Anthropic's terminal coding agent; its GitHub releases carry the CHANGELOG entries of each version. https://newruntime.com/tools/claude-code/ 2026-10-27T00:00:00Z New Runtime tag:newruntime.com,2026:tool-change:claude-code:ee1cab9a-e782-4f02-b3c8-69afa66ef0ea2026-10-27T00:00:00Z

Added oidc.user_id_claim to the Claude apps gateway, to identify people by an id_token claim other than sub, such as Microsoft Entra ID's oid · Added click to send: in fullscreen, clicking the "to send now" hint under a queued message sends it right away, as its key does · Fixed managed settings and organization policy not being fetched for the rest of the session after signing in from the VS Code extension · Fixed Claude overwriting a very large CLAUDE.md, rules file or @-included file in a subdirectory after seeing only its start; Write now asks Claude to read it all or edit in place · Fixed per-directory and paths: skills not being found after a Bash cd deeper into a git repository · Fixed a rare case where the first reply after resuming a session in the terminal could be missing the next time the session was resumed

tag:newruntime.com,2026:tool-change:claude-code:3809709b-e55e-4037-8244-1943d65b4b492026-10-26T00:00:00Z

Added --hold-idle-file and --max-hold-min to self-hosted-runner, to keep an idle session while your host reports processes it left running · Added a tip for the Explanatory output style, shown when you ask Claude for explanations · Fixed long freezes at startup and after reading or editing files when a CLAUDE.md file holds a very long list item · Fixed interrupting Claude not taking effect until a timeout while an MCP server had not answered a resource read or a skill was still downloading · Fixed standard-context sessions stopping with "Usage credits required for 1M context" when a request ran over 200K tokens; Claude Code now compacts the conversation and continues · Fixed Write and Edit stalling for up to 5 seconds after they ran, and reporting 0 lines changed, when changing thousands of lines in a file

tag:newruntime.com,2026:tool-change:claude-code:c3711cf5-bd4a-4f66-8416-44719e72adc82026-10-23T00:00:00Z

Added the Monitor tool and plugin monitors on Bedrock, Vertex, and Foundry, and when telemetry or nonessential traffic is disabled; long foreground sleeps are now blocked there too · Fixed requests failing behind some gateways and compatible servers that reject the effort-2025-11-24 beta value or mid-conversation system messages; Claude Code now retries without them · Fixed background cleanup deleting some recent files, such as pasted images, when cleanupPeriodDays is set to a very large value · Fixed compaction after a "Prompt is too long" error keeping too much of a conversation with dense text, such as base64 or SVG, so the next request could fail again · Fixed file read permission prompts not showing where a symbolic link leads · Fixed a question's auto-continue timeout firing the moment the external editor closed after a long edit

tag:newruntime.com,2026:tool-change:claude-code:041888a4-b482-424d-ae3c-b2155bc412552026-10-22T00:00:00Z

Bug fixes and reliability improvements

tag:newruntime.com,2026:tool-change:claude-code:3f0a253c-25bf-4e77-92ed-218920989c342026-10-22T00:00:00Z

Fixed sandboxed Bash commands on macOS and Linux running the shell's startup files outside the sandbox before each command · Fixed macOS sandbox denyWrite glob patterns not applying at a path's real location when the pattern's folder is reached through a symlink · Fixed sandboxed commands and auto-accepted edits being able to modify the MCP config file passed with --mcp-config · Fixed a disabled MCP server being reconnected by a later permission prompt in print and SDK sessions · Fixed the Bash permission check trusting a variable set by a command whose redirect can fail to open · Fixed Bash permission checks not prompting for some compound commands that change directory before running git when the cd is wrapped or prefixed, as they do for a plain cd

tag:newruntime.com,2026:tool-change:claude-code:1e341770-b1eb-4e7e-9d98-907c764be7822026-10-21T00:00:00Z

Fixed claude -p inside cloud sessions reporting "Not logged in" when started without the session's environment variables · Fixed an API error being replaced by "prompt is too long", and an unneeded compaction, in sessions with many MCP tools

tag:newruntime.com,2026:tool-change:claude-code:93d0150b-f3b6-4672-a085-e2c2c4930c492026-10-21T00:00:00Z

Added /claude-api api-version to move Claude API code to API version 2026-10-21 · Added the claude_code.safety_event OpenTelemetry event for each tool call a permission rule, auto mode, a safety check, a hook or the sandbox stopped, prompted or sent back · Fixed requests failing with a model-not-found error when CLAUDE_CODE_DISABLE_1M_CONTEXT is set and the model is an alias with the [1m] suffix, such as opus[1m] · Fixed the prompt-caching-scope beta header being sent behind custom ANTHROPIC_BASE_URL gateways and on Foundry, where it has no effect · Fixed MCP servers showing "needs authentication" in claude -p on macOS while the login keychain was locked; they now say why, and the next run after an unlock connects without a new sign-in · Fixed MCP servers being reported as timed out, and staying failed in headless runs, when a macOS or Linux computer went to sleep while they were connecting

tag:newruntime.com,2026:tool-change:claude-code:da9bebf3-2262-4f12-bb11-4025f952e9362026-10-20T00:00:00Z

Added sandbox.allowNestedUserNamespaces so sandboxed commands on Linux can create user namespaces (Chromium, rootless podman); this lets them get around the sandbox's file protections · Added CLAUDE_CODE_RETRY_WATCHDOG_USAGE_LIMIT_RECHECK_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) notices a usage limit that was lifted before its reset · Fixed every request failing on Vertex, Bedrock and other providers when the endpoint or a gateway rejects tool search, and behind gateways with ToolSearch disallowed or left out of --tools (a 2.1.304 regression): Claude Code now retries wi… · Fixed /effort and /autocompact settings not applying when the model name differed from a modelOverrides value by letter case or a [1m] tag · Fixed new worktrees in a bare repository sometimes starting from local HEAD instead of the default branch, and unchanged subagent worktrees sometimes not being cleaned up · Fixed Bash commands on a full disk failing with a raw ENOSPC file path: the error now says the disk is full and that nothing ran

tag:newruntime.com,2026:tool-change:claude-code:2adf46b2-ece5-49c4-9611-7031419b12062026-10-19T00:00:00Z

Added a transcript line when a plugin that runs first skips one of your mod's hooks, naming the event and the plugin · Added decider: "person" to a mod's tool.check answer: only the permission dialog or a host's callback can approve the ask, and it is refused with the mod's reason where nobody can be asked · Added e.isReadOnly to a mod's tool.check event, set when the tool call is read-only · Added /auto-mode-setup: a guided setup that reads your project and recent sessions to teach auto mode about your environment, now also available on Bedrock, Vertex, Foundry, Claude apps gateway and telemetry-disabled sessions · Added /claude-api managed-agents-secure, which compares a Managed Agents agent's settings with Anthropic's published security guide, without changing anything · Added the names of the tools called earlier to the compaction summary in the transcript view (Ctrl+O)

tag:newruntime.com,2026:tool-change:claude-code:6f4399fc-4553-4a17-bfb8-f18c4ddb7f402026-10-18T00:00:00Z

Bug fixes and reliability improvements

tag:newruntime.com,2026:tool-change:claude-code:45738360-2a4a-44f0-b7b0-f643c9fd3be92026-10-16T00:00:00Z

Added CLAUDE_CODE_AUTO_MODE_MODEL to choose the model the client-side auto mode classifier uses; it does not change the model for server-side auto mode · Added an Idle compaction row to /config for turning idle compaction off or back on; the notices shown after an idle compaction now say how to turn it off · Added a notice to /design-sync and /design-login that standalone Claude Design (claude.ai/design) closes by December 14, 2026 · Fixed a "Prompt is too long" error when stopping a turn while the conversation was being compacted · Fixed requests failing with "diagnostics: Extra inputs are not permitted" after switching to Vertex or Bedrock mid-session · Fixed the Read tool loading an image file of any size, or a pipe or device named like an image, entirely into memory; image sources over 128 MB are now refused

tag:newruntime.com,2026:tool-change:claude-code:5ad4308c-37bd-4316-aa68-0ea1ada531692026-10-15T00:00:00Z

Added CLAUDE_CODE_RETRY_WATCHDOG_MAX_USAGE_LIMIT_WAIT_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) ends a request at a usage limit that resets too far away instead of waiting · Added OpenTelemetry tracing guidance to the claude-api skill, including setting up trace destinations with the ant CLI · Added the % motion to vim mode: jump to the matching bracket, alone or with d/c/y · Added rows to a mod's Input: a text field of several lines in the terminal, where Enter submits and Shift+Enter or a backslash before Enter starts a new line · Added classifier_verdict and permission_mode to OpenTelemetry tool_decision events, so auto mode classifier decisions can be told apart from permission rules · Added classifier_category to OpenTelemetry tool_decision events, naming the built-in rule a classifier block matched, when OTEL_LOG_TOOL_DETAILS=1

tag:newruntime.com,2026:tool-change:claude-code:c2646532-efd1-408d-a19d-a4557a50da282026-10-14T00:00:00Z

Added CLAUDE_CODE_DISABLE_FILE_MENTIONS environment variable: Claude gets the paths of @ file mentions to read with its file tools, not the files' contents · Added idle compaction in the terminal: a 200K+ token conversation left idle for about 54 minutes is compacted before its one-hour prompt cache expires, so your next message doesn't reprocess it all · Added CLAUDE_CODE_IDLE_COMPACT_MIN_TOKENS to change idle compaction's 200K-token minimum; "idleCompaction": false in settings.json turns it off. Both need v2.1.290 or later · Added $.prompt.media so a prompt.submit hook of a mod installed by managed settings can read the bytes of an image or document attached to the prompt · Added $.session.identity() for mods installed by managed settings: how the session is signed in, and its organization and email when managed forceLoginOrgUUID lists that organization · Added size, weight, mono and tabular to a mod's Text and named spacing steps (xs to xl) to its Box; bold is deprecated in favor of weight

tag:newruntime.com,2026:tool-change:claude-code:b0104538-bc4b-4424-a67f-071a4c61226b2026-10-14T00:00:00Z

Added virtualText to a mod's prompt decorations: text drawn in the prompt box that never enters the draft or the submitted prompt · Added cache_creation_5m_tokens and cache_creation_1h_tokens to the OpenTelemetry api_request event, splitting cache writes by lifetime · Added $.ui.view({ agentId }) for mods: shows an agent's transcript in the main view when you ask, and $.ui.view({}) goes back · Added a dir prop on a mod's Text for right-to-left text: on Windows and in VS Code's terminal its rows read in that direction and sit flush right · Added /advisor on Claude Platform on AWS; no advisor runs until you pick one with /advisor, advisorModel or --advisor, and CLAUDE_CODE_DISABLE_ADVISOR_TOOL=1 turns it off · Added OpenTelemetry GenAI semantic-convention attributes to trace spans, such as gen_ai.provider.name, gen_ai.conversation.id, gen_ai.tool.name and error.type

tag:newruntime.com,2026:tool-change:claude-code:bf455538-1ba2-4d50-951b-8e948d65f3f22026-10-09T00:00:00Z

Added a code key to the Claude apps gateway's managed.policies[]: the same settings as cli, also applied in Claude Desktop's Code tab; beside desktop, it turns on Claude Desktop's gateway mode · Added autoCompactWindow to subagent frontmatter and --agents definitions, so a subagent can auto-compact earlier than the main conversation's window · Added CLAUDE_CODE_WORKFLOW_SUBAGENT_MODEL to run every workflow agent on one model while other subagents keep theirs · Added CLAUDE_CODE_OVERLOADED_RETRY_MAX_DELAY_MS environment variable to set a longer maximum delay for the backoff when retrying an overloaded (529) request · Added a note in /plugin on a plugin whose hooks are left out because another enabled plugin has the same name · Added an allow_large option to the Read tool so Claude can read a text file past the usual size limits in one call when it needs the whole file and the context has room

tag:newruntime.com,2026:tool-change:claude-code:19f0260c-4887-4526-bd8f-f5f5f317601f2026-10-08T00:00:00Z

Fixed prompt and agent hooks written as instructions (such as "Block commands that...") allowing what they should block · Improved how prompt hooks on Stop and SubagentStop written as instructions (such as "Carry on if the build is broken") are judged, so Claude is less likely to stop early

tag:newruntime.com,2026:tool-change:claude-code:e2fee5f0-1597-49ee-99a9-bec5cb95502b2026-10-08T00:00:00Z

Added onFailure: "block" for command and HTTP hooks: a hook that can't start, times out, or exits with an unexpected code blocks the action instead of letting it through · Added Program Status Protocol (OSC 7501) support: terminals that implement it can show whether Claude Code is working, waiting on you, or done · Added quoted text to the /copy picker, so a drafted message copies without its > markers · Added a warning to claude plugin install, enable, disable and marketplace add when the settings file they write to does not load · Added a line on stderr, when it is a terminal, that says what a claude -p run is waiting for when it stays open after its last turn · Added support for timeouts.upstream_ttfb_ms on the Claude apps gateway's Bedrock, Vertex, Foundry and other cloud upstreams: a value you set now limits how long a stream may take to start there, after which it fails over or gets a 502

tag:newruntime.com,2026:tool-change:claude-code:151ef236-ebf6-473e-9886-10497a5b11cc2026-10-07T00:00:00Z

Added Claude Haiku 5.5 (claude-haiku-5-5), now the default Haiku model on the Anthropic API — 1M context, $0.10/$0.50 per Mtok ($0.50/$2.50 for prompts over 100K) · Added agentType to the subagentStatusLine payload, so scripts can tell custom subagent types apart · Added isDeferred to $.tool.register for mods: false lists the tool's schema in the prompt from the start instead of behind tool search · Fixed Claude sometimes treating its own last actions before a context compaction as done after it, and retracting or redoing finished work · Fixed a memory leak where an HTTP MCP connection kept every request it had sent until it closed · Fixed a message sent while Claude was working being lost when ← moved the session to the background; if a queued message can't move, ← now stays put and says so

tag:newruntime.com,2026:tool-change:claude-code:cd300eaa-f062-47a5-9463-47f601bd36942026-10-06T00:00:00Z

Fixed a regression in 2.1.290 where cloud sessions could drop answers to permission prompts · Fixed a regression in 2.1.288 where the last messages of a session could be lost when quitting

tag:newruntime.com,2026:tool-change:claude-code:51a1ace3-386c-4eca-bc35-4fad0f25c4632026-10-06T00:00:00Z

Added --marketplace to claude plugin install: adds the marketplace if needed, under the same policy checks as claude plugin marketplace add, then installs the plugin from it · Added an effort parameter to the Agent tool, so Claude runs a sub-agent at the effort level you ask for · Added CLAUDE_CODE_OVERLOADED_RETRY_BASE_DELAY_MS environment variable to set a longer base delay for the backoff when retrying an overloaded (529) request · Added prompt.autocomplete, an event a mod hooks to add its own rows to the prompt box's autocomplete list · Added prompt caching to $.model.complete for mods: prompt and system take blocks of text, and cache: true on a block caches the request up to it · Added workflow agents to the agent.spawn mod hook, with their run and index, so a mod can refuse them

tag:newruntime.com,2026:tool-change:claude-code:446bb6e0-7000-4b76-84fb-4127b87c6d9b2026-10-05T00:00:00Z

Added serverToolUses to the result of a mod's turn.step hook: the tool calls the API ran itself (the advisor), each with its id, name, input, start and end · Added agentId to the tool.check event of plugin hooks, so a hook can tell a subagent's permission check from the main session's · Added ceiling to the question and verdict a mod's tool.check hook reads, naming the approval an organization requires for a tool · Added ThemeKey and Color types to the plugin hooks typings, so an editor lists the theme colors a mod's drawing can name · Added to claude plugin validate: each hook a mod registers at a gating site is listed with whether it has a .catch (gatingHooks under --json) · Added a Deny button to the Claude apps gateway's sign-in approval page: it ends the pending sign-in, so the waiting terminal stops within seconds

tag:newruntime.com,2026:tool-change:claude-code:1543eb32-4ada-480c-bb0d-f9a0e42dcb922026-10-03T00:00:00Z

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 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

tag:newruntime.com,2026:tool-change:claude-code:29c33945-67af-41ec-b270-f91d49dcffff2026-10-02T00:00:00Z

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 |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

tag:newruntime.com,2026:tool-change:claude-code:6156c5de-df04-4fe2-a863-cf63f9e4b59a2026-10-01T00:00:00Z

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: 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

tag:newruntime.com,2026:tool-change:claude-code:e1432733-69bf-4bea-b7aa-0ab90f90ad332026-09-30T00:00:00Z

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

tag:newruntime.com,2026:tool-change:claude-code:a4b8f786-08a7-45a4-901c-9be519bb6fe62026-09-29T00:00:00Z

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 · Added claude plugin configure to show a plugin's options and which are unset, or save new values read from stdin with --values-stdin · Added . = 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

tag:newruntime.com,2026:tool-change:claude-code:f11be725-d740-47d6-915d-4ea148f45b7c2026-09-28T00:00:00Z

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… · 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

tag:newruntime.com,2026:tool-change:claude-code:9d4ecf55-eba5-47e7-8be3-c4cd6fc573ad2026-09-25T00:00:00Z

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

tag:newruntime.com,2026:tool-change:claude-code:67a66275-1252-46f6-ab14-ab8b6e04f0872026-09-24T00:00:00Z

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)

tag:newruntime.com,2026:tool-change:claude-code:14451be3-c01c-405b-bfee-d94ea07a52ef2026-09-23T00:00:00Z

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