Desktop

Desktop settings

Every tab, row and action in the desktop app's Settings.

Command , or the footer gear opens Settings. The search box finds a row by label, description or setting key (showUsageIndicator) and jumps to its tab. Each tab in the sidebar shows how many settings it holds. Skills, MCP servers, Plugins, Extensions, Environments and Hosts show how many items they list instead. Accounts shows how many providers are signed in.

The TUI shares most settings. Appearance, layout and display stay per app (which are shared). The rows below are generated from the app's source.

Switch hosts#

Settings always opens on This computer. If you saved servers, the host menu at the top right of Settings lists This computer and each server, with its connection dot. To edit a server's settings, pick it in that menu. You stay on the same tab, and Settings hides the tabs that read this computer's files. You cannot pick a server that is not connected.

On a server, Skills, MCP servers, Plugins and Extensions list the server's, for the session's folder there, in the same rows as This computer's. A row shows only what the server can do:

MCP servers have every action of This computer's, run on the server. Remove works on the server user's mcps.json only. Add server to a project's file needs a recent server, and so do Shared, Restart and the process badge.
A skill shows no token sizes and does not open, because the server does not send its SKILL.md. A skill that a plugin or an extension brings follows the switch of that plugin or extension.
Install, Delete, Update and Remove show when the server takes installs from this app (allowRemoteInstalls), for its user's skills and extensions. Skills and extensions install from a GitHub or npm spec.
There is no Edit button and no Finder button, because the files are on the server.

On a server, Accounts, MCP servers and their tutorials name the server instead of this computer, for example "Keys and sign-ins saved on ipseity."

Settings tabs
Tab	What it holds
General	What it holdsSessions, updates, notifications and spaces.
Agent	What it holdsWhat new sessions start on, the helper models, approvals and limits.
Extensions	What it holdsProject and user extensions. Choose which ones can run.
Interface	What it holdsThe conversation, composer, sidebar, terminals, browser and git.
Accounts	What it holdsKeys and sign-ins, saved in ~/.zidane/credentials.json and shared with the CLI.
Advanced	What it holdsExperimental features and the agent loop internals.
Instructions	What it holdsWhat the session's agent reads, each part with its source.
Skills	What it holdsProject and user skills. Choose which ones the agent can use.
MCP servers	What it holdsServers from your mcps.json and the project's. Test one to check that it connects.
Plugins	What it holdsAgent Plugins and the skills and MCP servers they bring.
Environments	What it holdsWhere sessions run: this computer, a git worktree or a sandbox provider.
Appearance	What it holdsThemes, colors, fonts, size and motion on this computer.
Files & editor	What it holdsWhere files open and how the Files panel edits them.
Keybindings	What it holdsEvery shortcut. Change them in ~/.zidane/keybindings.json, then reload.
Hosts	What it holdsThis computer and your saved zidane-servers.
Logs	What it holdsExtension warnings, MCP diagnostics and host debug lines, live.
Performance	What it holdsLive CPU, memory and GPU per process. Samples only while open.

Run setup again, at the bottom of the sidebar above the version, closes Settings and opens the setup wizard with your current values.

Instructions, Skills, MCP servers, Extensions, Environments, Files & editor, Accounts and Hosts open with a tutorial on how that part of zidane works. A small scene plays its three steps in turn, and a click on a step shows it. Some tutorials have a button, such as Edit your system prompt on Instructions.

General#

Settings, General
Setting	Control	Default	Description
Start from last sessionSessions	ControlSwitch	DefaultOn	DescriptionOpen the last session on launch instead of the sessions list.
RemindersSessions	ControlSwitch	DefaultOff	DescriptionSend a prompt to a session at a set time, once or on a repeat. Extensions can schedule their own reminders.
Agent can set remindersSessions	ControlSwitch	DefaultOn	DescriptionGive the agent a tool to schedule prompts to its own session, such as "check the CI in 20 minutes". Needs Reminders.
Crash recoverySessions	ControlChoice: Ask before resuming, Resume, Off	DefaultAsk before resuming	DescriptionKeep a checkpoint of each run so it can continue after a crash. Applies to new runs. Unavailable on stores other than SQLite.
Check for updatesUpdates	ControlSwitch	DefaultOn	DescriptionLook for new releases and show them in the footer.
Install updates automaticallyUpdates	ControlSwitch	DefaultOff	DescriptionInstall new releases in the background. Restart when you are ready.
NotificationsNotifications	ControlSwitch	DefaultOff	DescriptionIf no Zidane window is focused, notify you when a run ends or needs you.
Notification soundNotifications	ControlSwitch	DefaultOn	DescriptionPlay the system sound with each notification.

Spaces#

Use spaces turns spaces on. Your spaces lists them: add, rename, pick an icon, move up or down (the sidebar order), or delete.

Each space has its own Default agent, Default model and Effort and options. A value that a space does not set comes from Agent › Defaults. Default can be renamed, not deleted. Deleting another space moves its sessions to Default. What spaces are: sessions. The sidebar's space switcher picks the one on show.

Import › Import from Claude Code shows when a Claude Code setup (~/.claude) exists. Tick conversations (this project or all), MCP servers, skills, and commands and subagents. Your Claude Code setup is left unchanged (what each part becomes).

Agent#

Settings, Agent
Setting	Control	Default	Description
Default agentDefaults	ControlAgent menu: The agents of the folder	DefaultBuild	DescriptionNew sessions start on it.
Default modelDefaults	ControlModel picker: Signed-in models	DefaultLast used	DescriptionNew sessions start on it.
Effort and optionsDefaults	ControlEffort menu: The default model's effort levels and options, else those of every signed-in model	DefaultThe last ones used with each model	DescriptionNew sessions start with them, on whatever model they run.
Interaction modeDefaults	ControlChoice: Ask normally, Skip interactions, Disable tools	DefaultAsk normally	DescriptionHow the agent handles questions: ask you, answer from the repository, or turn questions off.
Text modelHelper models	ControlModel picker: Signed-in models	DefaultAutomatic	DescriptionWrites session titles and suggestions. Automatic uses the session provider's smallest model.
DecisionsHelper models	ControlSwitch	DefaultOff	DescriptionHooks and extensions ask a decision model for quick yes/no, choice and score answers. Your provider bills each call.
Decision modelHelper models	ControlModel picker: OpenRouter and OpenAI platform models	DefaultFirst available	DescriptionAnswers decisions from hooks and extensions. Needs an OpenRouter key or an OpenAI platform key.
Auto-update session titlesHelper models	ControlSwitch	DefaultOff	DescriptionTitle sessions after their first run and rename them when the topic changes. Keeps titles you typed.
Estimate time remainingHelper models	ControlSwitch	DefaultOff	DescriptionShow how long running sessions and subagents have left, from a quick decision when a run starts. Uses tokens.
Compaction modelHelper models	ControlModel picker: Signed-in models	DefaultThe main model	DescriptionWrites the summaries. When to compact still follows the main model.
Allow subagents to use different modelsHelper models	ControlSwitch	DefaultOn	DescriptionLet the agent hand work to cheaper models.
Image generationHelper models	ControlSwitch	DefaultOn	DescriptionLet the agent generate images with your providers' image models. Pick the model in the model picker's Image tab. Each image is billed by the provider.
Tool approvalsApprovals & safety	ControlChoice: Ask, Model decision, Full access	DefaultAsk	DescriptionWho approves tool calls: you, the decision model, or nobody. Commands you safelisted always run.
SecretsApprovals & safety	ControlSwitch	DefaultOff	DescriptionLet the agent ask you for an API key or a token. It is kept in a private file for this project, out of the chat, and hidden in tool output.
Sandbox shell commandsApprovals & safety	ControlSwitch	DefaultOff	DescriptionKeep the agent's commands and edits inside the project and hide credentials.
Sandbox networkApprovals & safety	ControlChoice: Allow, Deny	DefaultAllow	DescriptionAllow keeps installs and git working. Deny blocks every connection.
Load project extensionsApprovals & safety	ControlSwitch	DefaultOff	DescriptionRun the extensions of this project. They can run any code on your computer.
Import configurations from other agentsApprovals & safety	ControlSwitch	DefaultOff	DescriptionUse other agents' servers, skills, commands and subagents. Imported servers run commands from files zidane does not own.
Support Ruler configuration (.ruler)Approvals & safety	ControlSwitch	DefaultOn	DescriptionRead .ruler folders. Their servers need "Import configurations from other agents".
Auto-compactContext & limits	ControlSwitch	DefaultOn	DescriptionSummarize the conversation when the context passes the threshold below.
Auto-compact thresholdContext & limits	ControlChoice: 60%, 70%, 80%, 90%	Default80%	DescriptionHow full the context gets before zidane summarizes it.
User instructionsContext & limits	ControlChoice: Both, User only, Project only, None	DefaultBoth	DescriptionWhich AGENTS.md and CLAUDE.md files the agent reads.
Max turns per runContext & limits	ControlChoice: Unlimited, 25, 50, 100, 200	DefaultUnlimited	DescriptionStop a run after this many turns.
Max cost per runContext & limits	ControlChoice: Unlimited, $1, $5, $10, $25	DefaultUnlimited	DescriptionStop a run once its estimated cost passes this amount.
Max tokens per runContext & limits	ControlChoice: Unlimited, 500K, 1M, 2M, 5M	DefaultUnlimited	DescriptionStop a run once it has used this many tokens.
Max run timeContext & limits	ControlChoice: Unlimited, 5 min, 15 min, 30 min, 60 min	DefaultUnlimited	DescriptionStop a run after this much time.
Max parallel subagentsContext & limits	ControlChoice: 1, 2, 3, 5, 10, Unlimited	Default3	DescriptionHow many subagents a session runs at once. More wait for a free slot.
Agent can use your terminalsAgent tools	ControlSwitch	DefaultOn	DescriptionLet the agent read your terminals and type in them after you approve.
Agent's background tasks in terminalsAgent tools	ControlSwitch	DefaultOn	DescriptionGive each background command the agent starts its own terminal tab.
Agent can use the browserAgent tools	ControlSwitch	DefaultOn	DescriptionLet the agent open, read, click and type in pages to check its work.
Web searchAgent tools	ControlSwitch	DefaultOn	DescriptionLet the agent search the web for docs, errors and recent changes.
CodemodeAgent tools	ControlSwitch	DefaultOn	DescriptionThe model batches tool calls in one short script that runs in a sandbox.

Default agent, Default model and Effort and options show only for this computer. Effort and options applies to every new session, whatever its model. It lists the levels and options of the default model when one is set. Else it lists every option that a signed-in model offers.

Every model row (Default model, Text model, Compaction model, Decision model) has a Test button. It sends the model one tiny prompt, or one decision for the decision model, with the credentials of the host running the sessions, and shows the latency or the failure reason under the row. An unset row tests the model it falls back to.

Tool approvals picks Ask, Model decision or Full access (approvals). Approvals & safety › Safelisted commands lists the Always allow entries of each project. You can revoke each one (safelist).

Instructions#

Each part of the open session's system prompt, with its source file or setting and its size in tokens. A bar shows each part's share. Click a part to read it.

Create SYSTEM.md shows when no SYSTEM.md exists in a place where one can apply. A SYSTEM.md that lost to another gets a note. Edit your system prompt, in the tutorial at the top, opens the SYSTEM.md in use. If there is none, it creates one from the built-in prompt first.

Where the app looks: files and folders. Agent › Context & limits › User instructions picks which AGENTS.md and CLAUDE.md files count.

Settings, Instructions: the parts of the system prompt with their sources and sizes.

Skills#

Project and user skills, each with an on/off switch. Under the note, the recommended sources show as small chips. Open one, or type a source, then pick its skills (sources).

Action	Does
Install N skills	Installs the picked skills into the project or into your user folder, one install per source
Edit	Opens a session on the skill's folder, to change it with the agent
Remove	Deletes the skill, after a confirmation
Scan for skills again (refresh icon)	Reads the skill folders again

How skills work: skills.

MCP servers#

The servers in your mcps.json and the project's (when Settings edits a zidane server, that server's). While a server runs, a badge says how it runs. "shared" with a count is one process that that many sessions use. "per session" is one process for each session.

Action	Does
Add server	Opens a form: name, transport (`stdio`, `streamable-http` or `sse`), command line or URL, env lines (stdio) or headers (HTTP and SSE), and the user or project config file. Advanced OAuth sets a pre-registered client: client ID, secret, callback port and scopes. A new server starts turned on. To change a server, add it again under the same name.
Remove	Deletes a server from the file that declared it, after Confirm remove
Sign in, Sign in again, Sign out	Starts or ends the OAuth sign-in of a server that needs one
Switch (Enable or Disable for this folder)	Turns a server on or off for the open project only
Expand tools	Lists the server's tools, each with its own switch
Shared (in the expanded row)	On: every session uses one process of the server. Off: each session starts its own, for a server that keeps per-user state (a browser it drives, an open document). Only for local `stdio` servers. Stored in the `mcpSharing` setting, which wins over `"shared"` in `mcps.json`. Sessions move to the new process when their next prompt runs.
Restart	Stops the server's running process. A call in progress fails, and the next call starts a fresh process. Sessions whose agent was built from an older config (an `mcps.json` you edited by hand) are rebuilt first, so the fresh process runs the current command. Shown while the server runs.
Test all	Connects to every server and shows which ones answer
Scan for MCP servers again (refresh icon)	Reads the config files again

Config files, lookup order and OAuth: MCP.

Settings, MCP servers with no servers configured.

Plugins#

The Agent Plugins found for the session's folder, with the skills and MCP servers each brings. The switch is a consent gate. When it is on, the plugin's skills reach the agent and its MCP servers start. A plugin that fails to load stays listed as broken.

Environments#

Where new sessions run: this computer, a git worktree, the OS sandbox, or a sandbox provider such as Docker, E2B or Daytona. Pick the Default and set each provider's options (execution contexts).

Extensions#

Project and user extensions, with the options they declare and a switch for each. Project extensions also need Agent › Approvals & safety › Load project extensions.

Action	Does
Install	Opens the extension browser (below)
Create extension, Build an extension	Asks for a name and a scope (user or project), creates the extension's folder and opens a session on it. Saved edits reload the extension once the session's run finishes. Build an extension is the button in the tutorial at the top.
Update	Runs the recorded installer again (`git pull` or an npm reinstall)
Update menu	Right-click Update, or click the arrow next to it. Update from `<source>` names where the extension comes from. Change origin… installs it again from another source
Remove	Uninstalls it, after a confirmation

An extension that fails to load has no switch. A red error chip sits next to its name. Point at the chip, or move focus to it, to read why it failed.

Add extensions#

Install opens a browser on the extensions that ship with zidane (Tahul/zidane). The built-in extensions are always listed, even when the repository cannot be read. Then a note says that you need access to install from it.

Type another source to list its extensions: owner/repo, a GitHub link, an npm package or a local folder. The browser reads each extension's package.json and runs no code. Pick one or more rows, choose User or This project, and click Install. This project shows the project trust hint. Each pick installs on its own, so one failure does not stop the others.

A private GitHub repository needs access. Run gh auth login and gh auth setup-git, or add an SSH key, then try again.

Change origin#

Change origin… opens with the current source filled in. Type a fork, a tag or an npm package. zidane installs the extension from the new source and keeps the old copy until the install works. The new source must hold an extension with the same name. If it does not, the dialog lists the names it found and nothing changes. After the change, Update follows the new source.

Each extension with settings has an entry under Extensions in the sidebar, titled with its display name and drawn with its icon. An extension without an icon shows the first letter of its name in a small square. An extension with a category gets a group of its own after Advanced instead (extension settings).

Writing and trusting extensions: extensions.

Interface#

Settings, Interface
Setting	Control	Default	Description
Conversation presetConversation	ControlPreview tabs: Focused, Balanced, Detailed	DefaultBalanced	DescriptionFocused, Balanced or Detailed, with a preview of each.
Transcript densityConversation	ControlChoice: Full, Compact	DefaultCompact	DescriptionFull shows every step. Compact folds each exchange's work into one row.
Row iconsConversation	ControlSwitch	DefaultOn	DescriptionShow an icon next to each message and step.
Thinking blocksConversation	ControlSwitch	DefaultOn	DescriptionShow the agent's reasoning in the chat.
Expand thinking while it streamsConversation	ControlSwitch	DefaultOff	DescriptionKeep a thinking block open while the agent reasons.
Run receiptConversation	ControlSwitch	DefaultOn	DescriptionShow agent, model, time, cost and tokens after each run.
Collapse subagentsConversation	ControlSwitch	DefaultOn	DescriptionStart subagent blocks collapsed.
Cache noticesConversation	ControlSwitch	DefaultOff	DescriptionAdd a row to the chat when the prompt cache expires or resets, or the provider drops earlier reasoning.
Todos badgeConversation	ControlSwitch	DefaultOn	DescriptionShow the agent's todo progress as a badge in the composer.
ArtifactsConversation	ControlSwitch	DefaultOn	DescriptionTrack each session's pull requests, branches, commits and files.
Keep scroll positionConversation	ControlSwitch	DefaultOn	DescriptionReopen each conversation where you left it.
DiagramsConversation	ControlSwitch	DefaultOn	DescriptionDraw Mermaid code blocks in replies as diagrams in your theme's colors. Off shows their code.
Tool calls displayTool activity	ControlChoice: Formatted, Full, Hidden	DefaultFormatted	DescriptionShow tool calls as a summary, their full input, or not at all.
Tool outputsTool activity	ControlSwitch	DefaultOn	DescriptionShow the output under each tool call.
Edit diffsTool activity	ControlSwitch	DefaultOn	DescriptionShow file edits as diffs.
Tool attachmentsTool activity	ControlSwitch	DefaultOn	DescriptionGather the images tool calls return under the Working block.
Group tool callsTool activity	ControlSwitch	DefaultOn	DescriptionFold each exchange's tool calls into one row.
Full shell outputTool activity	ControlSwitch	DefaultOff	DescriptionShow every line of ! command output, not only the last 10.
Show codemode tool callsTool activity	ControlSwitch	DefaultOff	DescriptionList the calls each script makes under its row. Calls that start a subagent always show.
Stream progressTool activity	ControlSwitch	DefaultOff	DescriptionShow which line of a script runs, how many of its calls are done, and what it prints, while it runs.
Smooth streamingStreaming	ControlSwitch	DefaultOn	DescriptionReveal replies at a steady pace as they stream.
ThrobberStreaming	ControlSwitch	DefaultOff	DescriptionAnimate an indicator while the agent works.
Messages during a runComposer	ControlChoice	Defaultqueue	DescriptionWhat happens to a message that you send while the agent works. Alt+Enter sends one message the other way.
Paste attachmentsComposer	ControlSwitch	DefaultOn	DescriptionTurn dropped images and long pastes into attachments.
Inline autocompleteComposer	ControlSwitch	DefaultOn	DescriptionSuggest the rest of a path as you type. Tab accepts.
Suggest the next promptComposer	ControlSwitch	DefaultOff	DescriptionAfter a run, suggest a next message in the empty composer. Uses the text model.
Run details in the sidebarSidebar & usage	ControlSwitch	DefaultOn	DescriptionShow each run's activity, time, commits and pull requests in the sidebar.
Check usageSidebar & usage	ControlSwitch	DefaultOn	DescriptionFetch plan limits and credits from signed-in providers and GitHub.
Usage indicatorSidebar & usage	ControlSwitch	DefaultOn	DescriptionShow the plan usage gauge in the footer.
TerminalsTerminal & browser	ControlSwitch	DefaultOn	DescriptionShow terminals next to the chat. They run where the session runs.
Close terminals that exit cleanlyTerminal & browser	ControlSwitch	DefaultOn	DescriptionClose a terminal once its shell exits cleanly. Failed ones stay open.
Browser tabTerminal & browser	ControlSwitch	DefaultOn	DescriptionShow a browser in the side panel to preview your app.
Show the browser when the agent uses itTerminal & browser	ControlSwitch	DefaultOn	DescriptionOpen the Browser tab when the agent starts using it.
Ask before syncingGit	ControlSwitch	DefaultOn	DescriptionConfirm before the git bar pulls, pushes or publishes your branch.

Conversation starts with a sample conversation and four tabs: Your settings, Focused, Balanced and Detailed. A tab only previews. Use Balanced, for example, sets every transcript setting of that preset. The rows below change one setting at a time, and the Your settings tab follows them. The command palette has the same presets, under Conversation preset.

Diagrams, under Conversation, draws Mermaid code blocks in replies as diagrams in your theme's colors (diagrams). Turn it off to see their code.

Try the conversation rows live: transcript.

Clear site data for this project, under Terminal & browser, removes the dev browser's cookies and storage for the project. Terminals run only in the daemon. So that section also shows the daemon's connection, or a link to Advanced › Experimental › Shared daemon runtime while the daemon is off.

Appearance#

Mode, themes, accent, app icon, fonts, sizes and motion: appearance and themes.

Files & editor#

How the Files panel opens and edits files.

Settings, Files & editor
Setting	Control	Default	Description
Open files and diffs inOpening	ControlSegmented: $EDITOR, Panels	DefaultPanels	DescriptionWhere a clicked file, folder or diff goes. ⌘-click flips it.
File tree sideOpening	ControlSegmented: Left, Right	DefaultLeft	DescriptionWhere the Files panel keeps its tree.
Edit files in the panelEditing	ControlSwitch	DefaultOn	DescriptionType in the viewer. ⌘S saves. Zidane never overwrites a file the agent changed after you opened it.
SaveEditing	ControlSegmented: ⌘S, On focus loss	Default⌘S	DescriptionWhen Zidane writes your edits to disk.
Tab sizeEditing	ControlSegmented: 2, 4	Default2	DescriptionSpaces per indent level in the panel editor.
Wrap long linesEditing	ControlSwitch	DefaultOff	DescriptionWrap lines wider than the editor instead of scrolling sideways.
Match bracketsEditing	ControlSwitch	DefaultOn	DescriptionHighlight the bracket pair around the caret.
Rounded selectionEditing	ControlSwitch	DefaultOn	DescriptionDraw text selections with rounded corners.
Auto-surroundEditing	ControlSegmented: Both, Quotes, Brackets, Off	DefaultBoth	DescriptionTyping a quote or bracket over a selection wraps it.
Check files with the project's toolsDiagnostics	ControlSegmented: Off, Project tools, + Language servers	DefaultProject tools	DescriptionRuns the tools the folder uses (tsc, ESLint, Biome, Ruff, cargo check, go vet). Findings show as squiggles and under the line.
RunDiagnostics	ControlSegmented: On open, On save	DefaultOn open	DescriptionOn open checks again each time the file changes on disk. On save checks only after you save.
TimeoutDiagnostics	ControlSlider: 5 s to 300 s	Default60 s	DescriptionPer tool, per run. Whole-project checks (tsc, cargo) are slow on big repos.
HoversLanguage servers	ControlSwitch	DefaultOn	DescriptionShow types and docs when the pointer rests on a symbol.
CompletionLanguage servers	ControlSwitch	DefaultOn	DescriptionSuggest names while you type. Ctrl+Space asks anywhere.
Stop when idleLanguage servers	ControlSlider: 1 min to 60 min	Default5 min	DescriptionZidane stops a server with no open file after this long. It starts again on the next file.

Under Diagnostics, you turn each project tool off on its own. The Language servers section (with Check files with the project's tools set to + Language servers) lets you change each server's command.

Keybindings#

Every shortcut, grouped as on the keyboard map. The tab is read-only. Edit in file opens keybindings.json, and Reload applies it without a restart (rebind a key).

Accounts#

Your provider keys and sign-ins, shared with the CLI and the TUI. When Settings edits a server, this page shows the server's keys and sign-ins. They stay on the server.

Action	Does
Set key, Replace key, Clear	Saves, changes or removes a provider's API key
Sign in with provider	Signs in with an account: Sign in with Claude, ChatGPT, xAI or Cursor. Sign in with Google (Google Vertex AI) shows only when a Google OAuth client is set (`ZIDANE_GOOGLE_CLIENT_ID`).
Add account	Adds another account to a provider you already signed in to. You name the account first.
Configure, Edit config	Sets the fields of a provider that needs more than a key: the project and location of Google Vertex AI, or the base URL, key and default model of a local server
Remove (on a credential)	Deletes one key or account, after a confirmation

A provider with several credentials (a key and an account) lists each one and marks the one in use. Click another to switch. A key from an environment variable shows for context only. Sign-in methods: providers. Where credentials are saved: files and folders.

Settings, Accounts: providers with their keys and sign-ins.

Hosts#

With Settings › Advanced › Experimental › Remote hosts on, this page lists this computer and your saved servers. Add, test, rename or remove one, and set up its machines and settings sync (hosts, server and sync).

The tutorial at the top explains zidane-server. It runs zidane on another machine with no window, such as a VPS. The tutorial has the command that starts it, zidane server start, with a copy button (install the server).

Advanced#

Settings, Advanced
Setting	Control	Default	Description
Shared daemon runtimeExperimental	ControlSwitch	DefaultOff	DescriptionRuns keep going when windows close and show in every window.
Remote hostsExperimental	ControlSwitch	DefaultOff	DescriptionRun sessions on other machines through zidane-server.
Main sessionExperimental	ControlSwitch	DefaultOff	DescriptionPin a session that starts, steers and reads your other sessions.
Project homeExperimental	ControlSwitch	DefaultOff	DescriptionClick a project in the sidebar to open its home: a new chat with the project's recent sessions, usage and blocks from extensions.
Persist large tool resultsAgent internals	ControlSwitch	DefaultOn	DescriptionSave tool outputs over 8 KB to disk and keep a preview in the chat.
Stable tool list (call_tool)Agent internals	ControlSwitch	DefaultOn	DescriptionUse found MCP tools through call_tool so the prompt cache stays valid. Off adds them to the tool list instead.
Freeze session promptAgent internals	ControlSwitch	DefaultOn	DescriptionKeep each session's system prompt as its first run saw it and tell the model about later changes. /refresh re-reads it.
Compact before the cache expiresAgent internals	ControlSwitch	DefaultOff	DescriptionExperimental. When a long session sits idle, compact it a minute before its prompt cache runs out, so your next message reads a short summary instead of re-reading the whole conversation.
Short MCP tool listAgent internals	ControlSwitch	DefaultOff	DescriptionExperimental. List MCP tools by name only in the prompt; the model looks up a tool before using it. Saves tokens when many tools are connected.
Preserved thinking (Anthropic only)Agent internals	ControlChoice: Drop silently, Fail the run, Account default	DefaultDrop silently	DescriptionWhat to do with reasoning that no longer matches the conversation.
Max output tokensAgent internals	ControlChoice: Model max, 8K, 16K, 32K, 64K	DefaultModel max	DescriptionThe most the model may write per turn.
Auto-resume on output limitAgent internals	ControlSwitch	DefaultOff	DescriptionKeep going when an answer hits the model's output limit.
Provider retry attemptsAgent internals	ControlChoice: Default (3), 1 (no retry), 2, 3, 5, 8	DefaultDefault (3)	DescriptionHow many times to retry a failed or stalled provider call.

Logs#

Live extension warnings, MCP diagnostics and host debug lines. The filter box narrows them. Follow new lines keeps the view at the latest line.

Performance#

Live figures, every 2 seconds. Sampling runs only while this page or the overlay is open.

The six tiles at the top are Zidane's own CPU, memory, GPU (the whole GPU on macOS, all apps), main-thread load, main-thread lag and the monitor's own cost. A + badge on CPU and memory is what your sessions and terminals launched.

Each list below folds away, and its header sums it up:

Processes (open): a tree that opens one level at a time. A closed row shows how many processes it holds and what they use together. Its columns still show its own figures. Zidane holds the app, the daemon, MCP servers, language servers and helpers. Launched holds what an agent's commands, a background task or a terminal started, such as a dev server or a benchmark. A row's tooltip has its pid and command line. An MCP server's process has a badge: shared with the number of sessions that use it, or per session. Its tooltip names the server. The list button on a row shows its operating-system threads (macOS doesn't name them). CPU is percent of one core.
Sessions: each session running something (its commands, terminals and own MCP servers), with what they use together. Open one to see its processes.
Threads: the main process's event loop, its worker threads, each window and its workers.
Slow frames: the scripts that ran in frames over 50 ms. "(rendering)" is style, layout and paint.
IPC: calls, total time, p95 and worst case per channel.
CPU profile: records the main process or this window, then lists the functions that took the most time. The .cpuprofile file opens in Chrome DevTools › Performance.

The IPC and slow-frame counters are always on and cost nothing while the app is idle. Reset counters starts them again. Export report writes a JSON summary with findings to ~/Library/Application Support/Zidane/perf/. An agent can do the same through the dev browser or CDP: await window.__zidanePerf.report(), and await window.__zidanePerf.profile('main', 5) for a profile.

The command palette's Performance overlay shows CPU, memory, main-thread load and lag, and the busiest process, in a corner of the window.

On a server

Pick a server in the Settings host switcher and Performance shows that server's own figures: the server process and what it runs (its MCP servers, language servers and helpers under Zidane, what its sessions started under Launched), its sessions, its event loop under Threads, and its GPU when it runs on macOS. The server samples only while the page is open. There are no slow frames, IPC counters, report or CPU profile there: those belong to this app's windows.

It needs an admin token for that server. With a chat token the page shows greyed out, with an Admin only tooltip. A server too old to report it says Not available on this host.

Reference#

zidane/chat settings: the Settings type and DEFAULT_SETTINGS.
Form rows: the kit rows these tabs are built from.