Chat settings control how new conversations start and how replies are shown. They apply to future chats and do not rewrite existing messages.

Where to find it#

  1. Open the user menu at the bottom of the sidebar.
  2. Choose Settings.
  3. Select Chat.

The page is grouped into Conversation basics, Input and sending, Display and rendering, Context management, File processing, and AI preference memory.

DEEIX Chat Chat settings

Choose the default model for new chats#

  1. Find Default model for new chats under Conversation basics.
  2. Open the model list and select a model, or keep System default.
  3. Leave it as System default to use the first available system-recommended model.

Only chat-capable models appear in the list. If a model is missing, it is not enabled, not allowed for your account, or not a chat model.

Configure title and label generation#

Under Conversation basics:

  1. Turn Auto-generate titles on or off. When off, a new chat uses the first 16 characters of the first message as its title.
  2. Turn Auto-generate labels on or off. When off, conversation labels are no longer generated automatically, which reduces auxiliary model calls and the tokens they use.

Both options apply to new chats only.

Adjust input and sending#

Under Input and sending:

  1. Choose a Send shortcut: Enter or the platform modifier plus Enter.
  2. Choose an Input area height: Compact, Standard, or Loose. This caps how tall the composer can grow when it expands automatically.
  3. Turn Restore draft on failure on to bring back the text and attachments of a failed send.
  4. Turn Preserve conversation drafts on to keep unsent content per conversation when you switch chats.
  5. Turn Reuse model configuration on to auto-fill the model parameters you used last time when a new chat uses the same model.
  6. Turn Delete files by default when deleting chats on to preselect file deletion in the delete dialog. Files still referenced by other conversations are kept.

The send shortcut line shows the actual key for your platform, for example Enter or Ctrl+Enter / Command+Enter.

Choose what appears under replies#

Under Display and rendering:

  1. Turn Markdown rendering on to format replies as Markdown, or off for plain text.
  2. Turn Auto-expand deep thinking on to open the active thinking step while a reply is generated.
  3. Turn Auto-expand tool calls on to open the active tool call while it runs.
  4. Turn Show called model, Show token usage, Show total latency, and Show total cost on or off.

Show total cost is disabled and hidden in self-use mode. The billing mode is set by the platform; see Subscription.

DEEIX Chat reply metadata

Set the chat area width and font#

Under Display and rendering, below the metadata switches:

  1. Pick a Chat area width: Compact, Standard, or Wide.
  2. Pick a Chat font: Default, Serif, Sans, or Mono.
  3. Pick a Chat font weight: Regular, Medium, Semibold, or Bold.

Manage context#

Under Context management:

  1. Turn Auto-compact context on to summarize older turns and keep the most recent turns in full when a conversation exceeds the turn or token threshold. This switch appears only when an administrator has enabled Context compression in the admin console.
  2. Turn Pass back reasoning context on so supported Chat Completions reasoning models include prior reasoning content in later turns.

With Auto-compact context off, long conversations reach the model context limit sooner.

Choose how files are processed#

Under File processing:

  1. Open File processing mode.
  2. Select one of the modes below.
ModeBehavior
AutoThe system chooses full-context injection or RAG based on file size, type, context budget, and retrieval capability.
Full contextLater turns try to include conversation file content directly. Best for precise analysis of small files.
Vector retrievalLater turns retrieve relevant file chunks first, then fall back to full-context injection when retrieval is unavailable.

The line under the selector states the current mode, for example Current: Auto.

Manage AI preference memory#

AI preference memory stores long-term preferences that guide replies.

  1. Click Add preference.
  2. Enter a Name, for example Reply style.
  3. Enter the Preference content, for example concise and direct, avoid filler.
  4. Click Add.

The counter above the list shows how many entries you have, up to 20. When it is full, the button reads Full.

To change an entry, click the edit icon, update the content, and click Save. To remove an entry, click the delete icon and confirm Delete this preference?.

DEEIX Chat AI preference memory

Saved preferences apply to future conversations. One-off requirements belong in the current message.

Option reference#

SectionOptionValues
Conversation basicsDefault model for new chatsSystem default or a chat-capable model
Conversation basicsAuto-generate titlesOn / off
Conversation basicsAuto-generate labelsOn / off
Input and sendingSend shortcutEnter or modifier + Enter
Input and sendingInput area heightCompact, Standard, Loose
Input and sendingRestore draft on failureOn / off
Input and sendingPreserve conversation draftsOn / off
Input and sendingReuse model configurationOn / off
Input and sendingDelete files by default when deleting chatsOn / off
Display and renderingMarkdown renderingOn / off
Display and renderingAuto-expand deep thinkingOn / off
Display and renderingAuto-expand tool callsOn / off
Display and renderingShow called modelOn / off
Display and renderingShow token usageOn / off
Display and renderingShow total latencyOn / off
Display and renderingShow total costOn / off (disabled in self-use mode)
Display and renderingChat area widthCompact, Standard, Wide
Display and renderingChat fontDefault, Serif, Sans, Mono
Display and renderingChat font weightRegular, Medium, Semibold, Bold
Context managementAuto-compact contextOn / off (needs admin Context compression)
Context managementPass back reasoning contextOn / off
File processingFile processing modeAuto, Full context, Vector retrieval

Common problems#

ProblemWhat to check
A model is missing from the default model list.The model is not enabled, not chat-capable, or not available to your account.
Show total cost cannot be turned on.The platform is in self-use mode, so cost is hidden.
Auto-compact context does not appear.An administrator has not enabled Context compression in the admin console.
Add preference is disabled.You reached the limit of 20 entries. Delete one first.
A change does not affect an existing chat.Chat settings apply to new behavior. Existing messages are not rewritten.