> ## Documentation Index
> Fetch the complete documentation index at: https://stampede.autonomousorganizations.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Console

> Work with Stampede from a terminal: the interactive console, one-shot questions, headless agent runs, slash commands and stopping a run.

The terminal is the most direct way to give Stampede work. You can hold a conversation in which the model reads files and runs tools, ask a single question, or hand over a task that runs to the end with nobody watching. Terms such as person, preset and run are defined in [Concepts](https://stampede.autonomousorganizations.ai/concepts.md).

## Ways to start

| Command | What it does |
| - | - |
| `stampede` | Opens the console. Resumes the last conversation when `resume_by_default = true`. |
| `stampede tui` | Starts a fresh conversation in the terminal interface (TUI). |
| `stampede chat` | Starts a fresh conversation in the line chat. |
| `stampede resume [NAME]` | Continues the most recent conversation, or the one saved as `NAME`. |
| `stampede -prompt "QUESTION"` | Asks one question and prints one answer. Nothing is kept. |
| `stampede agent "TASK"` | Runs a task to the end with no console, durably. |

Bare `stampede` opens the TUI when stdin and stdout are both a terminal, and the line chat when either is a pipe or a file, so scripts keep working. Set `console = "chat"` at the top level of `~/.stampede/config.toml` to make the line chat the default on a terminal too.

Start the console in the directory you want the model to work in:

```bash theme={null}
cd ~/projects/website
stampede
```

Then ask for something that needs a tool:

```text theme={null}
list the files here and say in two sentences what this project is
```

`chat`, `tui` and `agent` accept `--skill-lane stable|canary` to choose which skill catalog the run loads (`stable` by default). See [Skills](https://stampede.autonomousorganizations.ai/persons/skills.md).

## Choosing the person

Every conversation runs as one person. Without a choice it is the default person, `main`. To start as another person:

```bash theme={null}
stampede --person analyst
stampede --person analyst tui
```

`stampede person use NAME` sets the default person for later conversations. The current conversation keeps the person it started with.

## The terminal interface

The TUI prints the conversation into your terminal's own scrollback, so scrolling, selecting and copying work as usual. The input box, a separator and a status line stay pinned at the bottom.

| Key | Effect |
| - | - |
| Enter | Sends the message or command. |
| Alt+Enter (or Shift+Enter where the terminal supports it) | Inserts a newline. The box grows up to ten rows. |
| Up / Down | Moves between lines of the draft, then through earlier prompts. |
| Ctrl-C | Cancels the running turn. When idle, leaves the console. |
| Esc | Skips or denies an open question or approval; otherwise cancels the running turn; when idle, leaves the console. |

A multi-line paste is shown as `[Pasted text #N +M lines]` and expanded to the full text when you send it. Type `exit` or `quit` to leave.

With `require_approval = true` under `[tools]`, the console asks before every tool call. Press `y` to run the call; any other key denies it.

## The line chat

The line chat is the same conversation, one line at a time, for pipes and plain terminals. Type `exit` or `quit`, or press Ctrl-D, to leave. An empty line is ignored. Ctrl-C during a turn requests cancellation and waits for the run to stop safely.

The full history is sent to the model on every turn, which is what gives it memory of the conversation.

## Addressing a person

In the TUI, a line that starts with `@name` is a request to that person. It runs in the background while you keep typing, and the console prints its progress:

```text theme={null}
@editor review README.md for clarity and list three improvements
```

| Form | Goes to |
| - | - |
| `@person request` | A person on this machine. |
| `@node@person request` | A person on a paired machine. See [Multiple machines](https://stampede.autonomousorganizations.ai/teamwork/multiple-machines.md). |
| `#room request` | Every member of a cross-machine room. |

A request routes only when the mention is the first word, names an existing person, and has text after the name on the same line. A mention later in the line is ordinary text for the current model. The request is capped at 16 KiB.

Person mail does not carry the current conversation, selected file or earlier tool results. Make each request self-contained: name an exact path or paste the snippet.

Progress appears as `[people] NAME is working`, a live activity row with a task label and elapsed time, and finally one line such as `[people] editor finished with Completed in 25m 0s`. Leaving the TUI cancels its background work; unanswered mail stays queued for later. Persons, policies and mail are covered in [Persons](https://stampede.autonomousorganizations.ai/persons/overview.md) and [Mail and task rooms](https://stampede.autonomousorganizations.ai/teamwork/mail-and-task-rooms.md).

Person routing is a TUI feature. In the line chat, use `/person send`.

## Slash commands

A line that starts with `/` is a command. An unknown command is reported and never sent to the model. `/help` lists the commands and `/help QUERY` shows one in full:

```text theme={null}
/help
/help person edit
/help person schedule create
```

| Command | What it does |
| - | - |
| `/help [QUERY]` | Lists commands, or shows the syntax, options and examples of one. |
| `/model [NAME\|NUMBER]` | Lists the model profiles, or switches the conversation to one. |
| `/save NAME` | Names the current conversation; later turns save there. |
| `/sessions` | Lists saved conversations. |
| `/person ...` | The `stampede person` commands: `create`, `edit`, `policy`, `list`, `show`, `use`, `send`, `inbox`, `runs`, `goals`, `schedule`. |
| `/skill NAME [text]` | Loads one active skill for the next turn and sends the text with it. |
| `/skills ...` | The `stampede skills` commands. |
| `/feedback ...` | The `stampede feedback` commands. |
| `/reflect [save]` | Writes a reflection report with no tools; `save` turns new findings into inactive skill candidates. |
| `/allow PATH` | Lets the file tools reach one more path for this session. |
| `/add-secret NAME=VALUE` | Stores an encrypted secret. Needs `STAMPEDE_SECRET_KEY` in `~/.stampede/env`. |
| `/secrets` | Lists stored secret names. Values are never shown. |
| `/rm-secret NAME` | Removes a stored secret. |
| `/cost` | Token and cost totals for the runs this console started (TUI only). |
| `/room ...`, `/node ...` | Manage cross-machine rooms and peers (TUI only). |

`/model` takes a profile name or list number, a model name (`claude-*` implies Anthropic, `gpt-*` implies OpenAI, other names stay on the current provider), or an explicit provider, model and base URL:

```text theme={null}
/model
/model 2
/model claude-haiku-4-5
/model openai qwen3:32b http://localhost:11434
```

A switch on the same provider keeps the full history. A switch to another provider rewrites earlier tool turns as plain text. A switch that fails, such as a missing API key, changes nothing.

You can also ask the console about itself in plain words ("which persons exist?", "is the schedule worker up?"). The model answers from read-only tools and names the command for you to run when something should change.

## Questions from the model

On a terminal the model may stop and ask you up to four questions with the `ask_user` tool. Each question shows a short header, the question, and numbered options when it has any. Answer with a number, several numbers separated by commas when more than one may be chosen, or your own words.

An empty answer, or Esc in the TUI, leaves the question unanswered and the model reads `{"status":"no_answer"}`. A run with nobody to ask (a piped or scheduled run, a person working through its mailbox, a sub-agent) is not offered the tool, and a call that arrives anyway reads `{"status":"no_operator"}` at once.

A conversation keeps the tool set it started with. One started from a pipe, which has no `ask_user`, refuses to continue in a console that offers it, and says so.

## Saved conversations

`stampede resume` continues where you left off. Starting a fresh conversation renames the previous `last` to `last-previous`, and only one such generation is kept. Name anything you want to keep with `/save NAME`, then reopen it with `stampede resume NAME`.

```bash theme={null}
stampede sessions list
stampede sessions export NAME PATH
stampede sessions import PATH NAME
```

Exports are plaintext and the command warns about it.

## One-shot questions

```bash theme={null}
stampede -prompt "What is the capital of France"
```

One question and one answer, with no tools, no history and no run record. It is a quick way to prove that a key and a profile work.

## Headless runs

```bash theme={null}
stampede agent "inspect the project, run its tests, and summarize failures"
```

`stampede agent` gives the model the task and the tool catalog, runs tool calls and feeds results back until the model answers in plain text. Progress and narration go to stderr. Stdout carries only the final answer when it is piped, so the run fits in scripts:

```bash theme={null}
stampede agent "list the TODO comments in src/" > todos.txt
```

The run is durable: every model call and tool effect is journaled before and after it happens. `--ephemeral` turns that off explicitly.

| Exit code | Meaning |
| - | - |
| 0 | Success. |
| 1 | The API request failed. |
| 2 | A usage or configuration error. |

When the run ends, stderr shows `[stopped: WORD]`, where the word is one of `completed`, `budget_exhausted`, `wall_clock`, `no_progress`, `cancelled`, `provider_failed`, `interrupted` or `failed`. Budgets are described in [Limits](https://stampede.autonomousorganizations.ai/models/limits.md).

## Inspecting and stopping runs

Console turns and agent runs are recorded the same way.

```bash theme={null}
stampede runs list
stampede runs show RUN_ID
stampede runs show RUN_ID --tokens
```

`runs show` prints a redacted record of the run: its events, checkpoints, budget use and the `stop:` word. It never prints exact model or tool content. `--tokens` adds a line per model call with its tokens and cost.

To stop a run:

* In the TUI, press Ctrl-C or Esc. In the line chat or a foreground `stampede agent`, press Ctrl-C.
* From another terminal, run `stampede runs cancel RUN_ID`. The cancellation is journaled and reaches the process that owns the run.

A run that was interrupted can be picked up again:

```bash theme={null}
stampede runs resume RUN_ID
stampede runs conclude RUN_ID
```

`runs resume` continues the run exactly as it was recorded and refuses when the configuration, tools or workspace have drifted or an effect's outcome is unknown. `runs conclude` asks the model for a final answer with no tools, stating what is uncertain.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.