eval-harness

model

The fleet's production triage model llm

A model record: onboarded once for the project and used by any eval's arms.

aliases
eval-fleet-triage-pro
settings
reasoning_effort none it reasoned by default on the onboarding probe (2026-10-31); off unless a task needs it (RUNBOOK §16): left at the server's default, one model reasons at length and the next not at all
onboarding
vetted 2026-10-31
best result per goal
#35 of 55 Triage decisions on Orrery's error signals

Every model

01deployments and their onboarding

hosted · homelab LiteLLM (the fleet's gateway) · eval-fleet-triage-pro · onboarding pass 2026-10-31 · 18.9 tokens/s · 2 accepted
where
homelab LiteLLM (the fleet's gateway)
build
eval-fleet-triage-pro
matches the record
yes
checked
2026-10-31
onboarded on
homelab LiteLLM (the fleet's gateway)
probemeasurementflag
endpointprovider litellm · base url http://homelab:4001/v1 · model eval-fleet-triage-pro—
digest foundNone—
defaults 1.66 · tokens out 80 · reasoned: yes · finish stop—
chosens 1.22 · tokens out 23 · reasoned: no · finish stop · settings (reasoning effort none)—
tokens per s18.9—
deterministicno—
json validyes—

Accepted: where it ran: a hosted gateway serves the provider's current build; there is no digest, revision or hash to pin; determinism: a hosted provider batches requests, so temperature 0 does not repeat exactly; repeats measure it

What it can do, across its deployments: reasons: yes · json mode: yes · reasoning off reasoning_effort: none

02settings history

whenwhat changedwhy
2026-10-31reasoning_effort: (server default) → noneit reasoned by default on the onboarding probe (2026-10-31); off unless a task needs it (RUNBOOK §16): left at the server's default, one model reasons at length and the next not at all