Your robot.
A tested agent.

Reference Husky, no payload, flat empty arena, imposed friction 1.0, known station map and simulation position. Newton 1.5 / MuJoCo CPU, 16 ms, 8 configured substeps. Machine 9722d23d12a3 · RTX 3060 Laptop · Windows. Nominal linear target 0.25 m/s; measured peak 0.392 m/s. This target is not a certified speed ceiling. The qualified interface is typed/text requests and typed Stop; voice is not qualified. Unknown environments, obstacle avoidance, hardware validation and safety certification are outside this pilot.

# In a working public OmniSim 9.2.7 checkout, extract the source add-on here.
# Connect your own OmniKey and active model provider; set OMNI_KEY privately.
python -m omnisim doctor
python mission.py run --case case-003 --out .tmp/mission-live-01
python mission.py accept --out .tmp/mission-acceptance-01
# Prepared Windows delivery: .\mission.cmd verify
# Then: .\mission.cmd accept --out runs\acceptance-01

The prepared Windows delivery includes the pinned engine, full evidence, inventory verification and fresh acceptance commands. It is checked from an extracted ZIP with a clean launch environment. Delivery validation ↗. No OmniKey, provider account or credits are bundled.

19/20 episodes passed; 1 failed and 0 invalid/error episodes. 19/20 Cancel/Stop requests reached a running plan; 19 passed the halt criteria. One plan completed before its start reply returned, so the Cancel fixture remains a failed primary case. Separately, 3/3 cancellations during a pending HTTP request passed, without replacing the primary results.

Machine 9722d23d12a3, Newton / MuJoCo CPU, 16 ms and eight configured substeps. Relay origin and retained model traces establish connected model use; command parsing was disabled for qualification. This developer-authored regression suite is not an independent blind holdout. HTTP text and typed controls are qualified; native-window language and voice are not. No obstacle perception, collision-avoidance, force, payload or hardware-safety qualification is claimed.

Development misses and invalid attempts are retained, including the explicit Unlock omission found before the final repair. Every campaign, correction and model condition is listed in the report. The observed rates describe this finite contract and these requests; they are not a promise about arbitrary language or universal safety.

# Working public OmniSim checkout + source add-on extracted at its root.
# Connect your own OmniKey and active model provider; set OMNI_KEY privately.
python -m omnisim doctor
python -m pip install psutil
# Reuse your own dedicated profile for serial local reruns.
$env:OMNILINK_AGENT_TAG = "my-arm-assessment"
python arm_assurance.py run --episode 0 --out .tmp/arm-live-01
python arm_assurance.py verify .tmp/arm-live-01
# Full qualification: follow the package guide for dedicated parallel profiles.
python arm_assurance.py suite --parallel 1 --out .tmp/arm-suite-01

Use a fresh output directory. OmniKey and your active model provider are required; AI usage is separate. No credentials are bundled. Windows has the only prebuilt OmniSim package; other platforms build from source. Fifty-three arm unit checks and 55 relay checks exercise failure handling separately from the physical campaign.