Add slot pinning and eviction measurements to M0 findings

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

docs/inference-contract.md

@@ -8,7 +8,7 @@ the server README at tag `b10809`, the build that is running.
 **Conditions.** Every number below was taken while another session was generating on Ornith slot 1
 (an 85k to 105k-token conversation at about 50 tokens/s). Token counts (`cache_n`, `prompt_n`) are
 not affected by that. Throughput is, so section (a) reports a separate run taken after the GPU went
-idle. One check is still open: slot pinning (d).
+idle. Section (d) was also run with the GPU idle.
 
 ## What is running
 
@@ -121,11 +121,34 @@ suffix appended to a cached 32k-token prefix, then generation from there.
 The idle numbers match the brief's reference figures (about 1,100 and 700 tokens/s, 60 falling to
 49). A second active session on the same model roughly halves generation speed.
 
-### (d) Slot pinning: not yet measured
+### (d) Slot pinning and eviction
 
-`id_slot` is a documented request field and the pinned requests above all landed on slot 0. The
-two-session test (`m0.py pin`) needs slot 1 and sends unpinned requests, which would evict the
-100k-token cache of the session that is using slot 1. It runs when the owner says slot 1 is free.
+Run with the GPU otherwise idle and both slots free.
+
+**Pinning works.** Session A pinned to slot 0 and session B pinned to slot 1 (6k tokens each) did not
+disturb each other: A's second turn had `cache_n` 6028, `prompt_n` 17.
+
+**Eviction is recovered from the server's host-RAM prompt cache** (`--cache-ram`, default 8 GiB,
+with `--cache-idle-slots` on by default), as long as the session comes back on the same slot.
+
+| Scenario | Result for the returning session |
+|---|---|
+| Two unpinned 3k-token requests from "other clients" between turns of A and B | A: `cache_n` 6088, `prompt_n` 18. B: `cache_n` 6107, `prompt_n` 17. |
+| A (30k tokens) on slot 0, then three unrelated 8k prompts pinned to slot 0, then A again on slot 0 | `cache_n` 30695, `prompt_n` 16, 0.43 s |
+| The same session A then sent to slot 1 instead | `cache_n` 0, `prompt_n` 30728, 34.5 s |
+| Two sessions sharing a 3k baseline (same system text and tools), 10k tokens each, taking turns on slot 0 for three rounds | Every switch after the first: `cache_n` about 13k, `prompt_n` about 320, 1 s. The second session's first request also reused the 3,031-token shared baseline. |
+
+Consequences:
+
+- A session must always use the same slot. Moving it to another slot costs a full re-read.
+- Several Mattermost threads can share the main slot. Switching between them costs about a second,
+  not a re-read, while their saved states fit in the prompt cache.
+- Another client taking a harness slot is usually harmless for the same reason.
+- This does not survive a model unload (`--models-max 2`, or six idle hours), and the 8 GiB limit
+  was not probed. The size of one saved session was not measured. `loopd` still has to treat a cold
+  cache as a normal event.
+- One exception was seen in (e): after a prompt that shared a long prefix with the saved one but
+  differed in the middle, the saved prompt was restored on one attempt and not on another.
 
 ## Recommendation on the open question
 
@@ -152,8 +175,10 @@ plus KV cache) does not fit beside Laguna's 69 GB under the 104 GiB GPU memory c
 What the shared instance means for the harness:
 
 - `id_slot` pins the harness's own requests. It does not reserve the slot. An unpinned request
-  from another client can take it, loading a third model can unload Ornith (`--models-max 2`), and
-  six idle hours drop weights and cache. `loopd` must treat a cold cache as a normal event.
+  from another client can take it, but the evicted session is normally restored from the host-RAM
+  prompt cache (see (d)). Loading a third model can unload Ornith (`--models-max 2`), and six idle
+  hours drop weights and cache; neither is recoverable. `loopd` must treat a cold cache as a
+  normal event.
 - A pinned request can wait behind another client's generation on the same slot.
 - Another active session on Ornith roughly halves generation speed.
 - Serving flags are owned by `~/src/nixos`. This repo records expected values and checks them at