Follow Discord
Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
Claude Code v2.1.260 ·

Compaction now decides whether to strip thinking blocks via a 'wise comet' policy

Compaction now uses a named policy to decide whether to strip trailing thinking blocks.

TierUnder the hoodhow much it should matter to you
Useful2my rating, 1 to 5
Signal2worth watching, 1 to 5
AreaCompactionwhat it touches
KindInternal Changesin v2.1.260,
Under the hood No documentation found

Compaction now uses a named policy to decide whether to strip trailing thinking blocks.

Compaction now uses a new helper to decide, per-compaction, whether trailing thinking blocks in the kept tail should be stripped, based on the resolved model and thinking type. It logs the decision, whether from an env override, the thinking_type default, or a flag, and marks the boundary with a thinking_stripped marker when stripping occurs.

During reactive compaction, preserved messages now pass through a new step that may strip thinking blocks and insert a marker attachment, with new telemetry fields tracking how many thinking blocks were kept versus stripped and what determined the decision.

Read from
Names in the bundlethinking_stripped
Feature flag
tengu_wise_comet Off in both readings

The flag server returned off for the account this site reads and for the anonymous baseline. A reading of off cannot rule out a rollout these two readings sit outside of.

This account: off · anonymous baseline: off · compiled default in v2.1.260: 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 v2.1.260. It isn't a statement about your account. What a flag value here can and cannot tell you

What has happened since
Flag reading moved The flag server now returns off for tengu_wise_comet, read as this 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.

See this across every release →

How sure we are
One source agreesOne thing we can check says the same as this entry.
The name it cites is new in this buildNew in this build: tengu_wise_comet

See this entry in the whole of v2.1.260 →

Feedback