Docs · console

PriestAltar console

The console runs the same engine as the panel, in a terminal. It uses the same conversations, tools and permission checks. Open it from the PriestAltar desktop shortcut, or from any prompt with the priestai command.

Docs home Install The console Models & seats Permissions The fleet DevAd FAQ

Launching a model

Open from the website or your computer

The website’s Menu → Open PAVONA action offers a link to the installed PriestAltar console. On Windows, Setup registers the priestai://open/console app link for your user account. Existing installations need to run Setup again to register it. Your browser may ask before opening the app; visiting a page never launches it automatically.

If nothing opens, use the PriestAltar shortcut, or run priestai --console in a terminal where PAVONA is on your command path. Installation instructions explain how to set up the app.

Inside the console, /menu opens a numbered command palette; add a search term to narrow it, or press Enter to cancel. Use /theme night to change appearance, or launch with priestai --console --theme night. The twelve named themes are Night, Ember, Moss, Paper, Vigil, Reliquary, Sunward, and the five daylight twins — Lauds, Hearth, Meadow, Daybreak and Noon, which are Night, Ember, Moss, Vigil and Sunward in the same colours on a light page. Dark and Light are also accepted. Set PRIESTAI_REDUCED_MOTION=1 to disable the animated pane loader.

Start a conversation

Choose a model to start a conversation, the way ollama run does. The name can be an installed model, a short name, an OpenRouter id or the agent-mode word; they all go through the same resolver. The console prints what answered before the first prompt:

PAVONA> priestai launch qwen # installed model (a unique prefix is enough)
PAVONA> priestai launch claude # a paid cloud model, within your spending limit
PAVONA> priestai launch openclaw # agent mode: PAVONA's own tool loop
PAVONA> priestai launch anthropic/claude-sonnet-5 # an exact catalog id
PAVONA> priestai launch qwen --first "read the logs" # send a first message, then stay

When a name could mean more than one model (two qwen models installed, for example), the command refuses and names the candidates, so a model is never selected on your behalf.

Resuming with any model

A conversation is not tied to one model. Resume it and choose which model answers:

PAVONA> priestai resume # continue the newest conversation, current model
PAVONA> priestai resume claude # newest conversation, answered by Claude
PAVONA> priestai resume claude,qwen,openclaw # the first of these that answers, in order
PAVONA> priestai resume 20260903101422 qwen # a named chat (see /chats), answered by qwen

The comma list is tried in the order you typed it, and the first model that answers is used. If none answers, the command refuses and lists every miss. It does not keep the old model without telling you. Inside a conversation, /model claude switches models the same way, mid-conversation, and keeps the whole thread.

Task activity and messages

In a conversation, choose Activity to inspect recorded tool calls, worker progress and messages from other tasks. Changes opens captured file differences. Reviewing a difference does not apply it.

The shared command line is available on Windows and Linux:

priestai --cli task list --json
priestai --cli task new --title "Review the project" --workspace . --json
priestai --cli task inspect TASK_ID --json
priestai --cli task activity TASK_ID --json
priestai --cli task changes TASK_ID --json
priestai --cli task message TASK_ID TARGET_ID "Please review the changes" --request-id review-1 --json

Use task IDs returned by the list command. Reuse the same request ID and text to retry a message safely. Messages are delivered to another owned task in the same workspace; delivery does not start work or grant permission.

Command-line records belong to your operating-system account. Browser accounts have separate records. Goal budgets are requested limits unless enforcement is explicitly reported. Missing usage and file line counts remain unavailable.

TABLETS and the workspace

Upgrading from 1.5.53 or earlier on Windows? Use the 1.5.54 installer to receive all command-line components. Your existing notes and settings stay with your installation.

These note features arrived in version 1.5.54. Open TABLETS from the conversation workspace to work with your existing spaces and Markdown pages. The address records the selected space and page, so you can bookmark a note or return to the same note from the command line.

TABLETS saves pending edits before changing pages or spaces, closing the current note, or following Back to workspace. If a save fails, the editor keeps your text and explains the failure. Retry Save after restoring access or connectivity. For a conflicting version, use View theirs or Keep mine as a copy; a failed copy keeps your conflicting text available. Your browser may warn before closing a page with pending edits; unsaved text is not an offline backup.

Renaming, moving, restoring or deleting a note also saves pending text first. Restoring a version keeps the previous text in history, and deleting a note or space keeps its saved contents in trash. If another tab has moved or deleted a note, a stale save is refused; use Keep mine as a copy to recover your draft.

Editing briefly pauses while these operations finish. A timeout means the application could not confirm the result; check the note before retrying. An unsuccessful import is reported as a failure.

For bulk replacement, preview the changes before applying them. Changing the search, replacement or matching notes requires a fresh preview. If an external editor interrupts a replacement that has already begun, TABLETS reports how many pages were confirmed; review their histories before retrying.

To prepare a link to a particular note:

priestai --cli notes open --space team --page "Guides/Setup" --json

The command prints a link and reports handoff_required. Open the returned link in your signed-in application. It does not start the app or read, edit or export a note, and it does not verify that the target exists or that you have access. The application checks access when you follow the link. Use --app-url to name a different local application origin or an HTTPS installation.

Your existing spaces, history, comments, graph, exports and theme choices remain available in TABLETS. The link carries only the space and page names; avoid sharing it if those names are private.

Every command

CommandWhat it does
/model [name]Show the current model, or switch this chat to another. It takes installed names, short names like claude, or OpenRouter ids, all through the same resolver.
/modelsEvery model on this machine and on any other machine of yours that answered the probe, with sizes.
/pull [model] [host]Download a model onto a machine (this one by default) and watch the progress. Ctrl+C stops watching, not the download; a bare /pull shows what is downloading right now. The target must be a machine the install knows (see /hosts).
/hostsEvery machine this install can put a model on, probed live: which server answered, whether it can download models, and how models get there if it cannot. It also lists the cloud tier with its key status and this month's spending.
/catalog [word]The installable catalogue: the Ollama library and Hugging Face GGUF files, with sizes and an uncensored marker. Add a word to narrow it. This is what /pull can install.
/adopt <host>Add a second machine running Ollama as a model server. It is checked at the moment you add it, so an address that does not answer is refused rather than saved.
/key [value|clear]The OpenRouter key. With no argument it shows the status (stored or not, where it came from, the last four characters) and never the value. A value stores it; clear removes it. The key is stored through the same code path the panel uses.
/seatsWhich model is assigned to each role, and what each one measured.
/bareToggle bare mode (on by default): nothing is added to what you typed.
/toolsThe tools available in this conversation.
/skills [id]The skills on this machine; name one to switch it on or off for this conversation (at most 4 at once).
/project [name]Which project's shared notes read_notes and post_note use. No name clears it.
/newStart a fresh conversation.
/chatsRecent conversations.
/open <id>Resume one by id.
/attach <path>Attach a file: a local path, or a UNC path on another machine you own. A remote file is read in place, without maintaining a separate attachment copy.
/attachedWhat this conversation has attached.
/peersEvery other machine of yours, and whether it is online.
/browse <host> [p]List a directory on one of them over SMB.
/perm [mode]What the assistant may do without asking. See Permissions.
/clearClear this conversation's messages (the record of tool runs is kept).
/costThis month's paid-model spending against your limit, the same two numbers as the Money panel. Local inference has no provider fee.
/toolviewOpen the panel with the agent's picture-in-picture window, which shows what the agent is looking at while it works.
/updateAsk the panel for the newest release and, if you approve, install it through the same verified path the app uses; if the new build fails to start, the previous build is restored automatically.
/quitExit the console.

Cancelling a turn

Ctrl+C cancels the current turn and returns you to the prompt; the conversation is kept. Press it again at an empty prompt to exit.

Shell commands

A line starting with ! runs a shell command where you are, for example ! git status. The output streams as the command runs, so you do not have to leave the console to run a build.

A known limit: bare mode is the default, so the model receives only what you typed. Start with priestai --briefed (or the console flag of the same name) if you want the app's briefing text sent along with your messages.