Follow Discord
Sweep 25 Sep 2026 · 19:33Z Build v2.1.283 504 read Stable v2.1.274 Latest v2.1.283 Next v2.1.283 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.282 ·

Claude Code can record the API requests it sends into session transcripts

New, off-by-default recording writes each API request's system prompt, tools and message changes into the session transcript file

Under the hood Internal Changes
JSON All of v2.1.282
Under the hoodTier: how much it should matter to you
4Useful: my rating, 1 to 5
4Signal: worth watching, 1 to 5
SessionsArea: what it touches
Internal ChangesKind: in v2.1.282,
What probably matters to youSection of the release
What

A session transcript is the file on disk where Claude Code keeps the record of a conversation. Claude Code can now write a record of each request it sends to the model into that file. Requests from a subagent (a helper Claude runs to do part of a task) go into that subagent's own file. The records hold:

  • the system prompt and tool definitions, stored once and referred to by a fingerprint
  • how each request differs from the previous one in the same conversation
  • where caching markers sit, and a fingerprint of the whole request

Anything added through CLAUDE_CODE_EXTRA_BODY is left out and listed as withheld. Nothing is recorded when the system prompt and tools are too big for one record, when the session is mirrored remotely, or when account memory text cannot be cleanly cut out. Only requests from the main conversation and subagents are recorded.

Recording is off unless it is switched on remotely or through the CLAUDE_CODE_ELEGANT_MEADOW environment variable, which is checked first.

Why

When this recording is switched on, transcript files grow and hold more of what was sent to the model, including the system prompt, so they become larger and more sensitive to share.

Read from
Feature flag
tengu_elegant_meadow Not enough to say

Nothing 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 v2.1.282: 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.

tengu_humble_hammock Off by default, switched on for this account

The 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 v2.1.282: 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 v2.1.282. It isn't a statement about your account. What a flag value here can and cannot tell you

How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtIt is not known what reads these records back, or what value of `CLAUDE_CODE_ELEGANT_MEADOW` turns recording on.
The name it cites is new in this buildNew in this build: tengu_elegant_meadow

See this entry in the whole of v2.1.282 →

Feedback