Reasoning & Thinking

When reasoning is active, the model produces a chain-of-thought before writing its response. Bodega collects those thinking tokens in a separate stream and shows them in a collapsible Reasoning block above the response - the response text itself is always clean.

Three things control whether and how much reasoning happens for a given message, resolved in this order:

1. Per-message composer pill - overrides everything else for that one send
2. Claude Fast Mode - suppresses Claude reasoning globally (only affects Claude models; per-message pill still wins)
3. Per-model override - set in the expanded model card in Settings → Models
4. Global default - saved in Settings → Models as llm.reasoning_effort

If none of those are set, reasoning is off.

Not all models support reasoning. The composer pill appears only for models that do. Non-reasoning models silently ignore the effort value - setting a global default won't cause errors.

The composer pill and model cards show three states depending on the selected model:

Always-on reasoners manage their own reasoning depth - you can't tune it. For local Ollama models, the reasoning control appears when Bodega detects thinking support from the model's metadata; if it doesn't appear for a model you expect to support it, make sure the model is fully pulled and reconnect Ollama.

The composer has a row of controls below the text input. The reasoning pill is one of them - it looks like a brain icon with the current effort label.

1. Type your message in the composer (Chat mode or Code mode / Agent panel).
2. Click the brain icon button in the control row below the input.
3. Select Off, Low, Medium, or High from the dropdown. Press Escape or click outside to close without changing.
4. Send the message. The pill selection applies only to that message.

What "Off" means here: it means "use my default setting", not "force reasoning off". If your global default is set to Medium, selecting Off in the pill still sends Medium. The Off selection defers to the global - it does not suppress it. If you need to guarantee no reasoning on a message when your global default is non-zero, you must first lower your global default in Settings → Models → My Models (save it to Off), then send the message.

The selected effort resets to Off when you switch sessions or reload. It persists across messages within a session until you change it.

To set a default that applies to all messages without touching the composer pill each time:

Global default:

1. Go to Settings → Models → My Models.
2. Adjust the reasoning effort setting in the LLM settings form.
3. Click Save Model Settings.

The value is stored as llm.reasoning_effort (off / low / medium / high, default off) and applies to every reasoning-capable model when no per-message or per-model override is set.

Per-model override:

1. Go to Settings → Models → My Models.
2. Click the chevron on a model card to expand it.
3. Find the Reasoning Effort segmented control (Off / Low / Med / High).
4. Select the level you want for that model specifically.
5. Save.

The per-model value (llm.model_overrides[modelName].reasoningEffort) wins over the global default for that model only. Non-reasoning models ignore both values.

Claude Fast Mode suppresses extended thinking on Claude models to get faster replies - same model, no quality downgrade, just no reasoning pre-pass. It sits between the per-message pill and the per-model/global defaults in the resolution chain.

Click the Fast toggle in the message composer - it appears next to the reasoning control for Claude models.

To override it for one message, set the composer pill to Low, Medium, or High for that send - the pill always wins.

Fast Mode has no effect on OpenAI, Gemini, or local models. It exists specifically for Claude because Anthropic's adaptive and manual thinking architecture makes the skip-for-speed trade-off meaningful there.

When a model reasons during a response, a Reasoning block appears above the response text.

• While streaming: shows Reasoning... Ns with a live elapsed-seconds counter and a pulsing dot.
• After completion: shows Reasoning (N words) with a toggle button.
• Collapsed by default. Click the brain icon + label to expand.
• The reasoning chain renders in a fixed-height (500px) scrollable monospaced block. Chains longer than 2,000 characters show a character count at the bottom.

Reasoning content is held in client memory and is not persisted to the database. If you reload, the reasoning disclosure for past messages will be empty - the response text is preserved, but the thinking chain is not.

After a response completes, a metrics row appears below the message:

↳ N tokens (M thinking) • X tok/s

The thinking token count is included only when the model produced reasoning tokens. The metrics row appears after the response is fully done - not during streaming.

Note: thinking tokens count as input tokens for billing purposes on most providers.

You set Off / Low / Medium / High. The backend translates that into provider-specific parameters:

Claude Opus 4.7 and 4.8 reject temperature entirely - even with reasoning off. Bodega handles this automatically: it strips temperature for those models and retries on a 400 error, so it self-heals for future Claude releases that deprecate temperature before the internal list is updated.