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 ←olderv2.1.242 v2.1.245newer→

Claude Code v2.1.243

3 entries read diff v2.1.242 → v2.1.243 Markdown

This build carries the scaffolding for language-server support, but nothing in it turns that support on. There is a manager with start, restart and shutdown entry points, and none of those entry points is called anywhere in the shipped bundle. The tool that would use a language server only ever reads connection status, so no server is ever launched and the tool stays dark. Treat it as groundwork for a later release rather than something you can try today.

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

What probably matters to you

Anything you can use today, anything that visibly changes, and anything worth poking at. One line each, open for detail.

Not switched on
Useful2 Signal5
LSP Notable

Nothing in the shipped code starts an LSP server#

Language-server support is fully built but nothing in the app ever starts one, so it stays dark.

A language-server manager with start, restart and shutdown exists in the bundle, but nothing calls it and the LSP tool only reads connection status.

What

The language-server support has a manager with start, restart and shutdown entry points, but none of them are called anywhere in the shipped bundle. The LSP tool only ever reads connection status, so in practice no server is launched and the tool stays dark.

Details
  • The manager exposes get, status, connected, ever-connected, wait-for-initialization, initialize, reinitialize and shutdown; only the four read-only ones have callers.
  • The tool's own code waits on initialization if status is pending and checks the ever-connected flag to decide whether it is enabled, but nothing triggers the initialization it waits for.
  • The initializer additionally returns early unless the lspServers feature flag is on, so even a future caller would be gated.
  • Same shape as the previous build; this is not new in 2.1.243.
Evidence

[LSP MANAGER] initializeLspServerManager() called

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

Use it now
Useful2 Signal2
Elsewhere not in their notes

Gateway loopback escape hatch is still present#

Pointing the gateway's key-set URL at a loopback address still needs that environment variable set.

CLAUDE_GATEWAY_ALLOW_LOOPBACK
What

An earlier reading of this build suggested the check behind CLAUDE_GATEWAY_ALLOW_LOOPBACK had been removed. It has not: the check and its error text are unchanged, so pointing the gateway's key-set URL at a loopback address still requires that environment variable to be set.

Details
  • The code moved position in the bundle rather than being deleted.
  • Without the variable, a loopback target is rejected with the message naming cri.jwks_url.
Evidence

cri.jwks_url targets loopback but CLAUDE_GATEWAY_ALLOW_LOOPBACK is not 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.

Were these the right ones to put at the top? 0 answered
Below the fold

Everything else

Smaller changes and internals, grouped as the pipeline found them. Nothing is dropped, it is only further down.

1 entry

Internal Changesopen

Under the hood
Useful2 Signal1
Elsewhere

Version constant bumped to 2.1.243#

The version number now reads 2.1.243 everywhere it shows up.

--version/status
What

The build stamp changed from 2.1.242 to 2.1.243. Everything that reports a version now reports the new one, including --version, the /status version row, the updater's npm commands, the user-agent strings and the bug-report Environment Info block.

Details
  • Only the version, build time and git commit fields changed; the package URL, README URL, issues explainer, feedback channel, hooks worker URL and sourcemap group are untouched.
  • The same build-metadata object is inlined at roughly 118 places, so the daemon start log line, the x-environment-runner-version request header and the Remote Control minimum-version message all pick it up together.
  • No behaviour change beyond the reported string.
Evidence

BUILD_TIME: "2026-08-24T21:05:22Z"

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.

Verbatim
Official · Anthropic

Anthropic’s official release notes

Published verbatim by Anthropic for v2.1.243. 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.

  • Added a Loops breakdown to /usage: per-loop run count, total tokens, tokens per run, and last run, so runaway or chatty /loop tasks are easy to spot
  • Added modelPicker setting: curate the /model picker with an ordered, labeled list of models (any id spelling, including Vertex/Bedrock ids), appended to or replacing the built-in lineup
  • Added promptCacheTtl and subagentPromptCacheTtl settings so API-key and cloud-provider users can keep a 1-hour prompt cache on the main conversation while subagents stay at 5 minutes
  • Added modelPricing managed setting so an organization's contracted per-model rates and discount multiplier are used for /cost, the status line, and telemetry cost figures instead of list price
  • Added a keyless sign-in under /login → Anthropic Console: "Sign in with your Console account" (recommended) alongside creating an API key, so organizations that don't allow API keys can sign in
  • Added a Skipped sources line to /status that lists managed settings sources (for example managed-settings.json) present but not applied because a higher-precedence managed source is active
  • Added a managed marker in /mcp and /plugins on claude.ai connectors whose authentication is managed by your organization
  • Added a tip pointing claude.ai users who haven't connected GitHub for Claude Code on the web to /web-setup
  • Added a /status line showing whether GitHub is connected for Claude Code on the web (Pro/Max), pointing to /web-setup when it isn't
  • Added the model (and effort level) each subagent ran on to /tasks and the agent detail dialogs
  • Fixed remote MCP servers in non-interactive (-p) and SDK sessions never recovering after a dropped connection; they now reconnect automatically or report as failed
  • Fixed MCP server sign-in started from the desktop app failing with "Invalid redirect URI" on servers that support client ID metadata documents (for example Linear)
  • Fixed auto mode staying unavailable at startup when a temporary server-side disable was cached and later flag fetches failed
  • Fixed auto mode tool calls being denied as "temporarily unavailable" after about a minute of waiting when the API was briefly overloaded and asked the client to retry
  • Fixed the /model picker silently ignoring an Ultracode selection; picking Ultracode now applies it to the current session
  • Fixed /resume only listing the 50 most recent sessions; the picker now loads more as you scroll
  • Fixed cloud sessions resuming after a mid-turn restart with a pending hook or background-task notification re-sent as the prompt instead of the normal continuation message
  • Fixed cross-session messaging silently turning off inside user namespaces and rootless containers after the 2.1.232 socket-directory hardening
  • Fixed text that hangs outside its container (for example the sign-in URL in /login) losing its leading columns when another part of the screen repaints
  • Fixed spellcheck not underlining a misspelled word typed directly after an emoji
  • Fixed background subagents not waking when their last background Bash task completes
  • Fixed sessions going silent for 10+ minutes when the Anthropic API never starts a response: the request now times out after ~3 minutes, retries once, then shows API Error: No response from API
  • Fixed auth, model-availability, and other client-generated error messages rendering like model output instead of as error lines
  • Fixed workload identity federation in CI: processes in one job share the exchanged token instead of re-exchanging the single-use token; a rejected exchange fails fast with the server's message
  • Fixed server-managed companyAnnouncements not showing at startup in a session that began with signing in (for example the first launch after /logout)
  • Fixed hook if conditions like Bash(cat *) firing on unrelated Bash commands when the command contained $() or backtick command substitution followed by more arguments
  • Fixed plugin dependencies declared with a marketplace field never resolving when both plugins are loaded together via --plugin-dir
  • Fixed /reload-plugins keeping the LSP tool after the last LSP plugin is disabled; it now also warns before an LSP plugin change that would re-read the conversation
  • Fixed --agents silently ignoring invalid JSON or invalid agent definitions; it now exits with a clear error, like --mcp-config
  • Fixed /status showing "Found invalid entries in: ." with no filename when ~/.claude.json has an invalid MCP server entry
  • Fixed /clear removing the /rename session name from the prompt bar even though the name was kept for the new session
  • Fixed Ctrl+R history search and up-arrow history breaking when ~/.claude/history.jsonl contains a malformed entry
  • Fixed Ctrl+[ not leaving vim INSERT mode in terminals that encode modified keys (modifyOtherKeys / kitty protocol)
  • Fixed the local IDE connection being routed through HTTPS_PROXY (and sometimes failing) when localhost was listed in NO_PROXY but not lowercase no_proxy; both casings are now honored
  • Fixed sandbox network-violation details being dropped from the Bash tool result when the blocked command still exited 0 (for example curl printing the proxy's 403 page)
  • Fixed the status line rate_limits fields and /usage still showing a rate-limit window's pre-reset usage percentage after the window reset while the session was idle
  • Fixed claude --teleport <session> exiting on uncommitted changes instead of offering to stash them and continue, as the session picker already does
  • Fixed /web-setup repeatedly asking you to log in when an older GitHub CLI (without gh auth token) was already authenticated
  • Fixed Claude in Chrome losing its connection to Claude Code after an auto-update cleaned up the version it was set up with; the native host now launches via the stable claude launcher
  • [VSCode] Fixed sessions started before feature flags were first fetched (for example right after install) opening in the default permission mode instead of auto mode or your configured default mode
  • [VSCode] Fixed Focus view sections you expanded collapsing on their own during subagent tool activity
  • Improved startup time: sandbox and MCP bring-up no longer block the first frame, bare launches skip subcommand registration, and workflow discovery, settings, and trust-store work is cheaper
  • Improved native install and auto-update download size: the binary is now zstd-compressed (about 75 MB instead of 340 MB on Linux x64)
  • Improved attribution of usage telemetry to your organization for sessions that authenticate with ANTHROPIC_AUTH_TOKEN directly against the Anthropic API, so its data-handling settings apply
  • Improved native binary size: about 2 MB smaller by storing the bundled skill and prompt text more compactly
  • Improved memory usage of native builds: code is now loaded on demand instead of keeping the whole bundle resident (roughly 40–70 MB less memory per session)
  • Improved peak memory usage in long-running sessions (the runtime now garbage-collects sooner as the heap grows)
  • Improved /login over SSH: the sign-in URL appears immediately, pressing c reports how the URL was copied instead of always claiming success, and a hint explains how to select text in fullscreen
  • Improved the error when effort xhigh/max is used with thinking turned off: it now names the level, the setting that disabled thinking, and /effort high as the fix
  • Improved /loop: consecutive wake-ups where Claude has nothing to do now fold into a single line in the terminal instead of printing each one
  • Changed the sandboxed Bash tool prompt to no longer list allowed network hosts, so Claude attempts requests (and you can approve new hosts) instead of assuming unlisted hosts are blocked
  • Updated the /model picker and the bundled claude-api skill to show Sonnet 5's $2/$10 per Mtok pricing as its standard list price rather than a limited-time promo
  • Changed computer use on macOS so clicking the desktop, Dock, or a Finder window requires granting Finder via the access dialog, like any other app
  • Changed /model, /fast, and /effort to also run immediately instead of queueing until the turn ends on Bedrock, Vertex, and Foundry and when telemetry is disabled
  • Fixed claude remote-control exiting and stranding attached Remote Control sessions when the server drops its environment mid-session; it now recovers
  • Fixed Remote Control sessions served by claude remote-control sometimes getting stuck after it was stopped and restarted, for Team and Enterprise members without an admin or owner role
  • Changed the cross-session messaging inbox socket to close connections that send no complete line within 30 seconds; scripts posting to it should connect once their data is ready
  • Improved the notice when resuming a conversation whose Remote Control is held by another terminal: it now says sessions on other machines can't be seen from, or reach, this one
  • [VSCode] Improved history trimming in long sessions: older tool-activity rows are dropped first so your messages and Claude's replies stay visible
  • [VSCode] Improved attribution of the extension's own usage telemetry to your organization when you are signed in with a Claude account, so its data-handling settings apply
Read it on GitHub →
System prompt

No change to the system prompt since v2.1.242.

Claude Code, interactive mode

Read the prompts for this release →
Documentation

What the docs did around this release

671 documentation changes were recorded within 24 hours either side of this release, nearest first. The closest 12 are below. They're here because they happened near this release in time. That's not a claim that this release caused the edit, or that the page documents anything in it.

claude-tag/users/use-cases/your-own-channel Changed +8 -0 recorded here claude-docs claude-tag/users/use-cases/triage-requests Changed +10 -0 recorded here claude-docs claude-tag/users/use-cases/fix-bugs Changed +10 -0 recorded here claude-docs claude-tag/users/commands Changed +6 -5 recorded here claude-docs claude-tag/concepts/security-and-data Changed +1 -5 recorded here claude-docs claude-tag/concepts/how-it-works Changed +2 -0 recorded here claude-docs claude-tag/concepts/glossary Changed +1 -1 recorded here claude-docs claude-tag/concepts/agent-identity Changed +1 -1 recorded here claude-docs claude-tag/admins/troubleshooting Changed +0 -2 recorded here claude-docs claude-tag/admins/setup-overview Changed +4 -4 recorded here claude-docs claude-tag/admins/restrict-access Changed +1 -5 recorded here claude-docs claude-tag/admins/pair-workspace Changed +1 -1 recorded here claude-docs

Every time above is when this site's poller recorded the change, which is up to half an hour after the edit on an ordinary read and up to a day after it on a full sweep. Upstream's own edit time is used instead wherever a capture carries one. None of these do.

The documentation ledger →
Switches

Every name in this release

The 3 literal strings found in the bundle, with the number of entries that name each one. Picking one searches for it. A name is here because this build's code mentions it, which is not the same as it working or being finished.

Slash commands

CLI flags

Environment variables