enabled
A Claude Code settings key, read out of the shipped bundle. It was in the build from v2.1.138 and was gone by v2.1.284.
Remote sessions now use the host's auto-compact settings for context and token display.
Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.227.
In the changelogs
31Releases whose published page names enabled.
-
v2.1.304
Stricter checking of a remote feature switch's settings
Claude Code now checks a server-sent feature configuration more strictly and accepts two new on/off options in it
found in this entry's text
-
v2.1.293
Import prompt setting is now described as off unless set, with clearer modes
An admin setting that offers a prompt import now says it is off unless set, and that
showneedsenabledor a sign-in importfound in this entry's text
-
v2.1.285
Turning auto-memory off is now tracked per session and may carry over
Claude Code now tracks auto-memory being off for a session and adds a notice that memory is still paused from earlier
found in this entry's text
-
v2.1.282
Claude apps gateway adds an operator-only load test mode with canned replies
The gateway config accepts an optional load_test_mode block that returns canned replies instead of calling the model, off unless an operator adds it
found in this entry's text
-
v2.1.282
Self-hosted gateway can stay ready through short database outages
The self-hosted gateway gains
store.readiness_grace_secondsto keep reporting ready while Postgres is down, plus a load-test modefound in this entry's text
-
v2.1.282
Gateway gets a load-test mode that returns canned replies, with a startup warning
The gateway now has a load-test mode that answers every request with a canned reply, and it warns at startup whenever that mode is on
found in this entry's text
-
v2.1.282
Spend-limit proxy can run load tests without counting spend
The spend-limit layer records zero cost in load-test mode and now reports failed spend checks and failed spend writes
found in this entry's text
-
v2.1.281
Safety-check permission dialogs can now auto-deny after a timeout (new
tengu_splendid_horizonconfig)Safety-check permission dialogs can now deny the request on their own if nobody answers before a timeout runs out
found in this entry's text
-
v2.1.281
Admin schema: M365 connector Continuous Access Evaluation
Admins can turn Continuous Access Evaluation on or off for the built-in Microsoft 365 connector; it is on by default
found in this entry's text
-
v2.1.281
Destructive-command safety prompts now deny themselves after a timeout, and stop appearing after 3 unanswered
Unanswered safety-check permission prompts now deny themselves after a timeout, and after 3 of them the check denies without asking
found in this entry's text
-
v2.1.281
Cowork 'advanced file analysis' now requires the chat surface to be enabled
Cowork's advanced file analysis now also requires
chatSurface.enabledto be truefound in this entry's text
-
v2.1.274
Compaction can now keep a tail-announcement summary of key attachments across a compact boundary
Compaction can now carry forward a short summary of key attachments across the compaction boundary
found in this entry's text
-
v2.1.263
New API-error detection for thinking block_binding mismatch
Claude Code can now recognize a specific new 400 error about thinking-block mismatch settings.
found in this entry's text
-
v2.1.260
Adaptive thinking has an opt-out for specific models, unresolved by default
Adaptive thinking is now default; an env var can revert to the old mode for certain models.
found in this entry's text
-
v2.1.260
Claude.ai data-import toggle no longer force-hidden in enterprise config UI
The Claude.ai data-import toggle is no longer hidden in enterprise settings UI.
found in this entry's text
-
v2.1.257
SearchPlugins/SearchSkills results now flag which plugins are already enabled
Plugin and skill search results now mark which plugins are already enabled for this session.
found in this entry's text
-
v2.1.248
One-per-week session limit reset, present but dark
You could clear a five-hour session limit once a week, but the command stays hidden.
found in this entry's text
-
v2.1.248
Vendored Anthropic client updated with server-side compaction and new resources
The bundled API library gains server-side compaction blocks plus sessions, vaults, skills and MCP tunnel surfaces.
found in this entry's text
-
v2.1.246
Forged max-turns notes are now neutralised in untrusted text
Forged max-turns notes pasted into tool output are now escaped so they can't fake harness messages.
found in this entry's text
-
v2.1.239
Lower-priority continuation after a session limit, built but dark
Hitting the 5-hour limit could offer to keep working at reduced priority, but it is off for everyone.
found in this entry's text
-
v2.1.239
Default copy and confirmation text for lower-priority mode
Built-in wording exists for a lower-priority working mode, all replaceable by server config and off by default.
found in this entry's text
-
v2.1.236
Self-hosted sandbox workers can now mount memory stores
Shared memory stores now mount on your own sandbox workers, with tunable sync interval and deletion handling.
found in this entry's text
-
v2.1.228
Gateway gains a second admission path for machine identities
The self-hosted gateway can admit machine identities that skip managed-settings policy entirely, off by default.
found in this entry's text
-
v2.1.228
Gateway customer-routed inference config, disabled by default
The self-hosted gateway accepts a strict customer-routed inference config block, off unless you enable it.
found in this entry's text
-
v2.1.227
Remote sessions can adopt the host's auto-compact settings
Remote sessions now use the host's auto-compact settings for context and token display.
found in this entry's text
-
v2.1.227
Break reminders gain a persistent active-time ledger
Break reminders now track active time on disk, so they survive restarts once you enable them.
found in this entry's text
-
v2.1.170
Fable 5 Launch Announcement Banner
found in this entry's text
-
v2.1.120
Memory Write Confirmation [Gradual Rollout]
found in this entry's text
-
v2.1.94
--thinking-display CLI Flag
found in this entry's text
-
v2.1.38
Thinking Mode Deprecation Warning
found in this entry's text
-
v2.1.34
Refactored Inbox Polling Logic
found in this entry's text
First cited
0No release's published evidence quotes this name. The ledger indexes the Evidence lines of every changelog on this site, so this says nobody here has ever quoted it; it says nothing about how old the name is.
Presence across releases
2Build by build
149One 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.
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 settings key does. All settings keys.