Brief P8: describe the shared router as deployed

Approved 2026-09-17. Evidence is in docs/decisions.md.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

docs/design.md

@@ -16,17 +16,21 @@ authority, state in plain files the owner can read, a codebase small enough to a
 
 ## Target environment
 
-- Inference host: `straylight`, AMD Strix Halo, 128 GB unified memory, llama.cpp `llama-server`,
-  ~128k context configured.
-- Model: Ornith-1.5-35B-A3B (Qwen3.5-family MoE, hybrid linear/full attention, ~20 KB/token KV
-  at f16, Qwen XML tool calls with thinking blocks).
-- Memory is abundant. Generation is fast. **Prompt processing is slow and cache invalidation is
-  the dominant cost.** Hybrid-attention models cannot partially rewind their cache.
-- Reference numbers for the same model family on Strix Halo (Qwen3.6-35B-A3B Q4, llama.cpp,
-  community benchmark grid, May 2026): prompt processing ~1,100 tokens/s at depth 0 and ~700 at
-  32k depth; generation ~60 tokens/s falling to ~49. M0 replaces these with measurements from
-  straylight. At these rates an uncached 18k-token prompt costs 16–25 s and a 64k re-read costs
-  well over a minute.
+- Inference host: `straylight`, AMD Strix Halo, 128 GB unified memory, of which the GPU may
+  address 104 GiB. The harness runs on the same host.
+- Serving: llama.cpp `llama-server` in router mode. One endpoint, one child server per model, at
+  most two models loaded. The owner's coding agents and Open WebUI use the same router and the
+  same Ornith instance. Details and measurements are in `docs/inference-contract.md`.
+- Model: Ornith-1.5-35B-A3B (Qwen3.5-family MoE, hybrid linear/full attention, Qwen XML tool calls
+  with thinking blocks). As deployed: Q4_K_M weights, q8_0 KV cache, two slots of 131,072 tokens.
+  Weights and cache are unloaded after six idle hours, or when a third model is loaded.
+- Memory is not abundant: Laguna S 2.1 (69 GB) and Ornith (22 GB) are normally both loaded.
+  Generation is fast. **Prompt processing is slow and cache invalidation is the dominant cost.**
+  Hybrid-attention models cannot partially rewind their cache; M0 confirmed it.
+- Measured in M0 with the GPU otherwise idle: prompt processing 1,170 tokens/s at depth 0 and 669
+  at 32k depth; generation 69 tokens/s falling to 60. A second active session on Ornith roughly
+  halves generation speed. An uncached 32k-token prompt took 36 s, so a 64k re-read costs well
+  over a minute.
 - Deployment: rootless containers on a host that is already a tailnet node. Containers do not get
   their own tailnet identities, so tailnet ACLs cannot tell one role from another. Isolation
   between roles is done with container networking on the host (see "Network isolation"). Tailnet