decision-conformance / d1-omni-600m/hf-02b55d7/fp16-liquidai/decide-server-d1-torch-mps-tf5.19.0-torch2.14.1 /

2026-10-08-core-greedy-nothink-0be291

Checks: 48/49 passed

Check	Passed	Failures
invariants	33/33	none
batched vs separate	6/6	none
repeat stability	6/6	none
option order	2/2	none
monotonic	1/2	state 1 -> 2: 1.0505491930089192 -> 0.2837928960798308

Run

Subject: d1-omni-600m/hf-02b55d7/fp16-liquidai/decide-server-d1-torch-mps-tf5.19.0-torch2.14.1
Suite: decision-conformance · core tier · profile greedy-nothink · mode native
Items: 17 succeeded of 17 attempted (17 planned)
When: 2026-10-08 19:22:24 UTC · 0 min
Hardware: Apple M4 Pro · 24 GB
Harness: bench @ 6182c52 · scorer bench/decision-conformance 1
Suite hash: 554e796a858218e48bcb83da003554769782a4a32d3e061da87510d7f9cea490
Recipe: d1-omni-600m/apple-m/decide · profile fp16 · inference-engines @ 6490e6f
Latency: p50 145 ms · p95 220 ms · p99 220 ms (per request)
Usage: 4,685 input tokens · 0 output tokens · $0.00

Reproduce

npm run bench -- run --recipe d1-omni-600m/apple-m/decide \
    --recipe-profile fp16 \
    --on <host with a apple-m:m4-pro> \
    --suite decision-conformance --tier core --profile greedy-nothink

Files

exactly as committed under results/