Model tiers

When a sprint closes, two fresh agents check the work: the reviewer and the binding evaluator (see Sprint and gates). The gates always run. This page is about one choice only: which model runs them. You can set it once for every project, and override it for a single ticket.

The order canon picks the model

The first line that applies wins. Both gates use the same model.

Item If The gates run on
1 The ticket's plan has a Gate model: fable, opus, sonnet or haiku, session, or openai:<id> That model. session means the model of your current session.
2 The ticket is marked Lite and has no Gate model Haiku, for the evaluator only
3 Neither of those The Admin default for Review & Eval gates
4 The Admin default is missing, or names a model the gates cannot use The floor built into canon's gate definitions, claude-sonnet-5

A Gate model is always your choice: set by you on the Plan tab, in a live instruction, or by editing the plan. The agent never picks it for itself. Row 3 applies to every ticket, whatever the risk of the change, and it applies to code changes as much as to docs. If you set a weak model there, every close uses it unless a ticket says otherwise.

Two details:

The New Ticket form with the Lite option selected and a tooltip explaining the light close: security-review plus the binding evaluator only, forced Haiku, skipping the advisory reviewer and the rest of wrapup, never dropping below the evaluator.
Lite on a new ticket: the tooltip says what it changes.

Set the default in Admin

Admin has a Model Tiers section. It is a setting for your whole canon install: it covers every project, and each change is saved as soon as you make it ("Default updated").

The Admin page, Model Tiers section: a Review & Eval gates card and a Simple / Light work card, each with an Anthropic and an OpenAI picker, then Anthropic and OpenAI tabs listing models with their ids, Gate-model aliases and prices.
Admin, Model Tiers. The Review & Eval gates card is the default in row 3.

Override it on one ticket

Open the ticket, go to the Plan tab and use the sign-off row at the top.

  1. Fill in the Tier and a Risk line first. The model list stays disabled until you do ("Type a Risk summary to save"). The Risk line is your reason for the sign-off: what could go wrong with this change.
The Plan tab of a ticket: the sign-off row with Normal selected, a Risk box with the message Type a Risk summary to save, and a greyed-out Default model list.
Before the Risk line is saved, the model list is greyed out.
  1. Open the model list and pick one. It offers Default and every Anthropic model in Admin that has an alias, then the OpenAI models, each marked "OpenAI · Copilot gates only".
The model list open: Default, Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5 highlighted, Claude Haiku 4.5, and three GPT-6 models marked OpenAI, Copilot gates only.
The list of models you can pick for this ticket.
  1. Read the plan. Your pick is written into the Tier line of plan.md. Choosing Default removes it, so the order above applies again.
The Plan tab after picking Claude Sonnet 5: the sign-off now reads Tier: normal, Risk: Low level tier, Gate model: sonnet, and the line is highlighted.
The plan now reads: Tier: normal | Risk: Low level tier | Gate model: sonnet.

You can type the same thing into plan.md yourself. That is the only way to set session: add | Gate model: session after the Risk line. The board then shows it as a custom override and disables the list, so change it in the file.

Next to the list, No effect under Codex is a reminder: Codex cannot give a sub-agent its own model, so a Gate model does nothing there.

Where it applies

Where it is recorded

Every close writes the model and where it came from, so a later reader can tell a setting for all projects from a decision for one ticket. The evaluator's report carries it on its Model: line. This one is from a real close in this repo, .tickets/t-739b/eval-report.md:

Model: sonnet — Admin Review & Eval default (fallback: Plan)

The words after the dash are the source: Admin Review & Eval default, Gate model override (with session or OpenAI when that is what it was), demo mode, or definition floor. fallback: Plan is a separate note: canon's own reviewer and evaluator definitions were not available to the session, so the built-in Plan agent type ran the gate instead. See Registering skills.