tengu_slate_lantern
A Claude Code feature flag, read out of the shipped bundle. It has been in the build since v2.1.198, including the newest one read.
What it is
A new --watch-artifact flag follows a claude.ai artifact for new versions and comments, but needs account access.
Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.233.
Presence across releases
| Releases | Reading | Declared type | Default |
|---|---|---|---|
| 2.1.245 – 2.1.250 5 releases | never mined | — | — |
| 2.1.198 – 2.1.243 45 releases | in the build | — | bool:false |
A row reading never mined is a release with no archived bundle behind it. Nothing was read out of it, so nothing here says whether the name was in it. A declared type or a default is only ever what that release's own bundle stated.
Gate readings
| Release | Resolved | This account | Anonymous | Compiled default |
|---|---|---|---|---|
| v2.1.250 | On for this account, and not off by default | on | on | on |
| v2.1.239 | On for this account, and not off by default | on | on | on |
| v2.1.236 | On for this account, and not off by default | on | on | on |
| v2.1.233 read on another version | On for this account, and not off by default | on | on | on |
Two arms, because they disagree: this account is the one account this site reads and anonymous is a baseline with no identity attached. A reading says nothing about your account, and off cannot rule out a rollout both readings sit outside of. What these readings can and cannot show.
Changelog entries naming it
-
v2.1.250Failed live-watch startups are treated as temporary outages and retried on the slow schedule
Live artifact watches that fail to start from a server hiccup now retry on the patient schedule instead of burning attempts.
gate cited by this entry
-
v2.1.239Artifact watching now has three modes, and says which one you are in
Artifact watch status now tells you plainly when live watching is switched off rather than staying vague.
gate cited by this entry
-
v2.1.239Artifact watching now has an explicit "not available here" state
Claude is now told plainly when artifact watching isn't available, so it stops falsely promising to watch.
gate cited by this entry
-
v2.1.236New flag tengu_slate_lantern_ember for lease-based artifact auto-replies
One new switch controls both early artifact comment reads and a lease-based auto-reply mode, off by default.
gate cited by this entry
-
v2.1.233
--watch-artifactflag to follow a claude.ai artifact from a sessionA new --watch-artifact flag follows a claude.ai artifact for new versions and comments, but needs account access.
gate cited by this entry
Documentation pages
None of Anthropic's documentation pages this site has a copy of carries this name.
Names beside it
Every feature flag in the inventory starting tengu_slate, up to twelve of them.
tengu_slate_anchorSome feature flags now stay fixed for the whole session, including a new one that is on. never mined
tengu_slate_fernNo description from anybody. 2.1.172
tengu_slate_finchNo description from anybody. 2.1.138
tengu_slate_harborREPL contexts moved to a registry that releases timers even on error paths. 2.1.138
tengu_slate_harbor_experimentNo description from anybody. 2.1.138
tengu_slate_harrierClaude no longer spends up to a minute investigating before asking you a clarifying question. 2.1.138
tengu_slate_heronNo description from anybody. never mined
tengu_slate_ibisExplore and plan agents are now always on unless you set the disable environment variable yourself. 2.1.217
tengu_slate_kestrelNo description from anybody. 2.1.138
tengu_slate_lantern_emberRe-armed artifact watches could reuse an existing connection instead of starting over, but the flag is off. 2.1.236
tengu_slate_meadowNo description from anybody. 2.1.138
tengu_slate_mothNo description from anybody. 2.1.191
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 feature flag does. All feature flags.