Contextual Tips System [Gradual Rollout] / Claude Code v2.1.191

What

Claude now occasionally surfaces a short, context-aware tip after a response based on an AI analysis of the current conversation — suggesting a relevant command, shortcut, or workflow that fits what you are doing.

How it works

After eligible responses, a lightweight sidecar classifier (using the fast model) reads the last ~30 turns of the transcript alongside your session metadata (turn count, MCP servers, team skills) and decides whether a tip is relevant.
Declining to tip is the expected default — tips only fire when a known situation in the catalog matches. Examples from the catalog include correction spirals, previous-session references, large context windows, and long-running commands.
Tips include a short 1-2 sentence message, the relevant feature ID, and an optional suggested action (e.g., /clear, claude --resume).
You can give feedback on a tip by acting on it; reception is tracked.

Details

Gated by the allow_context_tips feature flag and the tengu_context_tip_classifier_outcome telemetry gate — not all users see tips yet.
Team discovery metadata (teammate MCP servers and skills) is included in session context to make tips more relevant when working in a shared project.
Tips are not shown in non-interactive or transcript-mode sessions.

Evidence

Context tip classifier system (search for "[context-tips] classifier eligible, firing sideQuery" or "emit_context_tip")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

How sure we are

One source agreesOne thing we can check says the same as this entry.

Anthropic's release notes agreeAdded /rewind support for resuming a conversation from before /clear was run

See this entry in the whole of v2.1.191 →

The build it came inv2.1.191

24 Jun 2026 · 21 entries, this one is #1.

Either side of it

v2.1.190Older
v2.1.193Newer

Open the release →

Names in this entry

slash/clear
Start a new conversation with empty context. Pass a name to label the previous conversation in the /resume picker. To free up context while continuing the same conversation, use /compact instead. Resume the previous conversation with /resume, or, in the same Claude Code process, restore it from the rewind menu's previous-session entry. Aliases: /reset, /new
cli--resume
Resume a specific session by ID or name, or show an interactive picker to choose a session. In place of an ID, you can pass the absolute path to a session's .jsonl transcript file. The picker and name search include sessions that added this directory with /add-dir. When you pass a session ID, Claude Code searches the current project directory and its git worktrees, then every other project on this machine. Before v2.1.223, the ID search covered only the current project directory and its git worktrees. Background sessions appear in the picker marked with bg
flagtengu_context_tip_classifier_outcome
An analytics event, not a feature flag. Claude Code logs it each time the context tips classifier (a model call with query source context_tip_classifier) finishes, with outcome one of tip, tip_ineligible, no_tip, parse_failure, error or outer_error. Other fields, when present: classifierLogId, durationMs, eligibleIds, featureId, inputTokens, cachedInputTokens, outputTokens and error details.

Anthropic's note

Upstream's own release notes for v2.1.191 name something this entry names, so the two are probably about the same change. Probably: the pairing is made on a shared name rather than on the words around it.

Added /rewind support for resuming a conversation from before /clear was run

Is this right?