what shipped.

- Fixed a deny or ask rule on a nested part of a compound shell command not holding over a user-installed mod's approval on managed machines
- Fixed the terminal freezing on short code blocks with many unclosed `<script>` tags or deeply nested `${` substitutions
- Fixed `Read` deny rules not applying to files @-mentioned, changed, or selected in the IDE through a symlink
- [VSCode] Reverted a 2.1.288 change to `claude auth status` that may have made sign-outs more frequent
- Improved how quickly large files open in a plugin code pane by laying the highlighted view out once at its final width
- Fixed `plugin list`, `plugin eval` and `plugin update` showing a stale copy of a plugin installed from a local folder marketplace, and hot reload for a symlinked `--plugin-dir`
- Fixed installed mods not loading in the first session after an upgrade
- Fixed a plugin's rows above the prompt showing a stale row while the Background tasks dialog was open in fullscreen
- Fixed plugin panes drawing nothing when a link used a localhost address, an `@` in its path, an uppercase host or a `file:` path
- Fixed a user-installed plugin being able to rewrite the descriptions of an organization-managed MCP server's sign-in tools
- Fixed a freeze or forced quit at launch when a plugin drew a Box with a border style the terminal does not know
- Fixed supervised and background sessions ending when a plugin's on-screen handler threw asynchronously
- Fixed sessions ending with an interface error when a plugin region with no height kept growing
- Fixed Bash deny and ask rules missing a command behind an environment variable prefix with an expanded value (e.g. `TZ="$HOME" rm -rf build`) when the sandbox auto-allows commands
- Fixed a Bash deny or ask rule being skipped under sandbox auto-allow when a bare variable assignment came before the command
- Fixed `claude plugin validate` skipping the plugin when the folder also holds a marketplace manifest
- Added `agent.spawn` for teammates, one agent id across plugin hook events, and idle and waiting states in `$.agent.list()`
- Fixed sessions ending with "unrecoverable interface error" when a value a mod's `ui.render` hook wrote made a row throw while drawn; the engine now draws its own row instead
- Fixed text with a tab, a stray escape and a C1 control, or a short text with a tab and CRLF line endings, drawing over the rows below it
- Fixed right-aligned content in a mod's pane or band drawing under the close mark or `[-]`, which now also keep one column in from the terminal's edge
- Fixed a mod's `Client` that fails while drawn taking down everything the mod drew around it; it now fails alone and raises `ui.fault`
- Fixed `claude plugin validate` failing an Anthropic marketplace's own plugin and listing a clean `plugin.json` in `--json`
- Fixed a mod's band that fails to draw briefly telling the cards under it to step aside
- Fixed a failed plugin component showing `Error` or nothing as its reason when the failure carried no message
- Improved the line a mod's author sees when its band or pane fails to draw: it names the mod and says nothing was drawn
- Fixed published artifact pages freezing or crashing the reader's browser tab on short code blocks with many unclosed `<script>` tags
- Fixed a mod's Client region staying failed for the whole session after the terminal threw while drawing it

- Added `$.ui.selection()` for mods: returns the text you last selected in fullscreen mode and, when the selection lies within one transcript row, that row
- Added a built-in `gh api` to cloud sessions whose image has no GitHub CLI, and fixed the built-in sending control characters from file names, jq filters or GitHub errors to the terminal
- Added recovery for a prompt cleared with Ctrl+C: pressing Up on the empty prompt brings the draft back, including pasted text and images
- Added a re-authenticate prompt when an MCP server asks for more OAuth scope during a tool call
- Added `--max-findings <n>|all` to /code-review to report more or fewer findings than the usual limit; the choice is reused until you pass `--max-findings default`
- Added Ctrl+F to find a session by name and Alt+↑/↓ to jump between groups in the agents view; both, and rename, can be rebound in keybindings.json
- Added a screen reader mode announcement of the new permission mode when you approve a plan, including with Shift+Tab
- Fixed mid-response API timeouts failing the turn: non-interactive sessions and subagents now continue from the partial response, and thinking-only responses are retried
- Fixed long conversations failing with "Prompt is too long" instead of auto-compacting when the last reply reported zero token usage
- Fixed `--resume` sometimes dropping files and other context that a compaction had just restored
- Fixed a resumed session sometimes not saving the last response of a turn, so that the next `--resume` showed the prompt unanswered
- Fixed resume occasionally loading a transcript cut short when the same session rewrote the file during the load
- Fixed resuming a conversation started on 2.1.286 or earlier dropping the model's earlier thinking
- Fixed session titles, memory recall and prompt hooks failing on Mantle or behind gateways that reject structured outputs; added `CLAUDE_CODE_DISABLE_STRUCTURED_OUTPUTS` to turn structured outputs off
- Fixed auto mode denials pointing Claude at a Bash permission rule when the blocked tool was not Bash
- Fixed auto mode on Bedrock and Mantle switching to the local classifier for the rest of the session after a request to an older model, such as a WebFetch summary or a `sonnet` subagent
- Fixed cloud sessions that restarted on a newly picked model replying with that model after the server refused it
- Fixed Cowork cloud sessions staying marked as waiting for input after a WebFetch permission prompt for an unapproved URL went unanswered for five minutes
- Fixed prompt suggestions not appearing on a phone that joins a Cowork cloud session started on another device
- Fixed a mod's button sometimes running a different button's action when pressed on a view drawn before Claude Code restarted
- Fixed a plugin's pane showing nothing when one `Code` element held a diff that does not parse; it now draws as plain code
- Fixed plugin LSP servers receiving literal `${user_config.*}` and `${CLAUDE_PLUGIN_ROOT}` placeholders in `initializationOptions` and `settings` instead of substituted values or manifest defaults
- Fixed a plugin's `tool.call` hook making Bash fail and file searches read the wrong folder in subagents that run in a worktree
- Fixed `git-subdir` plugin installs failing, or caching an incomplete plugin, on older git (before 2.39, e.g. Ubuntu 22.04's 2.34)
- Fixed plugins loaded with `--plugin-dir` not showing "Configure options" in `/plugin`
- Fixed background sessions ending when a plugin was reloaded or disabled while one of its timers or reads was still running
- Fixed sandboxed heredocs with an unquoted delimiter (`python3 <<EOF`) asking for approval on every run under sandbox auto-allow when the body holds only plain text and simple `$VAR` references
- Fixed Bash tool permission check to prompt before a `BASHPID` assignment whose value the shell would evaluate as arithmetic, instead of allowing it silently
- Fixed fullscreen sessions exiting with "unrecoverable interface error" when opening the background tasks dialog while a plugin or mod showed rows above the prompt
- Fixed Claude reporting a message to another session as delivered when that session held it: the notice now says it wasn't delivered and names the session, and in SDK sessions Claude can now learn of it mid-turn
- Fixed OpenTelemetry `claude_code.tool.blocked_on_user` spans reporting `unknown` source or decision in `-p` and SDK sessions and for PreToolUse hook approvals
- Fixed permission asks that ended unanswered, in `-p` or on an interrupted turn, emitting no `tool_decision` event
- Fixed Edit and Retry in Cowork cloud sessions refusing a message sent before `/compact` even though its history was still saved
- Fixed unattended sessions (`CLAUDE_CODE_RETRY_WATCHDOG`) retrying for hours after a very long response stream failed; Claude Code now streams again, and gives up after three timeouts
- Fixed `/login` reporting "Login successful" when credentials could not be saved to secure storage; it now shows the failure, and offers a retry when the new login didn't take effect (anthropics/claude-code#73861)
- Fixed a Stop during Bedrock credential lookup sometimes moving the session to a fallback model instead of ending the request
- Fixed a second `gcpAuthRefresh`/`awsAuthRefresh` browser sign-in opening when a laptop wakes from sleep while another Claude Code process is signing in
- Fixed agent teams: a plugin-defined agent spawned by name now runs with its own prompt, tools, disallowedTools and effort instead of the defaults
- Fixed headless (`-p` / SDK) sessions occasionally ignoring SIGTERM when a supervisor such as `timeout` or systemd sends SIGCONT alongside it
- Fixed restarted cloud sessions restoring a model that the organization's enforced model list refuses
- Fixed MCP tool calls sometimes running twice when a remote server's result was over 16 MB or could not be parsed
- Fixed subagents in Claude Desktop's Code tab getting none of the tools of a user-configured MCP server named `memory`
- Fixed Claude in Chrome asking before every screenshot and page read on a site you allowed when auto mode is unavailable (such as with `disableAutoMode` or an older model); typing, navigation and JavaScript still ask
- Fixed `claude plugin install` failing for GitHub-source plugins on macOS and Linux machines with no GitHub SSH key: the clone now falls back to HTTPS and prints a notice
- Fixed `sandbox.credentials.files` entries on git config files not taking effect while `permissions.blockReadsOutsideWorkingDirectories` is on
- Fixed Claude leaving out your organization's design systems when starting slides or a design with the Artifact tool on Team and Enterprise plans or machines with managed settings
- Fixed the keyboard not working on Windows after Claude Code restarts itself (first sign-in to a Claude apps gateway, provider setup, `/tui`)
- Fixed a stall when launching an agent whose `tools:` lists very many `Agent(...)` entries
- Fixed sessions on Claude 3 Opus and Claude 3 Sonnet failing on every turn after a whole PDF entered the conversation
- Fixed the npm auto-updater reporting success when the platform-native binary failed to download and only the placeholder `claude` stub was installed
- Fixed Remote Control cleanup archiving a session that is still connected or was just re-attached by another Claude Code process
- Fixed `owner/repo` plugin marketplaces showing only the second attempt's error when both the SSH and HTTPS fetch fail; both errors are now shown, with the transport tried first on top
- Fixed path-scoped `.claude/rules` and nested CLAUDE.md files not loading when Write or Edit creates or changes a file in their scope (previously only Read loaded them)
- Fixed a dangerous `rm` (such as one on `/` or the home directory) inside a `bash -c` or `sh -c` script running without a prompt in bypassPermissions mode or under a shell allow rule (anthropics/claude-code#96300)
- Fixed LSP tool calls hanging indefinitely when a language server uses dynamic capability registration or stops responding; requests now time out after 60s (per-server `requestTimeout`)
- Fixed `idle_prompt` notification hooks firing while background agents are still running (anthropics/claude-code#93672)
- Fixed PreToolUse and PermissionRequest hooks being skipped when matching them failed or the tool's input could not be serialized to JSON; the call is now blocked
- Fixed the first request in a fresh environment or after a model switch using the built-in output limit and auto-compact window, not the server's; that request may now wait up to 1.5 seconds
- Fixed the "What should Claude do instead?" hint showing on the Interrupted row after sending queued messages with ctrl+enter
- Fixed `/login` in a `--bare` session running a sign-in the session never reads, which could replace your saved login; it now says which credentials work
- Fixed the InstructionsLoaded hook omitting agent_id and agent_type when a subagent's file access loads a rule or nested CLAUDE.md; rules and nested CLAUDE.md files loaded on file access now also report effort
- Fixed the Agent tool in `claude mcp serve` always reporting no available agents and rejecting every subagent_type
- Fixed the terminal cursor not following the typed text in the fullscreen transcript viewer's search and in `/theme`'s custom color search
- Fixed `/permissions` in screen reader mode: typing a rule's number now picks it instead of opening the search box
- Improved auto mode: when a conversation grows too long for the client-side safety classifier to review, it is now compacted instead of prompting for, or failing, every tool call
- Improved screen reader mode: short announcements, such as a deleted word, now stay on screen until your next key press or until something above them on screen changes
- Improved screen reader mode: answered questions in question dialogs now say "answered" beside their box
- Improved the `/usage-credits` message shown to Team and Enterprise members whose organization has turned off usage credit requests
- Improved cloud sessions: a new conversation's first turn no longer waits for a stdio MCP server whose config sets `alwaysLoad: false`
- Improved "You should know" notes to say "we", "the main agent" or "you" depending on who was responsible for a decision
- Improved the error for an artifact database write refused at the database's size limit: it now states the limit and what frees space
- Improved Bash permission prompts to give a shorter reason when part of a command can't be checked before it runs
- Self-hosted runner: Improved the built-in `gh api`: a refused gh command now prints its `gh api` equivalent, `--paginate` follows every page of a repository's lists, and a nested `claude` no longer removes it
- Improved Remote Control's recovery from an expired server credential: sessions stay connected during renewal and are kept if it gives up after a server outage
- Changed the background command time limit to apply only in unattended sessions (`-p`, Agent SDK, CI, cloud); terminal, desktop app and VS Code sessions have no limit
- Changed the client-side auto mode classifier to ignore an `ANTHROPIC_DEFAULT_SONNET_MODEL` pin that names Claude Sonnet 5.5 or Opus 5.5 and use Claude Sonnet 5 instead
- Changed `claude project purge` to `claude purge`; the old name still works and prints a notice
- Changed the agents view `n:` filter (and Ctrl+F search) so Enter opens the session whose name matches best instead of the top row
- Changed `/autocompact` to save the auto-compact window per model, so each model keeps its own setting when you switch
- Changed MCP URL prompts from servers that can't report when you're done to wait for "I'm done, continue" before the tool call continues, so you can finish in the browser first
- [VSCode] Fixed a claude.ai connector staying on "Needs authentication" after you authorize it: the MCP servers dialog now offers Check connection
- [VSCode] Fixed the opt-in New Conversation shortcut (Cmd/

these notes continue in the original release.

grok-voice-transcribe-1.0 is deprecated and reaches end of life on October 2, 2026. All requests to that slug are routed to grok-voice-transcribe-2.0 at the same price, with higher accuracy. See the Speech to Text docs.

## New Features

- Browse older tasks in the agent command center with a keyboard-accessible “Show more” action. (#49106)
- Select transcript text and paste with middle-click in fullscreen mode on supported local Linux X11 terminals. (#49112)
- Start sessions outside a project with workspace defaults when policy permits, and restore saved permissions when resuming. (#49160)
- Added opt-in Guardian review capabilities to retrieve earlier user instructions and include context from agent handoffs. (#49036, #49057)

## Bug Fixes

- Unsent queued messages now resume after reconnection once uncertain submissions are resolved, avoiding duplicate sends. (#49105)
- The terminal UI now preserves server provider, reasoning-summary, and verbosity settings and shows the correct sessions in resume and fork history. (#49144, #49161, #49171)
- Fixed Windows sandbox PowerShell fallbacks and long-path permission repairs, and suppressed unwanted console windows from background helpers. (#49019, #49058, #49098, #49164, #49386)
- Subagents now retain environments that are still starting and receive their configuration or preparation failure. (#49075)
- Prevented SQLite stalls during connection setup and logging, and surfaced initialization errors instead of masking them as timeouts. (#49032, #49102)
- Explicit provider model catalogs no longer include unsupported bundled models or reuse stale entries after refresh failures. (#49135)

## Documentation

- Clarified how provider credentials use the configured storage backend and how `env_key` identifies the API-key environment variable. (#49118)

## Chores

- Reduced repeated plugin-loading work by caching parsed manifests and reusing HTTP connections for remote plugin requests. (#49099, #49100)
- Added background reclamation of unused log database space to reduce disk usage. (#49069)

## Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.159.0...rust-v0.160.0

- #48983 Avoid full metadata rewrites for thread timestamp updates @jif-oai
- #49000 Isolate the memory startup metadata test from Git enrichment @jif-oai
- #49019 Use a compatible PowerShell fallback for the Windows MXC sandbox @iceweasel-oai
- #49028 Use the numeric ioctl value in the macOS sandbox policy @aionescu-oai
- #49031 Clarify ChatGPT sign-in success copy @bc-openai
- #49032 Avoid SQLite stalls from connection setup and stderr span logging @jif-oai
- #49036 Add opt-in conversation history retrieval to Guardian reviews @felixxia-oai
- #49037 Show the Plan mode cycling hint in the fullscreen status line @fcoury-oai
- #49038 Preserve encrypted agent messages in Guardian reviews @felixxia-oai
- #49041 Copy selections within inline code as plain text @fcoury-oai
- #49043 Update Pro plan display names in the TUI @etraut-openai
- #49057 Add handoff-aware root context for Guardian reviews @jif-oai
- #49058 Fix Windows sandbox ACL repair for long runtime paths @darius-oai
- #49060 Update Guardian messaging snapshots for native agent messages @dkovalenko-oai
- #49065 Update Guardian handoff snapshot for separate agent messages @cassirer-openai
- #49067 Keep configuration values out of Windows sandbox policy events @zm-oai
- #49069 Reclaim unused SQLite log database pages in the background @dkovalenko-oai
- #49073 Surface realtime voice catalog failures in the TUI @etraut-openai
- #49074 Propagate Cargo package versions to Bazel Rust targets @tamird
- #49075 Preserve pending environments when spawning subagents @sayan-oai
- #49076 Avoid collecting unused Git metadata in skill analytics @tamird
- #49079 Update and centralize TUI subscription labels @etraut-openai
- #49082 Skip remote Git discovery for Guardian diff paths @jif-oai
- #49084 Track app-server running turns incrementally @tamird
- #49089 Render follow-up directive labels in the TUI and copied responses @etraut-openai
- #49093 Simplify startup promotions to platform-specific desktop app tips @etraut-openai
- #49096 Update `h2` from 0.4.16 to 0.4.19 in Cargo and Bazel lockfiles @cassirer-openai
- #49097 Notify lifecycle extensions of compaction usage limits @xli-oai
- #49098 Resolve Windows sandbox PowerShell fallbacks on the exec server @zm-oai
- #49099 Cache parsed plugin manifests across plugin workflows @dkovalenko-oai
- #49100 Reuse the HTTP connection pool for remote plugin requests @dkovalenko-oai
- #49102 Preserve SQLite vacuum modes and surface pool initialization errors @bc-openai
- #49103 Balance Windows Bazel test shards using duration estimates @jgershen-oai
- #49105 Resume unsent TUI input after reconnecting @etraut-openai
- #49106 Add history pagination to the agent command center @bc-openai
- #49112 Add X11 primary selection and middle-click paste support @fcoury-oai
- #49114 Point remote compaction tests at the mock ChatGPT server @OLI-OAI
- #49117 Attribute analytics requests to each thread's product SKU @papayo-oai
- #49118 Correct provider authentication storage documentation @celia-oai
- #49119 Add recovery guidance to content-filter retries @won-openai
- #49127 Deduplicate cloud and executor skill listings before budgeting @TAFOYA-OAI
- #49130 Move content-filter guidance into the shared Responses retry handler @won-openai
- #49135 Treat explicit provider model catalogs as authoritative @andrewgu-oai
- #49136 Remove the plus separator after Option symbols in TUI key hints @bc-openai
- #49138 Expose original error details to turn lifecycle contributors @bryanashley
- #49144 Preserve server reasoning summary and verbosity settings in the TUI @etraut-openai
- #49145 Hide reasoning summary settings in `/status` for server connections @etraut-openai
- #49147 Simplify cloud task base URL normalization @akira-oai
- #49153 Omit blockquote markers when copying quoted selections in the TUI @bc-openai
- #49160 Support projectless TUI sessions with workspace defaults @etraut-openai
- #49161 Honor app-server provider defaults in the TUI @etraut-openai
- #49164 Suppress Windows console windows for background subprocesses @etraut-openai
- #49171 Fix model provider lookup for TUI history @etraut-openai
- #49386 [0.160] Backport remaining Windows console fix to frozen alpha.6 @andrewgu-oai
- #49763 [0.160] Backport maintenance-line catalog and security reminder updates @andrewgu-oai

- Added Claude Mods: plugins may now modify deeper behavior
- Added You should know, a built-in mod where a side agent watches your back and flags things you or Claude might miss. Turn it on with `/plugin enable cc-plugin-you-should-know@builtin` (for first-party sessions with telemetry on)
- Added an `n:<text>` filter to the agents view that matches session names and tasks; a filter now shows matches in collapsed sections and Enter opens the first match
- Added `prompt_text` to the OpenTelemetry `user_prompt` event, a copy of `prompt` for backends that nest dotted keys; drop or mask it wherever you drop or mask `prompt` (anthropics/claude-code#70763)
- Added URL prompts from MCP servers on the 2025-11-25 protocol, for example to sign in. If a server no longer connects after this update, add "bareElicitationCapability": true to its MCP config entry
- Windows: Added a startup warning when denying the Bash tool also turns off the PowerShell tool, so Claude has no shell tool
- Self-hosted runner: Added a built-in `gh api` (REST only) for sessions that use Anthropic-managed git on macOS and Linux machines where the GitHub CLI is not installed
- Fixed fast mode staying off in remote sessions owned by an agent with no user account, even when the organization allows it
- Fixed Remote Control not receiving messages for minutes at a time when a reconnect request got no response; it now gives up after 30 seconds and retries
- Fixed hooks configured with `asyncRewake` waking Claude over and over with "found issues" notifications when the hook's script file is missing; the broken hook is now reported once
- Fixed tool heartbeats not reaching SDK hosts while the model's response stream was stalled with no data arriving
- Fixed Bedrock and Vertex startup model checks ignoring an enforced `availableModels` list, which could collapse `/model` to one Opus row
- Fixed the Claude in Chrome browser picker showing a JSON parse error when Chrome could not be reached
- Fixed picking Fable in `/model` on a claude.ai login saving the current version's id, so your saved default now follows the newest Fable like Opus and Sonnet do
- Fixed switching between Opus 5.5 and Sonnet 5.5 (`/model`, `opusplan`) rewriting earlier MCP tool announcements, which could drop earlier extended thinking
- Fixed Amazon Bedrock Guardrails blocks that arrive mid-response ending the turn with an API error instead of the guardrail's message when the reply began with thinking
- Fixed a dangerous `rm` (such as one on `/` or the home directory) losing its always-ask safeguard when the same command also redirected output to a `~` or wildcard path
- Fixed `claude -p` and SDK sessions repeating a model fallback on every later message after the model was switched while a reply was running
- Fixed a folder's CLAUDE.md being attached a second time after resuming a session or after a compaction
- Fixed background sessions that could not be reopened from `claude agents` after the agent exited and removed the worktree the session was started in
- Fixed `/advisor` pairing checks: Sonnet 5.5 can now advise Opus 4.7 and 4.8, and advisors the API would refuse are flagged up front instead of being silently dropped
- Fixed Bash permission prompts showing internal parser names such as "Contains simple_expansion" instead of a plain explanation
- Fixed a cause of fullscreen sessions on slow or busy machines exiting with "Claude Code exited after an unrecoverable interface error" while a scroll key was held in a long conversation
- Fixed organization per-tool permission ceilings being silently dropped for an MCP tool named `__proto__`
- Fixed Claude being told to page large MCP results saved as JSON with Read's offset and limit, which cannot split one long line
- Fixed the commit attribution reminder being delivered inside a tool result after a compaction
- Fixed screen reader mode leaving the cursor away from the typed text in search boxes (such as /resume and /permissions) and sign-in code fields
- Fixed screen reader mode refusing Enter with nothing typed on /rewind's summarize options, whose added context is optional
- Fixed screen reader mode showing a "Tab to amend" hint on approval prompts, where Tab does nothing
- Fixed screen reader mode listing arrow keys that do nothing in /permissions and /mcp, and saying "Select with numbers" in empty menus or while a search box has the keys
- Fixed screen reader mode leaving out the changed lines in file edit approval prompts and other diffs
- Fixed screen reader mode sending the `claude --teleport` progress screen, and an MCP form field while it is being checked, to the screen reader again on every spinner frame
- Fixed `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS` not removing the structured-output format from session-title and prompt-hook requests, which Bedrock-backed gateways reject
- Fixed screen reader mode leaving out the top lines of a second approval prompt, a changed /config row or the rejected-plan line when the previous screen was taller than the terminal window
- Fixed `--include-partial-messages` sending a cut-short reply's `message_stop` late or never, so apps could show the reply as still in progress
- Fixed `claude agents` sometimes not showing the permission prompt a background session is waiting on
- Fixed `/ultrareview` giving advice about `.git/info/attributes` when the upload stops on a committed `.gitattributes` it cannot read, such as one saved as UTF-16
- Fixed `claude remote-control` failing to register behind an HTTP proxy with a misleading "Check your organization permissions" error (anthropics/claude-code#97352)
- Fixed sandboxed Bash commands on Linux inheriting an open handle on the Claude Code executable
- Fixed the running-tool dot and three spinners still moving with the "Reduce motion" setting on, and /rewind's confirm screen updating its "ago" time while you type a note
- Fixed times in `claude agents` changing every second in screen reader mode; they now change at most every 10 seconds
- Fixed a revoked claude.ai login showing a generic `API Error: 401` instead of "OAuth token revoked"; in `-p` mode the error now starts with "Failed to authenticate"
- Fixed `/ultrareview` upload refusals advising you to copy a variable named by a repository's settings file into your own user settings
- Fixed `--output-format stream-json` and the SDK not streaming the turns of a `context: fork` skill run by typing `/<skill>` as the prompt, as they do for the Skill tool's fork
- Fixed /feedback and /bug: the pre-filled GitHub issue no longer includes your recent error messages, and the confirmation screen now lists them as part of the report
- Fixed `claude plugin marketplace add --sparse` and `git-subdir` plugin installs failing with "transport 'http' not allowed" when the repository is served over plain http
- Fixed cloud sessions sometimes losing the earlier conversation when the session restarted while it was being compacted
- Fixed a plugin reload that overlapped the startup `--plugin-url` download corrupting the session's cached copy of the plugin archive
- Fixed `/desktop` quoting partial output when opening Claude Desktop timed out or printed too much output; the error now names the cause
- Fixed an MCP connector tool call occasionally running twice, or the connector's calls failing until restart, when its server changed which MCP protocol version it supports
- Fixed SessionStart hooks from synced plugins not running in new cloud sessions
- Fixed the transcript's "N hooks ran" summary and the verbose debug log's matched-hooks count including Claude Code's internal callbacks, so one configured hook no longer shows as two
- Fixed files Claude sends from cloud and Remote Control sessions failing when the upload finished just after the 30-second timeout; it now waits 35 seconds
- Fixed repositories added mid-session in cloud and SDK sessions not loading their skills and plugins, and loading CLAUDE.md late, after Claude changed directory
- Fixed PNG, JPEG and WebP images over 8,000 pixels on a side failing to send from a remote session; Claude now sends a scaled-down copy
- Fixed messages sent from the Claude apps with 17 to 20 attached files delivering only the first 16
- Fixed headless sessions reporting an MCP server as needing authentication after one refused call, even though later calls succeed
- macOS: Fixed Remote Control sessions started with `claude remote-control` stopping mid-turn when the Mac went to idle sleep
- Windows: Fixed interactive `claude` hanging or crashing with "Raw mode is not supported" when its input is piped or redirected; it now says why and exits (use `-p` for piped input)
- Bedrock, Vertex, Mantle: Fixed model availability checks under `CLAUDE_CODE_SKIP_*_AUTH` sending a different `Authorization` header than real requests when `ANTHROPIC_CUSTOM_HEADERS` repeats it
- Improved `/config`: settings that cycle show ‹ › and step both ways with ←/→, narrow terminals stack each value under its label, and PgUp/PgDn page the list
- Improved plugin marketplace errors to say in plain words why a marketplace was ignored or refused, and what to do
- Improved plugin listings to note when a plugin's dependencies were not installed, and updating a plugin now retries an install that did not finish
- Improved the Claude apps gateway's error when Amazon Bedrock rejects a model ID: developers now see which model is unavailable, and the gateway log names the ID that was sent
- Improved SDK sessions so a message sent with priority "now" no longer cancels a running web fetch or web search; it keeps loading in the background
- Improved `/memory`: the left and right arrow keys now flip its on/off settings, such as Auto-memory
- Improved `/skill` names typed mid-message: Claude is now told they are skills, including `disable-model-invocation` ones
- Improved the contrast of the prompt input border in light themes and of the ❯ before your earlier messages
- Improved delivery of files Claude sends from cloud sessions and Remote Control: an upload that fails on a timeout, a network error or a 502, 503 or 504 is now retried once
- Improved what Claude says when a file cannot be sent for a reason that may be temporary: it now mentions that you can ask for the file again in a few minutes
- Improved the prompt for a held message from another session to show the message between dashed lines, matching other permission prompts
- Improved MCP and other tool permission prompts to show the tool call between dashed lines, matching file edit prompts
- Improved MCP startup in headless mode: a remote server whose first connect fails transiently is now retried without waiting for the slowest server to finish connecting
- Improved files Claude sends from a remote session: large files now stream from disk instead of being read into memory, and a file over the size limit is refused with the server's limit named
- Improved the explanation Claude gives when the server refuses a file it sends from a Remote Control or cloud session, such as an oversized image
- Improved handling of large MCP tool results: less memory, smaller session files, and no extra upload to count tokens for results far over the limit
- Windows: Improved Bash tool speed by removing a subshell that ran before every command
- Changed a shell write through a repo-committed symlink onto a sensitive file or out of the working tree to name where it lands and wait for a person, on lines with a `~` target too
- Changed Opus 4.7+ and Fable to use a 1M context window by default on Bedrock, Vertex, Foundry and the Claude apps gateway, with no `[1m]` suffix (`CLAUDE_CODE_DISABLE_1M_CONTEXT=1` keeps 200K)
- Changed replies from `claude agents` to arrive as queued messages; slash commands other than `/stop` sent while a turn is running now run when it ends
- Changed whole-tool `Bash` allow rules and allowing hooks to prompt for, not run, shell writes to files Claude Code's file tools refuse outright (the Anthropic profile store, the host 

these notes continue in the original release.

## New Features

- Eligible local sessions signed in with ChatGPT can now show optional reminders to complete account security setup. (#49744)

## Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.159.2...rust-v0.159.3

- #49744 [0.159] Backport account security setup reminders for 0.159.3 @andrewgu-oai

- Added a count such as "2 of 5" to the permission prompt when several permission requests stack up
- Added mouse support for the "N more" rows of lists in fullscreen mode: click one to jump to that end of the list, with hover and pressed states
- Fixed several Claude Code processes and IDE extensions each opening a login browser when gcpAuthRefresh or awsAuthRefresh credentials expire
- Fixed `claude --resume` and `--continue` sometimes losing every turn after a batch of parallel tool calls when the earlier session crashed or was killed
- Fixed API 400 errors after a tool or hook returned an object, number or boolean instead of text, including in resumed sessions
- Fixed cloud sessions with very large histories never waking up because the container was stopped while the transcript was still loading
- Fixed the Claude apps gateway's spend meter pricing 1-hour prompt cache writes at the cheaper 5-minute rate, and counting only the first model call's input tokens on streamed turns that run a server-side tool such as web search
- Fixed macOS sessions still showing "Not logged in" or "Login expired" after `/login` succeeds in another Claude Code window when a leftover `~/.claude/.credentials.json` exists
- Fixed every turn failing when the Anthropic API refuses the model your default or a model alias resolves to: Claude Code now retries once on the previous model of the same tier
- Fixed Remote Control sessions (including `claude remote-control`) staying connected after your organization's policy turns Remote Control off; they now disconnect with a notice
- Fixed refusal and `--fallback-model` retries failing when the fallback model can't run fast; they now run at standard speed, with a one-time notice in interactive sessions
- Fixed headless sessions repeating the "MCP servers require authentication" reminder after a successful re-authentication when the MCP discovery cache is enabled
- Fixed `claude auth status` reporting a Console sign-in's stored API key as `claude.ai`; it now reports `api_key`, and the VS Code extension treats that session as an API key session
- Fixed `/status` listing an Anthropic profile beside an API key as if both were in effect; the profile is now marked as not in use
- Fixed Claude not being told when a file attached to a message sent over Remote Control did not arrive, and a file sometimes getting only 10 seconds for its last download try
- Fixed a Remote Control message that arrived while Claude Code was exiting being marked delivered and then never answered; it now stays queued for the session's next run
- Fixed MCP error messages showing a credential's value when "Bearer" or "Basic" came before its key name
- Fixed percent-encoded Bearer tokens being only partly masked in error messages
- Fixed redacted logs and transcripts showing a secret whose key name has an invisible character inside, such as a zero-width space
- Fixed logs and transcripts showing part of a URL password that contains punctuation such as `)`, quotes, `]`, `&` or a second `@`, or that runs past a `/` to a bracketed host such as `[::1]` in an ssh URL
- Fixed the session transcript in the zip that `/feedback` saves to disk containing invalid JSON lines after secret redaction
- Fixed MCP connectors listing no tools for up to a day after their server dropped the older MCP handshake
- Fixed a repeat MCP sign-in request from Claude replacing the pending sign-in link, which could stop that link from working
- Fixed `/usage` not crediting an MCP server for a tool call made while that server was still connecting or had only just connected, such as right after a restart
- Fixed plugins enabled on claude.ai occasionally going missing from Claude Code for a session after a transient server error
- Fixed a message typed into a running subagent showing twice in its transcript after the subagent read it
- Fixed subagent hand-back messages showing a raw task id instead of the agent's name when the subagent had no registered name
- Fixed foreground subagents sometimes missing the task-tracking tools (TaskCreate/Get/Update/List, TodoWrite) in sessions that have them enabled
- Fixed subagents spawned with worktree isolation loading the project CLAUDE.md and its imports a second time from the worktree copy on their first file read
- Fixed Workflow tool subagents being restarted from their original prompt when a connection stalled for a few minutes mid-response
- Fixed `/compact`, `/clear`, and `/rewind` typed while viewing a background agent's or teammate's transcript silently acting on the main conversation: a dialog now names the target and asks first
- Fixed background jobs showing done while waiting for your approval
- Fixed the commit attribution reminder being re-sent inside tool output when a model fallback lasts only one turn
- Fixed a click on the space between words of a collapsed row (such as "Thought for 4s") highlighting the row without expanding it in fullscreen mode
- Fixed a row with no details, such as an action row with a long name, pushing every other row's details to the right in list screens
- Fixed files with very long names not reaching a cloud session when attached to it
- Fixed plugin errors for a marketplace Claude Code refuses to load: they now say why and how to fix it instead of "not found"
- Fixed `/plugin`'s Discover tab showing a marketplace name unquoted in its "Checking … for new plugins" line when its rows already show that name in quotes
- Improved commit guidance: when your project or user skills include one named `verify`, Claude is now told to run it right before committing, except for docs-only and tests-only commits
- Improved send now (ctrl+enter) in a subagent's view: it now moves the subagent's running command to the background so your message is read right away
- Improved replies from background agents to your messages so they no longer open with a separate recap of what you said
- Improved claude.ai artifact link reads: WebFetch now asks the same questions as the Artifact tool's read (no artifact prompt while the session's network access is on, one per artifact while it is off), and an auto-mode yes no longer counts where only you can answer
- Improved fetch, skill, file read, sandbox network, Claude in Chrome, workflow script and notebook edit permission prompts to match the look of file edit prompts
- Improved Bash, PowerShell and Monitor permission prompts to show the command between dashed lines, matching file edit prompts
- Improved list scrollbars in fullscreen mode: in most lists the bar no longer shifts as the "N more" rows come and go, and it now has ↑/↓ arrows you can click or hold to scroll
- Improved the external editor (Ctrl+G): editors that take a line number now open on the line your cursor is on in the prompt
- Improved slash command suggestion responsiveness while typing when many skills or plugin commands are installed; command descriptions now match by word prefix
- Improved the output style picker: it now opens on your current style instead of Default, with each style's description on the line under its name; number keys no longer pick a style
- Improved `/hooks`: the closing line of a hook's detail screen now says "this hook" instead of "it"
- Improved the model fallback notice and the autocompact-thrashing error to say when a fallback dropped the context window from 1M to 200K tokens
- Improved responsiveness of SDK and `-p` sessions when a host re-sends an MCP server enable for a server that is already connected
- Improved the protocol page a Claude apps gateway serves at `/protocol`: it now says not to reject unknown input and matches what Claude Code sends today
- Changed prompts sent while nothing is running or queued to show in the normal text color right away instead of gray
- Changed how failed API requests are retried: one limit now covers a whole model call, so with the default retry settings a failing call sends at most 14 requests
- Changed `--bare` to connect only the MCP servers named on the command line, send the model no system reminders, and start no background tasks; under `--bare`, a shell command that reaches its timeout now stops instead of moving to the background
- Changed the send-now key (ctrl+enter) to move a skill's own shell command to the background instead of ending it
- Changed the WebFetch error for a rate-limited domain safety check to tell Claude not to retry it in a loop
- Changed plugin installs to refuse npm sources that are git repositories or folders, and to install plugin dependencies only from registry packages
- Changed list screens (`/artifacts`, `/mcp`, `/skills`, `/hooks` and others) to always line up each row's details in one column after the names
- Changed the overflow rows of lists to read "↑ N more" / "↓ N more" instead of "N more above" / "N more below"
- Changed `/hooks` to open on one list of your configured hooks grouped by event, so viewing a hook takes one Enter instead of three
- Changed the theme picker to a scrolling list that fits your terminal instead of pushing the preview off screen; number keys no longer pick a theme
- Changed `/exit`'s Remove worktree to run after Claude Code stops the servers and shells it started there, which on Windows could keep the folder from being deleted
- Changed the `claude-api` skill's Managed Agents examples to create environments with limited networking
- Removed the browser link from `/ultrareview` and `claude ultrareview` output
- Windows: Fixed `claude --bg` and the agents view refusing a folder that `claude` already trusts when its trust record was saved with different letter case
- [VSCode] Added bookmarks: save Claude's responses and keep them in view in a Bookmarks side panel
- [VSCode] Added the questions Claude asks and your answers to the conversation: after you answer a question card, a Questions row shows each question with your picks
- [VSCode] Added option previews to question cards in the chat panel: the highlighted choice's mockup or snippet shows beside or under the options
- [VSCode] Added rows under a message that open to the terminal output, browser tab, browser instructions and selected code sent with it
- [VSCode] Fixed a second copy of a conversation opening in a tab when it was already open in the side bar; the side bar now switches to it
- [VSCode] Fixed settings dialogs reporting a failed save, without re-checking, when Claude Code printed more than 1 MB of output
- [VSCode] Fixed an endless "Teleporting session…" spinner when the extension stops responding
- [VSCode] Improved the Manage plugins dialog: it says when a turned-off plugin is still on because of other settings, and explains a plugin folder clash
- [VSCode] Changed Stop and Escape to end only the current turn; background agents keep running and can be stopped one by one from the agent map
- [VSCode] Changed the "✻ Claude Code" status bar item to show in every window, so you can open Claude when no file is open
- [Cloud sessions] Fixed an answered question card or approved tool call getting no reply when the session had gone idle after Claude sent a message
- [Cloud sessions] Fixed clearing an organization environment's setup script in admin settings leaving new cloud sessions still running the old script
- [Cloud sessions] Fixed the Runner actions menu on the self-hosted environments admin page closing on its own a few seconds after it opened
- [Cloud sessions] Fixed routine runs whose cloud session never started showing as Succeeded in the Runs pane, the routine's page and the sidebar; they now show as Failed
- [Cloud sessions] Fixed clicking an audio or video file in a cloud session's Outputs card opening an empty file search instead of playing the file
- [Cloud sessions] Changed a routine's page to read "Due" with the scheduled time, instead of a next run time in the past, when a scheduled run is late and hasn't started
- [Claude Tag] Added an Add channel button to Claude Tag's spend limits page in admin settings, so a limit can be set on any

these notes continue in the original release.

## Bug Fixes

- Suppressed console windows flashing on Windows when Codex launches background processes and sandboxed commands. (#49385)

## Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.159.1...rust-v0.159.2

- #49385 [0.159] Backport Windows console suppression for 0.159.2 @andrewgu-oai

## New Features
- Added GPT-6.1 Sol as the default model in the bundled catalog and Amazon Bedrock Mantle and Runtime catalogs. (#49323, #49342)

## Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.159.0...rust-v0.159.1

- #49323 [0.159] Prepare 0.159.1 release backports @andrewgu-oai
- #49342 [0.159] Backport GPT-6.1 Sol Bedrock catalogs @celia-oai

- Added `CLAUDE_CODE_DISABLE_WEB_FETCH` environment variable to turn off the WebFetch tool
- Added `claude --desktop` to open the Claude desktop app on the current directory, or on a session with `--continue` / `--resume <id>`
- Added `claude plugin configure <plugin>` to show a plugin's options and which are unset, or save new values read from stdin with `--values-stdin`
- Added `<server>.<key>=<value>` to `claude plugin install --config`, so a bundled `.mcpb` MCP server's own settings can be set at install time and it starts without visiting `/plugin` → Configure
- Added `allowedProviders` managed setting to limit which API providers a machine may use (Anthropic API, a custom endpoint, Bedrock, Mantle, Vertex AI, Foundry, Claude Platform on AWS, or a Cloud gateway)
- Added `CLAUDE_CODE_NONSTREAMING_TIMEOUT_RETRIES` environment variable to cap re-sends of a non-streaming fallback request that timed out
- Fixed `claude -p` with `CLAUDE_CODE_FORK_SUBAGENT=1`: a subagent's own Agent call now runs in the foreground, so the subagent gets the child's result
- Fixed plugin and marketplace installs and updates over SSH ignoring the ssh program set in `GIT_SSH` or in your git config's `core.sshCommand`
- Fixed Claude Code refusing to start when the OS denies reading the managed settings file; it now warns and starts without that file's policies. Other read errors and unparseable files stop every session
- Fixed cloud sessions that restarted after their conversation was compacted refusing the next update to an artifact the session had already read or published
- Fixed `claude plugin disable` and `enable` with a full `name@marketplace` id changing a settings entry in another letter case instead of the installed plugin's own
- Fixed files attached to a message sent over Remote Control being left out after a single failed download; a network error, timeout or server error is now retried up to twice
- Fixed switching models mid-session with a `set_model` request (such as the Agent SDK's `setModel`) leaving the new model on the built-in output-token limit and auto-compact window until restart
- Fixed redacted logs and transcripts showing part of a URL password that contains `@`, or all of it when the URL writes its `@` as `%40`
- Fixed SSH passphrase and new-host prompts from worktree and `/teleport` fetches taking over the terminal; these fetches now fail fast instead of asking
- Fixed switching off an MCP server added mid-session in SDK and `-p` sessions leaving its tools available
- Fixed `claude -p --permission-prompt-tool`: a background subagent's permission request now goes to the prompt tool instead of being auto-denied
- Fixed `claude mcp list` and `claude mcp get`, and the not-found error of `claude mcp remove`, `login` and `logout`, printing line breaks and terminal escape sequences from MCP server names and values
- Fixed sandbox auto-allow asking for approval on every run of many inline scripts (`python3 -c`, `node -e`) just because they contain `=`
- Fixed fork subagents not keeping the session's plan mode or `dontAsk` mode: a fork now runs under its parent's permission mode and cannot exit plan mode
- Fixed `claude remote-control --help` saying `--[no-]chrome` defaults to the machine's `/chrome` setting; spawned sessions keep Claude in Chrome off unless `--chrome` is passed
- Fixed background subagents in auto mode prompting a second, redundant reply after each report
- Fixed cloud session creation and `/remote-env` reading only the newest 20 of an account's environments
- Fixed Remote Control marking a message as read as soon as it arrived instead of when Claude started on it, and losing a message still queued when the terminal quit (it now arrives on the next resume)
- Fixed installing a plugin with `claude plugin install` or `/plugin` putting it into an installed plugin's cache or data folder when their ids differ only in `.`, `-`, `@` or (macOS, Windows) capitals; the install is now refused
- Fixed hooks and SDK permission callbacks seeing a missing or outdated plan on ExitPlanMode when the plan was written in the same response
- Fixed the first reply in cloud sessions arriving tens of milliseconds late, a regression in 2.1.283
- Fixed sessions that authenticate with `ANTHROPIC_AUTH_TOKEN` against the Anthropic API never loading the organization's policy
- Fixed a failed `agent()`, `parallel()` or `pipeline()` call that a workflow script awaits later, or not at all, being treated as an unhandled promise rejection, which could end a background session
- Fixed synchronous hooks hanging Claude Code while a background process the hook started (for example `some-daemon &`) kept its output open; the hook now finishes shortly after its own process exits
- Fixed WebFetch reporting a rate-limited domain safety check as a network or enterprise policy block
- Fixed the fullscreen ctrl+o transcript freezing briefly when opened on turns with hundreds of file reads or searches; tool calls still running when the transcript opens now show their results when they finish
- Fixed Amazon Bedrock mid-stream `modelTimeoutException` and `serviceUnavailableException` errors showing a raw JSON body instead of the error message
- Fixed `/autofix-pr` and `/schedule` saying the Claude GitHub App is not installed on a repository whose install status had not been checked yet
- Fixed dismissing a row (x) in `/artifacts` unlinking its file from the artifact, so publishing the same file again created a new artifact instead of updating it
- Fixed Artifact tool publishes after a conversation rewind (Esc Esc) overwriting a file's newer content that Claude had read only in the rewound turns; the publish is now refused until Claude re-reads the file
- Fixed an `Artifact` allow rule ("don't ask again") letting the Artifact tool publish a file outside the working directories without asking; add the file's folder with `--add-dir` for the rule to cover it
- Fixed `/cost` and SDK `modelUsage` reporting a turn under the wrong model when the server answered a refusal with a different fallback model than the client expected
- Fixed the Artifact tool so that publishing a page no longer lets Claude overwrite its source file without re-reading it when Claude's earlier read was cut short or the file had changed since
- Fixed auto mode skipping its classifier for Artifact tool asset uploads and reads of someone else's artifact when you had approved that artifact earlier in another permission mode
- Fixed a misleading "core.worktree is set" error from `/ultrareview` when the project folder briefly could not be read
- Fixed `/ultrareview` on macOS and Linux failing to upload the working tree from a git worktree whose per-worktree config sets `core.longpaths`
- Fixed the Artifact tool sometimes reporting a publish as a conflict with another session after retrying a temporary server error, when the first attempt had actually succeeded
- Fixed `/ultrareview` uploads including uncommitted changes to credential files whose name has a colon before the extension, such as `server:8443.key`
- Fixed a rare auth failure when two sessions recover a login refresh lock left by a crashed process at the same time
- Fixed the PowerShell tool's permission check skipping deny and ask rules, and caching that failure for later checks, when its command parser failed to start (for example when the machine was out of memory)
- Fixed `/ultrareview` uploads on macOS and Linux running slowly on some unusual file names, and their credential-file check missing file or folder names with many backup or editor marks
- Fixed a cancelled shell command or hook still starting, and running to its end, when the cancel arrived while it was being set up
- Fixed vim mode: after editing in the external editor (Ctrl+G), `x` or `r` in NORMAL mode no longer breaks a pasted-text placeholder at the end of the prompt
- Fixed responses blocked by the API's output content filter being re-sent and retried, sometimes for minutes, instead of showing the filter's error right away
- Fixed plugins silently skipping a bundled `.mcpb` MCP server that still needs configuration: `/plugin`, the install message and `claude plugin install` now say so and point to Configure
- Fixed compacting or resuming a session failing, opening without its history, or crashing when its saved transcript holds a compaction marker or loop wakeup entry with missing or malformed fields
- WSL: Fixed `/ultrareview` refusing to upload a checkout on a Linux volume when a changed file's name has a colon or ends in a dot or space
- Fixed `CLAUDE_CODE_RESUME_INTERRUPTED_TURN` re-running a turn that had ended at `--max-turns`
- Fixed sign-in that could wait forever after the browser showed success
- Windows: Fixed `/ultrareview` uploading a linked worktree of a repository rooted at your home folder in some cases
- Fixed cloud sessions reporting the uploads folder as missing before any file had been uploaded
- Fixed a reply sent from `claude agents` to a background session waiting on a permission prompt sometimes approving the pending command
- Fixed `claude attach`, `logs`, `stop`, `respawn` and `rm` starting a new session with the command name as its prompt when options came before it, such as from a shell alias
- Fixed `claude mcp list` leaving out WebSocket (`ws`) MCP servers; each is now listed with its URL and health status
- Fixed `claude mcp get` showing no Type, Command, Args, or Environment for stdio servers whose config entry omits the `type` field
- Fixed `.claude/settings.local.json` allow rules being held back outside a git repository when git's trace2 output is configured
- Fixed the `/claude-api` eval runner scaffold and report builder writing through a symlink or hard link planted at an output file
- Fixed the `/claude-api` eval runner scaffold counting responses cut off at `max_tokens` in the score averages; they are now marked truncated and counted separately
- Fixed `&nbsp;` showing as literal text in the terminal when a reply uses it to indent text, such as row labels in a markdown table
- Fixed a brief freeze (up to a second) partway through long sessions outside fullscreen mode, which came back after `/clear` or `/compact`
- Fixed an approved Edit never going through when its target is a device, such as a file symlinked to /dev/null, and the approval came from the IDE diff view or changed the edit
- Fixed a failing API request being retried up to 21 times when streaming kept failing; the non-streaming fallback now shares the request's retry budget instead of getting a fresh set of retries
- Improved Claude in Chrome: the native host now reports your computer's name, so connected browsers can be labeled by computer instead of "Browser 1" / "Browser 2"
- Improved Bedrock and Vertex AI sessions to switch to an older available model of the same tier, instead of failing, when an admin removes access to the default model; session titles and summaries now fall back with it
- Improved plugin marketplace errors to name why a git address is refused instead of citing enterprise policy
- Improved validation of git URLs for plugins, marketplaces and the current repository's remote
- Improved Artifact tool results: they now suggest publishing in the same step as writing or editing the page, which can save a round trip
- Improved Remote Control: a `/btw` side question asked of a session hosted by an app such as Claude Desktop now sees the turn in progress, not only the last finished one
- Improved pictures Claude sends as BMP, HEIC, HEIF, AVIF or TIFF files: the Claude apps now show a preview where Claude Code can convert them
- Improved subagents in auto mode: a subagent's run now ends as soon as it hands its report back to its caller, instead of taking extra turns that reach no one
- Improved Bedrock and Vertex start-up model checks: models your account cannot use are now remembered for up to a day instead of being re-checked on every launch
- Improved Artifact tool publish results to use fewer tok

these notes continue in the original release.

## New Features

- Opt-in `instant_interrupt` lets new input steer Codex during model responses or long-running code-mode calls. (#48135, #48141)
- New sessions get a compact welcome screen and consistent headers, with occasional tips during and after turns. (#48513, #48562, #48352)
- The warnings viewer dismisses reviewed warnings when closed; press `k` to keep one for later. (#48205, #48206)
- You can scroll the transcript while deciding whether to implement a plan. (#48805)
- Native Mermaid rendering supports more flowchart edges, labels, and node groups. (#48814, #48895)
- App-server clients can paginate thread history from a specific item. (#48151)

## Bug Fixes

- Windows launches avoid stray console windows for MCP servers, code-mode hosts, and piped commands; restrictive launchers can fall back to embedded mode. (#48138, #48238, #48483, #48491)
- Copying transcript selections preserves Markdown tables, formatting, and significant whitespace. More terminals now copy automatically on selection. (#48548, #48549, #48469)
- Blank sessions retain drafts when switching tasks, and threads can be archived and listed before their first turn. (#48628, #48828, #48199)
- Local ChatGPT sign-in opens the browser reliably; onboarding also provides a shortcut to copy the login link. (#48502, #48544)
- Approved commands retain explicit filesystem denials, and `.aws` directories are protected by default under writable roots. (#48155, #48176)
- Fixed macOS TLS access in network-enabled sandboxes and remote environments that require proxy access. (#48565, #48198)

## Chores

- Removed automatic follow-up prompt suggestions and the `tui.prompt_suggestions` setting. (#48621)
- Removed the bundled `plugin-creator` skill. (#48604)

## Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.158.0...rust-v0.159.0

- #48135 Add opt-in code-mode yielding on new user input @pakrym-oai
- #48138 Suppress console windows when spawning the code-mode host on Windows @zm-oai
- #48141 Preempt model responses when new user input arrives @pakrym-oai
- #48143 Preserve executor MCP credential boundaries across reconnects @rreichel3-oai
- #48151 Add item anchors to `thread/items/list` pagination @btraut-openai
- #48155 Preserve filesystem denials when preparing approved commands @viyatb-oai
- #48157 Allow Windows daemon launches with residual job membership @etraut-openai
- #48158 Fix Guardian retained context spacing and empty assistant handling @olliem-oai
- #48168 Generate unique exec-server process IDs for every request @sdcoffey
- #48174 Preserve usage limit windows in turn and compaction analytics @rhan-oai
- #48176 Protect `.aws` directories under sandbox writable roots @jackz100
- #48187 Fix zsh alias quoting in sourced shell snapshots @jif-oai
- #48190 Bound agent message board SSE frames before parsing @jif-oai
- #48197 Optimize `blake3` in Bazel fastbuilds @jif-oai
- #48198 Honor execution environment proxy requirements @seanh-oai
- #48199 Keep archived threads with empty previews visible in listings @acrognale-oai
- #48200 Extract Responses header conversion into a shared module @anp-oai
- #48205 Dismiss viewed TUI warnings when closing the viewer @fcoury-oai
- #48206 Add a keep-and-next action to the warnings viewer @fcoury-oai
- #48207 Preserve queued output for observers during code-mode termination @pakrym-oai
- #48211 Keep Codex visible during external editor handoff @etraut-openai
- #48213 Isolate executable fixture copies in CLI tests on Linux @jif-oai
- #48222 Preserve late result metadata for truncated code-mode calls @ningyi-oai
- #48224 Preserve model and access program pairs during compaction @jamy-OAI
- #48229 Extract Responses failure parsing into a dedicated module @anp-oai
- #48238 Suppress console windows for local Windows MCP servers @malsamiri-oai
- #48272 Prevent Windows daemon launches from retaining launcher stdio @zm-oai
- #48318 Keep TUI reconnect attempts running until the shared deadline @etraut-openai
- #48344 Preserve tool metadata for OpenAI provider endpoint overrides @peilin-openai
- #48350 Display reconnect commands on a separate line @etraut-openai
- #48352 Show turn tips while working and after completion in the TUI @fcoury-oai
- #48353 Stabilize skill catalogs across executor availability changes @vkg-oai
- #48469 Default to copying transcript selections in more terminals @fcoury-oai
- #48483 Prevent console windows for piped Windows child processes @fcoury-oai
- #48489 Fix Mermaid shape, relationship, and state description parsing @etraut-openai
- #48491 Fall back to embedded mode under restrictive Windows launchers @fcoury-oai
- #48502 Fix ChatGPT browser sign-in for local app servers @etraut-openai
- #48508 Preserve WebSocket continuations when steering a turn @pakrym-oai
- #48513 Refresh the TUI welcome screen for new sessions @fcoury-oai
- #48531 Add context to Windows sandbox runtime registration errors @zm-oai
- #48544 Make onboarding login links easier to copy @etraut-openai
- #48547 Fade blossom replays back to the idle state @fcoury-oai
- #48548 Preserve table cell source metadata through TUI rendering @fcoury-oai
- #48549 Preserve Markdown tables and whitespace when copying TUI responses @fcoury-oai
- #48551 Fix TUI math rendering for zero and big wedge expressions @etraut-openai
- #48560 Keep working tips stable during transcript interaction @fcoury-oai
- #48562 Use a consistent borderless session header in the TUI @fcoury-oai
- #48565 Allow macOS TLS trust evaluation in network-enabled Seatbelt profiles @winston-openai
- #48568 Allow exec-server to proxy permitted private IPs upstream @open-matt
- #48574 Preserve deferred tool namespace names before descriptions @adaley-openai
- #48575 Allow provisioned executors more time to come online @richardopenai
- #48604 Remove the bundled `plugin-creator` skill @martinauyeung-oai
- #48611 Centralize persistent mode enablement checks @alishobeiri-oai
- #48621 Remove follow-up prompt suggestions from the TUI @etraut-openai
- #48623 Preserve empty Markdown list markers in the TUI @etraut-openai
- #48626 Stop showing previous-session summaries when switching TUI sessions @etraut-openai
- #48628 Preserve blank TUI sessions when switching tasks @etraut-openai
- #48643 Set the provisioned macOS CLI bundle name to ChatGPT @riley-oai
- #48646 Fix the session-start helper call in the command center test @etraut-openai
- #48686 Remove WebSocket headers and tool payloads from info logs @chess-oai
- #48724 Prevent Linux ETXTBSY races in MCP stdio tests @jif-oai
- #48725 Retain confirmed Code Mode messages for Guardian reviews @ankushg
- #48727 Centralize executable fixture creation to avoid Linux ETXTBSY races @jif-oai
- #48754 Render `/status` without borders and wrap long values @fcoury-oai
- #48757 Match TUI status shimmer timing to desktop headers @fcoury-oai
- #48761 Show hidden output line counts in compact terminal activity @fcoury-oai
- #48764 Preserve MCP app resource URIs without defaulting display mode @victor-openai
- #48772 Fix Unix socket connections through long symlink paths @etraut-openai
- #48775 Match pinned transcript headers to the original prompt style @etraut-openai
- #48776 Remove the `current` badge from TUI task rows @etraut-openai
- #48779 Preserve independent Guardian history across parent compaction @felixxia-oai
- #48783 Add single-server MCP status discovery with thread connection reuse @victor-openai
- #48796 Add opt-in structured errors for Guardian circuit-breaker interruptions @won-openai
- #48799 Fix SGR mouse reporting for Windows terminal capture @etraut-openai
- #48800 Use the terminal palette for ordered Markdown list markers @etraut-openai
- #48805 Allow transcript wheel scrolling while a modal is open @fcoury-oai
- #48807 Show short turn durations in TUI completion footers @fcoury-oai
- #48812 Add history-aware prewarming for idle threads @vkg-oai
- #48814 Preserve punctuation and semicolons in Mermaid labels @etraut-openai
- #48819 Use explicit histogram buckets for tool and skill context metrics @mzeng-openai
- #48824 Keep voice RTP timestamps aligned to 20 ms packets @bc-openai
- #48827 Show a hand pointer over transcript links in Ghostty and Kitty @bc-openai
- #48828 Allow archiving threads before their first turn @bc-openai
- #48829 Wait briefly for the Windows sandbox provisioning service to start @zm-oai
- #48830 Show a short, neutral TUI interruption notice @fcoury-oai
- #48895 Expand native Mermaid flowchart syntax support @etraut-openai
- #48973 Isolate realtime auth fallback test from startup prewarm @jif-oai
- #48982 Prevent message-board notifications from reopening final answers @eknight-oai

- Added Claude Sonnet 5.5 (`claude-sonnet-5-5`), now the default Sonnet model on the Anthropic API — 1M context, $2/$10 per Mtok with $0.20/Mtok cache reads
- Added a "Yes, but ask again next time" answer to auto mode's prompt before a read outside the working directories, so you can allow that one read and still be asked about later ones
- Added dollar amounts to the Claude apps gateway spend limit in `/usage` and the status line (for example "$271.40 / $500.00 spent this month") when the gateway runs this version or later; the status line's `rate_limits.spend_limit` also gains `used_usd`, `limit_usd` and `period`
- Added `effortSlider:decreaseEffort`, `increaseEffort` and `toggleUltracode` keybinding actions, so the `/effort` slider's arrow and Tab keys can be rebound in `keybindings.json`
- Added `/rate-limit-options` to `/help` and the command menu for claude.ai subscribers, so the usage-limit notices that mention it point to a command you can find
- Added `/mcp reconnect all` in the interactive terminal to retry every MCP server that failed to connect or needs authentication at once
- Added Claude apps gateway startup warnings when a managed policy's `availableModels` is empty, or leaves out the model Claude Code starts on without setting `model` or `enforceAvailableModels`
- Added `auth: { google: {} }` for Claude apps gateway `telemetry.forward_to` destinations, so telemetry can be exported straight to Google Cloud's OTLP endpoint using the gateway's Google Cloud credentials
- Added certificate client authentication (`private_key_jwt`) between the Claude apps gateway and its identity provider, for identity providers that issue certificate credentials instead of client secrets
- Fixed a damaged response stream showing raw errors such as "JSON Parse error" or "undefined is not an object", or writing the word "undefined" into an answer, instead of being retried or reported as an interrupted response
- Fixed an overloaded or server error arriving right after a thinking block ending the turn with an error instead of being retried
- Fixed "Prompt is too long" errors that persisted after compacting: when the compacted request is still too long, Claude Code now compacts once more, keeping less of the recent conversation
- Fixed a session whose model is unavailable, with no fallback model left, showing a bare "is currently unavailable" message (or "Something went wrong" in cloud sessions) instead of the model-unavailable notice and its Learn more link
- Fixed Agent SDK sessions crashing when a user message contains an image with a malformed `source`, and failing on every later turn after a malformed document block; a malformed image is now replaced with an explanatory note
- Fixed MCP tool calls in a resumed session failing with "No such tool available" while their server was still connecting; the call now waits up to 10 seconds for the server
- Fixed repeated calls to the plan-usage endpoint after it rate-limits or rejects your login: `/usage`, `/extra-usage` and IDE usage views now back off instead of re-asking
- Fixed `claude mcp add` reporting success when managed settings restrict MCP servers to plugins; it now refuses and says what to do, instead of saving a server that never loads
- Fixed the `/plugin` configure screen: boolean options are now a true/false choice instead of free text, number options refuse invalid input, and ←/→ change an options field instead of switching tabs
- Fixed `ANTHROPIC_FOUNDRY_RESOURCE` being interpolated into the Foundry endpoint host unvalidated; a value that is not a plain resource name is now refused
- Fixed Claude Desktop behind a Claude apps gateway offering no 1M context option: the gateway now marks each 1M-capable model for Desktop automatically
- Fixed ↓ in shell mode selecting a hidden background-tasks pill, which stopped Backspace and Ctrl+U from editing the prompt
- Fixed Bash tool failing on Windows with many plugins enabled: plugin `bin/` directories that don't exist are no longer added to PATH, and inherited entries aren't added twice
- Fixed `sparsePaths` plugin marketplaces cloning empty and replacing a working local copy on older git (before 2.39), which failed every refresh with "marketplace.json file is no longer present"
- Fixed fullscreen rendering erasing the terminal output above the session when `[` in transcript mode writes the conversation to scrollback (macOS and Linux)
- Fixed fullscreen scroll position jumping to the previous message or to the bottom when a reply finished streaming while scrolled up
- Fixed tab bars in dialogs such as `/config` and `/plugin` breaking the title and tab labels mid-word in a narrow terminal; a tab that doesn't fit now moves to the next line whole
- Fixed the `/model` picker showing "+1 model" below the list after scrolling to the last model; the count now covers only the models below the visible rows
- Fixed `/keybindings` writing Backspace and Delete bindings for a footer action that does nothing into the generated `keybindings.json`
- Fixed a rebound agent panel close key (`footer:close`) typing "x" instead of itself on the row of the agent you're viewing
- Fixed vim mode `.` not repeating text typed very fast (for example over ssh or in tmux) or pasted without bracketed paste, and leaving the prompt in INSERT mode after repeating a change with nothing typed (such as `cw` then Esc)
- Fixed vim mode leaving the cursor on an image placeholder's opening bracket after `dd` on the last line or `yy` at the end of the prompt, where `r` or `x` would break or delete the image
- Fixed a key pressed the instant the terminal regained focus answering the Remote Control enable prompt before its short safety delay restarted
- Fixed the workspace trust dialog appearing a second time after switching renderers or updating when Claude Code was started in the home directory
- Fixed rules symlinked into `.claude/rules` from outside the project being skipped without ever showing the external-imports approval prompt; a `.claude` directory symlinked from outside the project now asks for the same approval
- Fixed plugins from marketplaces, claude.ai and npm pre-approving their own tools via `allowed-tools` under managed `allowManagedPermissionRulesOnly`; only plugins from an official Anthropic source or a source that managed settings vouch for keep that pre-approval
- Fixed a failed first `claude plugin install` leaving the plugin enabled and recorded when a dependency's version range could not be met
- Fixed the debug log dropping a failed hook's stderr when the hook also wrote to stdout, and logging nothing for a failed hook with no output; failed hooks now also log their status code
- Fixed `{"decision":"block"}` returned by Elicitation and ElicitationResult hooks being ignored; it now declines the MCP elicitation, as exit code 2 does
- Fixed sessions launched without the `SendMessage` tool (such as by Claude Desktop) still being told to message other sessions with it
- Fixed a photo sent from the Claude app over Remote Control being lost when its queued message was pulled back into the terminal prompt to edit, and the cursor moving one character for a photo with no caption
- Fixed typing a message during an automatic usage-limit wait taking the wait out of the "Continue automatically at usage limit" setting's control when that turn hit the limit again
- Fixed usage-limit warnings suggesting `/upgrade` to users already on the highest Max plan; the warnings and `/upgrade` itself now point at `/usage-credits` when it is available
- Fixed the Explore subagent switching to Opus on the Claude API when the session runs a model ID Claude Code doesn't recognize, such as a custom model behind a proxy; Explore now inherits that model
- Fixed `/loop` status updates in self-paced mode often not being shown because Claude wrote them only in its reasoning; Claude now writes each update, and the outcome when the loop stops, as visible text
- Fixed `/ultrareview` failing to upload the working tree when started from a git worktree that the Claude desktop app created on macOS or Linux
- Fixed sandboxed Bash commands failing to start on Linux when the working directory is write-denied and contains a read-denied directory
- Fixed artifact database write results telling Claude that every viewer sees a write to a viewer's private `data/users/` subtree, and added a "view" level to `as_level`
- Fixed the Claude apps gateway answering `431 Request Header Fields Too Large` to every request from a sign-in whose identity provider lists many groups; it now accepts request headers up to 256 KiB
- Improved the usage-limit wait: the limit's state and the countdown with the usage-credits option now show as one block under the prompt, and limit messages no longer repeat the countdown
- Improved the "No such tool available" error for Claude in Chrome tools called without their prefix: it now names the tool to call
- Improved Monitor event rows to show what each event printed instead of repeating the description, and stopped repeating an unchanged "Waiting for N … to finish" line after every event
- Improved Workflow tool sandbox hardening for errors thrown by async script hooks
- Improved startup time and memory use by building only the parts of the settings schema that your settings files actually use
- Improved `/claude-api`: `hillclimb` no longer spends rounds on prompt rewordings too small for the eval to measure, and an extra page you ask for beside `report.html` is built as one local file that loads nothing from the network
- Improved lists such as `/tasks`, `/copy` and `/hooks`: the details after each name now line up in one column when they fit, and otherwise sit at the right edge
- Improved `claude plugin marketplace add` to say when it replaces a marketplace already added under the same name from a different source, and how to undo it
- Improved the startup refusal when managed settings require a sign-in (`forceLoginMethod` or `forceLoginOrgUUID`) and an API key, token or `apiKeyHelper` is configured: it now names the credential in use, where it is set, and how to remove it
- Improved auto-memory loading: invisible characters and tags that imitate Claude Code's own markup are neutralized in `MEMORY.md` and recalled memory notes before they reach Claude
- Improved `claude remote-control`: in a folder you haven't trusted yet, it now asks for workspace trust on the terminal instead of exiting
- Improved artifact pages: Claude writes its design plan into the page instead of the reply, and uses the name you already gave something as the page title
- Improved the Artifact tool so that when Claude is given a claude.ai chat or project link, an artifact from a chat, or an artifact id on its own, it asks for the right link or the content instead of stopping
- Changed interactive terminal and VS Code sessions to start in auto mode when no permission mode is configured, on every plan and provider; `permissions.defaultMode` still overrides it
- Changed Ultracode into its own toggle in `/effort` (Tab, or `/effort ultracode [on|off]`): it no longer forces xhigh effort and stays on at any effort level
- Changed retries after a dropped connection mid-response to share one budget with the rest of the request's retries, so a failing request gives up sooner
- Changed the notice shown when a Sonnet model's safeguards flag a message to explain why it happened and to offer editing and retrying
- Changed safety-related model switches in sessions that pin an Opus model with `ANTHROPIC_DEFAULT_OPUS_MODEL` or `modelOverrides`: on the Anthropic API, the API now picks the model to switch to for each kind of flag, not the pinned model
- Changed the non-interactive first turn to still wait up to 2s for connecting MCP servers named by `--allowedTools` or an `mcp_tool` hook, even when `CLAUDE_CODE_MCP_STARTUP_WAIT_MS` is `0`
- Changed `/recap` to decline with a short notice when it arrives relayed from a chat thread (your own included) or from a routine

these notes continue in the original release.

## New Features

- Configure copy-on-select and right-click paste in the fullscreen TUI. Copied transcript selections now preserve Markdown formatting. (#47639, #47896, #48118)
- Connect to MCP servers that require pre-registered OAuth client secrets, including through `codex mcp add --oauth-client-secret`. (#47891)
- Secure direct exec-server WebSocket connections with bearer tokens, including connections configured through app-server. (#47601, #47648)
- Image generation and editing can explicitly request transparent backgrounds, and edits now accept file-backed conversation images. (#47484, #47956)
- Terminal input approval is enabled by default for commands running with elevated permissions; runtime-only grants no longer cause unnecessary reviews. (#47799, #48073)

## Bug Fixes

- Fixed Windows sandbox failures involving ordinary Windows 10 paths, rejected stored credentials, and large permission policies. (#47672, #47695, #47919)
- Fixed Linux sandbox startup with nested writable roots and preserved Git metadata protections across writable roots on Linux and macOS. (#47623, #47974)
- macOS patch operations now recognize system path aliases covered by existing permissions, avoiding unnecessary approval prompts. (#47879)
- Approval reviews now retry when new user input arrives, so a status question does not automatically abort a pending action. (#47819)
- Mermaid flowcharts now render quoted labels and ampersands; unsupported diagrams explain why they fall back to source. (#47572, #47678)
- Command completion events now include early output and report process-launch failures to clients. (#47529, #47665)

## Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.157.0...rust-v0.158.0

- #47441 Use secondary text styling for the transcript footer shortcut hint @etraut-openai
- #47447 Extract WebSocket authentication into `codex-websocket-auth` @euroelessar
- #47458 Parallelize instruction refresh and tool preparation @hlevy-openai
- #47484 Add explicit background control to image generation @alicec-oai
- #47520 Route session agent operations through `AgentControl` @jif-oai
- #47529 Emit command lifecycle events for unified exec launch failures @steipete-oai
- #47536 Route agent lookups and V2 context through `AgentControl` @jif-oai
- #47539 Test interrupted one-shot command launch failure persistence @jif-oai
- #47540 Add an option to disable multi-agent v2 direct messaging @jif-oai
- #47565 Classify rollout read failures by reason and progress @jif-oai
- #47568 Record sandbox backends in command execution analytics @iceweasel-oai
- #47571 Wait for idle before injecting remote compaction test history @felixxia-oai
- #47572 Explain Mermaid rendering fallbacks in the TUI @etraut-openai
- #47582 Retain assistant context for Guardian authorization reviews @felixxia-oai
- #47584 Preserve streamed assistant message order in retained context @felixxia-oai
- #47585 Preserve delivered assistant messages in Guardian retained context @felixxia-oai
- #47589 Keep unfinished link destinations out of rich streaming previews @etraut-openai
- #47590 Serialize numeric custom reasoning effort as JSON numbers @dylan-hurd-oai
- #47591 Stream daemon executable hashing off the async runtime @etraut-openai
- #47596 Refresh realtime context for each model request @reia-oai
- #47597 Guard prerelease channel and canary updates against older versions @imac-oai
- #47601 Add opt-in WebSocket authentication to exec-server @euroelessar
- #47603 Add a reap-only drop policy for child processes @charliemarsh-oai
- #47604 Extend child commands with session and descriptor controls @charliemarsh-oai
- #47605 Route pipe processes through the shared child launcher @charliemarsh-oai
- #47610 Use native POSIX spawning for command hooks @charliemarsh-oai
- #47611 Use the shared process launcher for Unix shell snapshots @charliemarsh-oai
- #47612 Launch Linux pipe processes through a fresh setup helper @freeqaz-openai
- #47613 Expand Linux spawn-helper lifecycle test coverage @charliemarsh-oai
- #47617 Route Linux PTY launches through the process setup helper @charliemarsh-oai
- #47618 Prefer Shift-arrow hints for queued messages and questions @imac-oai
- #47619 Add bounded buffering for global operation metrics @celia-oai
- #47620 Add portable project trust lookup APIs @seanh-oai
- #47623 Fix read-only metadata mount ordering for nested writable roots @jif-oai
- #47624 Recognize `user_message` tools in Guardian authorization context @ankushg
- #47625 Allow history and notes without experimental context capability @pmccrary-oai
- #47629 Route V2 child loading through `AgentControl` @jif-oai
- #47630 Bind Guardian reviews to the action's target environment @jif-oai
- #47633 Route message board agent resolution through the selected controller @jif-oai
- #47635 Overlap startup WebSocket preconnect with tool discovery @bromano-oai
- #47638 Classify retryable exec-server preparation errors by type @mtsui-oai
- #47639 Add configurable copy-on-select for transcript selections @fcoury-oai
- #47641 Honor Retry-After and preserve server retry deadlines @anp-oai
- #47642 Add model-specific prefixes to indirect tool descriptions @rhan-oai
- #47647 Apply Guardian computer-use review to the Browser connector @johnl-oai
- #47648 Support bearer tokens for app-server executor connections @euroelessar
- #47649 Add opt-in OTLP logging for final agent responses @xli-oai
- #47653 Attach inherited rollout history to diagnostic reports @dkovalenko-oai
- #47654 Make Linux descriptor cleanup fork-safe @yuzhu-oai
- #47655 Bump the exec-server stable compatibility test to Codex 0.156.1 @imac-oai
- #47657 Restrict the default Bedrock GovCloud model catalog @jackz100
- #47662 Expose tool dispatch and timing observations to extensions @euroelessar
- #47663 Preserve managed network policy in route-aware transports @jackz100
- #47665 Preserve early unified exec output in completion events @sdcoffey
- #47670 Support model-specific descriptions for agent message board tools @eknight-oai
- #47672 Fix no-reparse directory opens on Windows 10 @zm-oai
- #47673 Clarify registered Windows sandbox setup errors @zm-oai
- #47677 Support model catalog overrides for MCP resource tool specs @rhan-oai
- #47678 Support quoted labels and ampersands in Mermaid flowcharts @etraut-openai
- #47679 Add extension hooks for model requests and response streams @euroelessar
- #47680 Add exec-server RPC timing and process startup tracing @anp-oai
- #47683 Add executor capability discovery V2 infrastructure @TAFOYA-OAI
- #47686 Make thread-owned Guardian context always enabled @felixxia-oai
- #47688 Remove legacy Guardian authorization evidence paths @felixxia-oai
- #47689 Make Guardian thread context capture unconditional @felixxia-oai
- #47690 Remove obsolete Guardian context capture mode branches @felixxia-oai
- #47691 Materialize rollout persistence for pending inter-agent messages @dermanyang-oai
- #47693 Configure curl retries for DotSlash installation in CI @anp-oai
- #47695 Repair rejected Windows sandbox credentials during provisioning @zm-oai
- #47696 Avoid the shutdown timeout in the lagged-event test @jgershen-oai
- #47698 Allow WebSocket test server shutdown while waiting for requests @jgershen-oai
- #47701 Allow idle threads to prewarm and repair WebSocket connections @vkg-oai
- #47703 Preserve account network policy for ChatGPT backend requests @jackz100
- #47704 Fix spawn flag typing and isolate project configuration tests @seanh-oai
- #47709 Route resume prewarm through the cached WebSocket session @vkg-oai
- #47712 Update unified exec output buffers atomically @sdcoffey
- #47713 Reduce dependency coupling in shared configuration crates @aibrahim-oai
- #47714 Preserve tool result metadata more selectively under size limits @ningyi-oai
- #47717 Avoid recursive TUI event dispatch for model picker selections @etraut-openai
- #47741 Attribute tool telemetry to the invoking turn's product SKU @rennie-openai
- #47742 Honor network policy in history notes and image generation extensions @jackz100
- #47745 Skip startup prewarm preparation when the WebSocket is ready @vkg-oai
- #47748 Align Cargo and Bazel Rust debug information defaults @aibrahim-oai
- #47751 Reduce generic code duplication in RPC and Markdown rendering @aibrahim-oai
- #47755 Centralize typed app-server response decoding @aibrahim-oai
- #47757 Refactor tool telemetry product SKU matching to use an allowlist @rennie-openai
- #47758 Preserve more tool metadata within outgoing message budgets @ningyi-oai
- #47773 Honor catalog schemas for asynchronous user input @rhan-oai
- #47797 Support close-on-exec attachments without changing PTY semantics @jif-oai
- #47799 Enable terminal input approval by default @jif-oai
- #47808 Allow hosts to provide agent controllers through ThreadManager @jif-oai
- #47811 Preserve explicit user goal updates in Guardian authorization @felixxia-oai
- #47813 Fix sleep interruption test event handling and fixture lifetime @felixxia-oai
- #47814 Fix a lost wakeup in the unified exec termination test @felixxia-oai
- #47817 Stabilize thread resume and memory dual-write tests @jif-oai
- #47819 Retry Guardian reviews when authorization changes @teddywyly-oai
- #47820 Add integration coverage for host agent controllers @jif-oai
- #47824 Allow four concurrent threads in the multi-agent resume test @felixxia-oai
- #47828 Wait for login completion in recommended plugin tests @felixxia-oai
- #47830 Bind Guardian async scores to target environment permissions @jif-oai
- #47832 Stabilize Rosetta test timing and retry delay telemetry @jif-oai
- #47847 Keep the TUI responsive during clipboard copies @fcoury-oai
- #47851 Preserve human overrides across repeated heartbeat instructions @felixxia-oai
- #47852 Avoid blocking async proxy resolution on the system proxy cache @jif-oai
- #47856 Initialize media estimates outside the global cache lock @jif-oai
- #47858 Validate loaded plugins outside the cache lock @jif-oai
- #47861 Avoid nested read locking when rendering browser sign-in @jif-oai
- #47867 Render remote permission paths using executor context @iceweasel-oai
- #47870 Add opt-in OTLP logging for Guardian assessments @jif-oai
- #47871 Fix PID reservation test race and update guardian heartbeat snapshot @jif-oai
- #47873 Measure deferred tool namespace fragments before and after truncation @mzeng-openai
- #47879 Fix macOS system-alias matching in patch permission checks @felixxia-oai
- #47881 Use Tokio's clock for TUI paste timing @charliemarsh-oai
- #47886 Preserve diagnostic logs when SQLite logging fails @dkovalenko-oai
- #47887 Warn users when SQLite diagnostic log writes fail @dkovalenko-oai
- #47889 Include TUI client logs in diagnostic uploads @etraut-openai
- #47891 Support client secrets for pre-registered MCP OAuth clients @willwang-openai
- #47894 Clean up temporary Codex homes after TUI tests @fcoury-oai
- #47896 Preserve Markdown formatting when copying transcript selections @fcoury-oai
- #47898 Preserve local-binding inheritance in environment network policies @seanh-oai
- #47899 Add diagnostic reasons to MCP attribution errors @peilin-openai
- #47900 Default local threads to paginated history @owenlin0
- #47901 Add bounded credential-storage telemetry helpers @celia-oai
- #47902 Avoid repeated table clones during config merging @imac-oai
- #47903 Move config key alias normalization ahead of merging @imac-oai
- #47904 Support nested canonical paths in config key aliases @imac-oai
- #47908 Alias `tui.whimsy` to `tui.effects.starfield` @imac-oai
- #47912 Fix attestation routing during thread startup @charliemarsh-oai
- #47913 Add an opt-in flag to defer mailbox preemption @jif-oai
- #47915 Reuse verified V8 checksum manifests from the artifact cache @aibrahim-oai
- #47918 Parameterize the turn-start origin

these notes continue in the original release.

## Chores

- Release highlights could not be determined: the supplied PR index is empty, and the GitHub tag comparison returned 404.

## Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.157.0...rust-v0.157.1

- Added `x-claude-code-prompt-id` to the gateway hint headers so LLM gateways can group the requests that serve one user prompt; opt in with `CLAUDE_CODE_GATEWAY_HINT_HEADERS=1`
- Added `availableModelsMatch` managed setting: with `"exact"`, an `availableModels` entry allows only the model version it names, so new releases stay blocked until listed
- Added `deniedModels` managed setting to block specific models, even when `availableModels` allows them
- Added MCP tool, WebFetch and WebSearch outputs to the `tool.output` OpenTelemetry span event when `OTEL_LOG_TOOL_CONTENT=1`
- Added `/doctor prompt-audit` (also `/checkup prompt-audit`) to audit your CLAUDE.md files, skills, agents and commands for prompting patterns written for older models
- Added click-to-expand for truncated messages from your other sessions in fullscreen mode
- Added `path` to `--plugin-dir` load-failure entries in the stream-json `system/init` `plugin_errors`, naming the directory that did not load
- Added an opt-in `load_test_mode` block to the Claude apps gateway config: requests are built and signed but not sent upstream, and clients get a canned reply, so a deployment can be load tested
- Added a `mantle` upstream provider to the Claude apps gateway for Amazon Bedrock's Mantle endpoint
- Fixed SDK sessions losing a deferred tool call or finished tool result when a turn ended early, a held approval prompt after a worker restart, and a non-streaming fallback's `result.usage`
- Fixed MCP progress notifications being discarded once a long-running tool call moved to the background; the background task now shows the latest progress
- Fixed stdio MCP servers being left running when the session ended while they were still starting
- Fixed a brief HTTP 404 from a stateless remote MCP server (for example a proxy mid-redeploy) leaving that server unusable for the rest of the session while still shown as connected
- Fixed MCP sign-in for a server with no valid URL failing with an opaque SDK error; `/mcp` no longer offers Authenticate for such servers
- Fixed the weekly Fable limit not appearing in `/usage` and the VS Code usage meters when telemetry is disabled
- Fixed `/model` accepting Sonnet 4.6 or Sonnet 5 with `[1m]` when the id carried a date or `-v1:0` suffix, in the cases where the plain id was refused
- Fixed `/model` picker showing a hardcoded Haiku version and price when `ANTHROPIC_DEFAULT_HAIKU_MODEL` pins a different model
- Fixed dynamic workflows started during a model fallback running every agent on the fallback model instead of retrying the configured model
- Fixed `DISABLE_PROMPT_CACHING_HAIKU` having no effect when Haiku is the session's main model
- Fixed `claude plugin validate` saying Claude Code accepts a plugin or marketplace name it cannot install; such names in `marketplace.json` now fail validation
- Fixed `claude plugin validate` passing plugins whose `outputStyles`, `themes`, `monitors`, or `lspServers` paths are missing or point outside the plugin directory
- Fixed `claude plugin details` showing 0 MCP servers for plugins that declare their servers in `plugin.json`
- Fixed `claude plugin marketplace remove` not saying which installed plugins it uninstalled with the marketplace; it now lists them
- Fixed `claude plugin uninstall` removing the other of two installed plugins whose ids differ only in case, with its options and secrets, when the one named had no `enabledPlugins` entry at that scope
- Fixed plugins that declare no version being silently restored at their source's newest commit, not the installed one, when their cached files were missing
- Fixed user-installed plugins and marketplaces failing to load with "cache-miss" after the home or config directory was moved, for example in bind-mounted devcontainers
- Fixed `installed_plugins.json` showing no plugins when it holds a record under an invalid plugin id; such a file loads again
- Fixed `installed_plugins.json` being rewritten, losing records, when it holds a record this version cannot read; `claude plugin` commands now name the record and say how to recover
- Fixed permission dialogs in screen-reader mode reading quoted commands and paths as if they were the dialog's own text
- Fixed `/context` not counting MCP server instructions: they now appear as their own row and count toward the total
- Fixed markdown links in the Warp terminal rendering as plain text instead of clickable hyperlinks
- Fixed `claude mcp add`, `add-json`, and `remove` reporting success when the user or local config file could not be written, for example inside a sandbox
- Fixed the first words of a reply in a cloud session sometimes appearing late instead of streaming as Claude writes them
- Fixed Claude's built-in keybindings guide saying chords time out after 1 second instead of 3, and calling `cmd` an alias of `meta`, which could produce `cmd+` shortcuts most terminals never send
- Fixed `keybindings.json` silently accepting a misspelled modifier such as `ctl+k`; it now warns in the debug log and suggests the fix
- Fixed footer hints still saying "Enter to view" after `footer:openSelected` was rebound or unbound in `keybindings.json`
- Fixed keys typed quickly together (type-ahead, key repeat, bursts over ssh or tmux) sometimes being handled against stale state
- Fixed worktree checkouts failing certificate verification (for example on Git LFS downloads) when the CA certificate is passed to git as `GIT_CONFIG_COUNT` environment pairs
- Fixed sandboxed `git` asking credential helpers to store the sandbox proxy's login, which printed "failed to store"
- Fixed managed `sandbox` settings being ignored entirely when one nested value was invalid; the invalid value now fails closed and the rest of the block still applies
- Fixed Claude's edits to its own auto-memory notes being blocked as sensitive-file writes when Claude Code was started in a subdirectory of a git repository
- Fixed Remote Control being unavailable on paid plans when telemetry is turned off with `DISABLE_TELEMETRY` or `DO_NOT_TRACK`
- Fixed the `/remote-control` menu cutting its QR-code hint mid-word in narrow terminals
- Fixed vim mode `.` dropping a Shift+Enter newline, leaving the cursor inside an accented letter, and repeating an older change after `3J` or Visual-mode `J` on the last line
- Fixed vim mode cursor placement: recalling a prompt over 10,000 characters in normal mode no longer leaves the cursor past the end, and `V` then `p` now lands on the first non-blank
- Fixed vim mode `J` joining lines with different spacing than Vim (such as a space before `)` or after a tab), and `3J` or Visual-mode `J` on the last line not moving the cursor as Vim does
- Windows: Fixed the PowerShell tool letting `cmd /c rd`, `rmdir`, `del` or `erase` delete drive roots, the home folder and other folders that `Remove-Item` refuses
- Improved the `/mcp` tool list: it shows more tools at once, scrolls with the page keys and mouse, and marks tools your organization blocked with a warning icon
- Improved MCP tool results: images returned by MCP tools are now also saved to a file, so Bash, Read and other tools can open them
- Improved `/tasks`: rows show a status icon, the name and whole facts, the title and key hints stay on screen with many tasks, and the list gains paging keys, the mouse wheel and clicks
- Improved lists in `/help`, `/hooks`, `/copy`, `/chrome`, `/memory`, `/ide`, `/release-notes`, `/rewind`, `/diff`, `/remote-env`, `/plugin` and other pickers with page keys, mouse wheel and clicks
- Improved lists beside a search box, such as `/skills` and `/artifacts`, to draw their pointer dim while the search box has the keys, so only one pointer is highlighted
- Improved the compaction spinner: its timer now starts when compaction begins and it counts the summary's tokens as they stream, replacing the percentage bar
- Improved the browser page shown after signing in to an MCP server: centered layout, dark mode, and new artwork
- Improved the Skill tool's reply when a skill belongs to a plugin that failed to load, so Claude tells you the plugin could not be loaded instead of calling the skill uninstalled
- Improved `prompt-audit` on Claude Code configuration: stale paths, stale commands and contradicting instruction files now lead the report, and thinking keywords that Claude Code documents are kept
- Improved recovery from an `installed_plugins.json` that cannot be read at all: its contents are kept in a file beside it before it is rebuilt, and `claude plugin list` names that file
- Improved artifact database reads: an ordered query that returns a full page now says it is one page and how to read the rest
- Improved first-reply latency: a pattern-compile step that ran at the end of a session's first reply now runs while the reply streams in
- Improved first-request latency by reusing the preconnected API connection
- Improved startup: `claude -p` and Claude Code Remote no longer load the interactive UI, and the auto-mode classifier's rules and the Artifact tool load on first use instead of at launch
- Improved startup for claude.ai accounts whose Artifact tool features aren't known yet, as on a first run: the prompt no longer waits up to 1.5 s to check them; the first message waits if needed
- Changed interactive sessions on third-party providers or with telemetry off to start in auto mode when no permission mode is configured; `permissions.defaultMode` still overrides it
- Changed the `/ultrareview` launch dialog to say that reviewing a local branch may upload uncommitted changes to tracked files
- Changed the `/model` picker's Opus row and the Default model's name to drop "(1M context)" where Opus already has a 1M context window; the window is unchanged
- Changed prompt suggestions in the terminal to appear less often after 20 in a row go unused; using one brings them back
- Changed `--system-prompt` and `--append-system-prompt` to accept their text and `-file` forms together; the file's text comes first
- Changed `Skill(anthropic-skills:<name>)` deny rules to also block that skill when Claude Desktop delivers it as a plugin, and `Skill(skill:<name>)` denies to match the skill's alias and display name
- Changed `/rewind` and `/diff` lists to move on the same keybinding actions as every other list (`select:*`); `messageSelector:*`/`diff:*` rebinds still work
- Changed the `/workflows` run list to size itself like other lists: half the terminal inline, and it keeps its title on screen when the prompt shows below
- Changed `claude plugin eval` to require git 2.31 or later when git is installed; a run on an older git is refused with a message naming the version
- Changed artifact watching: a watch that was armed automatically (not one you asked for) now ends after 3.5 hours with no activity; publishing or watching the artifact again re-arms it
- Self-hosted runner: Changed lifecycle hooks' git to skip a repository's Git LFS `pre-push` hook, ignore a writable system `core.hooksPath`, and not sign commits without `--configure-git`
- Self-hosted runner: Changed `GIT_SSL_CAINFO` and `GIT_SSL_NO_VERIFY` under Anthropic-managed git: the runner's own git always verifies Anthropic's git route, and warning lines say what applies where
- Reverted the 2.1.282 reservation of the `claude-ai` name: skills, commands, workflows and MCP servers' skills and prompts so named load again, and `Skill(claude-ai:*)` rules are ordinary prefix rules
- [VSCode] Fixed the permission mode indicator showing Default while the session kept running in auto or bypass mode after an automatic switch out of it failed; the switch is now retried until it lands
- [VSCode] Fixed a session teleported from the web dropping the messages sent while Claude was working
- [VSCode] Fixed a Web session staying hidden from the session list, and an empty chat opening in its place, when an older version had saved an empty local copy of it
- [VSCode] Fixed a reopened session splitting a turn at a message Claude received mid-turn, such as an a

these notes continue in the original release.

## New Features

- Added GPT-6 Sol and Luna, including Amazon Bedrock support and migration prompts for older models. (#47332, #47347)
- Enabled fullscreen transcripts by default and added Shift-click to extend text selections. (#47178, #47414)
- Enabled automatic background-server startup for eligible interactive sessions, with recovery choices when server settings are incompatible. (#47179, #47318)
- Added an `f` shortcut to fork conversations open in another app, preserving drafts and queued prompts. (#47185)
- Made `/import` available in remote sessions and local background-server sessions. (#47317)
- Improved terminal rendering with Unicode bullets, checkboxes, aligned equations, and optimization notation. (#47191, #47322)

## Bug Fixes

- Preserved active voice conversations when switching threads. (#47381)
- Recovered unsent question answers into the composer when turns end, without disrupting active history searches. (#47422, #47423)
- Respected tmux mouse settings and restored native scrollback for Terminal.app over SSH in automatic screen mode. (#47399, #47417)
- Fixed configured proxy routing for realtime connections and standalone web search, including search redirects. (#47101, #47142, #47204)
- Added retries for transient file-upload failures and increased the upload timeout to five minutes. (#47122, #47393)
- Enforced network restrictions across redirects and ongoing HTTP and WebSocket traffic, including cancellation when policy changes revoke access. (#47389, #47407)

## Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.156.0...rust-v0.157.0

- #47063 Add a partial index for agent message board root posts @jif-oai
- #47064 Stop redundant message-board reads when limits reach one @jif-oai
- #47065 Deduplicate deprecation notices in the TUI transcript @etraut-openai
- #47068 Highlight selected newlines in the transcript view @etraut-openai
- #47073 Wait for thread idle in Guardian context budget tests @jif-oai
- #47074 Refresh host-supplied cloud skills at turn startup @TAFOYA-OAI
- #47075 Include attributed previews in agent message board notifications @jif-oai
- #47077 Serialize environment updates and cancel removed pending attachments @sayan-oai
- #47079 Mask daemon socket paths exposed through ancestor bind mounts @nicksteele-oai
- #47081 Track cumulative MCP attribution across requests and thread history @peilin-openai
- #47082 Show the voice toggle in the TUI shortcut overlay @etraut-openai
- #47083 Extract per-thread enrichment into a dedicated async helper @aibrahim-oai
- #47084 Avoid building a host SQLite driver for SQLx macros @aibrahim-oai
- #47085 Update model catalog descriptions and GPT-5.6-Sol priority @andrewgu-oai
- #47086 Format analytics credit usage with consistent decimal precision @fcoury-oai
- #47088 Disable unused default dependency features @aibrahim-oai
- #47089 Centralize JSON-RPC response serialization through payloads @aibrahim-oai
- #47094 Restrict Unix local MCP servers to stdio descriptors @yuzhu-oai
- #47095 Remove the `rust-release-prepare` workflow @andrewgu-oai
- #47096 Keep TUI hints immediately above the composer @fcoury-oai
- #47100 Preserve assistant answers in bounded TUI task responses @etraut-openai
- #47101 Honor configured proxies for realtime WebSocket connections @celia-oai
- #47106 Preserve originating turn metadata for yielded skill calls @eddie-openai
- #47108 Preserve required Windows runtime variables for filesystem helpers @iceweasel-oai
- #47112 Lowercase the retry hint for conversations open in another app @fcoury-oai
- #47113 Persist thread creator identity in rollouts and SQLite @nornagon-openai
- #47114 Preserve and expose thread item lifecycle timestamps @chiam-oai
- #47116 Honor the configured product SKU in remote plugin requests @jessedu-oai
- #47118 Support model-catalog overrides for Code Mode tool messages @rhan-oai
- #47121 Pass thread IDs to attachment uploads @kchainani-oai
- #47122 Increase OpenAI file blob upload timeout from 60 seconds to 5 minutes @wilkes-oai
- #47125 Add extra policy configuration for Guardian reviews @won-openai
- #47129 Preserve foreign working directories in extension tool environments @anp-oai
- #47130 Remove the `ultrafast` service tier from `gpt-5.6-sol` @andrewgu-oai
- #47132 Support caller-provided MITM CAs in the network proxy @viyatb-oai
- #47137 Prevent horizontal transcript selection from triggering autoscroll @imac-oai
- #47142 Honor system proxy settings for standalone web search @celia-oai
- #47143 Extract exec-server CLI startup into a dedicated module @anp-oai
- #47149 Update code mode catalog snapshot hashes @andrewgu-oai
- #47155 Ignore stale thread-close notifications after resuming a thread @etraut-openai
- #47158 Harden gateway OAuth credential persistence and error redaction @alexsong-oai
- #47159 Expose HTTP origins in MCP server status @frantic-openai
- #47162 Apply workspace routing to Guardian v2 classifier requests @acrognale-oai
- #47170 Add explicit gateway login control and authentication status @alexsong-oai
- #47174 Preserve empty cell metadata under pending tool-call pressure @ningyi-oai
- #47178 Enable the fullscreen transcript by default @etraut-openai
- #47179 Enable automatic daemon startup by default @etraut-openai
- #47185 Allow forking conversations locked by another app in the TUI @fcoury-oai
- #47191 Render aligned equations and optimization notation in TUI math @etraut-openai
- #47199 Separate thread preparation from execution persistence @dermanyang-oai
- #47204 Resolve proxy routes for standalone web search redirects @celia-oai
- #47207 Add explicit gateway OAuth sign-in to app-server @alexsong-oai
- #47212 Preserve MCP request trace context across transport workers @bromano-oai
- #47235 Route multi-agent spawning through `SpawnRequest` @jif-oai
- #47236 Suppress agent message board notifications to the post author @jif-oai
- #47240 Prevent V2 agent eviction from racing with queued messages @jif-oai
- #47244 Centralize agent resume handling in `LocalAgentControl` @jif-oai
- #47248 Add explicit app and account targets to MCP resource reads @victor-openai
- #47249 Drop descendant channel posts from retained remote compaction v2 history @jif-oai
- #47252 Return agent snapshots from `close_agent` @jif-oai
- #47257 Preserve explicit message-board unsubscribes when posting @jif-oai
- #47258 Test spawn settings reporting after child removal @jif-oai
- #47259 Subscribe authors to message-board channels created by posting @jif-oai
- #47263 Expose hosted plugin extensions in app-server summaries @victor-openai
- #47267 Stream agent snapshots from local status subscriptions @jif-oai
- #47271 Implement `AgentControl` for `LocalAgentControl` @jif-oai
- #47272 Allow Guardian sync review across compaction hash differences @felixxia-oai
- #47275 Enable Guardian thread context by default @felixxia-oai
- #47281 Add regression coverage for message board unsubscribe persistence @jif-oai
- #47287 Update the Guardian extra-policy snapshot for retained instructions @felixxia-oai
- #47292 Consolidate agent operations in the `AgentControl` implementation @jif-oai
- #47301 Separate local agent runtime state from controller handles @jif-oai
- #47302 Use compact display metadata for Guardian review threads @charliemarsh-oai
- #47303 Clean up legacy Guardian thread metadata in SQLite @charliemarsh-oai
- #47317 Enable `/import` in remote and local daemon sessions @etraut-openai
- #47318 Offer explicit recovery for incompatible background servers @etraut-openai
- #47319 Match agent status symbols to the selected row style @etraut-openai
- #47320 Fix Escape navigation in read-only agent sessions @etraut-openai
- #47321 Honor the system clock preference across more TUI timestamps @etraut-openai
- #47322 Render TUI Markdown lists with Unicode bullets and checkboxes @etraut-openai
- #47323 Persist resume metadata in compaction checkpoints @owenlin0
- #47325 Keep report reason tags within Sentry limits @ningyi-oai
- #47326 Restrict MCP OAuth authorization endpoints to HTTP(S) @viyatb-oai
- #47327 Preserve image generation request IDs on failure @chrisdong-oai
- #47329 Standardize TUI menu description wording and punctuation @etraut-openai
- #47330 Identify failed SQLite databases in `codex doctor` output @dkovalenko-oai
- #47331 Avoid redundant spacing above the transcript composer @fcoury-oai
- #47332 Add GPT-6 Sol and Luna to the model catalog @andrewgu-oai
- #47338 Move the activity inspection hint into keyboard shortcut help @fcoury-oai
- #47340 Add conditional turn interruption that preserves pending input @pmccrary-oai
- #47342 Skip stored title lookups for ephemeral forks @keyz
- #47347 Add GPT-6 Sol and Luna to Amazon Bedrock catalogs @celia-oai
- #47348 Overlap subagent spawn persistence and clean up cancelled children @owenlin0
- #47349 Move plugin recommendations into developer context @adaley-openai
- #47350 Reuse cloud skill catalogs across turns until invalidated @hlevy-openai
- #47353 Preserve `invalid_prompt` as a distinct error classification @rennie-openai
- #47355 Reserve spacing after recaps at the transcript tail @fcoury-oai
- #47358 Color paths and URLs in `codex doctor` by check status @dkovalenko-oai
- #47360 Preserve user prompt URL destinations across terminal widths @fcoury-oai
- #47361 Restrict Windows sandbox default object access to the logon session @viyatb-oai
- #47362 Bound inbound exec-server requests across client transports @viyatb-oai
- #47365 Resume model context from the latest compaction boundary @owenlin0
- #47369 Overlap agent metadata reads when resuming a V2 root @vkg-oai
- #47375 Add an opt-in preference for the local MXC sandbox @iceweasel-oai
- #47377 Add opt-in reasoning status for realtime V3 delegations @guinness-oai
- #47380 Route TUI voice controls through the app @etraut-openai
- #47381 Keep voice conversations running across TUI thread navigation @etraut-openai
- #47382 Show a voice badge in the agents overview @etraut-openai
- #47384 Restore composer hints after clearing selection at the transcript bottom @fcoury-oai
- #47389 Enforce network policy throughout HTTP and WebSocket requests @acrognale-oai
- #47393 Retry transient OpenAI file blob upload failures @mtsui-oai
- #47397 Refresh bundled model metadata and instructions @andrewgu-oai
- #47399 Respect tmux mouse settings in fullscreen and overlays @fcoury-oai
- #47407 Enforce application network policy across app-server requests @acrognale-oai
- #47408 Enforce application network policy for AWS auth and telemetry @acrognale-oai
- #47410 Honor network policy in remote control and recover remote execution @acrognale-oai
- #47411 Apply shared network policy throughout embedded Codex startup @acrognale-oai
- #47413 Cache decrypted gateway OAuth secrets per backend @charliemarsh-oai
- #47414 Support Shift-click to extend transcript selections @etraut-openai
- #47417 Use native scrollback for Terminal.app over SSH in auto mode @fcoury-oai
- #47422 Recover unsent question drafts when TUI turns end @imac-oai
- #47423 Preserve history search during background draft recovery @imac-oai
- #47424 Clear pending async question notifications when turns end @imac-oai
- #47428 Apply inherited environment settings at turn boundaries @sayan-oai
- #47435 Allow environment selection updates during an active turn @sayan-oai
- #47437 Stabilize retry timing and WebSocket tests @anp-oai

You can now send safety_identifier, an opaque end-user identifier assigned by your application, on Chat Completions, the Responses API, deferred chat completions, the Batch API, and the gRPC GetCompletionsRequest. It lets SpaceXAI attribute a policy violation to one of your end users rather than to your API key. The legacy user field is still accepted. See the Security FAQ.

- Added a `maxProseWidth` setting that caps the width of Claude's prose in wide terminals while tables and code blocks keep the full width
- Added a startup notice, and `/status` and `claude doctor` entries, listing telemetry variables in a project's settings files that were ignored or that turned telemetry off
- Added the `allowClaudeInChromeWithManagedMcp` managed setting to let `claude --chrome` run alongside an exclusive `managed-mcp.json`; the error shown when Chrome is blocked now names it
- Added `store.readiness_grace_seconds` to the Claude apps gateway so `/readyz` can stay ready through a short Postgres outage such as a database failover
- Added a scrollbar to the `/feedback` drafts list in fullscreen mode; it appears while the mouse is over the list
- Fixed every request failing with a 400 error in conversations whose history holds web search results the API cannot decrypt (for example, from a turn answered through a third-party gateway)
- Fixed more cases of continued or resumed sessions (`--continue`, `--resume`) re-sending earlier messages in a changed form, which could make the API drop Claude's earlier reasoning
- Fixed earlier extended thinking being dropped when `/model`, `/rename`, `/artifacts` or another immediate slash command was used while Claude was working
- Fixed continued or resumed conversations losing earlier extended thinking when relaunched with a `--tools` list that leaves out a built-in tool offered earlier in the conversation
- Fixed sessions failing on every turn with an "Invalid `data` in `redacted_thinking` block" API error; Claude Code now drops the conversation's thinking blocks and retries once
- Fixed compaction failing when the summarization request is refused; it now retries on a fallback model
- Fixed a failed turn ("Effort 'xhigh' isn't available with thinking turned off") after a safety-related model switch in sessions with thinking off and effort above high
- Fixed an unanswered Fable usage-credits prompt switching models in SDK-hosted sessions such as Claude Desktop; the turn now ends instead, and Remote Control clients now see the model-switch notice
- Fixed `/model` with a full Fable model id stopping at an API error instead of opening the usage-credits prompt when the plan needs usage credits that aren't turned on yet
- Fixed requests failing for up to a minute with an "another Claude Code process is refreshing it" login error after that other process was closed or killed mid-refresh
- Fixed sessions started while another Claude Code window was refreshing the sign-in (common with several VS Code windows) not retrying their organization policy fetch
- Fixed CLAUDE.md and rules being read at startup through a repository symlink reaching macOS's `/Network` via `..` or a `/.vol`-style kernel path, or a rules link to macOS's `/home` being listed
- Fixed Bash permission rules with a mid-pattern `:*` being skipped in settings files while `--allowedTools` honored them; they now work from every source, with a startup warning on how they match
- Fixed a command approved on a restored permission prompt running twice when a remote session's worker restarted
- Fixed managed settings ignoring a mistyped value for boolean lock keys such as `disableClaudeAiConnectors` or `allowManagedPermissionRulesOnly`; the lock now applies and startup names the key
- Fixed managed `permissions`, `autoMode`, `worktree` and `attribution` settings being ignored entirely when one nested value was invalid; the rest of the block now still applies
- Fixed repository, user and `--add-dir` skills, commands and skills-directory plugin manifests pre-approving their own tools via `allowed-tools` under managed `allowManagedPermissionRulesOnly`
- Fixed safeguard block messages on Amazon Bedrock and Bedrock Mantle not showing a request ID; block messages now also show the message ID
- Vertex AI: Fixed web search not being offered for models Claude Code doesn't recognize yet, such as newly released ones
- Fixed Bash and PowerShell hiding a full disk quota behind "Exit code 1" and leaving large output files in temp
- Fixed tool input validation errors naming only an unknown, missing or mistyped parameter when other parameters in the same call were also invalid; those are now listed too
- Fixed pasted multi-line text being submitted line by line after the terminal's bracketed paste mode was reset mid-session
- Fixed the prompt's example text flashing and disappearing at startup in projects with a `SessionStart` hook
- Fixed a blank screen flashing before the first frame when starting in fullscreen mode
- Fixed garbled, misplaced rows in the non-fullscreen renderer after the screen got shorter while still taller than the terminal, e.g. deleting a prompt line while a shell command streams output
- Fixed a stale character left in the last column of a diff when a redrawn line's CJK character or emoji wrapped to the next row
- Fixed the cursor landing before the end of a prompt recalled from history when the prompt contains a tab
- Fixed the send-now hint showing ctrl+enter on terminals that send it as a newline (Windows Terminal before 1.25); it now shows ctrl+x ctrl+s there
- Fixed `claude remote-control --debug` failing with "Unknown argument: --debug", although Remote Control's own eligibility error says to run with `--debug`
- Fixed `/install-github-app` saying "cancelled" and then still pushing the branch and saving the API key secret; leaving now stops the remaining steps and reports what was already done
- Fixed /feedback, /bug and /share on Bedrock, Vertex and other third-party providers still saving the report file after you cancelled during the save
- Fixed plugin uninstall reporting success and deleting the plugin's saved options when its settings file still enabled it or could not be read; it now stops and names the file
- Fixed plugin uninstall deleting a plugin's saved options and secrets when the list of installed plugins could not be read after the removal; they are now kept and the uninstall says so
- Fixed a key typed right after `/` in `/skills` moving the skill list instead of reaching the search box
- Fixed the terminal cursor jumping from the `/skills` search box to the skill list while typing, which could hide the caret and put IME input in the wrong place
- Fixed lists with a scrollbar, such as `/skills` and `/mcp`, being two columns narrower outside fullscreen mode, where the scrollbar can never appear
- Fixed the agent panel footer wrapping onto two lines with long rebound keys, and its "Esc to collapse" hint ignoring a rebound collapse key
- Fixed a doubled ` · ` separator in the `/tasks` dialog footer when the stop-all-agents shortcut is unbound in `keybindings.json`
- Fixed artifact publishes failing when Claude gave the version a label longer than 60 characters; the label is now shortened
- Fixed screen-reader mode, quoted lists and very long lists dropping the blank lines at the top of a code block that opens a list item, directly or inside a quote
- Fixed PDF page-read error messages: paths with accented or non-Latin characters now appear readably, and a folder named like "password" or "invalid" can no longer make the error name the wrong cause
- Fixed vim mode `>>` indenting empty lines, `r` with a count longer than the line changing text, `2J` joining one line too many, and a count on the last line (`2dd`, `2>>`) shifting or deleting it
- Fixed vim mode cursor placement: after `dd`, `dj`, `dG` or a whole-line `p`/`P` it lands on the first non-blank, `yy` no longer moves it, and Esc after an emoji no longer leaves it inside the emoji
- Fixed vim mode ignoring a count typed before `.` when repeating `x`, `s`, `p`, `d` or `c`, and whole-line `p`/`P`, `o`, `O`, `J`, `>>` and `<<` acting on the wrong line when a line above wraps
- Fixed vim mode leaving the cursor past the end of a prompt recalled from history or pulled back from the queue in normal mode, so `x` did nothing
- Improved the time to resume very large sessions, including ones that were never compacted
- Improved the error shown on Windows when a session can't be resumed because its transcript file could not be read (EBADF): it now names possible causes and what to try
- Improved the Claude Desktop unknown-model error to suggest switching to a different model
- Improved rendering of unusual Unicode in permission prompts
- Improved `/artifacts`: titles line up in one column, details are dropped whole instead of cut mid-word, and the list supports PgUp/PgDn, Home/End, the mouse wheel and clicks
- Updated the `claude-api` skill: pre-output refusal billing now links to the How refusals are billed docs, mid-stream refusals bill at normal rates, and pre-output refusals count against rate limits
- Updated the `claude-api` skill to recommend `ant apply` for keeping Managed Agents resources as version-controlled files
- Changed auto mode to use the server-side classifier by default on a direct Anthropic API connection when telemetry is off (`CLAUDE_CODE_AUTO_MODE_SERVER=0` opts out)
- Changed `sandbox.excludedCommands` to ignore project and local settings entries when managed settings or `--settings` set `allowUnsandboxedCommands: false`, or managed `allowManagedDomainsOnly: true`
- Changed project and local settings to ignore OpenTelemetry variables that turn on export, set its endpoint, or capture content, like `CLAUDE_CODE_ENABLE_TELEMETRY` and `OTEL_LOG_*`
- Changed Windows/WSL managed settings so an admin policy that is present but invalid or unreadable (HKLM, `managed-settings.json`) keeps user-writable HKCU and WSL `/etc/claude-code` from applying
- Changed `Skill(anthropic-skills:*)` and `Skill(claude-ai:*)` allow rules to cover only skills synced from claude.ai, not plugins or other skills that merely use such a name
- Changed skill folders, command files and workflow commands in the `anthropic-skills` or `claude-ai` namespace to no longer load; a plugin so named still loads but yields name ties to synced skills
- Changed MCP servers configured under the name `anthropic-skills` or `claude-ai` to list no skills or prompts (their tools still work); rename the server in your MCP configuration to list them again
- Changed the `ultracode` visuals in `/effort` and the prompt input to plain styling (no ripple, border flourish or keyword glimmer) and removed the dynamic-workflows spinner tip
- Changed the Clawd mascot's feet in the start-up banner to sit under the corners of his body
- [VSCode] Fixed long replies falling behind the stream: the panel no longer re-parses the whole reply on every update
- [VSCode] Fixed the dictation mic button covering the message input's scrollbar when the input is tall enough to scroll
- [VSCode] Fixed Remote Control sessions started on this computer not opening from their Web entry in the session list; they now open the local conversation unless it's running elsewhere
- [VSCode] Fixed an editor tab's sign-in screen hanging silently after the extension host restarts; it now shows the "stopped responding" notice too
- [Cloud sessions] Added Claude GitHub App status to Settings › Connectors › GitHub: whether the app is installed and reachable for your account, plus steps to connect, install or reconnect
- [Cloud sessions] Added "Open repository" and "Open compare page" links to the repository menu of a cloud session whose repository is hosted on a Git server other than GitHub
- [Cloud sessions] Added attaching a repository from a different GitHub owner, such as a fork's upstream, to a running cloud session that already has one, including sessions started from Slack
- [Cloud sessions] Fixed the next run time shown for an hourly routine being 30 minutes off for people in half-hour-offset time zones such as India
- [Cloud sessions] Improved how quickly the Routines page and the sidebar's Scheduled list load for accounts whose past sessions scheduled many check-in reminders
- [Claude Tag] Fixed auto-join channel patterns saved for one workspace in Claude Tag ad

these notes continue in the original release.

- Added Claude apps gateway support for newer Claude Desktop keys in `desktop` policy blocks, including `blockReadsOutsideWorkingDirectories` and `disableBypassPermissionsMode`
- Added `assume_role` on Claude apps gateway Bedrock upstreams: the gateway calls Bedrock as an IAM role it assumes through STS, in another AWS account if needed, optionally one session per developer
- Added `guardrail: {id, version}` on Claude apps gateway Bedrock upstreams to apply an Amazon Bedrock guardrail to every request sent through them (set it on all Bedrock upstreams or none)
- Added `telemetry.resource_attributes` to the Claude apps gateway config, to put fixed labels on the telemetry of Claude Desktop and `/login` sessions
- Added `"attribution": false` in `settings.json` to hide all commit and PR attribution; older CLI versions skip a settings file that holds it, so keep the object form in files shared across versions
- Added MCP URL-mode elicitation on 2026-07-28 protocol connections, so servers can ask Claude Code to open a browser-based flow; no waiting dialog is left on screen when the server has no way to confirm completion
- Added MCP server checks to `claude plugin validate`: it reports `.mcp.json` entries that would be silently dropped at load, undeclared `${user_config.*}` references, and insecure URLs
- Added an auto mode recommendation to `/insights` that estimates how many permission prompts auto mode could have handled in your recent sessions
- Added a scrollbar to the `/skills`, `/mcp` and `/plugin` Installed lists in fullscreen mode, like the one `/workflows` now has: it appears while the mouse is over the list and can be clicked or dragged
- Fixed a crash ("unrecoverable interface error") that could end a session while an API request was being retried
- Fixed a turn that could retry indefinitely, ignoring `--max-turns`, when the model alternated unparseable tool calls and output-limit truncation
- Fixed resumed sessions re-sending earlier turns in a changed form (a parallel tool-call turn, an MCP tool call's input or a tool-search result while its server was still reconnecting, or a tool-search result whose loading turn was interrupted), which could make the API drop the conversation's prior reasoning
- Fixed resuming a very large session sometimes restoring only its last few messages
- Fixed a session resumed after a restart during a pending permission prompt sending a different history than before, which broke the prompt cache from that point
- Fixed resuming a session that ended during a tool call: Claude now sees the call and is told its outcome is unknown, and a manual resume no longer adds a hidden "Continue" message
- Fixed sessions with an earlier advisor result the API could no longer read failing one request every turn and repeatedly losing earlier reasoning; the history is now repaired once
- Fixed the prompt cache being lost when an MCP server disconnects mid-conversation, or is still connecting after a resume, while tool search is off (for example behind a proxy or gateway)
- Fixed responses cut short by a proxy or gateway that closes the stream cleanly being shown as complete with no warning, and tool calls running twice on duplicated stream events
- Fixed responses failing with "Content block not found" when a proxy drops a stream event mid-response; the partial response is now kept, and web search keeps results that already arrived
- Fixed an empty completed response being requested twice when the connection dropped before the stream's final event
- Fixed the stop reason being lost when a proxy sends a trailing usage-only frame
- Fixed `CLAUDE_CODE_RETRY_WATCHDOG` sessions failing on the first 5xx or dropped connection after a run of 429/529 waits, and sleeping uncapped and silently on a long `Retry-After` from a 5xx
- Fixed fast mode retrying rate-limited requests back to back when the server sent `Retry-After: 0`
- Fixed a tool that returned an oversized image leaving sibling tool calls unanswered and still running, or ending the turn with no final message
- Fixed conversations getting permanently stuck on "tool_use.name: String should have at most 200 characters" after the model called a tool by an overlong name
- Fixed tool calls failing with "Failed to get memory usage", or being reported as failed after they ran, when Claude Code cannot read its own memory usage, for example when it has run out of file descriptors
- Fixed `--input-format stream-json` sessions (Agent SDK, VS Code extension) and scheduled cloud sessions failing every turn with an error when an earlier assistant message had plain-string content
- Fixed non-interactive sessions (`-p`, Agent SDK) failing on the next turn after the directory they were started in was deleted mid-session
- Fixed headless sessions with host-side (SDK) MCP servers stalling on the first message when the host stops responding mid-handshake; remote sessions now wait a few seconds at most
- Fixed interactive startup waiting on the managed-settings network request (about 80 ms, 17+ seconds when the network is unreachable) when no MCP servers or plugins are configured
- Fixed a delay of up to two minutes before responding when reading or @-mentioning a PDF larger than 3 MB
- Fixed an interrupted Read of specific PDF pages leaving its page render running for up to two minutes
- Fixed permission dialogs and attachment checks reading a path under macOS's `/.vol`, `/.nofollow` or `/.resolve` (which can reach a network mount) before approval
- Fixed a recursive `rm` whose target is only command-substitution output, such as `rm -rf "$(pwd)"`, running unprompted in auto and `--dangerously-skip-permissions` mode; it now asks even with a Bash allow rule, unless run with `CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT=1`
- Fixed a permission rule containing a NUL byte being expanded into a wildcard match; such a rule now matches nothing
- Fixed sandbox `excludedCommands` entries not matching `git rev-parse --git-dir`, programs named like shell builtins, and commit messages containing `[WIP]` or `#` lines
- Fixed sandboxed Bash commands being unable to write to `$TMPDIR` when `CLAUDE_CODE_TMPDIR` is set
- Fixed `claude --bg` starting a background session, and running its project hooks, in a directory that had not passed the workspace trust prompt; it now asks for trust first, or exits when not run interactively
- Fixed `--setting-sources` (and SDK `settingSources`) not being forwarded to spawned sessions: teammates, `/bg`, `claude agents` sessions and `--worktree --tmux` now start with the parent's restriction
- Fixed Read, Write, Edit and NotebookEdit: a file path containing a null byte now fails that tool call with a clear error instead of ending the whole turn
- Fixed Write refusing a call that gives the file path or content twice under two parameter names with identical values
- Fixed CLAUDE.md and rules files from an `--add-dir` directory inside the working directory being sent to the model twice in headless and SDK sessions
- Fixed remote sessions staying on "needs approval" with a stale prompt after a permission prompt and a sandbox network-access prompt overlapped and both were answered
- Fixed cloud sessions not telling Claude about background agents that finished just before a worker restart
- Fixed scheduled routine and notification turns in remote sessions not receiving turn-start notices (newly available tools, MCP changes, date, todos) until after the first tool call
- Fixed scheduled tasks and `/loop` wakeups being fired again every second when their delivery failed, which could make Claude Code exit at the end of a turn
- Fixed Remote Control reporting "disabled by your organization's policy" when the org policy simply hadn't loaded yet; it now retries the fetch and says it couldn't verify
- Fixed the Artifact tool missing from Remote Control sessions that `claude remote-control` starts for you to open from Claude Desktop, claude.ai or the mobile app
- Fixed macOS credential writes dropping stored MCP OAuth tokens or deleting the keychain entry when the login keychain was locked (e.g. right after wake)
- Fixed `gcpAuthRefresh`/`awsAuthRefresh` login processes being left running (and holding their localhost callback port on Windows) when Claude Code exits or the refresh times out
- Fixed the "Not logged in · Run /login" footer and missing claude.ai connectors persisting in a session after logging in from another Claude Code process
- Fixed `mcp_tool` hooks on blocking events (PreToolUse and similar) being skipped while their MCP server was still connecting; they now wait for it, up to the MCP connect timeout
- Fixed the same MCP server being connected twice when a plugin or claude.ai connector and a configured server spell its URL differently (host letter case, default port, trailing slash)
- Fixed `MCP_CONNECTION_NONBLOCKING=0` giving up on claude.ai connectors after 1s instead of honoring `MCP_CONNECT_TIMEOUT_MS`
- Fixed `--channels` plugin entries being checked against the installed plugin's marketplace alone; the installed plugin's name must now match the entry as well
- Fixed `--plugin-dir` on a folder of plugins that also has a `.claude-plugin/marketplace.json` loading one empty plugin instead of the plugins in it
- Fixed `claude plugin uninstall` refusing to remove a project-scope plugin that isn't enabled, saying it is "enabled at project scope" while `claude plugin disable` says it is already disabled
- Fixed `claude plugin update` failing for project-scoped plugins when `--scope` is omitted — it now resolves the scope the plugin is installed at instead of assuming user
- Fixed `claude plugin validate` reporting `privacyPolicyUrl`, `supportUrl` and other listing metadata keys in plugin.json as unknown fields
- Fixed `known_marketplaces.json` recording a marketplace as refreshed when its remote could not be reached and `CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE` kept the existing clone
- Fixed the `/plugin` Errors tab showing no confirmation after its last error is resolved
- Fixed `/plugin` starting a second uninstall or update of the same plugin when Enter was pressed again while the first was still running
- Fixed a `y` held while `/plugin` checks a marketplace source adding the marketplace the instant the "Add marketplace?" question appears, before it can be read
- Fixed `1` answering Yes in `/permissions`' delete and remove-directory confirms while the pointer is on No, which let a held `1` remove one workspace directory after another
- Fixed Alt+T and `/config` offering to turn thinking off on models that can't; thinking now stays on there, with a one-line reason in place of the switch
- Fixed `/context` total leaving out messages added since the last response; it now matches its categories and can read higher than the status line
- Fixed `/model` showing the raw API error JSON and request ID when the API refuses the picked model; it now shows the server's message and says the model was not changed
- Fixed API errors from an HTML error page (such as a proxy's 429 or 502 page) printing the page's raw markup or leaving out the HTTP status, and error messages breaking onto a second line when the server's error text ended in a newline
- Fixed /feedback, /bug and /share still sending your report after you cancelled it while it was being sent
- Fixed /feedback, /bug and /share failing every send with "Couldn't send feedback" after a Remote Control Stop arrived while the dialog was open
- Fixed `/ide` showing "No available IDEs detected" while also listing a running IDE
- Fixed the terminal being left in a broken state (crash or garbled input) when `/setup-bedrock` or `/setup-vertex` restarts Claude Code to apply new settings
- Fixed `/config` exiting when `respectGitignore` or `copyFullResponse` in `~/.claude.json` holds `null`
- Fixed the session name from /rename disappearing while Claude asks a multiple-choice question, so side-by-side sessions stay identifiable
- Fixed one-line pastes showing o

these notes continue in the original release.

## New Features

- Choose GPT-6 Sol or GPT-6 Luna from the model picker. The rate-limit switch prompt now recommends GPT-6 Luna. (#47405)

## Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.156.0...rust-v0.156.1

- #47405 [hotfix 0.156.0] Add GPT-6 Sol and Luna to the model catalog (#47332) @imac-oai

## New Features

- Choose an optional fullscreen UI with `/tui` for your next launch, including transcript search, mouse selection, and right-click copying. (#46732, #46734, #46883, #46895)
- Voice conversations are enabled by default, with an F8 toggle, a `/voice settings` picker, and bundled audio runtimes for Linux and Windows. (#44921, #46071, #44622, #44714, #44922)
- Explore account usage, token totals, and plugin and skill activity through the `/usage` analytics dashboard. (#45764, #45769)
- Filter tasks by status and create worktree sessions from the agent command center; worktree support is now enabled by default. (#46839, #45276, #44870)
- Customize the terminal with six new themes and view supported Mermaid diagrams and display equations directly in responses. (#46504, #46054, #45612)
- Update the local background server through `/daemon`, or bypass it with `--no-daemon`. (#45854, #46088)

## Bug Fixes

- Preserve streamed answers and plans when turns fail, are interrupted, or receive subagent completion events. (#45549, #46867)
- Fix clipboard forwarding in tmux and SSH sessions and preserve tab indentation when terminals send pasted text as individual keystrokes. (#45457, #45454)
- Restore Plan mode when resuming sessions and preserve thread identity and settings when editing earlier prompts. (#45519, #45845)
- Recover login through system proxies and refresh MCP credentials when OAuth discovery returns a 503 error. (#46562, #44636)
- Prevent speech from being dropped during playback pauses or bursts of incoming audio. (#46880)
- Close sandbox isolation gaps involving inbound Windows connections, privileged Linux/macOS sockets, and writes through read-only macOS file handles. (#44639, #45984, #46500)

## Documentation

- Clarify that deprecated `friendly` and `pragmatic` personality settings no longer select response styles. (#45809)
- Explain how `?` matches a single character in network proxy allow and deny patterns. (#46027)

## Chores

- Update bundled TLS dependencies, including OpenSSL 3.6.4 for Linux musl builds. (#45149, #45489)

## Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.155.0...rust-v0.156.0

- #44606 Preserve whole diagnostic attachments and report incomplete uploads @chess-oai
- #44611 Preserve root turn attribution in turn-start events @owenlin0
- #44613 Enable user verification for local Codex Desktop sessions @riley-oai
- #44615 Treat non-interactive dumb terminals as warnings in `codex doctor` @etraut-openai
- #44616 Simplify enterprise OAuth login helpers and expand callback tests @nicksteele-oai
- #44617 Invalidate cached Guardian approvals for unscored permission widening @jif-oai
- #44619 Allow discarded code mode tool responses to be garbage collected @jif-oai
- #44620 Support temporary and minimal filesystem grants in MXC @iceweasel-oai
- #44622 Add `/voice settings` to choose a voice for future conversations @bc-openai
- #44626 Add bounded environment transport for MXC launch requests @iceweasel-oai
- #44628 Expose session analytics state in Responses turn metadata @marksteinbrick-oai
- #44629 Add manual callback input to MCP OAuth login @willwang-openai
- #44631 Focus the task list when reopening the agent command center @etraut-openai
- #44636 Recover OAuth metadata discovery from 503 responses via OIDC @malsamiri-oai
- #44639 Block non-loopback inbound traffic for the Windows offline sandbox @viyatb-oai
- #44646 Honor thread analytics opt-outs when using shared clients @priyanshusingh-de
- #44650 Enforce managed model provider selection and definitions @alexsong-oai
- #44651 Keep command center errors visible and preserve drafts @etraut-openai
- #44654 Preserve missing environment variable diagnostics in Codex Doctor @etraut-openai
- #44655 Honor thread-level plugin exclusions across runtime capabilities @mzeng-openai
- #44656 Attribute turn metrics to the models used during the turn @eternal-openai
- #44658 Keep Windows sandbox private desktops alive across helper exits @chess-oai
- #44659 Preserve turn triggers across delegated agent work @joeytrasatti-openai
- #44661 Trace tool call receipt, result readiness, and code-mode dispatch @anp-oai
- #44666 Honor system reduced-motion preferences in the TUI @imac-oai
- #44669 Resolve filesystem denials with explicit path context @seanh-oai
- #44670 Restrict login setup redirects to known platform origins @hintz-openai
- #44671 Keep voice sessions alive through mute and audio backlog @bc-openai
- #44675 Refresh global instructions at model-request boundaries @vkg-oai
- #44676 Resolve permission profiles with explicit execution-host path context @seanh-oai
- #44691 Warn about ignored configuration settings @andrewgu-oai
- #44693 Preserve selected profile settings over managed new-thread defaults @alexr-oai
- #44694 Include the Windows sandbox service in release artifacts @johnl-oai
- #44701 Add a provider for thread-scoped instructions @vkg-oai
- #44711 Return to the command center after session cancellation or deletion @etraut-openai
- #44714 Bundle Linux voice runtimes and improve audio reliability @bc-openai
- #44732 Clarify folder trust prompts and add restricted widget support @etraut-openai
- #44742 Preserve editor yanks across new sessions and thread switches @bc-openai
- #44744 Make archive confirmation number shortcuts act immediately @etraut-openai
- #44746 Check folder trust after resolving the startup destination @etraut-openai
- #44747 Update `quinn-proto` and allow the pinned H3 Git source @richardopenai
- #44749 Preserve voice caption order when replaying TUI history @bc-openai
- #44752 Render Markdown in agent overview task details @etraut-openai
- #44755 Check folder consent before creating or resuming TUI tasks @etraut-openai
- #44814 Test approved command execution with managed unified exec disabled @jif-oai
- #44826 Expose advertised MCP server capabilities in status responses @gpeal
- #44832 Add trusted enterprise MCP auth configuration @nicksteele-oai
- #44857 Add consistent theme-based thread colors across the TUI @etraut-openai
- #44862 Preserve parent cache affinity for ephemeral forks @jif-oai
- #44865 Scope code mode callback delegates to individual executions @abhinav-oai
- #44866 Preserve originating context for yielded code-mode tool calls @abhinav-oai
- #44867 Preserve originating budgets for code mode notifications @abhinav-oai
- #44870 Enable worktrees by default and clarify local daemon errors @bc-openai
- #44872 Add managed network policy support to the Windows MXC sandbox @iceweasel-oai
- #44877 Return public key metadata from user verification enrollment @riley-oai
- #44879 Fade Astra composer stars and stabilize cursor redraws @imac-oai
- #44883 Reject token-budget history notes for unsupported starting models @jif-oai
- #44893 Expose available access programs in model discovery @faizan-oai
- #44903 Wire up the native Windows MXC helper entry point @iceweasel-oai
- #44905 Expose disabled plugin settings in the app-server API @mzeng-openai
- #44915 Remove the deprecated `thread/rollback` API @owenlin0
- #44921 Enable TUI voice conversations by default @bc-openai
- #44922 Bundle native voice runtimes in Windows releases @bc-openai
- #44924 Refresh the speaker format when restarting voice output @bc-openai
- #44925 Accept voice response audio before captions on quiet turns @bc-openai
- #44928 Preserve voice meter history through quiet samples @bc-openai
- #44930 Embed friendly instructions in bundled GPT-5.4 and GPT-5.5 @rhan-oai
- #44931 Stop setting `YARN_NO_PROXY` in the managed proxy environment @viyatb-oai
- #44932 Unify context snapshots and group requests into windows @pakrym-oai
- #44933 Remove Windows world-writable scans and warnings from the TUI @etraut-openai
- #44934 Add scenario snapshots for remote compaction and Code Mode tools @pakrym-oai
- #44935 Remove personality selection from the TUI @rhan-oai
- #44938 Add connector auth failure detection without an install URL @priyanshusingh-de
- #44939 Respect execution hosts in Windows sandbox setup @etraut-openai
- #44942 Clarify the Windows Visual C++ runtime notice for voice packages @bc-openai
- #44944 Enforce managed provider requirements on existing app-server threads @alexsong-oai
- #44945 Route TUI Windows sandbox setup through the app server @etraut-openai
- #44946 Retire Friendly and Pragmatic personality selection @rhan-oai
- #44948 Add context snapshots for async questions and plugin refresh @pakrym-oai
- #44952 Keep voice captions visible across speaker updates and history handoff @bc-openai
- #44957 Add model grouping to the agent command center @etraut-openai
- #44969 Open tasks managed elsewhere as read-only history in the command center @etraut-openai
- #44970 Show task tokens and usage estimates in the agent command center @etraut-openai
- #44976 Make context snapshot text rendering consistent @pakrym-oai
- #45035 Run DotSlash publishing directly on Ubuntu runners @charliemarsh-oai
- #45039 Use gzip compression level 6 for Codex package archives @charliemarsh-oai
- #45051 Consolidate Rust release artifact downloads @charliemarsh-oai
- #45089 Delay automatic recaps and compact their TUI layout @fcoury-oai
- #45090 Preserve conversation context and separate next actions in recaps @fcoury-oai
- #45094 Estimate history tokens from content instead of serialized envelopes @won-openai
- #45108 Cancel pending thread title generation after manual renames @fcoury-oai
- #45112 Use blueberry in the realtime background-agent test fixture @anp-oai
- #45116 Prevent multiline report notes from submitting early @etraut-openai
- #45124 Add a feature flag for asynchronous user messages @alishobeiri-oai
- #45135 Preview streaming prose before a newline arrives in the TUI @etraut-openai
- #45137 Remove Astra sparkle animation from the TUI composer @fcoury-oai
- #45149 Use OpenSSL 3.6.4 for musl builds @zm-oai
- #45169 Extract Windows sandbox setup and installation storage into the library @zm-oai
- #45176 Wire the Windows MXC sandbox into command execution @iceweasel-oai
- #45178 Split Windows sandbox cleanup into preparation and completion phases @zm-oai
- #45180 Extract shared network configuration and environment policy helpers @seanh-oai
- #45182 Validate Windows sandbox token groups before copying SIDs @zm-oai
- #45185 Bind direct tool-call metadata to invocation outputs @ningyi-oai
- #45224 Register Windows desktop uninstall ownership before sandbox setup @chess-oai
- #45248 Use captured step settings for request metadata and tool hooks @abhinav-oai
- #45255 Open new sessions directly from the command center @etraut-openai
- #45262 Route pastes into the active history search query @charliemarsh-oai
- #45271 Preserve terminal scrollback when growing the TUI viewport @fcoury-oai
- #45276 Add worktree session creation to the agents overview @etraut-openai
- #45312 Extract Windows sandbox configuration preparation into a helper @seanh-oai
- #45345 Publish opt-in provisioned macOS packages with Rust releases @riley-oai
- #45399 Cancel code mode timer tasks when cleared or the cell finishes @jif-oai
- #45409 Add session and originating window IDs to MCP request metadata @jif-oai
- #45413 Invalidate Guardian review sessions after parent history resets @jif-oai
- #45417 Extract guardian transcript selection into `guardian-context` @felixxia-oai
- #45418 Extract Guardian conversation bookkeeping into the reviewer crate @felixxia-oai
- #45420 Extract Guardian sampler execution into a dedicated module @felixxia-oai
- #45428 Avoid cloning MCP server status snapshot data @charliemarsh-oai
- #45439 Share tool output schemas and defer MCP envelope construction @charliemarsh-oai
- #45440 Share Apps tool catalogs without retaining unused snapshots @charliemarsh-oai
- #45441 Preserve Guardian parent response IDs across sampling requests @jif-oai
- #45445 Attribute command and plugin analytics to the invoking model @jwang-openai
- #45454 Preserve tabs in non-bracketed paste bu

these notes continue in the original release.

- Added Claude Opus 5.5 (`claude-opus-5-5`), now the default Opus model — 1M context, $4/$20 per Mtok with $0.20/Mtok cache reads
- Added mouse support to more lists in fullscreen mode: the wheel scrolls the `/skills` list, and a skill's state options in `/plugin` can be clicked
- Added `CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH` to change the 2,048-character cap on MCP tool descriptions and server instructions for every MCP server in the session
- Added hook output sizes and the number of oversized outputs saved to a file to the `hook_execution_complete` OpenTelemetry event
- Fixed writes through a symlinked path being judged by their in-tree spelling: the prompt names where the write lands, and `acceptEdits`, allow rules and auto mode no longer approve one landing outside
- Fixed auto mode retrying an action over and over when a safety check declined to review it; the action is now denied once, noting that retrying won't help
- Fixed auto mode denying actions over and over without pause when a safety check gave no answer; retries now back off, and the turn stops with a message after ten in a row
- Fixed Write calls failing validation when a model sends `path`, `file_text`, `file_content` or a stray `description` instead of `file_path` and `content`
- Fixed Ctrl+C or Ctrl+D pressed twice in most dialogs (`/model`, `/effort`, `/config`, `/status`, `/usage`, `/plugin`, `/sandbox`, `/permissions`, `/artifacts`, `/mobile`, `/login`, `/upgrade`, `/usage-credits`, `/install-github-app`, `/setup-bedrock`, `/setup-vertex`) quitting Claude Code instead of closing the dialog
- Fixed a click that only brought the terminal window to the front also triggering the item under the pointer — in search pickers, tab bars, agent/workflow rows, slash-command links and suggestion dropdowns
- Fixed a stray `n` closing dialogs and a stray `y` confirming them; Enter and Esc accept and cancel (bind `y`/`n` to `confirm:yes`/`confirm:no` in `keybindings.json` to restore)
- Fixed text fields in dialogs losing a typed letter, digit or Space to a keybinding on that key
- Fixed the prompt line staying scrambled on Windows terminals after invisible characters were removed on Enter; the screen is now repainted so you review the exact text that will be sent
- Fixed the invisible-character cleanup removing the zero-width non-joiner that Persian and Arabic text uses to attach a suffix to a Latin word or number, such as the plural of "PDF"
- Fixed voice dictation not stopping on Ctrl+C (the prompt cleared but the microphone kept recording), Esc not cancelling while a transcript was processing, and held Space starting dictation from the transcript view and vim NORMAL mode
- Fixed a model switch made from a host app (Claude Desktop, VS Code, SDK) while Claude is working causing a prompt-cache miss on the next prompt
- Fixed resumed fork subagents rebuilding their tool list instead of re-sending the one they first used, which broke prompt caching for that agent
- Fixed subagent hand-back messages showing an internal provenance preamble when expanded outside verbose mode
- Fixed `installed_plugins.json` keeping the install-time commit after updating a plugin from a GitHub repository or git URL that tracks a branch or tag
- Fixed skills in `~/.claude/skills/` being moved to `~/.claude/skills/.trash/` when a `manifest.json` in that folder listed their names
- Fixed the session feedback survey showing no hover highlight on light and ANSI themes
- Fixed `/workflows` briefly showing a one-row list before opening the only run
- Fixed the mouse wheel not scrolling selection lists with hidden options (such as `/model` and `/permissions`) in fullscreen mode
- Fixed a skill you switched off showing the same red ✘ as a plugin that failed to load in `/plugin` and `/skills`; off now shows a dim ◯
- Fixed multi-select option descriptions being indented under the option number instead of under the label
- Fixed the search box in `/plugin`, `/skills` and `/mcp` losing its right border in fullscreen mode
- Fixed `/mcp` showing △ in the server list but ⚠ in the detail view for the same server; the list, detail views and `/plugin` now all show ⚠
- Fixed Home and End doing nothing in the `/config` settings list and in selection lists such as `/model`, `/memory` and permission prompts
- Fixed PgUp/PgDn in the `/skills` menu wrapping past the first or last skill instead of stopping there
- Fixed Tab silently changing the selected setting's value in the `/config` list; it now does nothing there
- Fixed conversations failing on every turn with a "role 'system' must precede an 'assistant' message" API error
- Fixed conversations with the advisor on failing every turn with API Error 400 "Input tag 'advisor_20260301'" behind a proxy or gateway that doesn't support it; the request now retries without it
- Fixed a session failing on every turn and `/compact` when its saved history held a malformed notice about MCP tools that could not be loaded
- Fixed a crash when resuming a session whose saved transcript holds a malformed system message or a memory-saved notice without its file list
- Fixed one cause of long-running fullscreen sessions exiting with "Claude Code exited after an unrecoverable interface error": a damaged cached message list is now rebuilt
- Fixed Claude Code hanging when a settings file, or a file it re-reads after an edit, is replaced by a named pipe mid-read
- Fixed `/config` crashing and some on/off preferences being misread when a preference that has moved to `settings.json` still holds a value like `null` or `"false"` in `~/.claude.json`
- Fixed resuming a session with unfinished background agents, shells or workflows starting a model turn on its own before you typed anything
- Fixed messages sent to a background subagent being silently lost in headless and SDK sessions when the subagent was finishing its turn
- Fixed a finished subagent's report being lost when the conversation that launched it was compacted before the report was read
- Fixed background subagents being unable to use the LSP tool when an LSP plugin is active
- Fixed background shell tasks reporting benign non-zero exits (e.g. grep with no matches) as failures
- Fixed background sessions (`claude --bg`) being unable to run git, hooks, plugins and other helper programs when an environment variable handed to the session contained a NUL character
- Fixed Ctrl+C needing three or four presses to exit while background subagents are running; two presses now exit
- Fixed IDE selection being dropped when a sent prompt comes back into the input, such as pressing Esc to edit it, rewinding to it, or pressing Esc while startup hooks run
- Fixed a `!` shell-mode prompt stashed with Ctrl+S coming back as a plain prompt when restored, and `/` listing file paths right after stashing one
- Fixed `claude agents` showing a blank, unresponsive screen instead of an error when the temp directory is full, not writable or owned by another user
- Fixed an MCP server re-added under the same name after `claude mcp remove` still showing as needing authentication instead of reconnecting
- Fixed background plugin marketplace auto-update ignoring git credential helpers, so private-repo marketplaces were re-cloned every run or never updated
- Fixed `claude plugin update` clearing a plugin's recorded commit and moving it to version "unknown" when the official marketplace's snapshot file is a link or too large
- Fixed the Artifact tool silently disappearing when your organization's policy can't be loaded (for example behind a web proxy); Claude now says what's blocking it
- Fixed artifact republishes silently resetting stored database access rules or dropping the viewer profile scope when that capability was re-sent without them; they are now refused
- Fixed `/ultrareview` reporting a stopped cloud review as completed or as an error to retry, and waiting out the full timeout when its session was deleted or the signed-in account changed
- Fixed the Claude app showing a missing or stale context usage figure for Remote Control and cloud sessions right after /compact or /clear
- Fixed the Claude app's diff view for Remote Control and cloud sessions dropping a branch's committed files whenever there are also uncommitted changes
- Fixed cloud and self-hosted runner sessions failing with "Authentication failed" after waiting out a long overload during which the session's access token was rotated
- Fixed memory write conflicts in Cowork sessions showing Claude only the start and end of a memory file over about 10,800 characters, so the retried write dropped the middle
- Self-hosted runner: Fixed lifecycle-hook commits failing to sign under `--configure-git`
- Windows: Fixed background cleanup deleting a directory symlink or junction used to relocate `~/.claude/session-env`, `image-cache` or another cleaned-up folder
- Self-hosted runner: Fixed a turn that ended right at a `--retire-at` release losing its finished signal; the runner now briefly waits for the turn to be reported before stopping the session
- Reverted `ctrl+l` / `cmd+k` in fullscreen mode clearing the transcript view (added in 2.1.260); they redraw the screen again
- Improved `/permissions`: focus returns to the rule list after viewing, adding or deleting a rule, and the delete-rule and remove-directory confirmations now default to No
- Improved `/permissions` tab navigation: ←/→ and Tab pressed in a rule list now switch tabs without moving focus to the tab bar
- Improved `/cost` cache-miss causes to name thinking mode and thinking display changes
- Improved the Artifact tool so that when Claude cannot read an artifact link it was given, it tells the user before continuing
- Improved `/install-github-app`: the GitHub CLI check and repository selection steps now show "Esc to cancel"
- Improved the `/artifacts` and `/workflows` lists: a scrollbar at the right edge shows how much of a long list is hidden and where you are in it
- Improved the workflow progress tree: running agents and phases now show a dim dot instead of ⟳
- Improved `/plugin`'s Add Marketplace form in fullscreen: it no longer draws a box inside the pane, and its text and key hints line up with the rest of `/plugin`
- Improved the `/workflows` detail view in fullscreen: it no longer draws a second horizontal rule under the pane's divider
- Improved code blocks that don't name a language: they are now colored like inline code, so commands stand out from the surrounding text
- Improved `/btw` asked while a tool is still running: the side question now knows that call is in progress instead of reading it as a failed one
- Improved the UserPromptSubmit hook timeout notice and the debug log to name which hook command timed out
- Improved `@` file suggestions: a file whose name contains the query now ranks above one that only matches across its folder names
- Improved artifact pages: no Print buttons, confirm dialogs or device features the viewer blocks, email and phone details shown as text, and dark mode that reaches form controls and scrollbars
- Improved `/ultrareview` uploads: renamed copies of key files, such as `id_rsa copy` or `kubeconfig (1).yaml`, now also stay on your machine
- Improved the cross-session messaging startup warning to explain that `--debug-file` writes a debug log to a path you choose
- Changed the default model on Pro and Team Standard plans from Sonnet to Opus, matching Max, Team Premium, and Enterprise
- Changed an effort level saved before `/effort` became per-model to no longer apply to newly released models such as Opus 5.5; they start at their default until you pick a level
- Changed Opus 4.7, Opus 4.8 and Fable 5 to stop holding their launch-default effort over `/effort` in `-p` or the Agent SDK, a project, managed or `--settings` `effortLevel`, or a per-model level
- Changed `/autocompact`'s footer hint to name ←/→, the keys that adjust other ordered values
- Changed `/fast`'s footer to name Space as the toggle key
- Self-hosted runner: Chang

these notes continue in the original release.

Grok 4.7, SpaceXAI's frontier model for coding, agentic tasks, and knowledge work, is now available on the xAI API as grok-4.7. It has a 500k context window, text and image inputs with text-only output, and no text output limit. Pricing is $2 / $0.50 / $6 per 1M tokens (input / cached input / output) below 200k prompt tokens, and $4 / $1 / $12 above. Reasoning effort supports low, medium, high (default), and xhigh. On the Responses API, grok-4.7 always returns reasoning.encrypted_content, even when include does not list it. It is also served on the US regional endpoint. Grok 4.7 Fast is the same model and costs 2x the standard token rates, or 1.5x for long-context requests. It's available only in Cursor and Grok Build, not on the public xAI API, and is billed through your plan there. See the Grok 4.7 overview and the announcement.

- Changed auto mode for Claude API and Enterprise users, and on Bedrock, Vertex, Foundry and gateways, to default to the server-side classifier, which does not charge for classifier overhead (`CLAUDE_CODE_AUTO_MODE_SERVER=0` opts out on Bedrock, Vertex, Foundry and gateways); warns on billed fallback. See https://code.claude.com/docs/en/auto-mode-classifier-billing
- Added an `Auto mode server` row to `/status` showing whether this session's auto mode classifier runs on the server

- Added AGENTS.md support: in a project with no CLAUDE.md, Claude Code reads AGENTS.md instead; change it under "Project instructions" in `/config`
- Added `CLAUDE_GATEWAY_PROXY_IS_EGRESS_BOUNDARY=1` for Claude apps gateways whose only egress is a forward proxy: every outbound request hands the proxy the hostname instead of resolving it locally
- Added an optional `headers:` map on Claude apps gateway upstreams, to send static headers to a proxy you run in front of a provider
- Added a line saying a background task's update is waiting when it finishes while a panel such as `/tasks` is open
- Fixed `claude -p` and Agent SDK sessions that could hang with no result after an internal error; they now report the error and exit with code 1
- Fixed conversations failing every request with "text content blocks must be non-empty" when an earlier assistant turn held an empty text block beside other content, including after `--resume`
- Fixed being unexpectedly logged out when an older Claude Code build (for example an IDE extension's bundled CLI) runs on the same machine as the current one
- Fixed interactive start-up hanging or showing an error for `ANTHROPIC_API_KEY` users when `~/.claude.json` holds a malformed `customApiKeyResponses` value
- Fixed update checks erroring every 30 minutes, and `claude update` hanging when a minimum or maximum version is set, if a proxy returns an invalid version; a malformed `minimumVersion` is now ignored
- Fixed `claude update` on winget- or apk-managed installs reporting "up to date" when the version lookup failed
- Fixed `claude plugin install` sometimes failing and breaking the installed copy when reinstalling a plugin version that a session or another program was using; an unchanged copy is now left alone
- Fixed Grep and Glob reporting no matches when the search could not start because the system was out of processes, memory or file handles; they now return an error saying so
- Fixed the Write tool silently ending the turn as a declined permission when the target path is an existing directory; it now reports a clear error
- Fixed the Edit tool treating an escaped backslash followed by `uXXXX` text as a `\uXXXX` escape, which could make an edit of a non-ASCII character rewrite an escaped backslash sequence instead
- Fixed the Edit tool reporting "Invalid regular expression: regular expression too large" instead of "String not found in file" when a very large edit containing non-ASCII text did not match the file
- Fixed a turn ending early with "Path contains null bytes" when a tool call's file path contained `\u0000` written as an escape sequence; escaped control characters now stay as literal text
- Fixed background sessions (`claude --bg`) exiting when a plugin's LSP server exited or closed its stdin
- Fixed a crash ("Type error") when opening `/mcp` or `/plugin manage` with a malformed `claudeAiMcpEverConnected` value in `~/.claude.json`
- Fixed a crash at launch when `~/.claude.json` holds a malformed `theme` value
- Fixed a crash ("unrecoverable interface error") when the prompt held text containing terminal color codes, for example a prompt recalled from history or text loaded from the external editor
- Fixed a crash when resuming a session whose saved history holds an assistant message stored as a plain string
- Fixed sessions on slow or heavily loaded machines sometimes exiting with "Claude Code exited after an unrecoverable interface error" when the first spinner appeared
- Fixed a rare case where the screen could stop updating for the rest of the session after an internal rendering error
- Fixed a rare case on Windows where a turn could stop with an error such as "Out of memory" right after Claude replied, so that reply's tool calls never ran
- Fixed sessions continued after `/clear` (restart, `--continue`, `--resume`) missing part of their first message when a SessionStart hook printed output, causing a full prompt-cache miss
- Fixed messages from other agents (such as a subagent's SendMessage) that arrived mid-turn showing up below the "Ran N shell commands" row instead of where they arrived
- Fixed the "copied" notice not appearing after drag-selecting text in the fullscreen `/resume` picker and other panels that cover the prompt area
- Fixed `$TMPDIR` expanding empty in Bash commands that run outside the sandbox while sandboxing is enabled
- Fixed WebFetch and WebSearch in Cowork cloud sessions not telling Claude why a request was refused, such as a used-up fetch budget or an admin policy
- Fixed the Claude apps gateway's telemetry relay ignoring a collector hostname or domain listed in `NO_PROXY` when a proxy is set
- Fixed one malformed `strictKnownMarketplaces` or `blockedMarketplaces` entry silently disabling the whole enterprise marketplace policy
- Fixed failed auto-updates leaving large staged downloads behind in `~/.cache/claude/staging`
- Fixed `/plugin` not stripping terminal control characters from messages on the Installed tab, such as the error of a failed plugin update
- Fixed `/plugin` → Installed and `/skills` crashing when a skill or legacy command is named like a built-in Object property such as `constructor` or `toString`
- Fixed `/plugin` closing with no message when every install in a multi-select failed
- Fixed uninstalled plugins reappearing as "failed to load" rows in `/plugin` Installed, and Remove not clearing such a row
- Fixed plugins from the official marketplace being recorded without their commit in `installed_plugins.json`, and `installed_plugins.json` keeping the old commit after updating a pinned-commit plugin
- Fixed plugin reload previews keeping every previewed copy of a plugin archive unpacked until exit, and overwriting the cached `--plugin-url` archive a reload falls back to when its download fails
- Fixed Remote Control session bookkeeping failing when `~/.claude.json` holds a malformed placeholder record
- Fixed the error after a revoked claude.ai login blaming an expired Anthropic profile; it now leads with `/login`
- Fixed typed or pasted text occasionally coming out scrambled in the `claude agents` dispatch input during key repeat or very fast input
- Fixed a crash ("unrecoverable interface error") when resuming a session whose saved transcript contains a stop hook summary without a well-formed hook list
- Fixed Enter on a selected agent panel row doing nothing when `keybindings.json` rebinds Enter in the Chat context, for example to `chat:queueSubmit`
- Fixed PDF page reads on Windows failing when the working folder's path is long (about 120 characters or more)
- Fixed a headless resume (`claude -p --resume`, the SDK, a VS Code extension window reload) starting the session's cost and usage totals at zero; headless sessions now save their totals at exit
- Fixed project skills from the main repository not loading in `--worktree` sessions when `.claude/skills` is untracked
- Fixed a `sandbox.excludedCommands` glob exempting an entire compound Bash command from the sandbox when only one part matched; every part must now match
- Fixed resumed subagents and teammates re-rendering the MCP tool definitions they had loaded, which broke prompt caching for that agent
- Fixed rate-limited artifact publishes telling Claude to stop retrying; Claude is now told nothing was published and when to send the same publish again
- Fixed attachments recorded earlier in a conversation being re-rendered after a resume or relaunch, which dropped extended thinking and missed the prompt cache
- Fixed Console sign-in showing only "Request failed with status code 400" when the server refuses to create an API key; it now shows the server's message
- Fixed messages typed while Claude is still working sometimes being ignored by the model
- Improved session start-up for SDK and headless (`-p`) use: the first turn no longer waits on the per-directory CLAUDE.md lookup
- Improved the Claude apps gateway's loopback error messages to name `CLAUDE_GATEWAY_ALLOW_LOOPBACK`
- Improved `/plugin` Installed: an MCP server listed apart from its plugin now shows which plugin it belongs to
- Improved `claude plugin install` on an already-installed plugin: it now says when the marketplace offers a newer version and names the `claude plugin update` command
- Improved the startup notice overflow line under the logo: it now reads "N more notices hidden" instead of "+N more · /status"
- Improved prompt handling: invisible Unicode formatting and tag characters in a prompt are removed and the cleaned prompt is shown for review before it is sent
- Improved `/ultrareview` when there's nothing to review: messages say which case you're in, offer a command that reviews your latest commit, and a new repository's first commit is reviewed in full
- Improved artifact link handling so Claude reads claude.ai artifact links with the Artifact tool instead of WebFetch when that tool is available
- Improved the dangerous-rm permission prompt to name the flagged rm command and suggest a `${VAR:?}` guard, so headless runs can recover
- Improved the Artifact tool's permission prompts: shorter sentences, pages and artifacts named by title or file name, and links listed after the text
- Changed Fable to always appear in `/model` on the Anthropic API; it is greyed out only when your organization's settings disable it
- Changed the Bash sandbox instructions on Bedrock, Vertex and Foundry to the first-party wording, which frames the sandbox as the boundary of what the task was given
- Changed `/ultrareview` in non-interactive sessions to refuse when the repository has no base branch or shared history
- Changed subagent results to reach the main agent under a header marking them as subagent output, with the result indented, so text in a subagent's result cannot pass as the session's own instructions
- Changed workflow scripts' computed `agent()` prompts on Bedrock, Vertex and Foundry to reach the subagent framed as script-authored text, so the safety classifier does not read them as the user
- Removed the background Haiku auto-title request from `claude -p` runs launched outside an SDK or IDE
- Removed the deprecated TaskOutput tool; Claude reads a background task's output file with Read instead, and the `taskOutputMaxChars` setting and `TASK_MAX_OUTPUT_LENGTH` no longer have any effect
- [VSCode] Added a Sign out row to the panel menu, with `/logout` in the typed command menu
- [VSCode] Added background shells and other running tasks to the agent map, each with a Stop, and a typed `/tasks` that opens it
- [VSCode] Added a Copy response button on responses and a typed `/copy`
- [VSCode] Added a one-time notice when inactive sessions are archived automatically, and an "Unarchive all" action on the Archived sessions group
- [VSCode] Added the session's cost and token usage to the Account & usage dialog and the session manager where plan limits do not apply (Vertex, Bedrock, Foundry, API key)
- [VSCode] Fixed the "General config" menu row showing `/config` usage text instead of opening settings, and made typed `/mcp`, `/hooks`, `/memory`, `/rewind` and similar commands open their dialogs
- [VSCode] Fixed the effort slider's level not persisting into later sessions on a model that already had a level saved with `/effort`
- [VSCode] Fixed Auto missing from the mode picker for conversations opened in an already-used panel when the saved model setting is a differently-cased alias such as "Sonnet"
- [VSCode] Fixed `/fast` not saving fast mode as the default, so it was lost when the extension relaunched Claude Code
- [Claude Code on the web] Added Personal and Organization sections to the environment picker on Team and Enterprise plans, and admins can now share a personal environment with the organization
- [Claude Code on the web] Changed organization environments to open as a read-only summary from the Code tab on Team and Enterprise plans, with editing under Admin settings → Cloud environments
- [Claude Code on the web] Fixed a cloud environment saved with Custom n

these notes continue in the original release.

- Fixed every request failing with `400 … Input tag 'advisor_20260301'` when `ANTHROPIC_BASE_URL` points at a proxy or gateway (2.1.275 regression)

- Added the signed-in account to Claude apps gateway sign-in: when the gateway names it, you confirm it before the credential is saved, and `/status` shows it
- Added a send-now key (ctrl+enter, or ctrl+x ctrl+s) that interrupts the current turn and sends all queued messages at once; sent and queued messages show in gray until the model receives them
- Added a startup warning when a configured `otelHeadersHelper` fails, so sessions that silently export no telemetry are noticed
- Added syncing of the skills and plugins enabled on your claude.ai account to terminal sessions signed in with it; opt out with `syncClaudeAiSkills: false` or `syncClaudeAiPlugins: false`
- Added `/plugin install <plugin> --marketplace <source>`, which offers to add the marketplace before installing the plugin
- Fixed a restored memory file's age note changing between requests after a compaction or resume, which caused prompt cache misses
- Fixed `--forward-subagent-text` stream-json and SDK output dropping the messages of subagents spawned by a `context: fork` skill, and of forked skills invoked by a subagent or another forked skill
- Fixed @-mention file suggestions being buried below MCP resources when using a custom `fileSuggestion` command or typing `@.`/`@./`
- Fixed fullscreen mode placing background-task completion notices beneath a long turn's collapsed tool row instead of where they arrived; each notice now closes the open row
- Fixed `claude plugin marketplace update` deleting a GitHub marketplace's local copy when the fetch failed and the marketplace was named after its repository
- Fixed plugin and marketplace messages, logs and `claude plugin marketplace list` showing a password or token stored in a git, ssh or marketplace URL
- Fixed a resumed cloud session leaving an unanswered question open in the transcript after a queued message superseded it
- Fixed vim mode placing the cursor one character right after a dot-repeated "!" or a fast-typed "i!" switched a non-empty prompt into shell mode
- Fixed fullscreen mode freezing or blanking for several seconds when scrolling up past a large file diff
- Fixed a stray `</ccmemory>`-style closing tag occasionally appearing in responses
- Fixed plugin messages, logs and the VS Code plugin dialog showing the wrong server for some git addresses
- Fixed a terminal `API Error: 400` on every turn for users behind a network gateway that rewrites API error responses when a beta request header is rejected
- Fixed sandboxed Bash commands on Linux reporting exit code 0 for failed commands when the shell is zsh
- Fixed the Read tool hanging instead of reporting an error when part of a large file could not be decoded under memory pressure
- Fixed `--resume`, the resume picker preview, resumed background agents and the transcript view failing on a session whose saved history contains a malformed task-reminder or @-file attachment entry
- Fixed a crash when resuming a conversation whose transcript contains a malformed message entry, and a fullscreen crash when such a conversation received new messages while scrolled up
- Fixed sessions failing to resume or start when their saved transcript contains a malformed message content block
- Fixed Grep, Glob and @-file suggestions hanging or running out of memory on searches over the 20MB output cap, and system ripgrep reporting "no matches" instead of an error after a flood of warnings
- Fixed `/rewind` in a forked or background session restoring a zero-filled or truncated file when the session's file-history backups could not be fully copied
- Fixed fullscreen sessions sometimes exiting with "Claude Code exited after an unrecoverable interface error" when typing fast or holding a key with the slash-command dropdown open
- Fixed background sessions crashing and restarting their worker when a command fed through stdin ran on a machine that had run out of file descriptors
- Fixed a crash at launch when `~/.claude.json` holds a malformed `mcpNeedsAuthNoticed` value
- Fixed `--resume` and `--continue` dropping a conversation's earlier thinking when a built-in tool it started with has since been switched off by a server-side flag
- Fixed text selected with the mouse in the fullscreen `claude --resume` session picker never reaching the clipboard
- Fixed plugin reload previews replacing a running session's extracted plugin files when the plugin was loaded from a `--plugin-dir` or `--plugin-url` archive
- Fixed self-hosted runners with `--drain-wait-sec` losing the final result of a turn that finished during a SIGTERM drain; the runner now waits briefly for the turn to be reported
- Fixed `SubagentStop` hooks with a specific `matcher` firing for every stopping subagent whose agent type was empty
- Fixed sandboxed Bash commands being unable to write to project directories named `hooks/` or `config/`
- Fixed Artifact updates failing with "File not found" after a session resumes on another machine or its scratchpad is cleared: the page's last published version is restored
- Fixed `/update-config` writing `Write(path)` permission rules, which file permission checks don't match, instead of `Edit(path)` rules
- Fixed four dead documentation URLs (Pricing, Computer Use, Skills, CLI) in the bundled claude-api skill's live-sources table
- Improved prompt caching for a `--system-prompt` that contains a `__SYSTEM_PROMPT_DYNAMIC_BOUNDARY__` line: the text above it is now cached globally, as the SDK's array form already is
- Improved the `/desktop` error when Claude Desktop does not open: it now says why and what to do next
- Improved the Artifact tool's publish and read results: they now say who can open the page and what the owner's Share menu offers
- Improved artifact publish results: they name the tab icon sent, warn when the page contains a NUL byte, and retry a flaky fetch of the newer page to merge after a stale publish
- Improved pasted and attached images: they are now saved where Claude can open them as files without a permission prompt, including in Desktop and VS Code
- Improved the Artifact tool's guidance so Claude updates a shared artifact in place when you were given edit access to it, instead of publishing a separate copy
- Improved plan-usage reads: editor windows and non-interactive sessions on one machine now share a read made in the last minute instead of each calling the usage endpoint
- Improved the `ListPlugins` tool description so Claude knows it lists plugins enabled on your claude.ai account, not plugins installed locally with `/plugin`
- Improved responsiveness when the terminal is slow or paused: output no longer falls further behind while the terminal catches up
- Improved Write and Edit results for files in the synced account-skills folder: they now say the change is not saved to your account and how to save it
- Updated `/logout` for Claude apps gateway sign-ins to also end the session on gateways that advertise token revocation
- Changed hosted sessions to keep an unanswered permission prompt up after a container restart, instead of asking again
- Changed the Artifact tool to ask for a one-word tab icon on a first publish instead of an emoji favicon
- Changed Claude in Chrome in auto mode to skip the extension's per-site check for classifier-approved calls, as bypass mode does, fixing `browser_batch` "Permission denied" after a redirect
- Changed plugins installed from an npm source to be fetched with `npm pack --ignore-scripts` and integrity-verified, so a package's install scripts no longer run
- Changed scheduled and Run now routine runs to save data to, and republish the page of, an artifact you can edit without asking; public artifacts, first publishes and deletes still ask
- Removed the startup notice that told you a one-off scheduled routine had run since your last session
- [VSCode] Added viewing, editing and deleting a saved memory inside the Memory dialog
- [VSCode] Added sending an attached image without typing any text
- [VSCode] Added a Retry link to the MCP servers dialog when the server list fails to load
- [VSCode] Added accept and reject buttons under each change in the proposed-change diff tab, so an edit can be reviewed change by change
- [VSCode] Fixed the transcript creeping toward the bottom in small steps while a permission card waits and content keeps arriving
- [VSCode] Fixed rewound and forked conversations not keeping the permission mode you had picked for the original conversation
- [VSCode] Fixed an empty `CLAUDE_CONFIG_DIR` entry in the `environmentVariables` setting making Claude Code keep its files in the workspace
- [VSCode] Fixed plugin install links opening the Manage plugins dialog for plugin names and marketplace addresses that can't be used in a link
- [VSCode] Fixed Remote Control staying shown as connected after a turn-off that Claude Code reported as failed; it now shows as off
- [VSCode] Fixed the scroll to the bottom on send stopping short of the reply when the reply starts arriving during the scroll
- [VSCode] Fixed the agent map showing agents a crash left unfinished as stopped instead of failed once the session is reopened
- [VSCode] Fixed the "Continuing the step" notice not appearing, and the continue limit resetting, after a reload that follows a crash with background tasks still running
- [VSCode] Fixed the session list showing when a session was last reopened, such as after a window reload, instead of when its last message was sent
- [VSCode] Fixed "Fork conversation from here" failing on the message right after one sent while Claude was working
- [VSCode] Fixed the prompt cache clock showing too few minutes after reopening a session with a message sent while Claude was working
- [VSCode] Fixed a background agent that finished while Claude was running a tool losing its completion notice, and its result on the agent map, after a window reload
- [VSCode] Fixed a rare case where text selected in a git-ignored file could be sent to Claude after the extension was unresponsive for several seconds
- [VSCode] Fixed renaming a running session reverting to the generated name (regression in 2.1.269)
- [VSCode] Fixed slash commands typed while Claude is responding being sent to the model as text instead of running once the response finishes
- [VSCode] Fixed unreadable code in the plan preview and the Hooks and Permission rules dialogs with the High Contrast Light theme
- [VSCode] Fixed `/remote-control` being ignored while Remote Control is still connecting: running it again now turns Remote Control off immediately
- [VSCode] Fixed the conversation pulling you back to the bottom while a reply streams after you scroll up, and added a `claudeCode.scrollToBottomOnSend` setting to turn off the jump on send
- [VSCode] Fixed the Manage plugins dialog showing a password or token that was typed into a marketplace URL
- [VSCode] Improved the agent map: the pill counts running agents and turns red after a failure, the main agent stays in view while the map scrolls, and agents sort by state then end time
- [VSCode] Changed New session in a Claude editor tab to open in the sidebar when Preferred Location is set to Sidebar, instead of always opening another tab
- [VSCode] Changed a message sent while Claude is working to wait at the bottom of the conversation until Claude starts on it
- [Claude Code on the web] Added a "New routine" button to the page shown when a routine link no longer resolves, next to the link back to your routines list
- [Claude Code on the web] Fixed routine "paused" and "on hold" notifications being cut off mid-sentence; the paused-subscription notice now says to turn the routine back on yourself
- [Claude Code on the web] Fixed cloud environments with a very long allowed-domains list saving fine and then failing every session start; saving now fails up front and says how much to trim
- [Claude Code on the web] Fixed Claude's guidance when a cloud session on a personal account is denied GitHub access: it now links to claude.ai/connect-github instead of

these notes continue in the original release.

grok-voice-transcribe-2.0 is now available. Use grok-voice-transcribe-1.0 or grok-voice-transcribe-2.0; the default is grok-voice-transcribe-2.0. See the Speech to Text docs.

- Added a visible warning when memory usage is critical, with steps to free memory or restart safely
- Added `CLAUDE_CODE_MCP_STARTUP_WAIT_MS` to bound how long the first non-interactive turn waits for connecting MCP servers (`0` = don't wait)
- Added `effort` attribute to the `claude_code.llm_request` OpenTelemetry trace span, matching the `api_request` event
- Added `claude_code.managed_settings_resolved` OTel event: managed-settings sources and policy helper state; redacted settings and digests with `OTEL_LOG_MANAGED_SETTINGS=1`
- Added `store.connect_timeout_seconds` to the Claude apps gateway config to lengthen the Postgres connect timeout (default 5 seconds), and improved the boot error when the database is unreachable to point to `store.postgres_url` and the configured timeout
- Added `enduser.sub`, the IdP subject, to the telemetry Claude Desktop and Cowork send through a Claude apps gateway
- Added a Claude apps gateway warning when a replica has more requests open than the 256 it sends upstream at once, and a startup log line showing that limit
- Added click-to-expand for collapsed teammate and agent messages in fullscreen mode
- Fixed sessions getting stuck endlessly retrying "unexpected tool_use_id" 400 errors: corrupted transcripts now self-heal where possible, and otherwise a clear error (with a `/rewind` hint) ends the loop
- Fixed MCP servers configured as `http` that only speak legacy HTTP+SSE failing to connect when they answer the first request with 422 or another 4xx error
- Fixed Streamable HTTP MCP tool calls timing out after about 5 minutes even when a longer per-server `timeout` was set
- Fixed MCP prompts and resources not refreshing when a server sends list-changed notifications without declaring `listChanged`
- Fixed MCP tool calls refused with 403 insufficient_scope being reported as an expired sign-in: the error now names the missing permissions and points to `/mcp` re-authentication
- Fixed hook-driven sessions (such as an active `/goal`) ending with "Prompt is too long" instead of compacting when the context overflowed again after a reactive compaction
- Fixed an active `/goal` being lost when resuming (`--continue` / `--resume`) a session that had compacted
- Fixed `claude agents` losing `--model`, `--effort`, `--permission-mode`, `--allow-dangerously-skip-permissions` and `--agent` after an auto-update relaunch
- Fixed a per-turn slowdown when a language server publishes project-wide diagnostics for thousands of files
- Fixed subagents with `model: "opus"` on Bedrock, Vertex or Foundry leaving the session's model when its id has no recognizable model family (unless `ANTHROPIC_DEFAULT_OPUS_MODEL` is set)
- Fixed self-hosted runner sessions failing every turn with a 401 after a few failed token refreshes, until the next scheduled refresh; the runner now keeps retrying, and fetches a new token after a 401
- Fixed clickable links to local file paths doing nothing in VS Code and other terminals that require a `file://` URI
- Fixed the transcript renumbering ordered lists in your own messages (typing "3. 2. 1." displayed "3. 4. 5."); numbers and "N)" markers now show as typed
- Fixed AskUserQuestion preview notes being attached to a previously chosen option instead of the highlighted one
- Fixed AskUserQuestion preview mode dropping the highlighted option when submitting a note with Enter
- Fixed a resumed background agent keeping half of an interrupted tool batch when one of its calls was approved with a message
- Fixed a local `claude -p --resume` started with `CLAUDE_CODE_RESUME_INTERRUPTED_TURN` not reporting background tasks the previous process left unfinished
- Fixed the first turn of a cloud session sometimes starting without the tools of an SDK-hosted MCP server that was still connecting
- Fixed background agent notifications claiming the agent had no live background work when it was still waiting on its own background task and would resume
- Fixed error hints in Claude Desktop sessions to suggest slash commands like `/usage-credits` instead of CLI flags that cannot be used there
- Fixed `/schedule` saving a routine's prompt without its message role when Claude writes the routine in the shape that listing routines returns
- Fixed `/status` not showing the `apiKeyHelper` failure that its own error banner told you to check
- Fixed `/fast on` in non-interactive sessions reporting on and then turning off under an organization's managed fast mode policy; it now says the organization has disabled it
- Fixed the Artifact tool asking you to approve an update to an artifact that it then refused because the session had not read the latest version
- Fixed Cowork and claude.ai cloud sessions with network access on treating reads of a teammate's artifact as if network access were off
- Fixed a plugin or marketplace directory with no git repository of its own taking its version from an enclosing git repository, such as a git-managed `~/.claude`
- Fixed `--strict-mcp-config` with an empty `--mcp-config` holding the first non-interactive turn for up to `MCP_TIMEOUT` on incidental MCP servers
- Fixed Stop prompt hooks re-sending their whole prompt on every block in a conversation; repeat blocks now name the condition with a 500-character label
- Fixed extra empty editor windows opening at startup on Linux under Wayland when running inside the Cursor or VS Code terminal
- Fixed an unhandled promise rejection in the Claude apps gateway when Postgres drops a connection during a spend check
- Fixed Claude apps gateway cutting every open stream on SIGTERM: it now lets in-flight requests finish for up to 25 seconds before exiting (`CLAUDE_GATEWAY_DRAIN_TIMEOUT_MS`)
- Fixed `installed_plugins.json` being rewritten on nearly every start-up when plugin policy comes from remote managed settings, which made Claude Desktop reload every open session's plugins
- Fixed headless and SDK sessions making a separate model call for every background task that finished; completions already queued are now answered by one call
- Fixed the Bash tool re-sourcing the shell profile (a multi-second stall on the next command) after every plugin reload; it now does so only when the plugins' `bin/` directories changed
- Fixed plugins with a top-level `$schema` in `hooks/hooks.json` showing an "unknown key" notice
- Fixed MCP connection errors and the MCP login tool's description showing secrets resolved from `${VAR}` placeholders in MCP configs
- Fixed Bash permission checks for commands that loop over or assign certain special shell variables; these commands now ask for permission
- Fixed worktree-isolated sessions accepting Bash commands with certain nested shell expansions; these are now refused
- Fixed the Edit permission prompt preview sometimes showing a different location than the approved edit in files with multi-byte characters
- Fixed background commands being stopped after 30 idle minutes on machines under mild memory pressure; they're now stopped only when memory is critically low, and the debug log says why
- Fixed a message a subagent sends to the main session disappearing from the Claude Desktop transcript after a relaunch
- Fixed a plugin loaded from a `.zip` being served from a stale extraction after several overlapping reloads
- Fixed a sub-agent's progress summary being replaced by a runaway multi-paragraph reply
- Improved startup in `--input-format stream-json` sessions: the first turn no longer waits up to 2s for still-connecting MCP servers whose tools tool search defers; they arrive on a later turn
- Improved Monitor tool notifications: a script's final output and its exit now arrive as one notification instead of two, saving a model turn
- Improved Artifact tool errors: when you are not signed in to claude.ai the terminal now says so on the first attempt, and Claude is told to stop retrying a rejected call sooner
- Improved artifact publishing: a publish built on an older version is stopped before it is sent, with the newer page to merge
- Improved safety checks before removing an agent worktree that contains submodule checkouts
- Improved `OTEL_LOG_RAW_API_BODIES=file:<dir>` output: a new `index.jsonl` and `request_body_id` / `message.id` event attributes link each response to its request file and transcript message
- Improved Claude apps gateway boot: it now tries the first Postgres connection up to three times before exiting, so a database that is reachable a few seconds late no longer fails the boot
- Improved the Claude apps gateway's spend-limit check under load: it now takes one database round trip instead of four, so fewer checks time out on a busy gateway
- Improved Claude apps gateway sign-in rate limit errors: `/login` now explains the refusal, and the gateway log says which limit was hit and which setting to change
- Changed Bedrock, Vertex, Foundry and telemetry-disabled installs to use the v2 MCP client and MCP 2026-07-28 negotiation with direct HTTP servers by default, as other installs already do (opt out: `MCP_SDK_GENERATION=v1` or `MCP_PROTOCOL_NEGOTIATION=legacy`)
- Changed `/code-review` to use leaner inline review prompts for every model that has no tuned settings of its own, instead of spawning many review subagents
- Changed `"type": "sdk"` MCP entries in `.mcp.json`, settings, plugins and agent files to be skipped with a warning: only an SDK host application can register in-process servers
- Changed artifact watching in local sessions: a new version published elsewhere no longer starts a turn; Claude learns of it from a later Artifact tool result
- Changed plugin and marketplace clones to leave Git LFS files as pointers instead of downloading them; `git lfs pull` in the checkout fetches them
- Changed self-hosted runners to skip a read-only repository the git host refuses at the access check instead of failing the session start
- Changed the `/status` GitHub line to read "Cloud sessions", and `/web-setup`, `/ultrareview`, and teleport messages to say "cloud session" instead of "Claude Code on the web"
- [VSCode] Added continuation of the step a window reload interrupted, labeled in the chat, with a Claude Code: Continue After Reload setting to turn it off
- [VSCode] Added Memory and Instructions entries to the Customize menu: Memory shows the auto-memory toggles, the saved memories and the memory folders, and Instructions edits the CLAUDE.md files
- [VSCode] Added a `claudeCode.lockEditorGroups` setting to stop Claude from locking the editor groups it opens in
- [VSCode] Fixed a `/btw` side question asked in a new conversation's first seconds occasionally showing another session's side-question history
- [VSCode] Fixed a brief freeze when the extension first looks up your global gitignore file
- [VSCode] Fixed a message sent while Claude was running a tool disappearing from the conversation after a window reload
- [VSCode] Fixed the Manage Plugins enable toggle and MCP servers dialog rows being unreachable from the keyboard
- [VSCode] Fixed sign-ins and sign-outs made in a terminal not showing until a reload after `CLAUDE_CONFIG_DIR` changed in the Environment Variables setting
- [VSCode] Fixed Edit diffs in the chat being cut off at the bottom at some panel widths and for long wrapped lines; diff boxes now fit the rows shown
- [VSCode] Fixed overlapping settings writes from the extension leaving `~/.claude/settings.json` unparseable or dropping a setting
- [VSCode] Fixed Open in New Tab (Ctrl/Cmd+Shift+Esc) sometimes leaving the new tab's message box unfocused, so typing went nowhere until you clicked it
- [VSCode] Fixed reopening a closed Claude tab splitting the editor layout when its locked group still holds another Claude tab and a file
- [VSCode] Fixed New session opening another locked editor group whenever a file tab shared the group with your Claude tab
- [VSCode] Fixed session names shifting sideways in the session picker while typing a search query
- [VSCode] Fixed the plan review card cutting off its Send feedback button a

these notes continue in the original release.