Source Intelligence
Follow Discord

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

← All releases Home ←olderv2.1.170 v2.1.173newer→

Claude Code v2.1.172

27 entries read diff v2.1.170 → v2.1.172 Markdown

Version 2.1.172 ships the Artifact tool — a new capability letting Claude publish HTML and Markdown files to private claude.ai web pages — alongside improved ultra (cloud review) error messages that guide users through auth requirements. The release also renames "Remote Control" status labels to /rc, improves Chrome browser tool loading instructions to emphasize batching, and overhauled the team memory prompt with a clearer two-step save process.

Find
Pick an entry · j / k steps through
8 entries

New Featuresopen

Artifact Tool#

Feature flag
tengu_cobalt_plinth On for this account, and not off by default

The flag server returned on for the one account this site reads, and nothing in this release compiles it off by default. The compiled default is shown below, and says which it is when we cannot read one: a fifth of gates compile in a string or a number rather than on or off, and most published releases have no gate table behind them at all. No client can see what the server returns for your account.

This account: on · anonymous baseline: on · compiled default in v2.1.172: 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 v2.1.172. It isn't a statement about your account. What a flag value here can and cannot tell you

What

Claude can now render an HTML or Markdown file to a private, shareable web page hosted on claude.ai. The resulting URL can be shared with teammates.

Usage
Artifact(file_path="report.html", favicon="📊")
Artifact(file_path="notes.md", favicon="📝", label="v2")
Details
  • Accepts .html, .htm, and .md files; Markdown is converted to styled HTML automatically
  • The favicon parameter (required) sets the browser-tab emoji icon — use one or two emoji, no markup
  • The optional label parameter provides a human-readable version label shown in the version picker
  • The optional url parameter lets Claude redeploy to an existing artifact URL the user provides
  • A strict CSP blocks all external resources — inline all CSS/JS and embed assets as data: URIs
  • Same file path → same URL on redeploy; different file path → new URL
  • Controlled by the CLAUDE_CODE_DISABLE_ARTIFACT environment variable and the disableArtifact setting
  • Gated by feature flag tengu_cobalt_plinth; enabled for eligible claude.ai accounts
Evidence

Artifact tool implementation (search for "Render an HTML or Markdown file to an Artifact" and uAH = "Artifact")

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

--plugin-dir-no-mcp Flag#

What

A new --plugin-dir-no-mcp flag that loads a plugin directory without also reading its .mcp.json file. Useful when the SDK host already owns and manages the plugin's MCP connections.

Usage
claude --plugin-dir-no-mcp <path>
Details
  • Behaves exactly like --plugin-dir except the engine skips .mcp.json / mcpServers discovery for that plugin
  • Equivalent behavior is also available as a setting: noMcp: true in the plugin frontmatter
  • Intended for SDK hosts that register MCP servers themselves rather than delegating to the engine
Evidence

New flag definition and help text (search for "Like --plugin-dir but the engine will not read this plugin's .mcp.json")

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

Ultra (Cloud Review) — Improved Auth Error Messages#

What

When ultra (cloud review) is unavailable, Claude Code now surfaces specific, actionable error messages depending on the exact auth state rather than a single generic message.

Details
  • API key auth → "ultra (cloud review) requires claude.ai account auth. Unset ANTHROPIC_API_KEY … to use ultra."
  • Missing profile scope → "ultra (cloud review) requires a full-scope login token — run claude auth login to use it"
  • Not yet in rollout → "ultra (cloud review) isn't enabled for your account yet — run claude auth login to refresh your entitlements"
  • Unauthenticated entirely → "ultra (cloud review) requires a claude.ai account — sign in to claude.ai to use it"
  • All error messages include a link to https://code.claude.com/docs/en/ultrareview
Evidence

Error routing function (search for "ultra (cloud review) requires claude.ai account auth")

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

URL Provenance Check for web_fetch#

What

web_fetch now enforces a provenance check — it can only retrieve URLs that appeared in a user message or a prior web_fetch result. Attempts to fetch URLs outside this set present a permission prompt asking the user to approve.

Details
  • If the user approves, the fetch proceeds; if denied or timed out, Claude receives an error
  • Timeout message: "The permission request for this URL was not answered in time. Ask the user to approve the fetch or include the URL in a message, then try again."
  • The error type is PROVENANCE_REQUIRED
  • Suppressed in bypassPermissions and dontAsk modes
Evidence

Provenance enforcement and prompt (search for "URL not in provenance set. web_fetch can only retrieve URLs that appeared in a user message")

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

/memories/export Route#

What

A new internal /memories/export route has been registered, enabling memory export functionality.

Evidence

New constant (search for "/memories/export")

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

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

ShowOnboardingRolePicker Tool (Cowork)#

What

A new internal tool for Cowork onboarding that renders an interactive role-picker chip row. Users can tap a chip (e.g. "Legal", "Engineering") to select their role and trigger automatic plugin installation.

Details
  • Blocks until the user responds: chip click, free-form text entry, or dismissal
  • Returns {"role": "..."} on selection, {"dismissed": true} on cancel, {} on confirm-without-role
  • Only enabled in Cowork sessions; not available in normal conversations
  • Gated via KOf (Cowork environment check)
Evidence

Tool definition (search for "Render a clickable role-picker chip row during Cowork onboarding")

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

CLAUDE_CODE_CHILD_SESSION Environment Variable#

What

A new CLAUDE_CODE_CHILD_SESSION environment variable that marks a session as a child session, suppressing certain persistence behaviors (e.g. session data is not persisted when this is set alongside other child-session conditions).

Evidence

New env var check (search for "CLAUDE_CODE_CHILD_SESSION")

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

CLAUDE_CODE_SKIP_PLUGIN_MCP_SERVERS#

What

A new environment variable that, when set, skips MCP server discovery for plugin directories during startup.

Evidence

Log message (search for "CLAUDE_CODE_SKIP_PLUGIN_MCP_SERVERS is set")

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

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

13 entries

Improvementsopen

Remote Control Status Labels Renamed to /rc#

What

The status-bar labels for the Remote Control / remote session feature have been shortened from "Remote Control active / connecting / failed / reconnecting" to /rc active, /rc connecting…, /rc failed, /rc reconnecting.

Evidence

Status label function (search for "/rc active" and "/rc failed")

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

Chrome Browser Tools: Batch ToolSearch Loading#

What

The Chrome browser automation system prompt now explicitly instructs Claude to load all needed tools in a single ToolSearch call using a comma-separated select: query, rather than one call per tool.

Details
  • New guidance: "Do NOT load tools one at a time; each separate ToolSearch call wastes a full round-trip"
  • The recommended starter set covers tabs_context_mcp, navigate, computer, read_page, and tabs_create_mcp in one call
  • Task-specific extras (recording, forms, console debugging) should be added to that same call when the task obviously needs them
Evidence

Updated browser automation prompt (search for "batch every tool you expect to need into ONE ToolSearch call")

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

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

Team Memory: Two-Step Save Process Instructions#

What

The team memory system prompt has been overhauled with clearer, step-by-step guidance for saving memories. When using indexed memory, the instructions now explicitly describe a two-step process (write the memory file, then add a pointer to the index).

Details
  • Step 1: Write memory to its own file using the frontmatter format
  • Step 2: Add a pointer entry (- [Title](file.md) — one-line hook) to the index file
  • Index entries are capped at ~150 characters
  • Clarified that team memory directories already exist — no need to run mkdir
  • Read-only sessions now receive: "If the user asks you to remember something, explain that memory is read-only in this session."
Evidence

New team memory prompt builder (search for "Step 1 — write the memory to its own file in")

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

AWS Region Display Shows Configuration Source#

What

The AWS region display in Bedrock configuration now shows where the region came from — environment variable, AWS shared config file, or the built-in default — rather than just the region name.

Details
  • us-east-1 (from environment) → shown as-is
  • From ~/.aws/config → shown as us-east-1 (from AWS config)
  • Default fallback → shown as us-east-1 (default — set AWS_REGION or add a region to your AWS config)
Evidence

Region source display function (search for "(from AWS config)" and "(default — set AWS_REGION or add a region to your AWS config)")

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

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

--bg / --pool Conflict Error Message Improved#

What

The error shown when combining --bg with another backend flag now distinguishes between --pool and --cloud.

Details
  • Using --bg with --pool: "Use claude -p '<task>' --pool <pool_id> directly to start a session on the pool."
  • Using --bg with --cloud: "Use claude --cloud '<task>' directly to start a cloud session."
Evidence

Updated error message function (search for "--bg and --pool are different backends")

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

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

"Help improve our AI models" Renamed#

What

The consent UI string "Help improve Claude" has been renamed to "Help improve our AI models" across all display states (ON, OFF, OFF for domain emails).

Evidence

String changes (search for "Help improve our AI models" — previously "Help improve Claude")

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

Plugin Disuse Tracking#

What

Claude Code now tracks the last time each plugin was used (lastUsedAt and lastUsedNumStartups). This data enables the tip system to surface a warning when a plugin hasn't been used in a while.

Details
  • Tip shown: "You haven't used the [plugin] in a while. It still adds startup and context cost — review it with…"
  • Tracks both calendar days and session count since last use
Evidence

Plugin usage tracking functions (search for "plugin in a while. It still adds startup and context cost")

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

MCP OAuth Token Clearing: Preserve Client Registration#

What

When clearing MCP OAuth tokens, Claude Code can now optionally preserve the client registration (client ID) while discarding only the access/refresh tokens. This avoids a full re-registration flow when tokens simply need refreshing.

Details
  • When preserveClientRegistration: true is passed, only accessToken, refreshToken, expiresAt, and scope are cleared
  • Log message: "Cleared stored tokens (preserved client registration)"
Evidence

Updated token-clear function (search for "Cleared stored tokens (preserved client registration)")

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

Fullscreen Feedback Prompt Simplified#

What

The fullscreen mode exit survey prompt has been simplified. The old prompt included the parenthetical "(optional, Enter to skip)"; the new prompt is more direct.

Evidence

String change (old: "To help us make fullscreen mode better, what made you switch back? (optional, Enter to skip)" → new: "To help us make fullscreen mode better, what made you switch back?")

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

Structured Output Retraction Error Messages#

What

When a model fallback causes structured output to be retracted and no retry succeeds, Claude Code now surfaces a more specific error message instead of the previous "the cloud agent called StructuredOutput but every attempt failed schema validation."

New message: "the cloud agent called StructuredOutput but no attempt produced a surviving valid output (failed schema validation, or retracted by a model fallback)"

Evidence

Updated error string (search for "retracted by a model fallback and no retry produced a valid result")

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

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

Subagent Model Allowlist Warning Improved#

What

When a subagent is configured with a model that is not in the availableModels allowlist, the warning message now distinguishes between inheriting the parent model vs. using the default teammate model.

Details
  • Subagent case: "Subagent model X is not in the availableModels allowlist; inheriting the parent model instead"
  • Teammate case: "Teammate model X is not in the availableModels allowlist; using the default teammate model instead"
Evidence

New warning functions (search for "Subagent model" and "Teammate model" with allowlist messages)

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

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

Trusted Device Error Message Centralized#

What

The "not enrolled as a trusted device" error message is now generated from a single function, ensuring consistent text: "this device is not enrolled as a trusted device; run /login to enroll".

Evidence

Centralized message function (search for "this device is not enrolled as a trusted device; run /login to enroll")

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

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

Session Status Update Timestamps#

What

When a session's status changes, a separate statusUpdatedAt timestamp is now recorded alongside the general updatedAt timestamp, enabling more precise tracking of status transition times.

Evidence

Updated session state function (search for "statusUpdatedAt" alongside "updatedAt")

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

1 entry

Bug Fixesopen

#

  • Deep-link injection guard: --handle-uri invocations with extra arguments after the URI are now rejected with an explanatory message, blocking URI-based argument injection. (search for "claude: rejected deep-link invocation — unexpected arguments after the URI")
  • Artifact upload precondition retry: Uploading an artifact now detects HTTP 412 (create-only precondition failed) and returns a clear message: "upload 412: this version was already written (create-only precondition). Re-run publish to mint a fresh version." (search for "this version was already written (create-only precondition)")
  • Transcript third-party marker filtering: When sharing session history, transcripts containing third-party markers are now silently excluded rather than included verbatim. The raw transcript and recent sessions lists are independently filtered. (search for "rawTranscriptJsonl withheld from session history: contains_3p_transcript_markers")
  • Model [1m] suffix handling made case-insensitive: Functions that strip or normalize the [1m] model suffix now use case-insensitive matching (/\[1m\]/i), preventing edge cases where mixed-case suffixes were not recognized. (search for "/\\[1m\\]/i")
  • Interactive command detection message updated: The message shown when a command appears blocked on an interactive prompt now says "Stop this task" instead of "Kill this task", matching the updated UI terminology. (search for "The command is likely blocked on an interactive prompt. Stop this task")
  • tmux session cleanup label corrected: The worktree cleanup option now reads "Keep worktree, end tmux session" instead of the previous "Keep worktree, kill tmux session". (search for "Keep worktree, end tmux session")
Verbatim
Official · Anthropic

Anthropic’s official release notes

Published verbatim by Anthropic for v2.1.172. Text is unmodified from the upstream changelog. Everything else on this page came out of the bundle instead, which is why the two lists don't match.

  • Sub-agents can now spawn their own sub-agents (up to 5 levels deep)
  • Amazon Bedrock now reads the AWS region from ~/.aws config files when AWS_REGION isn't set, matching AWS SDK precedence; /status shows where the region came from
  • Added a search bar when browsing a marketplace's plugins in /plugin
  • Added model attribute to the claude_code.lines_of_code.count OTEL metric
  • Fixed sessions using 1M context without usage credits getting permanently stuck — the session now automatically compacts back under the standard context limit
  • Fixed a repeating "an image in the conversation could not be processed and was removed" error when the conversation contained multiple images
  • Fixed the agents view keeping a session under Working with a busy spinner for up to 30 seconds after the worker replied
  • Fixed background agents potentially reading another directory's project settings (.mcp.json approvals, trust) when dispatched onto a pre-warmed worker
  • Fixed background-session attach failing with EAUTH for sessions started on an older version after the daemon auto-updated
  • Fixed a background sub-agent staying stuck as "active" in the agent panel after a nested agent it spawned was stopped
  • Fixed /model suggestions in the claude agents dispatch input rendering with a misleading slash prefix and showing models disabled for your org
  • Fixed availableModels restrictions not being applied to subagent model overrides, the agent dispatch model picker, and the advisor model
  • Fixed availableModels allowlists hiding the /model picker's Opus and Sonnet 1M rows when entries use version-specific IDs like claude-opus-4-8
  • Fixed the /model picker on Bedrock offering models the provider doesn't serve — selecting one silently switched the session model and lit the selection marker on multiple rows
  • Fixed model IDs getting a doubled 1M-context suffix (e.g. [1M][1m]) when ANTHROPIC_DEFAULT_OPUS_MODEL already includes one
  • Fixed opusplan model setting not shipping with 1M context in plan mode for entitled users; the opusplan[1m] workaround now also correctly switches to Opus in plan mode
  • Fixed WebFetch(domain:.example.com) wildcard domain rules never matching subdomains in allow, deny, and ask position, and file permission rules with mid-pattern wildcards (e.g. Read(secrets-/config.json)) being rejected at startup
  • Fixed up-arrow prompt history showing the main agent's prompts while a subagent's chat tab is open
  • Fixed memory recall not finding mounted team memory stores (CLAUDE_MEMORY_STORES) in remote sessions
  • Fixed workflow validation rejecting scripts whose prompt strings or comments merely mention Date.now()/Math.random()
  • Disable mouse tracking on Windows consoles that don't fully support it
  • Fixed the /plugin marketplace list losing its cursor after backing out of a long plugin list, and Esc from the plugin browser returning to the wrong tab
  • Improved performance in long conversations by removing redundant message normalization and avoiding full message-history transforms when streaming tool-use state is unchanged
  • Reduced idle CPU usage: /goal status chip no longer re-renders the terminal at 5 Hz while idle, and fewer UI re-renders while subagents run in parallel
  • Improved Claude in Chrome tool loading: browser tools now load in a single batched call instead of one per tool
  • Improved the non-interactive Usage Policy refusal message to suggest starting a new session or changing your model
  • /code-review now keeps the ultra option visible when you're not signed in to claude.ai, with an explanation that the cloud review requires a claude.ai account
  • Shortened the Remote Control footer indicator to "/rc active" and hid it on narrow terminals
  • Stopped promoting /loop in remote sessions, where pending loops don't keep the container alive
  • [VSCode] Fixed PowerShell tool calls rendering as raw JSON instead of a proper command display and permission dialog, and stripped ANSI escape codes from displayed shell output
Read it on GitHub →
System prompt

1 prompt changed. 1 of 25 tool descriptions changed.

Claude Code, interactive mode

Read the prompts for this release →