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 v2.1.265 ·

Classifier-only tools can now be flagged instead of blocked in auto mode

Auto mode's classifier-only tools can now be allowed-with-warning instead of blocked, and are always routed through the classifier

TierNothing to try yethow much it should matter to you
Useful3my rating, 1 to 5
Signal3worth watching, 1 to 5
AreaAuto Modewhat it touches
KindIn Developmentin v2.1.265,
Group of 3 Nothing to try yet Notable

Auto mode's classifier-only tools can now be allowed-with-warning instead of blocked, and are always routed through the classifier

What

  • Tools that declare classifierOnly() are now always evaluated by the auto mode classifier — saved always-allow rules and hook-based allows are ignored, and outside auto mode such tools are denied with a message naming the tool.
  • These tools can now set onBlock: 'flag'. When the classifier would otherwise block the action, refuse to review it, or return no verdict, the action is now delivered (allowed) instead of denied, but annotated with a decisionReason noting it was "Flagged by the classifier, delivered with its warning: ...".
  • A new guard denies the action with an explicit bug message if a classifier-only tool serializes to an empty classifier input, since the classifier would have nothing to judge.
  • The core auto-mode permission pipeline now checks each tool's classifier-only config: if onBlock === "refuse" and a hook asked for a prompt (or the host re-asks on every allow), it denies with an explanation; if onBlock === "flag", it forces the new allow-with-flag outcome.

Why This lets certain sensitive tools stay strictly gated by the auto-mode classifier (never allowed by saved rules or hooks) while giving them a softer failure mode: instead of silently blocking an action the classifier is unsure about, Claude Code can deliver it with a visible warning explaining why it was flagged.

Read from
Names in the bundleonBlock
What the documentation says
Documented inapi/api/beta
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.

Confirmed since Anthropic's documentation has since written up onBlock, on sent_count = len(messages sent in the compaction request). use Anthropic\Beta\Messages\BetaCompactionBlock; build-with-claude/compaction 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 doubtWhether `tengu_auto_mode_decision` affects this behavior is unclear, since no reading of that gate has been taken yet.
Anthropic's documentation agreesAnthropic's documentation has since written up onBlock, on sent_count = len(messages sent in the compaction request).

See this entry in the whole of v2.1.265 →

Feedback