The Unified Smart Bar

Every chat message is different. A quick unit conversion doesn't need the same firepower as debugging a production crash. And you shouldn't have to dig through settings menus to tell Meggy which model to use.

The Unified Smart Bar puts three controls into a single pill-shaped widget, right below the chat input field:

1. Model / Category — choose a specific model or an entire category (Thinking, Fast)
2. Thinking toggle — enable or disable extended reasoning per conversation
3. Execution Preset — dial the AI intensity from Quick to Try Till Done

Each conversation remembers its Smart Bar state independently, so you can have one chat pinned to a fast model for quick lookups and another using Try Till Done with thinking enabled for a deep research project.

Model & Category Selection

Tap the left section of the Smart Bar to pick which model (or model category) handles your messages. The dropdown is split into two tiers:

• Categories (top) — logical tiers like Thinking, Fast, and Utility that map to the models you've configured in Settings. Selecting a category tells Meggy to pick the best available model from that tier.
• Individual models (below categories) — override the category and pin the conversation to a specific model.

The Smart Bar label updates to show your current selection — either the category name or the specific model name — so you always know what's active.

Thinking Toggle

The brain icon in the Smart Bar enables extended reasoning — sometimes called chain-of-thought. When active:

• Meggy uses <thinking> blocks internally before answering
• The response includes a collapsible "Reasoning" section you can expand
• Models that support extended thinking will use it; others behave normally

This is a per-conversation setting. Toggle it on for a research chat, leave it off for casual conversation. The toggle state persists across sessions.

Execution Presets

The right section of the Smart Bar lets you choose how hard Meggy tries. By default it shows Chat — standard conversation with no engine overhead. Tap it to choose one of four execution presets:

Mode	Icon	What It Does	Model Category
Quick	zap	Single pass, no retries — fastest possible answer	Fast
Standard	target	Balanced multi-approach with automatic fallbacks	Thinking
Thorough	microscope	Deep research with task decomposition	Thinking
Try Till Done	flame	Full stubbornness ladder — Meggy never gives up	Thinking

When you pick a preset, two things happen:

1. Your message is routed through the engine instead of plain chat — meaning Meggy can break it into subtasks, retry failures, and escalate approaches
2. The model automatically switches to the category that fits the preset (fast models for quick answers, thinking models for complex problems)

Model Categories

Each execution preset has a preferred model category — a logical tier that maps to the models you've configured in Settings:

• Fast — lightweight models optimized for speed (Quick mode)
• Thinking — your primary capable model (Standard, Thorough, and Try Till Done modes)

When you select a preset, Meggy picks the first model from the matching chain in your settings. You can always override this by selecting a specific model or model category from the model section of the Smart Bar — the preset sets the default, but you stay in control.

Stubbornness Levels

Behind each preset is a stubbornness parameter that controls how hard Meggy tries before giving up:

Mode	Max Approaches	Stubbornness Cap
Quick	1	Level 2
Standard	3	Level 4
Thorough	3	Level 6
Try Till Done	3	Level 8

Higher stubbornness means more retries with different strategies. At Level 8, Meggy cycles through every model in your chain, decomposes the task, and escalates approaches until the job is done — or the budget is exhausted.

Try Till Done (TTD)

TTD is the most powerful mode. It's designed for tasks where failure isn't an option:

• Complex code generation — writing a multi-file feature with dependencies
• Research tasks — finding specific information across multiple sources
• Debugging — isolating a bug through systematic elimination

TTD uses thinking-class models by default and pushes stubbornness to maximum. If the first approach fails, Meggy reformulates and tries again with a different strategy. If that fails too, it escalates to a more powerful model.

When to Use Each Mode

Scenario	Recommended Mode
Quick math, conversions, or lookups	Quick
Writing emails, summaries, or explanations	Standard
Multi-step analysis or detailed code review	Thorough
Critical tasks where you need a guaranteed result	Try Till Done
Casual conversation or brainstorming	Chat

Getting Started

1. Open any chat conversation
2. Look at the Smart Bar just below the input field
3. Left section — tap to choose a model or category
4. Brain icon — tap to toggle Thinking on or off
5. Right section — tap to choose an execution preset
6. Type your message and send — Meggy handles the rest
7. The message bubble shows which model actually processed your request

Each chat remembers its Smart Bar settings independently, so you can fine-tune per conversation.

What's Next?

• Model Categories — how Meggy picks the right AI for every task across 9 categories
• Multi-Agent System — pipeline vs engine execution, DAG orchestration, artifact system
• Autonomous Agents — self-learning, YOLO mode, parallel execution, and failure museum
• Brain System Transparency — see the prompt, model selection, and token usage behind every response
• Skills & Routines — ready-made capabilities your assistant can use
• Built-in Tools — the 170+ capabilities that execute behind the scenes