Follow Discord
Sweep 10 Nov 2026 · 02:18Z Build v2.1.322 539 read Stable v2.1.311 Latest v2.1.322 Next v2.1.322 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeReleasesv2.1.269entry #222

Claude Code v2.1.269 ·

Auto-memory and auto-dream settings gain a dedicated editor and refreshed status display

Auto-memory/auto-dream settings now have a validated editor function and a refactored settings-screen status display

Group of 3 Under the hood Internal Changes
JSON All of v2.1.269
Under the hoodTier: how much it should matter to you
2Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
SettingsArea: what it touches
Internal ChangesKind: in v2.1.269,
Internal ChangesSection of the release

Unclear The finding does not show any caller of these editors, so what surface (if any) will expose them to users is unknown.

What

  • The settings screen's auto-memory and auto-dream rows now compute their status/dim/detail text through shared status objects instead of inline logic; the same visible states remain (unavailable for this model, off in safe mode with a re-enable hint, on/off, and "Auto-dream: off while auto-memory is off").
  • A new function validates and writes {autoMemoryEnabled, autoDreamEnabled} to user settings, firing the same tengu_auto_memory_toggled and tengu_auto_dream_toggled telemetry as the manual toggle UI.

Why This consolidates how auto-memory and auto-dream settings are read and written, making the settings screen and any other caller of the new editor function behave consistently.

Read from
Names in the bundleautoMemoryEnabledautoDreamEnabled
What the documentation says
Documented inclaude-code/agent-sdk/claude-code-features
Since it was published

The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.

Added since A small documentation edit on How Claude remembers your project touched a line naming autoMemoryEnabled after this was published. To toggle it, open `/memory` in a session and use the auto memory toggle, which saves `autoMemoryEnabled` to your user settings at `~/.claude/settings.json`. To turn it off for a single project, set `autoMemoryEnabled` in that project's se… memory see the edit
Confirmed since Anthropic's documentation has since written up autoMemoryEnabled, on Use Claude Code features in the SDK. | Auto memory at `~/.claude/projects/<project>/memory/` | Loaded into the system prompt at session start. The agent writes new memories there with the standard `Write` and `Edit` tools rather than a dedicated memory tool, so those tools mu… agent-sdk/claude-code-features see the edit
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 doubtThe finding does not show any caller of these editors, so what surface (if any) will expose them to users is unknown.
Anthropic's documentation agreesAnthropic's documentation has since written up autoMemoryEnabled, on Use Claude Code features in the SDK.

See this entry in the whole of v2.1.269 →

Feedback