Agent settings

The Settings tab holds the configuration that is not instructions, knowledge, or tools. Which sections appear depends on the agent's runtime; see Runtimes for the full matrix.

Opening the tab requires edit permission on the agent. Owners and Admins have it on every agent, and a member has it on an agent they were invited to under access control. Without it, the tab shows an access-denied page instead of the settings.

Model#

The Model Selection section appears on Claude Agent SDK, Anthropic and OpenAI Responses agents; Classic agents have no model setting. Which rows it offers depends on the runtime: Claude Agent SDK agents offer Claude, GPT and Gemini models, Anthropic agents offer Claude models, and OpenAI Responses agents offer GPT models.

The Claude Opus, Sonnet and Haiku rows are named by family, the GPT Astra, Sol, Terra and Luna rows by tier, and on Claude Agent SDK agents the Gemini Pro, Flash and Flash Lite rows by tier too. Each carries a Stable badge: a Stable row automatically follows the latest available version in that family or tier. Today the GPT tiers follow GPT-6 for Astra and Luna and GPT-6.1 for Sol and Terra, and the Gemini tiers follow Gemini 3.1 Pro, Gemini 3.8 Flash and Gemini 3.5 Flash Lite. To keep the agent on one exact release, choose it under Specific version instead; on OpenAI Responses agents that list is called Other versions and also holds the GPT models that have no tier, such as GPT-5.5 and GPT-5.4, which always run as chosen. Specific versions may become unavailable when their provider retires them.

A model the agent can't use right now stays in the list, shown disabled with a badge that says why:

For Claude Agent SDK agents, Runbear-provided access uses Runbear credits. If the agent uses its own API key, Claude models require an Anthropic key, GPT models require an OpenAI key, and Gemini models require a Google AI Studio key; the selected provider bills usage on your own key. To change providers while using your own key, first switch the agent back to Runbear-provided access, select the new provider's model, then save its key.

Claude Fable 5.2 runs only on an agent's own Anthropic key. It is not offered on Runbear-provided access, so until the agent is on its own key the row is shown disabled with the Requires Own API Key badge.

A more capable model is not automatically a better agent. If an agent mostly answers from a knowledge base, the cheapest tier usually matches the most expensive one on answer quality while consuming a fraction of the credits. See billing and credits.

Reasoning#

The Reasoning section appears only on OpenAI Responses agents. Effort sets how much the model thinks before answering, and Verbosity, shown for models that support it, sets how much of that it writes out. Both start at Default, which uses OpenAI's own setting. Higher effort improves multi-step work and tool sequencing, and costs more credits per message. Leave it low for lookup-style agents.

API key#

The API Key section appears on Anthropic, Claude Agent SDK and OpenAI Responses agents. By default the agent runs on Runbear's key and uses Runbear credits. To use your own key instead, turn on the switch named for the provider (Use my own Anthropic API key, Use my own OpenAI API key or Use my own Google AI Studio API key), paste the key, and click Save. Anthropic agents use an Anthropic key and OpenAI Responses agents an OpenAI key; Claude Agent SDK agents use the key of the selected model's provider: Anthropic for Claude models, OpenAI for GPT models and Google AI Studio for Gemini models. With your own key, the provider bills your account directly and the agent uses no Runbear credits.

A saved key is never displayed again; submit a new one to replace it. Turn the switch off to return the agent to Runbear's key. Changing the key requires the feature:write permission on the agent.

If an OpenAI Responses agent's uploaded files live in a vector store on your own OpenAI account, it can't switch back to Runbear's key from here; the section says so and points you to the Classic Editor, which re-provisions the store.

Access control#

Access control decides who can view and edit this agent in the dashboard. Choose one of:

• All organization members can view and edit — the default. Every member can open the agent, but changing it, including its Settings tab, still needs write permission on the agent; see Members and roles.
• Only invited users can view and edit — then add the members who should have access.

This setting does not affect who can talk to the agent. Anyone in a connected Slack channel, Microsoft Teams chat or other channel can still use it there. For Slack, a connection can be limited to specific users where that option is available; see Restricting who can use a Slack connection.

Data handling#

The Data handling section appears only for organizations entitled to HIPAA mode. It sets whether the agent uses standard data handling or HIPAA data handling. In HIPAA mode the agent runs on a restricted processing path; agents left on standard data handling are unchanged.

Only Anthropic agents can be switched to HIPAA. The mode is chosen per agent, and it appears in the create dialog as well, so a new agent starts in the right mode instead of being switched afterward.

A HIPAA agent can be returned to standard data handling: select Standard, click Save data handling, and confirm Return to Standard in the "Return this agent to standard data handling?" dialog. Don't do this while the agent handles protected health information.

Claude Fable models are not available in HIPAA mode. An agent in HIPAA mode cannot be moved onto one, and an agent already on one cannot be switched into HIPAA mode.

Before switching modes, read the HIPAA setup guide for Enterprise eligibility, BAA requests, supported runtimes, knowledge migration, and data-handling limits.

Long-term memory#

The Enable long-term memory toggle ("Remember user preferences and frequently referenced resources across conversations") is on by default. What it controls depends on the agent's runtime; see Memory.

Response feedback#

Enable response feedback adds feedback buttons under this agent's Slack responses ("Show 👍 / 👎 feedback buttons under this agent's Slack responses"), so people can rate an answer with one click. It applies to Slack only and doesn't use emoji reactions. The User Feedback chart in analytics is separate: it counts the emoji reactions people add to the agent's replies.

Tool activity#

While an agent works, it reports each tool call as it happens — a task card in Slack, and a thread.tool_call.progress event on the API and SDK streams. The Tool Activity section controls whether this agent does that.

The setting is on by default, and turning it off is a presentation change only: the agent still runs exactly the same tools, and the run's own trace still records every one of them, so the activity remains available to anyone reviewing the run afterwards. What stops is the live reporting, on every surface at once — a reply arrives without the intermediate steps.

Turn it off when the steps are noise to the people reading, or when a custom frontend built on the API should show only the answer.

The section appears only on agents whose model family reports tool calls at all. Where it is absent, the agent has no tool activity to hide rather than a setting that was withheld. Surface still matters independently: Teams and Discord replies never show tool calls, whatever this setting says.

Response components#

This section holds the agent's switch for clickable options on every channel, plus the controls for the structured components the agent can show in the Web SDK: confirm and select buttons the visitor answers, a card with one record's details, a list of results with links, thumbnails and short facts, a sortable, paged table, and a line, bar or area chart with hover details and, for dates, a range selector.

The section appears only on agents whose runtime reads it. Its Component frequency select and Web SDK components switches appear only once Runbear has enabled Web SDK components for your organization — they are in limited availability — and only on agent types that can emit components: Anthropic, OpenAI Responses, Mastra and Claude Agent SDK agents.

Choice buttons (all channels)#

Rather than ending a turn with a typed-out question, an agent can offer the answers as clickable options — "Approve" and "Reject", or a short list of the choices it was about to describe. The Choice buttons (all channels) switch controls whether this agent may do that.

The setting is on by default, and turning it off withdraws the buttons on every surface the agent answers on, not just one. Turn it off when the agent should carry out what your instructions authorize without stopping to ask.

Native Gemini, Perplexity, Upstage and legacy OpenAI Assistants agents never offer buttons, so the section is hidden there rather than shown as a switch that does nothing; a Claude Agent SDK agent keeps it whichever model it runs. Buttons are also never offered on scheduled or other automated runs, where nobody is waiting to click.

Clicking an option runs the choice as the person's next turn, so it is billed like any other message. The conversation is never blocked on a click — answering in your own words instead is always valid.

Where the buttons appear, and how long they stay clickable, depends on the channel. Slack renders them as message buttons and deliberately leaves them in place after a selection, so someone can try another option later; each of those clicks runs as its own turn. In the Web SDK the buttons go inert once a later message answers them.

This switch is the master for everything in this section. Turning it off also withholds every Web SDK component — buttons, cards, lists, tables and charts — whatever the controls below say. It is the only control here that reaches Slack, and unlike the controls below it needs no feature:write permission.

Component frequency#

Component frequency sets how readily the agent offers components in the Web SDK, with the levels Off, Low, Medium and High.

• Off withholds every Web SDK component, whatever the switches below say.
• Low, Medium and High change only how readily the agent offers Confirm and select buttons. A card, list, table or chart that is switched on is available whenever the level is not Off; the level does not make it rarer or more common.
• With Confirm and select buttons off, the three levels behave the same, and the dashboard says so under the select.
• The three levels cost the same.

Changing it requires the feature:write permission; without it the select is shown but disabled. It affects only the Web SDK, and it stays visible and editable while Choice buttons (all channels) is off, but it does nothing then: that switch overrides it.

Web SDK components#

One switch per component chooses what the agent may show in the Web SDK:

• New components start off. Switching one on affects only this agent. Existing agents keep exactly what they had: buttons and cards on.
• Upgrade your widget before switching on Lists, Tables or Charts, and before relying on card images or links. On an older widget the visitor reads the component's plain-text summary instead, and a widget older than 0.6.0 shows a card without its image and links. See which SDK release renders what.
• Only the switches this agent's type can use are shown. The others are hidden, and a note under the group says which ones the type supports. A Claude Agent SDK agent shows only Confirm and select buttons.
• Configure first, then enable. The switches stay usable while Choice buttons (all channels) is off or Component frequency is Off. The group is dimmed, and a note at its top explains why the switches have no effect yet. A note also appears when every component is off: the agent then answers in plain text on the web. To avoid showing a default card or buttons to live visitors before you have decided, set the switches you want while the level is Off, then choose a level.
• Permissions. Changing a switch requires feature:write, as the select does. Without it the switches are shown but disabled. A change takes effect immediately and is confirmed by a short message such as "Lists turned on".
• Two different switches. Confirm and select buttons only decides whether the agent may offer buttons in the Web SDK; it never affects Slack. Choice buttons (all channels) is the switch for every channel and every component, and it wins.
• Cost. Each switched-on component adds a fixed amount to the prompt of every eligible web turn, whether or not the agent uses it. See what each switch costs.

The same level and switches can also be read and set over the REST API — see Choosing components.

What decides whether a visitor sees a component#

Every one of these must hold. When a component does not show, check each in turn; the first six decide whether the agent is offered the component at all, and the last decides how the visitor's widget shows it:

1. Choice buttons (all channels) is on. Off means no components anywhere.
2. Someone is waiting on the run. Scheduled and other automated runs never show components.
3. Runbear has enabled Web SDK components for your organization (limited availability).
4. Component frequency is not Off.
5. The component's switch under Web SDK components is on.
6. The agent's type can use that component.
7. The visitor's widget runs a release that renders it. An older widget shows the component's plain-text summary, and a widget can also choose to show a component as its summary (config.components.disabled); see which SDK release renders what.

Related#

• Runtimes
• Instructions
• Billing and credits
• Members and roles