Smart Queue

Routes each message you send to a busy thread: corrections steer the running turn, and new tasks wait until it ends. TypeSafe's Jev model decides, reached with a TypeSafe, Vercel AI Gateway, OpenRouter, or OpenCode Zen key, or through any endpoint that speaks its System One API. Without a key, a model from a BB provider you already use decides in a hidden thread, and if nothing answers the message waits. Each decision sends the thread title, your recent requests, and the new message to that provider, which bills the usage.

Overview

View source

Send a message to a busy thread without choosing between steer and queue.

What you get

Corrections, cancellations, and urgent changes steer the running turn now.
New or later tasks wait as follow-ups until the turn ends.
When several messages steer, they reach the agent in the order you sent them.
bb smart-queue recent lists each decision and the provider that made it, and bb smart-queue classify dry-runs one.

Choose how to reach Jev

Smart Queue asks TypeSafe's Jev model to decide. Add a TypeSafe key, or reach the same model through Vercel AI Gateway, OpenRouter, or OpenCode Zen. auto tries each configured provider in order and moves on when one fails. To bring your own provider, point Smart Queue at any HTTPS endpoint that accepts TypeSafe's System One API.

Without a Jev key, a model from a BB provider you already use decides in a hidden, temporary thread. If nothing answers, the message waits as a follow-up.

What leaves your machine

Each decision sends the thread title, your last three requests, the end of the latest assistant output, and the new message to the Jev provider you configured, or to the fallback model's provider. That provider bills the usage.

Smart Queue acts only on messages you type. It leaves agent messages, plugin messages, retries, scheduled sends, and Bot Teams threads alone.

More from Patrick Lee

ChecklistsKeeps a persisted set of agent-owned steps attached to each BB thread and continues incomplete work automatically.165 Agent PluginsInstalls plugins that follow the Agent Plugins spec in BB, making their skills and approved MCP tools available to Codex and other BB providers; it is not a Claude marketplace integration.82 Copy Session IDCopy a thread's session ID from its left-sidebar context menu.79 Emoji ReactAnswer an agent with one click: pick an emoji reaction and it drafts your reply. Select text in a reply to quote it with your reaction from the selection menu, or use the reaction buttons under each message. Turn on smart reactions and the agent adds reactions that fit its question, such as SQLite or Postgres, as buttons in its reply. Smart reactions add a short instruction to each thread.33

More in Thread Content 89

Change what people see or do inside an open thread.

View all

Generative UITurns agent replies into charts, diagrams, maps, plans and forms you can use, right in the chat. Agents choose from 86 components on their own, with no setup: sliders and filters recompute in the page, and buttons, choices and forms put your answers in your message, which reaches the agent when you send it. Test reports, logs, lint errors and coverage files render as their own components instead of pasted text, and a thread's changes, commits, pull request and workers are read live from BB. Adds about 6,400 tokens of instructions to sessions whose replies you read, and looks up photos, places and map tiles on Wikimedia Commons, Wikipedia, Photon and OpenStreetMap unless you turn web lookups off. Relies on BB internals, so a BB update can show the blocks as code until the plugin catches up.

ComicBit894

Agent BoardFollow live BB agent activity, freshness, completion outcomes and monitoring health. Filter and group visible work by project, repository, provider or status. Optional Ollama Fleet and Redteam add worker visibility. Requires BB 0.40+; BB 0.46.0 recommended.

Aaron Phifer363

Agent TracesSee where your agents' time goes, from every thread down to each command, tool call, and subagent of a turn. A turn opens as a timeline that splits the agent's time into waiting on you, tools, subagents, thinking, writing, and model time, and it grows live while the agent works. Select a call to see its exit code, output, and arguments, or jump to the reply that followed it in the chat. A Traces page in the sidebar compares your recent threads by active time, calls, and errors, and two turns can be compared phase by phase. Turns export as OpenTelemetry or an HTML snapshot, and the bb agent-traces command gives agents the same answers. Traces come from the thread history on your bb server; an OpenTelemetry collector is optional.

Nicolas Charpentier277