Skip to content

providers-fx.md

Latest commit

 

History

History
58 lines (34 loc) · 3.39 KB

providers-fx.md

File metadata and controls

58 lines (34 loc) · 3.39 KB
Raw

fx

T3 Code can run fx. fx uses the login on the machine that runs the T3 Code server.

Set up fx

  1. Install fx on that machine:

    curl -fsSL https://fx.sh/setup.sh | bash

  2. Run fx login in a terminal on that machine.

  3. Open Settings → Providers, enable fx, and refresh the provider.

If fx is not on the server's PATH, set Binary path to the executable.

Every fx instance on the same machine shares that machine's fx login. T3 Code does not keep a separate login per instance.

Models and effort

The model picker lists Default first. That option runs the model fx status reports on the server's machine. A model set only for one project in fx's settings is not picked up, so choose it from the list instead. If the thread's fx backend does not offer that model, the thread keeps its current one. The other entries come from fx models. A custom model you add in the provider settings goes to fx as is, and fx reports an error if its backend does not offer it.

fx also has an Effort control. A new thread starts at Medium.

T3 Code does not show fx's backend selector. To use Codex, Grok, or Vercel AI Gateway, run fx provider on the environment's machine.

Type $ in the composer to list the skills fx finds in its skill folders, in the order fx's own skill menu shows them. When two different skills share a name, the menu lists the one fx loads for that name: the first copy in fx's folder order, starting with the workspace. The menu shows one skill per name regardless of case; to run a skill whose name differs only in case, such as Review next to review, type its exact name.

Permission modes

fx offers two composer modes.

Mode Behavior
Supervised fx asks before it changes files or runs commands. Read requests run without asking.
Auto fx handles routine actions itself. Anything it still asks about reaches you.

T3 Code does not offer Full access or Auto-accept edits for fx. A thread already set to one of those runs in Supervised. Changing the permission mode restarts the connection and reloads the same fx session.

On fx versions after vercel-labs/fx#1189, fx saves the mode T3 Code sets as its default permission mode. T3 Code sets it each time it opens an fx thread, so fx in the terminal then starts in that thread's mode.

A message steered into a running turn stops that turn, and fx answers the new message in the same session.

Sub-agents

When fx hands work to a sub-agent, it opens in its own thread under the parent. That thread shows the sub-agent's task and its reply, which fx shortens to a couple of lines. fx doesn't share the sub-agent's individual steps.

fx doesn't pass on a sub-agent's permission requests, so a sub-agent that needs one waits until you press Stop. This mostly happens in Supervised. In Auto, sub-agents can finish routine work by themselves.

Not supported yet

  • Plan mode.
  • Full access.
  • Auto-accept edits.
  • Commit messages, pull request text, branch names, and thread titles. Pick another provider for those.

See provider setup and Permission modes.