Skip to content

Agent Configuration

Each workspace runs its own Claude Code agent session. You can configure agent behavior per-workspace or set defaults for all new sessions.

Select a model from the dropdown in the chat header. Available models:

ModelIDDescription
Opus 4.6 1MopusOpus 4.6 with 1M context window
Opus 4.6claude-opus-4-6Standard Opus 4.6
Sonnet 4.6sonnetFast and capable
Haiku 4.5haikuFastest, most affordable

The model selection is per-workspace — you can use different models for different tasks.

Set the default model for new sessions in Settings > Models > Default model.

Control how much reasoning the agent applies to each response:

LevelDescriptionAvailable Models
AutoLet Claude decide (default)All models
LowFast, minimal reasoningOpus, Sonnet
MediumBalancedOpus, Sonnet
HighDeep reasoningOpus, Sonnet
MaxMaximum reasoning budgetOpus 4.6 only

Select the effort level from the dropdown in the chat header, next to the model selector.

Set the default in Settings > Models > Default effort level.

When enabled, the agent shows its reasoning process in expandable “thinking” blocks before its response.

  • Toggle thinking: Enable/disable in the chat header toolbar
  • Show/hide blocks: Even with thinking enabled, you can choose whether to display the thinking blocks in the chat UI

Set defaults in Settings > Models:

  • Default thinking — enable/disable for new sessions
  • Show thinking blocks — show/hide by default

Fast mode prioritizes speed over depth. When enabled, the agent uses quicker, more concise responses.

Toggle fast mode in the chat header toolbar. Set the default in Settings > Models > Default fast mode.

In plan mode, the agent outlines its approach before writing code. This is useful for complex tasks where you want to review the plan before execution.

  • Toggle: Click the plan mode button in the chat header, or press Shift + Tab
  • Default: Set in Settings > Models > Default plan mode

When the agent produces a plan, you’ll see a plan approval prompt where you can approve, reject, or modify the plan before the agent proceeds.

Type @ in the chat input to reference specific files in your workspace. A file picker appears showing matching files — select one to include it as context for the agent.

This is useful for directing the agent’s attention to specific files:

“Review the error handling in @src/api/handler.ts and suggest improvements”

Configure defaults for all new sessions in Settings > Models:

SettingDescriptionDefault
Default modelModel used for new chats
Default effortReasoning effort levelAuto
Default thinkingEnable thinking blocksOff
Show thinking blocksDisplay thinking in UIOff
Default plan modeStart in plan modeOff
Default fast modeUse fast modeOff