kld-out writes the JSON report, whose .rows
-# carry every position's KL/top-1. Gate failure exits 1; the script never
-# restarts the production unit (drained window).
+# (run-swift15-bf16.sh kld): 1.0.13, tp 2, disk-tier, fp8 KV, no speculation,
+# deterministic, max-model-len 16384, vram-kv 3072, 4 slots. Two deviations
+# are forced by the w4 file: MNBT 2048 (the w4 kernels stream from the file
+# tier ONLY at MNBT<=2048 — at the recording's 32768 the engine demands a
+# widened form: "DID NOT FIT ... stored form is not the container's"), and
+# pool 40960 (the recording's 12 GiB pool predates the w4 tables; at 12288 the
+# gate_up slab cannot be cached). Chunk size is softmax-invariant, so the
+# MNBT delta is float-order noise riding on the KL floor.
 set -uo pipefail
 PIN=sha256:4c3f484564bb2872784e46b0a59cbd71becc9c1e746e301a3596ffae253c322e
 C=swift15gate
@@ -32,15 +37,15 @@ podman run --rm --name "$C" \
     -v "$KLD_REF_DIR:/data/kld-ref:ro" \
     "stilldeadcode/radiance@$PIN" \
     --model /models/rad/qwen4exp-swift15-w4dn8-i8-hc8m.rad \
-    --placement expert_tiered --weights-disk-tier \
-    --host-pool-mib 40960 --deterministic --gpu-headroom-mib 512 \
+    --tp 2 --placement expert_tiered --weights-disk-tier \
+    --host-pool-mib 40960 --deterministic --gpu-headroom-mib 768 \
     --num-speculative-tokens 0 \
     --kv-cache-dtype fp8 --max-model-len 16384 \
     --ngram-placement ram \
     --override-chat-template /models/tpl.jinja \
     --kld-ref /data/kld-ref --kld-out /data/kld-gate.json \
-    --vram-kv-mib 2048 \
-    --max-num-seqs 4 --max-num-batched-tokens 3072 \
+    --vram-kv-mib 3072 \
+    --max-num-seqs 4 --max-num-batched-tokens 2048 \
     2>&1 | tee "$LOG"
 rc=${PIPESTATUS[0]}
 [ "$rc" -eq 0 ] || { echo "KLD GATE BOOT FAILED rc=$rc; log: $LOG"; exit "$rc"; }