user
A Claude Code settings key, read out of the shipped bundle. No mined inventory carries it: everything below comes from what this site has written about it.
Recalled memories no longer get silently dropped when the model echoes back the category label with the name.
Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.219.
In the changelogs
65Releases whose published page names user.
-
v2.1.280
Teammate name reservation expanded to include 'user' and 'system'
Teammate names "user" and "system" are now reserved alongside "main" and "team-lead"
named in this entry
-
v2.1.280
Proxy URL check strips credentials before hostname comparison
Proxy no_proxy hostname checks now ignore any username/password embedded in the URL
found in this entry's text
-
v2.1.280
New session-initiator / wakeup-source telemetry categories
New telemetry categories record why and how a session was started or woken up
found in this entry's text
-
v2.1.280
Artifact publish now refuses declarations that silently reset db rules or user scopes
Publishing an artifact capability now gets refused if it would silently wipe out existing db rules or user scopes
found in this entry's text
-
v2.1.280
New credential-redacting URL formatter
New helper masks usernames and passwords embedded in URLs before display
found in this entry's text
-
v2.1.277
New helper
ir()detects wildcard characters in git/URL marketplace source stringsNew helper detects wildcard characters in git or URL marketplace source addresses
found in this entry's text
-
v2.1.275
Post-turn memory: new 'memory' settings layer and MCP memory tool with read/write/append/delete, gated by CLAUDE_CODE_POST_TURN_MEMORY
A new 'memory' settings layer and MCP memory tool let Claude write, read, and edit notes across turns
found in this entry's text
-
v2.1.274
Git tag/GPG signing config keys defined but apparently unused
New git config entries for tag and commit signing (like tag.gpgSign, gpg.format) added, purpose unclear
found in this entry's text
-
v2.1.274
Escaping team-memory mount-dir check refactored into scope-aware
jfnTeam memory's mount-directory escape check was refactored to dispatch by scope, now including the new account scope
found in this entry's text
-
v2.1.274
New MCP tool metadata field describing the serving MCP server
MCP tools now carry structured metadata identifying which server and source they came from, for security purposes
found in this entry's text
-
v2.1.273
New OAuth scope
user:pluginsgated by PLUGINS_SCOPE_REGISTEREDA new OAuth scope, user:plugins, is requested for accounts with plugin access registered
found in this entry's text
-
v2.1.271
OAuth scope default no longer hardcodes 'user:inference'
CLAUDE_CODE_OAUTH_SCOPES no longer defaults to 'user:inference' when unset
found in this entry's text
-
v2.1.269
OAuth token refresh now requests and reports the user:plugins scope
Token refresh now also asks for the user:plugins permission scope and logs whether it was granted
found in this entry's text
-
v2.1.269
Refresh retries once with the full scope set if the server rejects an expanded scope request
If a server rejects the new expanded OAuth scope request, Claude Code retries once with the old scopes
found in this entry's text
-
v2.1.269
New try/finally cleanup around pushing user and compact-boundary messages
Appending user or compact-boundary messages mid-turn now always runs a cleanup step, even on error
found in this entry's text
-
v2.1.269
OAuth refresh now tracks whether the plugins scope was requested/granted, with automatic downgrade retry on invalid_scope
OAuth token refresh now requests a plugins scope and retries without it if the server rejects the scope
found in this entry's text
-
v2.1.269
New plugin-search scope gate: skip_no_scope decision function Qt()
New gate decides whether to skip plugin/skill search requests based on OAuth scope and session type
found in this entry's text
-
v2.1.268
New URL redaction helpers for stripping credentials/query/hash before logging or telemetry
New helper functions strip credentials, query strings, and fragments from URLs before they're logged
found in this entry's text
-
v2.1.267
Plugin hook modules gain a resolved 'tier' controlling next.to() ordering
Plugin hooks can now be assigned a resolved ordering tier that next.to() calls are validated against
found in this entry's text
-
v2.1.267
Plugin hooks now report a tier (core/prepend/user)
Plugin hooks now report a tier of core, prepend, or user
found in this entry's text
-
v2.1.267
Automatic OAuth plugin-scope expansion now skipped in non-interactive sessions
Automatic OAuth plugin-scope refresh no longer runs silently in non-interactive sessions
found in this entry's text
-
v2.1.265
URLs with embedded credentials now rejected
URLs containing a username or password, like user:pass@host, are now rejected during normalization
found in this entry's text
-
v2.1.265
OTEL resource attributes now include user.groups
Telemetry can now include your group memberships as a user.groups attribute, alongside your email
found in this entry's text
-
v2.1.260
Bootstrap config request headers
Bootstrap config fetches can now require auth headers via a static or helper-script setting.
found in this entry's text
-
v2.1.260
New URL validation rejects credentials/backslashes in managed-config URLs
Managed config URLs with embedded credentials or backslashes are now rejected.
found in this entry's text
-
v2.1.260
URL schema now rejects credentialed URLs and gained an allowHttp option
MCP server URLs with embedded credentials are now rejected, and plain-http can be explicitly allowed.
found in this entry's text
-
v2.1.259
New settings key to disable unattended remote-tool serving
A new settings key turns off unattended remote tool serving, at org or user level.
found in this entry's text
-
v2.1.251
MCP auth now tracks which kind of login token it used
MCP connection failures now record which kind of login token was in play.
found in this entry's text
-
v2.1.248
MCP server allow and deny lists get settings keys
You can allow or block specific MCP servers with allowedMcpServers and deniedMcpServers settings.
found in this entry's text
-
v2.1.248
Sessions record where their name came from
Sessions now record whether you named them or a peer process did.
found in this entry's text
-
v2.1.248
Backgrounded shell commands may return a structured task acknowledgement
Backgrounded shell commands may return a structured task record instead of raw output.
found in this entry's text
-
v2.1.248
Settings scopes now carry an explicit operator-or-repo rank
Settings sources now carry explicit precedence ranks and whether they belong to you or the repo.
found in this entry's text
-
v2.1.248
Claude Design 403 message says whether your credential has access
A Claude Design 403 now says whether your credential actually grants access.
found in this entry's text
-
v2.1.248
More session-name origins survive a reload
Session names set by you, a peer, a hook or automatically keep their origin after reload.
found in this entry's text
-
v2.1.239
Plugin ids with an @ earlier in the source resolve correctly
Plugin sources containing an earlier @, like scoped packages, no longer get truncated ids.
found in this entry's text
-
v2.1.238
Malformed SDK input frames are repaired or dropped instead of erroring, on remote transports
Odd or damaged input frames on remote connections are now fixed up or quietly dropped instead of erroring out.
found in this entry's text
-
v2.1.235
Fork guidance and artifact-database wording tweaks
Subagent guidance and the artifact tool description got small wording corrections
found in this entry's text
-
v2.1.234
SDK reports where an API key actually came from
The SDK now reports where an API key really came from, like the env var or an apiKeyHelper.
found in this entry's text
-
v2.1.229
Artifact database gains a private per-viewer area
Artifact databases can give each viewer a private area, documented only when an internal flag is on.
found in this entry's text
-
v2.1.228
Agent session stream passes through plain tool results
Managed agent sessions now pass through plain tool results, not just custom tool events.
found in this entry's text
-
v2.1.227
Prompt text de-dashed
Memory and shell-command prompt wording swaps em-dashes for plainer punctuation.
found in this entry's text
-
v2.1.225
Fewer shell-outs for environment probing
Docker detection and git identity lookups no longer spawn subprocesses, so startup is slightly lighter.
found in this entry's text
-
v2.1.224
Managed Agents sessions can carry a hard dollar spend cap
The bundled Claude API docs now describe a hard dollar spend cap that pauses a session idle.
found in this entry's text
-
v2.1.223
Transcript existence checks and project-directory discovery can use record streams
Checking whether a past transcript has content can now run over streamed records instead of files.
found in this entry's text
-
v2.1.223
Plugin and skill search requests a new
user:pluginsOAuth scopeSigning in can request an extra permission for plugin search, though search itself remains policy-gated.
found in this entry's text
-
v2.1.219
Memory recall tolerates label-prefixed selections
Recalled memories no longer get silently dropped when the model echoes back the category label with the name.
found in this entry's text
-
v2.1.211
--forward-subagent-textCLI Flagfound in this entry's text
-
v2.1.199
Windows Sandbox: No Logout Required
found in this entry's text
-
v2.1.198
Memory Stores Env Var
found in this entry's text
- v2.1.191
-
v2.1.182
Design MCP Connector Scope Auto-Expansion
found in this entry's text
-
v2.1.178
/design-login — Standalone Design-System Authorization
found in this entry's text
-
v2.1.174
Projects Tool — Read and Write claude.ai Project Docs
found in this entry's text
-
v2.1.169
/design-syncSkill — Sync React Design Systems to Claude Designfound in this entry's text
-
v2.1.139
Claude.ai MCP Connector Diagnostics
found in this entry's text
-
v2.1.119
--setting-sourcesFlagfound in this entry's text
- v2.1.75
-
v2.1.69
Memory System Overhaul
found in this entry's text
-
v2.1.63
Enhanced Shell Security Checks
found in this entry's text
-
v2.1.30
SDK Schema Documentation
found in this entry's text
-
v2.1.15
Cowork Plugins Directory Support [Hidden]
found in this entry's text
-
v2.1.14
Claude.ai MCP Server Integration Improvements
found in this entry's text
-
v1.0.122
Setting Sources Control
found in this entry's text
-
v0.2.96
OAuth Scope Changes
found in this entry's text
-
v0.2.80
New Features
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
0The miner has never read a build containing this name. It is here because a changelog entry of ours names it, which is evidence that it existed and not evidence of which releases carried it. The inventory starts at v2.1.138 and everything older than that was never mined.
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.