frank-medium: route by workload — spread batches, pin agent loops

The two replicas behind :7770 were on plain round-robin, which throws away
prefix-cache hits: an agent loop re-sends its system prompt and file context
every turn, and alternating replicas means every other turn pays a cold
prefill. Measured with 90k-token contexts, warm-turn TTFT was 2676 ms.

Pinning everything to one replica is not the answer either — a cold batch
(the shape a benchmark or a burst of parallel subagents produces) then loses a
card's worth of prefill: 16 requests took 30.1 s pinned against 18.6 s spread.

So the policy routes by request shape. A continuation (more than one message —
the agent-loop signature) is pinned to the replica that served its prefix;
anything else spreads across the cards by counter. Measured: 19.97 s for the
burst and 1095 ms warm-turn TTFT — the best of both, without a regression on
either workload.

The policy lives in proxy/routing.py, separate from the HTTP plumbing in
proxy/affinity-proxy.py, so it can be tested without aiohttp, a network or a
GPU. tests/frank_medium_proxy.bats covers it, and it earned its keep: the
first version hashed fresh prefixes to pick a card, which sends every member of
a same-prefix burst to one card (29.8 s, measured), and a stale index in the
pin path returned 500 on every continuation. Both are now assertions.

ROUTING=roundrobin and ROUTING=affinity stay available to re-measure the
choice on this host; the default is adaptive.

AGENTS.md

@@ -23,7 +23,7 @@ merge absorbed the former `vllmScripts` repo, history preserved).
 
 | Target | Service | Runtime | Model | Port |
 |--------|---------|---------|-------|------|
-| Dankserver | `frank-medium` | vllm-radiance 0.9.3 (ggz14/radiance-vllm-mxfp4 patches), 2x single-GPU rootless Quadlets behind a round-robin proxy | just1moremodel Qwen3.8-27B-Uncensored-MXFP4-awq + Qwen3.8-27B-DFlash2-FP8 drafter, 2x Radeon AI PRO R9700 (one card per replica, TP=1), 114688 ctx / 4 seqs each | 7770 |
+| Dankserver | `frank-medium` | vllm-radiance 0.9.3 (ggz14/radiance-vllm-mxfp4 patches), 2x single-GPU rootless Quadlets behind an adaptive-routing proxy | just1moremodel Qwen3.8-27B-Uncensored-MXFP4-awq + Qwen3.8-27B-DFlash2-FP8 drafter, 2x Radeon AI PRO R9700 (one card per replica, TP=1), 114688 ctx / 4 seqs each | 7770 |
 | Dankclaw | `frank-large` | ik_llama.cpp master d85a1d7 (root systemd unit) | mradermacher Qwen3.8-Flash-Next-Uncensored i1-Q4_K_M GGUF, RTX 3090 (dense/attn/KV) + LPDDR (experts/PLE) hybrid, 262144 ctx / 1 slot, vision via mmproj | 7770 |
 
 Retired endpoints (`frank-npu`, `frank-small`, and every prior runtime) are in
@@ -256,7 +256,7 @@ patches are applied at every container start), serving
 `just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq` with the
 `Qwen3.8-27B-DFlash2-FP8` block-diffusion drafter (`SPEC=7`).
 
-The deployment is **two single-GPU replicas behind a round-robin proxy** —
+The deployment is **two single-GPU replicas behind an adaptive-routing proxy** —
 `frank-medium-a` (:7771, R9700 #1), `frank-medium-b` (:7772, R9700 #2) and
 `frank-medium-proxy` (:7770, the fleet endpoint), three rootless Quadlets
 under `dankserver/frank-medium/quadlet/`. Each replica is TP=1 at