Typing "ultrathink" in a message now sets reasoning effort to "high" for that turn. In the previous version, ultrathink was deprecated and showed a dismissive message — it now has real functionality again.
ultrathink about the architecture of this codebase and suggest improvements- When "ultrathink" appears anywhere in your message, effort is automatically set to high for that turn
- A notification briefly displays: "Effort set to high for this turn"
- The word "ultrathink" is rendered with a rainbow color shimmer effect in the terminal (cycling through red, orange, yellow, green, blue, indigo, and violet)
- Controlled by the
tengu_turtle_carbonfeature flag (defaults to enabled) - Replaces the old "Ultrathink no longer does anything. Thinking budget is now max by default." deprecation message
Ultrathink effort injection (search for "ultrathink_effort") — rqY() at line ~290076 checks jd() ("tengu_turtle_carbon") and Vf7() (/\bultrathink\b/i)
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
tengu_turtle_carbon On for this account, and not off by defaultThe flag server returned on for the one account this site reads, and nothing in this release compiles it off by default. The compiled default is shown below, and says which it is when we cannot read one: a fifth of gates compile in a string or a number rather than on or off, and most published releases have no gate table behind them at all. No client can see what the server returns for your account.
This account: on · anonymous baseline: on · compiled default in v2.1.68: no gate table built for this version
These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.
Read once, for one account on one subscription tier, against v2.1.68. 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.