Models and role activation

Role-model only works as well as the active model and role inventory you give it.

The operator job here

Before benchmarking or routing, the operator needs to make four things true:

• the provider or local backend is connected
• the target models or endpoints are actually active
• the intended roles are assigned
• the candidate set reflects real production intent

Do not over-activate

Avoid assigning every role to every model just because you can.

If a model is only meant to serve general.chat, do not also assign coder.patch or tool.agent unless you want it to compete for those requests and be benchmarked as part of those routing stories.

Why role activation comes before benchmarking

The benchmark should grade the same role-aware candidate set that Router will later use.

If the role assignments change after the benchmark, your benchmark story and your routing story will drift.

Useful baseline roles

Typical first-run role assignments are:

• general.chat for general assistant routes
• coder.patch for patch-oriented code work
• coder.review for review and structured verdicts
• tool.agent when tool calling is part of the route

Next

Continue to Benchmarks and evaluation.