All settings changedsettings-reference
Nearest release: v2.1.252, published 12 hours after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+33added
Lines−4removed
From line
646
where the diff opens
First seen
21 Aug 2026
this site's first read of the page
Recorded edits148to this page, all time
### `modelSettings`
The whole hunk
from line 646, old and new numbered
/
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 646
646646| [`disableSkillShellExecution`](#disableskillshellexecution) | Stop [skills](/docs/en/skills) and custom commands from running inline shell | Plugins and skills | Any file |
647647| [`disableWorkflows`](#disableworkflows) | Turn [dynamic workflows](/docs/en/workflows) off for everyone; use `enableWorkflows` for yourself | Hooks and automation | Any file |
648648| [`editorMode`](#editormode) | Use [vim key bindings](/docs/en/interactive-mode#vim-editor-mode) in the input prompt | Interface and terminal | Any file |
649| [`effortLevel`](#effortlevel) | Save the [`/effort` level](/docs/en/model-config#adjust-effort-level) so future sessions reason more or less deeply | Model and responses | Any file |
649| [`effortLevel`](#effortlevel) | Set a default [effort level](/docs/en/model-config#adjust-effort-level) for models without a saved level of their own | Model and responses | Any file |
650650| [`emojiCompletionEnabled`](#emojicompletionenabled) | Turn off [`:shortcode:` emoji suggestions and replacement](/docs/en/interactive-mode#emoji-shortcodes) in the prompt input | Interface and terminal | Any file |
651651| [`enableAllProjectMcpServers`](#enableallprojectmcpservers) | Approve every server in project [`.mcp.json`](/docs/en/mcp#project-server-approvals-and-workspace-trust) files without a prompt | MCP | Any file |
652652| [`enableArtifact`](#enableartifact) | Turn the [Artifact tool](/docs/en/artifacts) off with a `false` in any file; no file can turn it back on | Remote, desktop, and notifications | Any file |
from line 684
684684| [`modelOverrides`](#modeloverrides) | [Map model IDs](/docs/en/model-config#override-model-ids-per-version) to your provider's IDs, such as Bedrock ARNs | Model and responses | Any file |
685685| [`modelPicker`](#modelpicker) | Choose which models the [`/model` picker](/docs/en/model-config#available-models) lists, in your own order and with your own labels | Model and responses | User or managed |
686686| [`modelPricing`](#modelpricing) | Report spend at your organization's contracted rates instead of list price | Model and responses | Managed |
687| [`modelSettings`](#modelsettings) | Keep a saved [effort level](/docs/en/model-config#adjust-effort-level) per model, which Claude Code writes when you run `/effort` | Model and responses | Any file |
687688| [`otelHeadersHelper`](#otelheadershelper) | Generate rotating [OpenTelemetry](/docs/en/monitoring-usage#dynamic-headers) headers with your own command | Authentication and providers | Any file |
688689| [`outputStyle`](#outputstyle) | Change Claude's role, tone, and output format with an [output style](/docs/en/output-styles) | Model and responses | Any file |
689690| [`parentSettingsBehavior`](#parentsettingsbehavior) | Apply or drop restrictions an [SDK or IDE host](/docs/en/managed-settings#let-an-embedding-host-add-policy) passes when you deploy [managed settings](/docs/en/managed-settings) | Enterprise and managed settings | Managed |
from line 868
867868
868869### `effortLevel`
869870
870Keep an [effort level](/docs/en/model-config#adjust-effort-level) across sessions. Lower levels are faster and cheaper on straightforward tasks, and higher levels reason more deeply on complex problems. Claude Code writes this key to your user settings when you run `/effort low`, `medium`, `high`, or `xhigh` in an interactive session on your machine. In a `-p` run, the Agent SDK, or a session attached to a remote worker, `/effort` applies to that session only. The message `/effort` prints says which happened.
871Set a default [effort level](/docs/en/model-config#adjust-effort-level) for models you haven't saved a level for. Lower levels are faster and cheaper on straightforward tasks, and higher levels reason more deeply on complex problems.
871872
873When you run `/effort low`, `medium`, `high`, or `xhigh` in an interactive session on your machine, Claude Code saves the level for the active model under [`modelSettings`](#modelsettings) rather than writing this key. Within the same settings file, Claude Code uses a model's saved level rather than this key; [`modelSettings`](#modelsettings) states the cross-file precedence. In a `-p` run, the Agent SDK, or a session attached to a remote worker, `/effort` applies to that session only. The message that `/effort` prints says which happened. Before v2.1.251, `/effort` wrote this key.
874
872875* **Scope**: [`Any file`](#scopes)
873876* **Type**: string, one of:
874877 * `"low"`: the least reasoning, for short, scoped, latency-sensitive tasks that aren't intelligence-sensitive
from line 887
884887}
885888```
886889
887On Opus 4.7, Opus 4.8, and Fable 5, Claude Code holds that model's default effort until you change effort once with `/effort`, `--effort`, or the `/model` picker. After that, it reads this key. See [Adjust effort level](/docs/en/model-config#adjust-effort-level).
890On Opus 4.7, Opus 4.8, and Fable 5, Claude Code holds that model's default effort, organization-set or built-in, until you change effort once, for example with an interactive `/effort`, the `/model` picker's effort slider, or `--effort` at launch. After that, Claude Code resolves effort by the precedence stated at [`modelSettings`](#modelsettings). See [Adjust effort level](/docs/en/model-config#adjust-effort-level).
888891
889892### `enforceAvailableModels`
890893
from line 1116
11131116* **Any other key**: a key that isn't a built-in model's ID, such as a gateway model alias. Claude Code applies the row to that one ID only. When a model ID matches one of your keys exactly and also falls under a row keyed by a built-in model's ID, Claude Code uses the exact match.
11141117* **A Bedrock application inference profile**: once Claude Code has resolved the profile to the model it routes to, through your [`modelOverrides`](#modeloverrides) map or the [`bedrock:GetInferenceProfile` lookup](/docs/en/amazon-bedrock#iam-configuration), Claude Code applies that model's row to the profile.
11151118
1119### `modelSettings`
1120
1121Requires Claude Code v2.1.251 or later. Save an [effort level](/docs/en/model-config#adjust-effort-level) for each model you use. In an interactive session on your machine, when you run `/effort low`, `medium`, `high`, or `xhigh` or move the `/model` picker's effort slider, Claude Code saves that level here under the model you're using, so you rarely edit this key yourself. The [`effortLevel`](#effortlevel) entry lists the sessions in which `/effort` applies to that session only. Edit the key by hand to change or remove a level you saved.
1122
1123A model's entry here takes precedence over [`effortLevel`](#effortlevel) in the same settings file. Across files, Claude Code resolves each model separately: the highest-precedence [settings file](/docs/en/settings#settings-precedence) that sets either that model's entry or `effortLevel` decides, so an `effortLevel` in managed settings outranks a level you saved in user settings. [Adjust effort level](/docs/en/model-config#adjust-effort-level) lists what else can override a saved level, such as `--effort` at launch.
1124
1125* **Scope**: [`Any file`](#scopes)
1126* **Type**: object mapping a model name to an object with an `effortLevel` field, one of `"low"`, `"medium"`, `"high"`, or `"xhigh"`
1127* **Default**: unset
1128
1129Claude Code writes each entry under the model's canonical name, such as `claude-opus-5`, and matches that model's alias, date-suffixed, `[1m]`, and recognized provider-specific IDs to the same entry.
1130
1131This example keeps Opus 5 at `medium` while other models use their own saved or default levels:
1132
1133```json settings.json theme={null}
1134{
1135 "modelSettings": {
1136 "claude-opus-5": {
1137 "effortLevel": "medium"
1138 }
1139 }
1140}
1141```
1142
1143Run `/effort auto` to clear your saved level for the model you're using. Claude Code leaves the other entries and any top-level `effortLevel` in place.
1144
11161145### `outputStyle`
11171146
11181147Select an [output style](/docs/en/output-styles) by name. An output style is a saved set of instructions that Claude Code adds to the system prompt to change Claude's role, tone, and output format, such as the built-in Explanatory and Learning styles or one you wrote yourself.
from line 1256
12271256}
12281257```
12291258
1230Ultracode runs the session at `xhigh` effort and takes precedence over `effortLevel`. An Agent SDK `apply_flag_settings` control request also accepts the key.
1259Ultracode runs the session at `xhigh` effort and takes precedence over `effortLevel` and [`modelSettings`](#modelsettings) entries. An Agent SDK `apply_flag_settings` control request also accepts the key.
12311260
12321261## Permission settings
12331262
from line 3388
33593388Set the transcript view Claude Code starts in: `"default"`, `"verbose"`, or `"focus"`. When set, it overrides both the sticky `/focus` selection and the [`verbose`](#verbose) setting.
33603389
33613390* **Scope**: [`Any file`](#scopes)
3362* **Type**: string, one of:
3363 * `"default"`: the normal transcript with truncated tool output
3364 * `"verbose"`: the transcript with full tool output
3365 * `"focus"`: only your last prompt, a one-line summary of tool calls with edit diffstats, and the final response. Focus view needs the [fullscreen renderer](#tui)
3366* **Default**: unset, so the `verbose` setting and your last `/focus` choice apply
3367* **Per-session overrides**: [`--verbose`](/docs/en/cli-reference#cli-flags) takes precedence over this key for one session
3368
3369```json settings.json theme={null}
3370{
3371 "viewMode": "focus"
3372}
3373```
3374
3375### `vimInsertModeRemaps`
3376
3377Map two-key INSERT-mode sequences to Escape in [vim editor mode](/docs/en/interactive-mode#vim-editor-mode). Each key is exactly two printable characters typed in sequence, and `"<Esc>"` is the only supported target; Claude Code ignores other entries. Requires Claude Code v2.1.208 or later.
3378
3379* **Scope**: [`User or managed`](#scopes). A repository can't remap your keystrokes.
3380* **Type**: object mapping a two-character sequence to `"<Esc>"`
3381* **Default**: unset
3382
3383```json settings.json theme={null}
3384{
3385 "vimInsertModeRemaps": {
3386 "jj": "<Esc>"
3387 }
3388}
3389```
3390
3391Has no effect unless `editorMode` is `"vim"`. See [Remap INSERT-mode key sequences](/docs/en/interactive-mode#remap-insert-mode-key-sequences). Requires Claude Code v2.1.208 or later.
3392
3393### `voice`
3394
3395Turn on [voice dictation](/docs/en/voice-dictation) and choose how the dictation key behaves. Claude Code writes this object for you when you run `/voice`.
3396
3397* **Scope**: [`Any file`](#scopes)
3398* **Type**: object with `enabled` as a Boolean, `autoSubmit` as a Boolean that applies in hold mode only, and `mode`, one of:
3399 * `"hold"`: you hold the dictation key while speaking and release it to stop
3400 * `"tap"`: you tap the key once to start recording and again to send
3401* **Default**: unset, so dictation is off; when `enabled` is `true` and `mode` is unset, Claude Code uses `"hold"`
3402
3403This example turns dictation on and makes the key tap once to start recording and again to send:
3404
3405```json settings.json theme={null}
3406{
3407 "voice": {
3408 "enabled": true,
3409 "mode": "tap"
3410 }
3411}
3412```
3413
3414`autoSubmit` sends the prompt when you release the key in hold mode. Voice dictation requires a claude.ai account.
3415
3416### `voiceEnabled`
3417
3418<Warning>
3419 Deprecated since v2.1.92, when the [`voice`](#voice) object replaced it. Claude Code still reads it so older settings files keep working, but new configurations should set `voice.enabled`.
3420</Warning>
3421
3422Turn voice dictation on with the single Boolean form that predates the `voice` object. When both are set, `voice.enabled` applies.
3423
3424* **Scope**: [`Any file`](#scopes)
3425* **Type**: Boolean
3426 * `true`: voice dictation is on when you're logged in with a claude.ai account an
3391* **Type**
No line in this hunk matches that.