1# Agent Settings
  2
  3Learn about all the settings you can customize in Zed's Agent Panel.
  4
  5## Model Settings {#model-settings}
  6
  7### Default Model {#default-model}
  8
  9If you're using [Zed's hosted LLM service](./subscription.md), it sets `claude-sonnet-4` as the default model for agentic work (agent panel, inline assistant) and `gpt-5-nano` as the default "fast" model (thread summarization, git commit messages). If you're not subscribed or want to change these defaults, you can manually edit the `default_model` object in your settings:
 10
 11```json [settings]
 12{
 13  "agent": {
 14    "default_model": {
 15      "provider": "openai",
 16      "model": "gpt-4o"
 17    }
 18  }
 19}
 20```
 21
 22### Feature-specific Models {#feature-specific-models}
 23
 24You can assign distinct and specific models for the following AI-powered features:
 25
 26- Thread summary model: Used for generating thread summaries
 27- Inline assistant model: Used for the inline assistant feature
 28- Commit message model: Used for generating Git commit messages
 29
 30```json [settings]
 31{
 32  "agent": {
 33    "default_model": {
 34      "provider": "zed.dev",
 35      "model": "claude-sonnet-4"
 36    },
 37    "inline_assistant_model": {
 38      "provider": "anthropic",
 39      "model": "claude-3-5-sonnet"
 40    },
 41    "commit_message_model": {
 42      "provider": "openai",
 43      "model": "gpt-4o-mini"
 44    },
 45    "thread_summary_model": {
 46      "provider": "google",
 47      "model": "gemini-2.0-flash"
 48    }
 49  }
 50}
 51```
 52
 53> If a custom model isn't set for one of these features, they automatically fall back to using the default model.
 54
 55### Alternative Models for Inline Assists {#alternative-assists}
 56
 57With the Inline Assistant in particular, you can send the same prompt to multiple models at once.
 58
 59Here's how you can customize your `settings.json` to add this functionality:
 60
 61```json [settings]
 62{
 63  "agent": {
 64    "default_model": {
 65      "provider": "zed.dev",
 66      "model": "claude-sonnet-4"
 67    },
 68    "inline_alternatives": [
 69      {
 70        "provider": "zed.dev",
 71        "model": "gpt-4-mini"
 72      }
 73    ]
 74  }
 75}
 76```
 77
 78When multiple models are configured, you'll see in the Inline Assistant UI buttons that allow you to cycle between outputs generated by each model.
 79
 80The models you specify here are always used in _addition_ to your [default model](#default-model).
 81
 82For example, the following configuration will generate three outputs for every assist.
 83One with Claude Sonnet 4 (the default model), another with GPT-5-mini, and another one with Gemini 2.5 Flash.
 84
 85```json [settings]
 86{
 87  "agent": {
 88    "default_model": {
 89      "provider": "zed.dev",
 90      "model": "claude-sonnet-4"
 91    },
 92    "inline_alternatives": [
 93      {
 94        "provider": "zed.dev",
 95        "model": "gpt-4-mini"
 96      },
 97      {
 98        "provider": "zed.dev",
 99        "model": "gemini-2.5-flash"
100      }
101    ]
102  }
103}
104```
105
106### Model Temperature
107
108Specify a custom temperature for a provider and/or model:
109
110```json [settings]
111"model_parameters": [
112  // To set parameters for all requests to OpenAI models:
113  {
114    "provider": "openai",
115    "temperature": 0.5
116  },
117  // To set parameters for all requests in general:
118  {
119    "temperature": 0
120  },
121  // To set parameters for a specific provider and model:
122  {
123    "provider": "zed.dev",
124    "model": "claude-sonnet-4",
125    "temperature": 1.0
126  }
127],
128```
129
130## Agent Panel Settings {#agent-panel-settings}
131
132Note that some of these settings are also surfaced in the Agent Panel's settings UI, which you can access either via the `agent: open settings` action or by the dropdown menu on the top-right corner of the panel.
133
134### Default View
135
136Use the `default_view` setting to change the default view of the Agent Panel.
137You can choose between `thread` (the default) and `text_thread`:
138
139```json [settings]
140{
141  "agent": {
142    "default_view": "text_thread"
143  }
144}
145```
146
147### Font Size
148
149Use the `agent_font_size` setting to change the font size of rendered agent responses in the panel.
150
151```json [settings]
152{
153  "agent": {
154    "agent_font_size": 18
155  }
156}
157```
158
159> Editors in the Agent Panel—whether that is the main message textarea or previous messages—use monospace fonts and therefore, are controlled by the `buffer_font_size` setting, which is defined globally in your `settings.json`.
160
161### Auto-run Commands
162
163Control whether to allow the agent to run commands without asking you for permission.
164The default value is `false`.
165
166```json [settings]
167{
168  "agent": {
169    "always_allow_tool_actions": true
170  }
171}
172```
173
174### Single-file Review
175
176Control whether to display review actions (accept & reject) in single buffers after the agent is done performing edits.
177The default value is `false`.
178
179```json [settings]
180{
181  "agent": {
182    "single_file_review": true
183  }
184}
185```
186
187When set to false, these controls are only available in the multibuffer review tab.
188
189### Sound Notification
190
191Control whether to hear a notification sound when the agent is done generating changes or needs your input.
192The default value is `false`.
193
194```json [settings]
195{
196  "agent": {
197    "play_sound_when_agent_done": true
198  }
199}
200```
201
202### Message Editor Size
203
204Use the `message_editor_min_lines` setting to control the minimum number of lines of height the agent message editor should have.
205It is set to `4` by default, and the max number of lines is always double of the minimum.
206
207```json [settings]
208{
209  "agent": {
210    "message_editor_min_lines": 4
211  }
212}
213```
214
215### Modifier to Send
216
217Make a modifier (`cmd` on macOS, `ctrl` on Linux) required to send messages.
218This is encouraged for more thoughtful prompt crafting.
219The default value is `false`.
220
221```json [settings]
222{
223  "agent": {
224    "use_modifier_to_send": true
225  }
226}
227```
228
229### Edit Card
230
231Use the `expand_edit_card` setting to control whether edit cards show the full diff in the Agent Panel.
232It is set to `true` by default, but if set to false, the card's height is capped to a certain number of lines, requiring a click to be expanded.
233
234```json [settings]
235{
236  "agent": {
237    "expand_edit_card": false
238  }
239}
240```
241
242### Terminal Card
243
244Use the `expand_terminal_card` setting to control whether terminal cards show the command output in the Agent Panel.
245It is set to `true` by default, but if set to false, the card will be fully collapsed even while the command is running, requiring a click to be expanded.
246
247```json [settings]
248{
249  "agent": {
250    "expand_terminal_card": false
251  }
252}
253```
254
255### Feedback Controls
256
257Control whether to display the thumbs up/down buttons at the bottom of each agent response, allowing you to give Zed feedback about the agent's performance.
258The default value is `true`.
259
260```json [settings]
261{
262  "agent": {
263    "enable_feedback": false
264  }
265}
266```