Unclear It is not clear what the 'compact' rule changes in how the conversation is read.
In auto mode, Claude Code uses a classifier to decide whether Claude may take an action without asking you. A classifier is an automatic check that reads the conversation and gives a verdict. That check can now be given a 'compact' rule for how it reads the conversation, in place of the original one.
Which one it uses is decided like this:
CLAUDE_CODE_AUTO_MODE_COMPACT_THREAD_RULE, if you set it, decides.- Otherwise a server-side setting decides, and that setting is off unless it is switched on remotely.
When neither is on, the check uses the original rule. In some cases it uses an unmarked view instead.
This looks like a switch for trying out a different way of reading the conversation. Once it is turned on, it could change which actions auto mode allows without asking.
tengu_projects_compact_thread_rule_enabled Off by default, switched on for this accountThe shipped code defaults this off, and the flag server returned on for the one account this site reads on this version. That is the reading that makes the entry above worth a second look, and it still says nothing about your account.
This account: on · anonymous baseline: on · compiled default in v2.1.299: off
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 v2.1.299. 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.
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.
It is not clear what the 'compact' rule changes in how the conversation is read.
New in this build: tengu_projects_compact_thread_rule_enabled