Merge pull request 'docs(archon): four-slot ledger, resolver law from source, probe self-calibration' (#60) from wt/20261020-213526 into main

scripts/frank-archon.env

@@ -48,7 +48,7 @@ FRANK_ARCHON_TP=2
 FRANK_ARCHON_TP_WIRE=wht6
 # Decode slots. A slot costs KV and pinned RAM, never decode: the cache target is
 # exactly MAX_SEQS x MAX_MODEL_LEN and the checkpoint store asks (1 + what the
-# retention policy keeps) per slot. Ordered 2026-10-21: FOUR slots over a pool of at
+# retention policy keeps) per slot. Ordered 2026-10-20: FOUR slots over a pool of at
 # least 700,000 fp8 tokens, rounding UP if the resolver cannot land it exactly. The
 # target is therefore 4 x 200,000 = 800,000 tokens and HOST_POOL_MIB decides whether
 # the cache gets it (expert_vram_floor, core/place/planner.cpp:100-104: the card must

scripts/probe-frank-archon-kv.py

@@ -147,10 +147,21 @@ def main():
     deep = corpus(160_000)
     wide = corpus(1_100_000)
 
-    # 3.28 chars/token is the measured ratio of this corpus through the
-    # froggeric template (646,000 chars -> 196,919 tokens at the 2026-10-11
-    # deploy); 98.5 % of the window leaves the response room under the ceiling.
-    chars = int(0.985 * maxlen * 3.28)
+    # The corpus's chars/token ratio is MEASURED here, not stored. A stored 3.28
+    # (646,000 chars -> 196,919 tokens, 2026-10-11) had drifted to 3.20 by
+    # 2026-10-20 (646,299 chars -> 201,876 tokens) as the repo's docs grew, and a
+    # stale constant sends leg B past --max-model-len, where the engine answers a
+    # perfectly legitimate 400 ("the request (201900 tokens) exceeds the available
+    # context size (200000)") and the leg reads as a capacity failure. One small
+    # request prices the ratio; 97 % of the window leaves the response room.
+    sample = prompt(wide, 4000, "CAL", "cal-marker")
+    cal, _, _ = post({"model": MODEL,
+                      "messages": [{"role": "user", "content": sample}],
+                      "max_tokens": 1, "temperature": 0.0,
+                      "chat_template_kwargs": {"enable_thinking": False}})
+    ratio = len(sample) / cal["usage"]["prompt_tokens"]
+    print(f"[cal] corpus ratio {ratio:.2f} chars/token")
+    chars = int(0.97 * maxlen * ratio)
     # Each marker's FIRST hyphen-separated word is unique, because show()
     # scores the hit on that word — a shared prefix would score every slot HIT
     # on any answer that says the word.
@@ -176,7 +187,7 @@ def main():
                 print(f"[B-{s}] FAILED after {time.time() - t0:.1f}s: {e!r}")
     print(f"[B] total {time.time() - t0:.1f}s")
     # D — concurrency decode: seqs streams, 512 tokens each, ~25 % depth.
-    dchars = int(0.25 * maxlen * 3.28)
+    dchars = int(0.25 * maxlen * ratio)
     dbodies = [chat(deep, dchars, f"D{i + 1}-9137", f"flint-marker-{i}", 512)
                for i in range(seqs)]
     print(f"[D] {seqs} concurrent streams x 512 tokens, "

scripts/serve-frank-archon.sh

@@ -15,7 +15,7 @@
 # log states every budget before anything is allocated (weights vs KV
 # split, the expert host pool's coverage of the worst case, the PLE pin,
 # the P2P answer per pair) — read it after every resize.
-# Deployed shape (2026-10-21, radiance 1.8.1): FOUR decode slots x 200,000 tokens over a
+# Deployed shape (2026-10-20, radiance 1.8.1): FOUR decode slots x 200,000 tokens over a
 # >= 700,000-token fp8 KV pool, 48 GiB/rank pinned expert pool, MTP depth 2, prefix cache
 # in pinned host RAM, PLE pinned in RAM. The per-card split between the expert slab and the KV
 # pool is NO LONGER an operator number — 1.3.0 removed the VRAM pair and the budget