Source Intelligence
Sweep 28 Aug 2026 · 00:00Z Build v2.1.250 478 read Stable v2.1.236 Latest v2.1.250 Next v2.1.250 Feeds RSS JSON llms.txt

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

Reference / Feature flags

tengu_remote_backend

A Claude Code feature flag, read out of the shipped bundle. It has been in the build since v2.1.138, including the newest one read.

What it is

Nobody has written a line about this one. It is not in any of Anthropic's reference tables and no changelog entry here carries a description of it. It is in the build, which is the whole of what this page can claim.

Presence across releases

ReleasesReadingDeclared typeDefault
2.1.245 – 2.1.250 5 releases never mined
2.1.138 – 2.1.243 95 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

No release here has a gate table behind it for this flag. Most published releases have none at all: the readings exist only for versions the pipeline captured flag state on.

Changelog entries naming it

No changelog entry here has ever named it. That is a statement about what has been written, not about the name: it has been in the build since v2.1.138 without anybody writing a line about it.

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_remote, up to twelve of them.

tengu_remote_agent_permission_fallbackCloud agents now ask for tool permission in your terminal, marked as remote, with no "always allow" option. never mined tengu_remote_agent_permission_forwardedCloud agents now ask for tool permission in your terminal, marked as remote, with no "always allow" option. never mined tengu_remote_attach_sessionAnalytics ids are now filtered to safe characters before being sent, with no change you'll see. never mined tengu_remote_attach_session_rejectedAttaching to a cloud session with an unknown or malformed id is refused immediately with a message. never mined tengu_remote_auto_mode_include_destructive_mcpDestructive MCP tools could stop skipping permission prompts in remote auto mode, but that is off. 2.1.222 tengu_remote_autocompact_state_adoptedRemote sessions now use the host's auto-compact settings for context and token display. never mined tengu_remote_create_permission_mode_pushA cloud session's starting permission mode is retried, and falls back to default with a warning. never mined tengu_remote_create_sessionCreate a cloud session straight from the command line with --environment and a prompt, optionally as JSON. never mined tengu_remote_create_session_errorCreate a cloud session straight from the command line with --environment and a prompt, optionally as JSON. never mined tengu_remote_create_session_successCreate a cloud session straight from the command line with --environment and a prompt, optionally as JSON. never mined tengu_remote_headless_client_A full headless client for driving cloud sessions over stream-json is in the bundle. never mined tengu_remote_headless_client_host_dialogDialogs shown by your editor now fall back to a safe default when anything goes wrong. 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 feature flag does. All feature flags.