Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.301 ·

Some MCP tool results now skip the large-output handling

MCP tool results marked as not meant for Claude are now returned as they are, without being cut short or saved to a file

Under the hood Internal Changes
JSON All of v2.1.301
Under the hoodTier: how much it should matter to you
2Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
MCPArea: what it touches
Internal ChangesKind: in v2.1.301,
Internal ChangesSection of the release

Unclear It is not clear what sets the not-meant-for-the-model mark, or whether it is ever set in normal use.

What

MCP (Model Context Protocol) is the way Claude Code connects to outside tools and services. When one of those tools returns a very large result, Claude Code normally shortens it and saves the full output to a file.

A result can now be marked as not meant for the model. When that mark is set and the result is ordinary content, Claude Code returns the content unchanged and skips both the shortening and the save to a file. The only place that sets this mark is a remote, step-by-step way of making MCP calls. That path checks a remote switch that falls back to on when the server sends nothing.

Why

Output that Claude never reads does not need to be trimmed to fit the conversation. Programs that make MCP calls this way can now get back the whole result, where before they got the shortened, saved-to-file version.

Read from
Feature flag
tengu_ptc_enabled 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 v2.1.301: on

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 v2.1.301. 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 clear what sets the not-meant-for-the-model mark, or whether it is ever set in normal use.

See this entry in the whole of v2.1.301 →

Feedback