Home / Reference / Environment variables

`CLAUDE_CODE_DISABLE_PROACTIVITY`

env in the build JSON

A Claude Code environment variable, read out of the shipped bundle. It has been in the build since v2.1.290, including the newest one read.

A --proactivity flag picks the proactivity level when Claude Code starts, and CLAUDE_CODE_DISABLE_PROACTIVITY turns the selector off

Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.290.

First seen v2.1.290 5 Oct 2026

Last seen v2.1.295 8 Oct 2026

Builds6 / 138on this box, as of v2.1.295

Written about v2.1.290 first named in a changelog, 5 Oct 2026

v2.1.290in the build not in the build never minedv2.1.295

In the changelogs

Releases whose published page names CLAUDE_CODE_DISABLE_PROACTIVITY.

v2.1.295 8 Oct 2026
Sessions started by Claude Code can inherit the restrict-personal-config mode
Under a certain condition, Claude Code now sets CLAUDE_CODE_RESTRICT_PERSONAL_CONFIG to 1 for the sessions it starts

found in this entry's text
v2.1.290 5 Oct 2026
New --proactivity flag sets how much Claude does on its own at startup
A --proactivity flag picks the proactivity level when Claude Code starts, and CLAUDE_CODE_DISABLE_PROACTIVITY turns the selector off

found in this entry's text
v2.1.290 5 Oct 2026
New variables to turn off proactivity and carry it across a relaunch
Claude Code adds CLAUDE_CODE_DISABLE_PROACTIVITY and variables that pass proactivity state to a relaunched Claude Code

found in this entry's text
v2.1.290 5 Oct 2026
Proactive mode choice now survives worker restarts
In headless sessions, Claude Code now keeps your proactivity opt-in when the worker restarts

found in this entry's text, named in this entry

First cited

The earliest release whose published evidence quoted CLAUDE_CODE_DISABLE_PROACTIVITY was v2.1.290, 5 Oct 2026. That is the oldest release this project wrote about it, so it is a floor on the name's age and not the release that introduced it. It is not a presence reading: which builds carried the name is the table below.

ReleaseDateThe span that was quoted

v2.1.2905 Oct 2026CLAUDE_CODE_DISABLE_PROACTIVITY

Presence across releases

BuildsHow manyDatesReading

v2.1.290 – v2.1.2956 builds5 Oct 2026 → 8 Oct 2026 ◆in the build

Build by build

One row per release since the first build this name was read out of. Absent means the build was read and the name was not in it, never mined means no bundle for that release was ever archived, and a declared type or a default is only ever what that release's own bundle stated.

BuildDateStateThe record behind it

v2.1.2905 Oct 2026·addedverdict: added · bool

v2.1.2916 Oct 2026·presentverdict: present · bool

v2.1.2926 Oct 2026·presentverdict: present · bool

v2.1.2937 Oct 2026·presentverdict: present · bool

v2.1.2948 Oct 2026·presentverdict: present · bool

v2.1.2958 Oct 2026·presentverdict: present · bool

Read out of the published npm bundle release by release, and out of Anthropic's own documentation as this site captured it. Nothing on this page is a description anybody here wrote about what the environment variable does. All environment variables.

Names beside it

Every environment variable in the inventory starting claude_code_disable, up to twelve of them.

CLAUDE_CODE_DISABLE_1M_CONTEXT v2.1.138
Set to 1 to disable 1M context window support. When set, 1M model variants are unavailable in the model picker, and Claude Code holds sessions on models with a native 1M window, such as Sonnet 5.5 and the Fable models, to a 200K window; see Extended context for how the hold is enforced. Useful for enterprise environments with compliance requirements. For its role in correcting the window for an unrecognized [1m] model ID, see Correct the window for a gateway or custom model ID
CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING v2.1.138
Set to 1 to disable adaptive reasoning on Opus 4.6 and Sonnet 4.6 and fall back to the fixed thinking budget controlled by MAX_THINKING_TOKENS. Has no effect on Fable models, Sonnet 5 and later, or Opus 4.7 and later, which always use adaptive reasoning
CLAUDE_CODE_DISABLE_ADMIN_ENV_UNION v2.1.223
Set to 1 to stop Claude Code from merging managed settings env blocks per key across admin sources, so only the highest-priority source's whole env block applies, as before v2.1.223. Set it in the environment that launches Claude Code, since Claude Code ignores a copy delivered through a settings env block. Requires Claude Code v2.1.223 or later
CLAUDE_CODE_DISABLE_ADVISOR_TOOL v2.1.138
Set to 1 to disable the advisor tool. The /advisor command becomes unavailable, any configured advisorModel is ignored, and the --advisor flag is accepted but has no effect, so existing scripts that pass it continue to work without errors
CLAUDE_CODE_DISABLE_AGENT_VIEW v2.1.139
Set to 1 to turn off background agents and agent view: claude agents, --bg, /background, and the on-demand supervisor. Equivalent to the disableAgentView setting
CLAUDE_CODE_DISABLE_AGENTS_FLEET v2.1.138
A true value (1, true, yes, on) turns off the background-agents fleet, the same as the disableBackgroundAgents setting: the fleet gate that otherwise follows tengu_slate_meadow returns false, so claude daemon subcommands that need the gate stop with 'daemon' is not enabled., the built-in Claude agent is left out of the built-in agent list, and claude daemon run exits with claude daemon: background agents disabled (ZDR/3P/opt-out).
CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN v2.1.138
Set to 1 to disable fullscreen rendering and use the classic main-screen renderer. The conversation stays in your terminal's native scrollback so Cmd+f and tmux copy mode work as usual. Takes precedence over CLAUDE_CODE_NO_FLICKER and the tui setting. You can also switch with /tui default. Does not apply to background sessions opened from agent view, which always use fullscreen rendering
CLAUDE_CODE_DISABLE_ARTIFACT v2.1.172
Set to 1 to turn off the Artifact tool, which publishes session output as a private web page on claude.ai. Once you set it, no settings file turns the tool back on. To turn the tool off from a settings file instead, set enableArtifact to false; the deprecated disableArtifact key also turns it off
CLAUDE_CODE_DISABLE_ATTACHMENTS v2.1.138
Set to 1 to disable attachment processing. File mentions with @ syntax are sent as plain text instead of being expanded into file content
CLAUDE_CODE_DISABLE_ATTRIBUTION_BASELINE_REUSE v2.1.282
No description from anybody.
CLAUDE_CODE_DISABLE_ATTRIBUTION_CROSS_REPO v2.1.275
Two new environment variables are now recognized: CLAUDE_CODE_DISABLE_ATTRIBUTION_CROSS_REPO and CLAUDE_CODE_SDK_HAS_OAUTH_REFRESH
CLAUDE_CODE_DISABLE_AUTH_REFRESH_LOCK v2.1.286
When true, the awsAuthRefresh and gcpAuthRefresh commands run directly instead of being coordinated across Claude Code processes through a lockfile, and the related waiting, takeover and sign-in failure counting are skipped.

Documentation pages 0

None of Anthropic's documentation pages this site has a copy of carries this name.