Home / Reference / Environment variables

`CLAUDE_CODE_DISABLE_STRUCTURED_OUTPUTS`

env in the build JSON

A Claude Code environment variable, read out of the shipped bundle. It has been in the build since v2.1.288, including the newest one read.

Setting CLAUDE_CODE_DISABLE_STRUCTURED_OUTPUTS stops Claude Code from asking the model for replies in a fixed format

Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.288.

First seen v2.1.288 2 Oct 2026

Last seen v2.1.288 2 Oct 2026

Builds1 / 131on this box, as of v2.1.288

Written about v2.1.288 first named in a changelog, 2 Oct 2026

v2.1.288in the build not in the build never minedv2.1.288

In the changelogs

Releases whose published page names CLAUDE_CODE_DISABLE_STRUCTURED_OUTPUTS.

v2.1.288 2 Oct 2026
CLAUDE_CODE_DISABLE_STRUCTURED_OUTPUTS turns off structured outputs
Setting CLAUDE_CODE_DISABLE_STRUCTURED_OUTPUTS stops Claude Code from asking the model for replies in a fixed format

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

First cited

The earliest release whose published evidence quoted CLAUDE_CODE_DISABLE_STRUCTURED_OUTPUTS was v2.1.288, 2 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

v2.1.2882 Oct 2026CLAUDE_CODE_DISABLE_STRUCTURED_OUTPUTS

Presence across releases

BuildsHow manyDatesReading

v2.1.2881 build2 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

v2.1.2882 Oct 2026·addedverdict: added · 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.