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/fleet-probes-swift15.sh

@@ -0,0 +1,55 @@
+#!/usr/bin/env bash
+# fleet-probes-swift15.sh — RUNS ON DANKSERVER. The cutover contract probes.
+set -uo pipefail
+B=http://localhost:7770/v1
+
+echo "== vision (solid red 512px, expect 'Red')"
+python3 - <<'PY'
+import base64, json, urllib.request, struct, zlib
+def png(color):
+    w = h = 512
+    raw = b"".join(b"\x00" + bytes(color) * w for _ in range(h))
+    def chunk(t, d):
+        c = t + d
+        return struct.pack(">I", len(d)) + c + struct.pack(">I", zlib.crc32(c))
+    return (b"\x89PNG\r\n\x1a\n"
+            + chunk(b"IHDR", struct.pack(">IIBBBBB", w, h, 8, 2, 0, 0, 0))
+            + chunk(b"IDAT", zlib.compress(raw)) + chunk(b"IEND", b""))
+b64 = base64.b64encode(png((255, 0, 0))).decode()
+body = json.dumps({"model": "frank-primary", "max_tokens": 64, "temperature": 0,
+    "messages": [{"role": "user", "content": [
+        {"type": "image_url", "image_url": {"url": "data:image/png;base64," + b64}},
+        {"type": "text", "text": "What color is this image? Answer with one word."}]}]}).encode()
+r = urllib.request.Request(B + "/chat/completions", data=body,
+                           headers={"Content-Type": "application/json"})
+d = json.load(urllib.request.urlopen(r, timeout=300))
+m = d["choices"][0]["message"]
+print("VISION ANSWER:", ((m.get("content") or "")[:80]).replace("\n", " "))
+PY
+
+echo "== tools (expect tool_calls)"
+curl -s -m 120 $B/chat/completions -H 'Content-Type: application/json' -d '{
+ "model":"frank-primary","temperature":0,"max_tokens":128,
+ "messages":[{"role":"user","content":"What is 23 times 47? Use the calculator tool."}],
+ "tools":[{"type":"function","function":{"name":"calculator","description":"evaluate arithmetic",
+ "parameters":{"type":"object","properties":{"expr":{"type":"string"}},"required":["expr"]}}}]}' \
+ | python3 -c 'import json,sys; d=json.load(sys.stdin); m=d["choices"][0]["message"]; print("TOOL_CALLS:", m.get("tool_calls"))'
+
+echo "== reasoning_effort fold (xhigh/medium/low ok, high -> 500)"
+for lvl in xhigh medium low high; do
+  code=$(curl -s -o /dev/null -w "%{http_code}" -m 120 $B/chat/completions \
+    -H 'Content-Type: application/json' \
+    -d "{\"model\":\"frank-primary\",\"max_tokens\":8,\"reasoning_effort\":\"$lvl\",\"messages\":[{\"role\":\"user\",\"content\":\"hi\"}]}")
+  echo "  reasoning_effort=$lvl -> HTTP $code"
+done
+
+echo "== reasoning_content channel"
+curl -s -m 120 $B/chat/completions -H 'Content-Type: application/json' \
+ -d '{"model":"frank-primary","max_tokens":64,"messages":[{"role":"user","content":"Is 97 prime? Think briefly."}]}' \
+ | python3 -c 'import json,sys; m=json.load(sys.stdin)["choices"][0]["message"]; print("has reasoning_content:", bool(m.get("reasoning_content")), "| content:", (m.get("content") or "")[:60].replace(chr(10)," "))'
+
+echo "== response_format json_object"
+curl -s -m 120 $B/chat/completions -H 'Content-Type: application/json' \
+ -d '{"model":"frank-primary","max_tokens":64,"response_format":{"type":"json_object"},"messages":[{"role":"user","content":"Return JSON {\"ok\": true}"}]}' \
+ | python3 -c 'import json,sys; d=json.load(sys.stdin); print("JSON MODE:", (d["choices"][0]["message"].get("content") or "")[:60])'
+echo "PROBES_DONE"

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"; }