Setup P3

Setup p3

Write p3-models.md, a file that sets p3-stack's model per role. Default location is the current project root. Offer ~/.agents/p3-models.md as the global option, and ask which one. A project file wins over the global one.

Steps

1. Detect available models

Call orchestrator_capabilities. It lists the providers and models you can pass to delegate_task in this session, custom models included, with each one's provider instance ID and any reasoning options. That is the only source. If it returns nothing, stop and tell the user. Never write a provider or model it did not return. inherit-parent is always valid even though it is not a detected model.

2. Load current state

The roles are the labels shown in step 5. If p3-models.md already exists at the chosen location, read it and treat its # budget line and its role values as the current choices. Otherwise start from the defaults in step 3(b). A line whose role is not in step 5, such as how critics, is from a retired role. Drop it.

3. Budget, map, and confirm

(a) Ask for a budget. Ask plainly in the thread. Offer these four options with these exact labels, and name the current budget when the file records one.

• unlimited — keep max
• large — xhigh reasoning
• medium — high reasoning
• small — medium reasoning

(b) Apply it. Build the working table. On a fresh run, give code roles (feature, refactoring, bug-fix, perf-issue, hillclimb) and the explorer, investigator, and swarm roles the fastest strong coding model detected. Give judgment and prose, hardest tasks, the explainer, the synthesizers, and reflect tooling the most capable model detected. Fill each panel role with one entry per distinct provider detected, up to three. On a re-run, keep any role the user changed.

When the catalog exposes reasoning options for a model, set each real entry's effort option from the budget: unlimited takes the highest option, and large, medium, and small take xhigh, high, or medium. The ladder is max > xhigh > high > medium > low. If the model does not expose the target, use the highest option at or below it, else mark the role as needing a choice. inherit-parent does not change. When the catalog exposes no reasoning options, map roles only and drop effort tokens; the budget label is still recorded.

(c) Show the roles and confirm. Show every role with its model, marking any entry not in the detected set as needing a choice. Also list each line step 2 dropped. Ask whether to accept as-is or change specific roles, offering the detected models plus inherit-parent (the role runs on the parent thread's model, so omit the model in delegate_task) as the options. For panel roles (arena runners, architect runners, interrogate reviewers) the value is a list, and one delegate_task runs per entry, inherit-parent entries included, so the list length sets the count. arena cross-judge pool is also a list, but Arena selects one value from it whose provider differs from the parent's when possible. swarm workers is the default model for every worker unless a race or comparison assigns another model per arm.