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.

This commit is contained in:

2026-09-30 12:58:19 -07:00

parent 579b1f5d42

commit ff552abf1f

13 changed files with 3449 additions and 13 deletions

									
										services/intern-decision-serve/pyproject.toml
									
		+1
		-1
	
												View File
												
				@@ -1,6 +1,6 @@

				[project]

				name = "intern-decision-serve"

				version = "0.1.0"

				version = "0.1.1"

				description = "Intern-Decision-4B (its own inference.py) behind semif-serve's HTTP surface"

				requires-python = ">=3.12"

				dependencies = [