feat(intern-decision-serve): 0.1.1 adds POST /v1/systemone (Jev wire shape)

Straight passthrough to the checkpoint's own DecisionEngine.predict — never the
semif mapping, whose different prompt would change the answers. Reuses the one
inference thread, bearer auth, MAX_QUEUE, VRAM cap and error envelope; no new
concurrency. 1..16 questions in ONE call (never chunked: Jev questions share a
prompt); images 422; over MAX_TOKENS 422 before the forward. /health advertises
the surface. Response 'model' is a string name@revision (JevBench's runner
hashes it; a dict broke its manifest step).

Acceptance on the live service (see acceptance/systemone-2026-09-30/): JevBench
v1.2.16 typesafe adapter over the 231 public items scores all 202/231, hard
83/111, with 0 changed answers across all 924 rows of the bench's own r1..r4;
controls 401/422x3 (token boundary proven at 7168 pass / 7169 refuse); GPU 1
per-process peak 9,866 MiB under the largest accepted request (budget 9,876);
/decide/shared positive control unchanged. 120 tests green.

services/intern-decision-serve/acceptance/systemone-2026-09-30/jb-manifest.json

@@ -0,0 +1,21 @@
+{
+  "adapter": "typesafe",
+  "charged_usd": 0.0,
+  "cost_basis": null,
+  "dataset_hash": "dc3995d8ae1e2fc8e81ce38431add509eb8bb39b85aadfd0c7c32079382dde51",
+  "delay_s": 0.0,
+  "endpoint": "http://intern-decision.fv.internal:8033",
+  "finished_utc": "2026-09-30T19:57:44.055953+00:00",
+  "key_env_used": true,
+  "n_attempted": 231,
+  "n_planned": 231,
+  "price_input_per_m": 0.0,
+  "price_output_per_m": 0.0,
+  "request_options": {},
+  "requested_model": null,
+  "resolved_models": [
+    "Intern-Decision-4B@0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd"
+  ],
+  "run_label": "typesafe",
+  "started_utc": "2026-09-30T19:57:18.649032+00:00"
+}