feat(semif): 0.1.3 — order averaging, fast kernels, bug-hunt hardening (Prime)

Order averaging (Prime, after the 739aa03 spike):
- A decision may set orderings: rotations|all (all only for <= 4 options). Every
  ordering goes to the engine in one shared batch.
- The reply keeps each native result and adds combined {probabilities (log-mean),
  top, agreement, spread}.
- Through the service on SemIf's labelled sets (252 rows): 78.6% -> 88.1%
  (group-bootstrap 95% CI +5.1..+14.3). Unanimous agreement is 94.5% accurate.

Fast kernels: flash-linear-attention 0.5.2 and causal-conv1d 1.7.0 are now the
default build. A/B on the empty GPU 3:
- parity with upstream went from 142/144 to 144/144;
- a ~2k-token /decide went from 169 to 92 ms server-side;
- short 3-rotation batches cost ~3-6 ms more.
triton builds a C shim at runtime, so the image carries gcc. Without it the
warm-up failed and startup failed closed.

Heid bug-hunt panel (4/4 arms, thread 01M3H3F4RR7XBP90KQ3A39H4SX), folded:
- Startup validation: VRAM cap 0 no longer means uncapped (C1); limits must be
  >= 1 (S1); the token must be visible ASCII (S2); the calibration file must
  exist and parse, with T in [0.05, 20] (S8, and C3's NaN leg).
- The body limit is checked before a chunk is kept, and a Unicode-digit
  Content-Length no longer crashes (C2, S3).
- Failures while building the response now get the 500 envelope (C3).
- 429 busy past SEMIF_MAX_QUEUE requests in progress (C6).
- The engine releases memory on every non-validation failure, unchained after
  gc; an empty OOM message is handled; 'out of memory' RuntimeErrors map to 503
  (C4, C5, S9).
- The entry point forces HF_HUB_OFFLINE (S10). README wording fixed (S5, S6).
- New guard tests close the gaps the arms' mutation grids exposed: early stop of
  the body read, a shared-route lock, calibration pass-through, the gc cycle,
  the exact caps, TorchEngine.load's arch and device checks, and the offline
  entry point.
86 tests.

Deployed on fv-ml1 GPU 1: parity 144/144, OOM and burst release verified, shared
capacity 63/51/26/16 rows at ~140/520/1960/3900 prefix tokens.

stacks/semif/README.md

@@ -16,7 +16,7 @@ service. The contract is `services/semif-serve/semif-serve.contract.md`.
 | **Model** | `Qwen/Qwen3.5-4B` @ `851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a`, BF16, from `/tank/aimodels/huggingface` (read-only, offline) |
 | **SemIf** | commit `23cf1f39fc9534fe81437200959b6dfc7106e45a`; torch `2.10.0+cu128`, transformers `5.17.0`, the same stack SemIf's committed predictions were made on |
 | **Image** | `semif-serve:<version>`, built on fv-ml1 from `services/semif-serve/` |
-| **State** | none. Weights re-download at the pinned revision. No backup needed beyond the host's `/opt/docker` restic. |
+| **State** | none. If the weights are ever lost, re-pull them by hand at the pinned revision (the service itself never downloads: `HF_HUB_OFFLINE=1`, read-only mount). No backup needed beyond the host's `/opt/docker` restic. |
 
 ## API
 
@@ -34,6 +34,18 @@ curl -s -H "Authorization: Bearer $T" http://10.251.50.54:8032/decide -d '{
   the state once and scores every criterion in one batch. Use it when many questions
   share one long state.
 - `GET /health`: the pins, limits and calibrated workloads.
+- **Order averaging (0.1.3):** add `"orderings": "rotations"` to a decision, or
+  `"all"` for ≤ 4 options. The option list is asked in every rotation inside ONE
+  shared batch. The reply keeps each ordering's native result under `orderings` and adds
+  `combined: {method, orderings, probabilities, top, agreement, spread}`. **Use it for
+  anything real:** a small model leans toward the first-listed option on ambiguous
+  inputs, and averaging cancels that. Through the service on SemIf's labelled sets,
+  accuracy goes from 78.6% to **88.1%** (group-bootstrap 95% CI +5.1..+14.3 pts, 252
+  rows). **`agreement` is the cheap confidence signal**: unanimous rows are 94.5%
+  accurate, split rows 76.4%. The orderings count toward the decision cap. `workload`
+  calibration is not available together with `orderings` yet (422).
+- Past `MAX_QUEUE` (32) requests in progress, new POSTs get `429 busy` before their
+  body is read.
 
 ## ⚠ Probabilities are uncalibrated
 
@@ -57,18 +69,55 @@ not squeeze scriberr, which shares GPU 1. A request that would exceed the cap ge
 behaviours were verified on the card (0.1.0 held 11.9 GiB after an OOM, and 12.6 GB
 after a large request; 0.1.2 returns to 7.85 GiB in both cases).
 
-**What fits under 12 GiB** (measured, `/decide/shared`, binary decisions):
+**What fits under 12 GiB** (measured on 0.1.3, `/decide/shared`, binary decisions;
+0.1.2 figures in brackets, before the fast kernels):
 
-| state size (prefix tokens) | max decisions in one request |
+| state size (prefix tokens) | max rows in one request |
 |---|---|
-| ~140 | 52 |
-| ~520 | 43 |
-| ~1,960 | 19 |
-| ~3,900 | 13 |
+| ~140 | 63 (52) |
+| ~520 | 51 (43) |
+| ~1,960 | 26 (19) |
+| ~3,900 | 16 (13) |
+
+Rows = decisions × orderings, so `rotations` over 3 options uses 3 rows per decision.
 
 `/decide` fits at the full 4,096-token limit. Past the table you get a 503, so split
 the decisions across requests.
 
+## Fast kernels (0.1.3)
+
+The image ships Qwen3.5's fast kernels, `flash-linear-attention` 0.5.2 and
+`causal-conv1d` 1.7.0 (a prebuilt cu12/torch2.10 wheel). Without them transformers
+logs that it falls back to "much slower" reference PyTorch paths. They are adopted
+because an A/B on the empty GPU 3 showed:
+- **parity improved**: 144/144 vs upstream (142/144 without), so upstream evidently
+  ran with them;
+- **long inputs got much faster**: a ~2,000-token `/decide` went from 169 to 92 ms
+  server-side.
+
+Short 3-rotation batches cost ~3–6 ms more; everything else is equal or faster.
+⚠ triton builds a C shim at runtime, so the image carries `gcc`. Without it the
+warm-up fails, and startup fails closed. Build without the kernels:
+`--build-arg EXTRAS="--extra model"`.
+
+## Latency (0.1.3, from nh3-dev, 3 runs × 20, network floor ~33 ms)
+
+| request | end to end | server |
+|---|---|---|
+| `/decide`, short (~130 tok) | 69 ms | 35 ms |
+| `/decide`, ~2,000-token state | 131 ms | 92 ms |
+| 3 rotations, short | 115 ms | 78 ms |
+| 6 orderings, short | 118 ms | 81 ms |
+| 3 rotations, ~2,000-token state | 200 ms | 158 ms |
+
+## Acceptance (2026-09-27, v0.1.3)
+
+Raw: `services/semif-serve/acceptance/result-2026-09-27-v0.1.3.json`,
+`averaging-2026-09-27-v0.1.3.json`. v0.1.3 matches upstream on **144/144** (identical
+prompt hashes, max prob gap 0.049), is deterministic, fails the negative control as it
+should (14/144), and shared matches direct on 72/72. The v0.1.2 table below is the
+reference-kernel baseline.
+
 ## Acceptance (2026-09-27, v0.1.2)
 
 Raw: `services/semif-serve/acceptance/result-2026-09-27-v0.1.2.json`.