Agent Run Console TemplatePro
A resumable agent run: human-in-the-loop approvals, per-step cost and tokens, retry and step-level re-run, and cancellation that actually stops the model.
Step 1 of up to 40
Triage the login redirect bug and comment on the issue with what you find.
- 01searchIssues
Starting with the open issues so I know what people are actually hitting.
The approval is real — the run will sit there until you allow or deny it, and it answers differently either way. Everything else is scripted: there is no model and no route behind this page. In the template the run lives in a server-side event log, which is what Reload above is standing in for.
Every file in it
The full file list, with line counts — nothing is hidden about what you are getting, only the contents are.
30 files, 2,886 lines
Every file below is real and readable once you have Pro — downloaded as a zip, installed with one shadcn command, or read here in the browser. $49 once, for this and every other Pro item.
Built on these components
All free, all documented on their own pages. The template is what wires them together.
Status for an AI agent working on its own — running, waiting on you, completed or failed, with what it did last.
Approval RequestThe human-in-the-loop confirmation — what the agent wants to do, the exact details, and allow or deny before it acts.
Tool CallHow to show a function call in chat — the arguments sent, the result returned, run status, and an expand toggle.
Error & RetryWhat to show when a generation fails — a plain-English reason, a retry button, and a countdown for rate limits.
Running it
- Download the zip and unpack it, or install it with the shadcn command above — either way the app lands in its own directory. Then
npm install. - Add an
AI_GATEWAY_API_KEYto.env.local— one key reaches every model the template uses. npm run dev. To use a provider directly instead, install its package and change one line in the chat route.