Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.whim.run/llms.txt

Use this file to discover all available pages before exploring further.

​
Authentication

Each provider has a different auth method. During alpha, Claude and Codex are the supported providers. CCR + OpenRouter is managed by Whim and will not require setup once it launches.

​
CCR + OpenRouter

Coming soon. CCR + OpenRouter is currently disabled during alpha.
No setup required. CCR is managed entirely by Whim. When it launches, API usage is billed as part of your CU allocation.

​
Claude Subscription

1

Get your OAuth token

Run this in your local terminal (requires Claude Code installed):
claude setup-token
Copy the output token.
2

Paste in Whim

Go to Settings > My Defaults > Claude and paste the token. Click Save.
3

Verify connection

The status indicator shows a green dot with Connected when ready.
Your OAuth token is encrypted before storage and never exposed in logs or to other workspace members.
Token management:
  • The settings panel shows when your token was created and last used
  • Paste a new token to replace the existing one
  • Clear the field and save to disconnect

​
Codex Subscription

1

Start the login flow

Go to Settings > My Defaults > Codex and click Sign in to ChatGPT.
2

Enter the device code

Whim displays a device code and a link to the OpenAI verification page. Open the link in your browser.
3

Authorize

Enter the code on the OpenAI page and approve. The page confirms when complete.
4

Verify connection

The connection status updates to Connected once verified.
Device codes expire quickly. If it expires before you finish, click Sign in to ChatGPT again.

​
Connection status

IndicatorMeaning
Green dot - ConnectedAuthenticated and ready
Grey dot - Not connectedNeeds setup
Spinner - CheckingVerifying connection
You can only set a provider as your default if it shows Connected and is available to your workspace.
CCR + OpenRouter is platform-managed, so it currently appears connected. During alpha it is still unavailable and cannot be selected.

​
Workspace and user defaults

​
Workspace defaults (admin)

Go to Settings > Workspace > Defaults to configure for all members:
  • Default provider and model
  • Permission mode
  • Fast mode
  • Reasoning effort

​
User defaults

Go to Settings > My Defaults to override workspace defaults for your tasks only. User defaults take precedence over workspace defaults. Per-task settings override both.

​
Provider-specific settings

SettingCCR + OpenRouterClaudeCodex
ModelComing soonYesYes
Permission modeComing soonYesYes
Fast modeNoYesYes (native GPT models)
Reasoning effortNoYes (Low/Medium/High/Max)Yes (Low/Medium/High/xhigh)

​
Fast mode

Fast mode tells the provider to prioritize response speed. Useful for straightforward tasks - simple edits, boilerplate, quick fixes.
ProviderEffectSupported models
ClaudeEnables fast output mode in Claude settingsAll Claude models
CodexSets service_tier=fastNative GPT models
CCRNot available-
Fast mode for Claude uses the same model and does not change reasoning effort. Use Reasoning effort below to control Claude’s --effort level.
Enable fast mode at three levels:
  1. Per task - toggle when creating a task
  2. User default - Settings > My Defaults
  3. Workspace default - Settings > Workspace > Defaults
Codex has fast mode enabled by default for GPT 5.5. Claude has fast mode disabled by default.

​
Reasoning effort

Reasoning effort is available for both Claude and Codex. Fast mode is a separate control.

​
Claude

LevelBest forSupported models
LowSimple, well-defined tasksAll Claude models
MediumGeneral coding workAll Claude models
HighComplex tasks needing deeper analysisAll Claude models
MaxExtended thinking on the hardest problemsClaude Opus 4.6 and Claude Opus 4.6 (1M) only
Claude reasoning effort controls the --effort flag passed to the Claude CLI. When unset, Claude uses its own default behavior.

​
Codex

LevelBest forSupported models
LowSimple, well-defined tasksAll Codex models
MediumModerate tasks, some reasoning helpfulAll Codex models
HighComplex tasks benefiting from deeper analysisAll Codex models
xhighDifficult problems - complex debugging, architecture, multi-file refactorsGPT 5.5, GPT 5.4, GPT 5.3 Codex, GPT 5.2 Codex
GPT 5.1 Codex Mini and GPT 5.3 Codex Spark top out at High.
Set reasoning effort at the same three levels as fast mode: per task, user default, or workspace default.

​
Speed vs quality reference

For Claude, fast mode and reasoning effort are separate controls. For Codex, fast mode is separate and applies only to native GPT models.
ConfigurationSpeedQualityCU impact
Claude Haiku 4.5 + fast modeFastest (Claude)GoodLeast container time
Claude Sonnet 4.5 + high effortModerateHighModerate
Claude Opus 4.6 + max effortSlowestHighestMost container time
Codex GPT 5.5 + fast mode + low reasoningFastest (Codex)LowerLeast container time
Codex GPT 5.5 + xhigh reasoningSlowerHighest (GPT)More container time
Fast mode and lower reasoning effort reduce agent time per task, directly lowering CU costs. During alpha, supported providers only consume CU through container time.

​
Troubleshooting

Your OAuth token may have expired. Run claude setup-token locally to generate a fresh token and paste it in Whim.
Device codes are time-limited. Click Sign in to ChatGPT again to generate a new one.
Verify the provider is connected (green dot) before setting it as your default. Existing tasks keep the provider they were started with.
User defaults only apply to new tasks. Check Settings > My Defaults (not workspace defaults) and verify the provider is connected.