Documentation

Routing & failover

How Frontier decides which agent takes a task, and the narrow set of failures that move work to a different one.

Eligibility comes first

Before anything is scored, a provider must be:

  • enabled and detected;
  • below its concurrency limit and any optional token budget;
  • outside a cooldown from a recent quota or unavailability error;
  • below any plan-window utilisation its own CLI has reported.

Anything that fails one of those tests is not a candidate at all.

Then the ranking

Remaining providers are scored, highest first, on:

  1. Your provider override

    An agent pinned on the task wins outright.

  2. Routing policy

    Balanced, Quality first, or Token saver.

  3. Task and provider affinity

    How well that agent suits this kind of work.

  4. Your priority order

    The order you arranged the providers in.

  5. Today's usage and current load

    Locally estimated tokens and how busy the agent is right now.

Task classification

Every task is typed as coding, debugging, review, planning, documentation, or general work. The type feeds the affinity score — which is why the plain Ollama provider, having no file-editing tools, is only ever offered planning, review, documentation, and general tasks.

Routing policies

PolicyOptimises for
BalancedA sensible mix of capability and spreading load across your subscriptions.
Quality firstThe strongest agent for the task type, accepting faster quota burn.
Token saverPrefers local and cheaper agents, keeping subscription windows in reserve.

When work moves, and when it stops

This is the distinction that matters most, and Frontier is deliberately conservative about it.

What happenedWhat Frontier does
Quota / rate limit Cools that provider down and fails over to the next eligible agent.
Overloaded / unavailable Same — treated as temporary unavailability.
CLI is logged out Classified as unavailable on a non-zero exit, so it cools down and fails over instead of failing the whole task. The real fix is still to log that CLI back in.
Agent failure Stops the task. Re-running a partially completed coding task through another agent could duplicate or conflict with edits already on disk.
You cancelled it Terminal for that run. Cancellation never enters automatic failover.

Failover applies everywhere a provider runs: first turns, follow-up messages, and every stage of an orchestrated run. Reported 100% plan utilisation and configured tracked-usage limits also remove a provider from routing before launch, so a doomed run never starts.

Concurrency and budgets

Frontier runs multiple independent tasks in parallel while respecting a global limit and a per-provider limit (the shipped default is one concurrent run per agent). Optional per-provider daily token budgets give you a deterministic ceiling on top of whatever the CLI itself enforces — useful because subscription tools expose no universal "tokens remaining" interface.