Status-line narration below the spinner is built and paced by a configured interval, off unless explicitly enabled.
While the main loop is busy, Claude Code can run a background one-turn query with no tools available that produces a short status line saying what Claude is doing now and what it plans to do next, then draws it as a block below the spinner instead of the old single-suffix line. It is paced by a configured interval and is off unless explicitly enabled, so nothing changes for most users in this build.
- Enabled by the
CLAUDE_CODE_ENABLE_NARRATIONenvironment variable; pacing comes from thetengu_pewter_kite_msinterval, which defaults to 0 and so leaves narration off on its own. - The model output is parsed into a
now:line and anext:line, and anext:value of "none", "n/a" or "not stated" is dropped rather than displayed. - The spinner no longer appends a single "Next: …" or "Tip: …" suffix when narration is active, and instead renders a block with bold
now:andnext:labels plus a separatetip:line. - Narration is registered as a query source alongside "prompt_suggestion", "away_summary" and "agent_summary", meaning it never triggers auto-compact and never shows the user a prompt-too-long error.
- Each generation emits
narration_generatetelemetry.
Status line for the user, who is glancing at the screen., "narration"
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
tengu_pewter_kite_ms Not enough to sayNothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.
This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.234: not a boolean we can read
Read once, for one account on one subscription tier, against v2.1.234. It isn't a statement about your account. What a flag value here can and cannot tell you
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
New in this build: CLAUDE_CODE_ENABLE_NARRATION