packages/kilo-docs/pages/code-with-ai/gastown/settings.md
Gas Town settings control how your agents behave — which models they use, how they review code, and how they interact with your repositories.
Access settings from your town dashboard → Settings.
The primary model used by all agents (polecats, refinery, mayor). This affects quality, speed, and cost.
Popular choices:
Override the default model for specific agent roles. By default, all roles use the town-level model. You can override per-role if you want to optimize cost vs quality for different tasks (e.g., a faster model for the mayor, a stronger model for the refinery).
Used for lightweight tasks (classification, routing, summarization). Usually a smaller, cheaper model.
{% callout type="tip" title="Strongly Recommended" %} Adding a GitHub PAT ensures that all commits, branches, and PRs created by your agents appear as you in git history. Without it, activity shows up under the Kilo GitHub App bot account. {% /callout %}
To add a PAT:
{% callout type="info" %} Use a fine-grained token limited to only the repository your town is connected to. Agents act autonomously on your behalf, so limiting scope is a best practice. {% /callout %}
What the PAT enables:
gh CLI commands on your behalfWithout a PAT:
gh CLI operations may not workThe Kilo GitHub App provides base-level repository access. It's installed per-organization or per-repository and gives agents read/write access to code, PRs, and issues.
The GitHub App is required — it's how Gastown gets installation tokens for cloning and pushing. The PAT is optional but recommended — it provides user-level attribution.
Controls how reviewed code lands in your repository:
| Strategy | Behavior | Best for |
|---|---|---|
direct | Refinery merges directly (no PR) | Speed, trusted environments |
pr | Refinery creates a PR | Audit trail, team visibility, CI integration |
For pr mode, you can also configure:
| Mode | Behavior |
|---|---|
always | Every completed bead goes through review (default, recommended) |
never | Skip review entirely — merge on polecat completion |
pr_only | Only review work that generates a PR |
Strictness level from 1 (lenient) to 5 (strict). Higher levels mean the refinery will reject more frequently but produce higher quality output.
How many write → review → revise cycles before a bead fails and escalates. Default: 3.
How many coding agents can work simultaneously on a single rig. Default: 2.
Higher values mean more parallel work but also more resource consumption. Consider:
Controls how frequently the reconciler checks for work:
Lower active intervals mean faster response to events but more compute usage.
Add environment variables that are available to all agents in the container. Useful for:
{% callout type="warning" %} Environment variables are visible to all agents in the town. Do not store production secrets here — use test/development credentials only. {% /callout %}
Free-form text injected into every agent's system prompt. Use this to communicate:
vendor/ directory"Custom instructions are powerful — they let you encode institutional knowledge that agents follow consistently.
When true, new convoys are created as staged (paused until you un-stage). Default: true.
| Mode | Behavior |
|---|---|
review-then-land | Each bead merges to a feature branch, then a landing review merges to main (default) |
review-and-merge | Each bead goes through review and merges directly to main (no feature branch) |
review-then-land provides the strongest quality guarantees but takes longer. Use review-and-merge for simpler tasks or when you want immediate feedback.
Any town-level setting can be overridden at the rig level. This lets you:
Access per-rig settings from the rig detail page → Settings.