{"version":"2.1.305","summary":"Claude can now upload a local file to Google Drive by naming it, up to 10 MB. Claude Code reads the file only after you approve the call. In remote sessions that support it, you can now run '!' shell commands, with a 10 minute timeout. Sonnet 4, Sonnet 4.6 and Opus 4.6 now list a 1 million token maximum context window. `claude plugin validate` now also checks a plugin's folder layout. A new environment variable, `CLAUDE_CODE_CCR_EVENT_FLUSH_POLICY`, sets how a remote session sends out its events.\n\nSeveral features are in this build but not switched on yet. \/usage is getting a way to look through your recent sessions and suggest how to use less of your plan. It could then queue the fixes you pick, such as `\/compact` or lower effort, as prompts. Groundwork is also present for `--resume` to pick up a cloud session. Cloud sessions may later check each MCP server's host against an allow or deny list. While waiting on a usage limit, Claude Code could send a test request to see whether the limit has lifted.\n\nShell commands sent to a session for one folder are now refused if the session is working in a different folder. Disallowed tools now stay blocked while a leftover permission request is handled. Team memory changes held back by a sync pause are now kept and retried instead of dropped. The hint to raise `API_TIMEOUT_MS` after a timeout now notices a value set in your settings. Worktrees made from origin's default branch now use the exact remote branch. The message saying auto mode works only inside the sandbox has been removed.","filter":{"section":null,"tier":null,"area":null},"offset":0,"limit":50,"count":50,"total":252,"next_offset":50,"next_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/entries.json?offset=50","entries":[{"anchor":"remote-sessions-bash-commands-now-run-locally-when-the","heading":"&#039;!&#039; shell commands can now run in remote sessions that support them","glance":"In a remote session that supports it, a '!' shell command can now run, with limits on output and a 10 minute timeout","teaser":null,"tier":"use","area":"Sessions","section":"What probably matters to you","position":0,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/remote-sessions-bash-commands-now-run-locally-when-the","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/remote-sessions-bash-commands-now-run-locally-when-the.json"},{"anchor":"claude-plugin-validate-profile-directory-runs-plugin-dir","heading":"<code>claude plugin validate --profile directory<\/code> checks a plugin against the plugin directory&#039;s rules","glance":"`claude plugin validate` gains `--profile directory`, which checks a plugin folder for the plugin directory's submission rules and can fail a CI run","teaser":null,"tier":"use","area":"Plugins","section":"What probably matters to you","position":1,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/claude-plugin-validate-profile-directory-runs-plugin-dir","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/claude-plugin-validate-profile-directory-runs-plugin-dir.json"},{"anchor":"new-env-var-claude-code-ccr-event-flush-policy-feeds-a-launc","heading":"Remote sessions can hold transcript uploads across model calls, with a new launch-time flush policy","glance":"Remote (CCR) sessions gain new rules for batching transcript uploads: holding across model calls, merged status reports, viewer checkpoints and a launch policy","teaser":null,"tier":"use","area":"Sessions","section":"What probably matters to you","position":2,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/new-env-var-claude-code-ccr-event-flush-policy-feeds-a-launc","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/new-env-var-claude-code-ccr-event-flush-policy-feeds-a-launc.json"},{"anchor":"bash-mode-input-in-sdkheadless-path-with-a-client-bash-com","heading":"<code>!<\/code> shell commands get their own path in SDK input and are refused in the cloud-session view","glance":"Bash-mode `!` input now travels with `inputMode` and `clientBashCommandCwd` in SDK input, and is refused with a message in a remote cloud-session view","teaser":null,"tier":"use","area":"SDK","section":"What probably matters to you","position":4,"scope":"individual","heads_up":true,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/bash-mode-input-in-sdkheadless-path-with-a-client-bash-com","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/bash-mode-input-in-sdkheadless-path-with-a-client-bash-com.json"},{"anchor":"usage-gains-actionable-savings-suggestions-with-one-click-f","heading":"\/usage suggests ways to save usage and can queue fixes for them","glance":"\/usage now ranks what is using your plan, offers savings suggestions such as lowering effort or compacting, and can queue a fix prompt","teaser":null,"tier":"notice","area":"Usage Report","section":"What probably matters to you","position":5,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/usage-gains-actionable-savings-suggestions-with-one-click-f","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/usage-gains-actionable-savings-suggestions-with-one-click-f.json"},{"anchor":"cloud-worker-bash-command-can-run-through-the-bash-tool-gat","heading":"Cloud sessions can run shell commands as a turn Claude sees","glance":"A second mode lets cloud workers run a requested shell command through Claude's Bash tool, so Claude sees it and the folder carries over","teaser":null,"tier":"soon","area":"Cloud Sessions","section":"What probably matters to you","position":7,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/cloud-worker-bash-command-can-run-through-the-bash-tool-gat","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/cloud-worker-bash-command-can-run-through-the-bash-tool-gat.json"},{"anchor":"claude-code-entrypoint-on-requests-env-var-renames-the-entr","heading":"A desktop host can set the name Claude Code&#039;s requests are sent under","glance":"`CLAUDE_CODE_ENTRYPOINT_ON_REQUESTS` sets the name requests go out under, but only when `CLAUDE_CODE_ENTRYPOINT` is `claude-desktop-3p`","teaser":null,"tier":"use","area":"Desktop","section":"What probably matters to you","position":8,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/claude-code-entrypoint-on-requests-env-var-renames-the-entr","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/claude-code-entrypoint-on-requests-env-var-renames-the-entr.json"},{"anchor":"new-ccr-early-sync-escape-hatch-after-a-settings-403","heading":"Cloud sessions can sync early even after a refused settings fetch","glance":"A new switch, `CLAUDE_CODE_CCR_EARLY_SYNC_AFTER_SETTINGS_REFUSAL`, lets cloud sessions take the early sync path when the settings fetch is refused","teaser":null,"tier":"use","area":"Cloud Sessions","section":"What probably matters to you","position":9,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/new-ccr-early-sync-escape-hatch-after-a-settings-403","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/new-ccr-early-sync-escape-hatch-after-a-settings-403.json"},{"anchor":"new-profile-forget-hint-for-sandboxed-commands-reading-the","heading":"New message explains how to withdraw sandbox access to your user profile","glance":"A new message says to close every Claude Code session and run `profile forget` so sandboxed commands stop reading your user profile","teaser":null,"tier":"use","area":"Sandbox","section":"What probably matters to you","position":10,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/new-profile-forget-hint-for-sandboxed-commands-reading-the","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/new-profile-forget-hint-for-sandboxed-commands-reading-the.json"},{"anchor":"pointerless-mcp-elicitation-consent-prompt-behind-claude-cod","heading":"MCP question dialogs know which plugin asked, with an optional no-preselection mode","glance":"MCP elicitation dialogs now receive the plugin source, and CLAUDE_CODE_CONSENT_POINTERLESS can stop Accept being preselected","teaser":null,"tier":"use","area":"MCP","section":"What probably matters to you","position":11,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/pointerless-mcp-elicitation-consent-prompt-behind-claude-cod","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/pointerless-mcp-elicitation-consent-prompt-behind-claude-cod.json"},{"anchor":"windows-sandbox-user-profile-read-grant-with-credential-sto","heading":"Windows sandbox reworked: localhost access fixed at install, readable profile, clearer repair messages","glance":"On Windows the sandbox now sets localhost access at install, can let commands read your profile except credential stores, and explains how to repair it","teaser":null,"tier":"use","area":"Sandbox","section":"What probably matters to you","position":12,"scope":"individual","heads_up":true,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/windows-sandbox-user-profile-read-grant-with-credential-sto","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/windows-sandbox-user-profile-read-grant-with-credential-sto.json"},{"anchor":"drive-file-references-upload-files-without-typing-base64","heading":"Google Drive connector can upload local files by reference instead of typed base64","glance":"Behind tengu_wobbly_dewdrop, Drive's create_file can take a file reference that Claude Code reads after approval; HIPAA orgs are denied","teaser":null,"tier":"notice","area":"MCP","section":"What probably matters to you","position":13,"scope":"both","heads_up":true,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/drive-file-references-upload-files-without-typing-base64","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/drive-file-references-upload-files-without-typing-base64.json"},{"anchor":"iterm2-inline-image-support-in-the-fullscreen-renderer","heading":"Images can display in iTerm2 in fullscreen mode","glance":"The fullscreen renderer can now show images in iTerm2 3.5 or later using its inline image protocol, alongside the existing kitty support","teaser":null,"tier":"notice","area":"Terminal UI","section":"What probably matters to you","position":15,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/iterm2-inline-image-support-in-the-fullscreen-renderer","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/iterm2-inline-image-support-in-the-fullscreen-renderer.json"},{"anchor":"promo-credit-notice-fable-is-on-us","heading":"One-time startup notice for free Fable credit chosen by your admin","glance":"A one-time startup notice, \"Fable is on us\", tells eligible organisation users their admin opted them in to free credit for Fable usage","teaser":null,"tier":"notice","area":"Models","section":"What probably matters to you","position":16,"scope":"both","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/promo-credit-notice-fable-is-on-us","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/promo-credit-notice-fable-is-on-us.json"},{"anchor":"usage-view-gets-recommendations-and-a-one-key-fix-that-sends","heading":"Usage view now gives recommendations and a one-key fix","glance":"The usage view and the SDK `get_usage` reply now carry recommendations, plus a fix you can send with one key unless Remote Control is on","teaser":null,"tier":"notice","area":"Usage Report","section":"What probably matters to you","position":18,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/usage-view-gets-recommendations-and-a-one-key-fix-that-sends","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/usage-view-gets-recommendations-and-a-one-key-fix-that-sends.json"},{"anchor":"cloud-only-mcp-host-allowdeny-list-via-tengu-gleaming-creek","heading":"Cloud sessions can allow or block MCP servers by host","glance":"In Anthropic cloud sessions, Claude Code can check each MCP server's host against an allow or deny list sent by the server","teaser":null,"tier":"soon","area":"MCP","section":"What probably matters to you","position":20,"scope":"org","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/cloud-only-mcp-host-allowdeny-list-via-tengu-gleaming-creek","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/cloud-only-mcp-host-allowdeny-list-via-tengu-gleaming-creek.json"},{"anchor":"hybrid-sign-in-and-settings-only-grant-plumbing-in-login-ui","heading":"Login screen gains a hybrid sign-in path and a settings-only grant","glance":"The login screen can now finish with a hybrid sign-in, and the sign-in flow accepts a `settingsOnlyGrant` option with an extra scope","teaser":null,"tier":"soon","area":"Auth","section":"What probably matters to you","position":21,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/hybrid-sign-in-and-settings-only-grant-plumbing-in-login-ui","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/hybrid-sign-in-and-settings-only-grant-plumbing-in-login-ui.json"},{"anchor":"bridgeremote-internals-new-origin-user-presence-queued-w","heading":"Groundwork for remote sessions, including email-started sessions and wake-ups","glance":"Claude Code adds internal pieces for remote sessions: a new email origin, tracking of when a person last wrote, queued wake-ups and more","teaser":null,"tier":"soon","area":"Sessions","section":"What probably matters to you","position":22,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/bridgeremote-internals-new-origin-user-presence-queued-w","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/bridgeremote-internals-new-origin-user-presence-queued-w.json"},{"anchor":"cloud-with-a-named-resume-maps-resume-to-a-cloud-session","heading":"Groundwork for resuming a cloud session with <code>--resume<\/code>","glance":"Code that would let `--resume` pick up a cloud session alongside `--cloud` is present but cannot be reached in this build","teaser":null,"tier":"soon","area":"Cloud Sessions","section":"What probably matters to you","position":23,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/cloud-with-a-named-resume-maps-resume-to-a-cloud-session","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/cloud-with-a-named-resume-maps-resume-to-a-cloud-session.json"},{"anchor":"cloud-session-shell-routing-gated-by-tengu-cloud-session-she","heading":"Groundwork for running your own shell commands in cloud sessions, off by default","glance":"Claude Code can now queue and run shell commands sent by the client in headless and SDK sessions, behind a remote switch that defaults to off","teaser":null,"tier":"soon","area":"Cloud Sessions","section":"What probably matters to you","position":24,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/cloud-session-shell-routing-gated-by-tengu-cloud-session-she","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/cloud-session-shell-routing-gated-by-tengu-cloud-session-she.json"},{"anchor":"cloud-resume-launch-option-resumeincloud","heading":"Startup options include a new resume-in-cloud value","glance":"Claude Code's startup options now produce a value for resuming in the cloud","teaser":null,"tier":"soon","area":"Cloud Sessions","section":"What probably matters to you","position":25,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/cloud-resume-launch-option-resumeincloud","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/cloud-resume-launch-option-resumeincloud.json"},{"anchor":"usage-limit-wait-now-probes-to-see-if-the-limit-has-lifted","heading":"Waiting on a usage limit now checks whether the limit has lifted","glance":"While a request waits on a usage limit, Claude Code can now probe and resend it at once if the limit has already lifted","teaser":null,"tier":"soon","area":"Usage & Limits","section":"What probably matters to you","position":26,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/usage-limit-wait-now-probes-to-see-if-the-limit-has-lifted","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/usage-limit-wait-now-probes-to-see-if-the-limit-has-lifted.json"},{"anchor":"claude-auth-login-handles-no-callback-listener-headlessssh","heading":"Sign-in falls back to pasting a code when the local listener cannot start","glance":"If Claude Code cannot open its local sign-in listener, login now shows a URL and asks you to paste the code instead of failing","teaser":null,"tier":"use","area":"Auth","section":"What probably matters to you","position":27,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/claude-auth-login-handles-no-callback-listener-headlessssh","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/claude-auth-login-handles-no-callback-listener-headlessssh.json"},{"anchor":"cloud-sessions-sign-in-screen-on-auth-failure-existing-ses","heading":"Cloud sessions can open a sign-in screen when sign-in fails","glance":"If sign-in fails when starting a `--cloud` session, Claude Code can now show a sign-in screen and carry on instead of only printing an error","teaser":null,"tier":"use","area":"Cloud Sessions","section":"What probably matters to you","position":28,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/cloud-sessions-sign-in-screen-on-auth-failure-existing-ses","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/cloud-sessions-sign-in-screen-on-auth-failure-existing-ses.json"},{"anchor":"headless-client-supplied-disallowed-tools-can-persist-acros","heading":"Headless runs can keep a tool block list across turns","glance":"In headless runs, a list of tools the client blocks can now be kept and reused across turns instead of being read fresh every turn","teaser":null,"tier":"use","area":"Headless Mode","section":"What probably matters to you","position":29,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/headless-client-supplied-disallowed-tools-can-persist-acros","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/headless-client-supplied-disallowed-tools-can-persist-acros.json"},{"anchor":"local-option-value-all-for-running-every-test","heading":"New local option to run every test, not only the ones covering your changes","glance":"A new choice labelled \"all\" runs every test on your own machine instead of only the tests that cover what changed","teaser":null,"tier":"use","area":"Testing","section":"What probably matters to you","position":30,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/local-option-value-all-for-running-every-test","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/local-option-value-all-for-running-every-test.json"},{"anchor":"sign-in-prompt-when-cloud-session-launched-without-claudeai","heading":"Cloud sessions now point you to \/login instead of failing","glance":"When no cloud session can run because you are not signed in, Claude Code blocks input, tells you to run \/login, and restarts into the session afterwards","teaser":null,"tier":"use","area":"Cloud Sessions","section":"What probably matters to you","position":31,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/sign-in-prompt-when-cloud-session-launched-without-claudeai","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/sign-in-prompt-when-cloud-session-launched-without-claudeai.json"},{"anchor":"email-sender-turn-rules-added-to-the-auto-mode-classifier-pr","heading":"Auto mode learns how to read requests that arrive by email","glance":"Auto mode's safety checker gains rules for messages sent by email, where only the sender's new words count as their request","teaser":null,"tier":"notice","area":"Auto Mode","section":"What probably matters to you","position":32,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/email-sender-turn-rules-added-to-the-auto-mode-classifier-pr","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/email-sender-turn-rules-added-to-the-auto-mode-classifier-pr.json"},{"anchor":"autonomous-mode-prompt-loosens-when-to-ask-questions","heading":"In autonomous mode Claude now asks first only before actions it cannot undo","glance":"The autonomous-mode instructions now tell Claude to ask only before irreversible steps and go ahead on anything reversible, including pushing an approved PR","teaser":null,"tier":"notice","area":"Autonomous Mode","section":"What probably matters to you","position":33,"scope":"individual","heads_up":true,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/autonomous-mode-prompt-loosens-when-to-ask-questions","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/autonomous-mode-prompt-loosens-when-to-ask-questions.json"},{"anchor":"key-scan-prompt-for-mod-sharing-and-in-chat-packaging-guidan","heading":"Mod sharing asks in the chat whether to check a folder for secret keys","glance":"Before a mod is shared, Claude Code can now ask in the chat whether to check a folder and its subfolders for secret keys","teaser":null,"tier":"notice","area":"Mods","section":"What probably matters to you","position":34,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/key-scan-prompt-for-mod-sharing-and-in-chat-packaging-guidan","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/key-scan-prompt-for-mod-sharing-and-in-chat-packaging-guidan.json"},{"anchor":"1m-context-window-metadata-maximum-window-and-clamp-flag-ad","heading":"Long-context window detection reworked, with new maximum_window and clamp fields","glance":"Model data gains maximum_window and clamp_long_context_without_beta, and the check for 1M context without opt-in now compares window sizes","teaser":null,"tier":"notice","area":"Models","section":"What probably matters to you","position":35,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/1m-context-window-metadata-maximum-window-and-clamp-flag-ad","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/1m-context-window-metadata-maximum-window-and-clamp-flag-ad.json"},{"anchor":"new-allow-loopback-field-oncheckpointrequest-tengu-amber-l","heading":"Early groundwork for a loopback policy option and remote checkpoint requests","glance":"Policies can now record an allow-loopback setting, and remote sessions gained a hook for checkpoint requests, with no visible effect yet","teaser":null,"tier":"soon","area":"Sessions","section":"What probably matters to you","position":37,"scope":"both","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/new-allow-loopback-field-oncheckpointrequest-tengu-amber-l","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/new-allow-loopback-field-oncheckpointrequest-tengu-amber-l.json"},{"anchor":"added-mcp-task-holdcapped-predicate-and-rename-gains-a-cloud","heading":"MCP tasks in cloud sessions stop keeping the container up after a time limit","glance":"In Anthropic cloud sessions a running MCP task stops holding the container up after 168 hours by default, set by tengu_curious_river","teaser":null,"tier":"soon","area":"Cloud Sessions","section":"What probably matters to you","position":38,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/added-mcp-task-holdcapped-predicate-and-rename-gains-a-cloud","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/added-mcp-task-holdcapped-predicate-and-rename-gains-a-cloud.json"},{"anchor":"fleet-view-remote-session-rename-kept-cloud-marks-keyed-by","heading":"Fleet view keeps local titles for remote sessions, but renaming does nothing yet","glance":"The fleet view now shows locally kept titles for remote sessions, while its rename action for them is still empty","teaser":null,"tier":"soon","area":"Background Tasks","section":"What probably matters to you","position":39,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/fleet-view-remote-session-rename-kept-cloud-marks-keyed-by","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/fleet-view-remote-session-rename-kept-cloud-marks-keyed-by.json"},{"anchor":"hybrid-settings-scope-constant-added-off","heading":"New hybrid settings scope constant added","glance":"A build constant `HYBRID_SETTINGS_SCOPE_REGISTERED` appears next to the plugin and project scope constants, groundwork for a new settings scope","teaser":null,"tier":"soon","area":"Settings","section":"What probably matters to you","position":40,"scope":"both","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/hybrid-settings-scope-constant-added-off","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/hybrid-settings-scope-constant-added-off.json"},{"anchor":"plugin-authoring-hand-over-telemetry-constant-tengu-woven-p","heading":"Groundwork for handing over plugins written in a session","glance":"Claude Code can now track whether a plugin it wrote in a session was safety-scanned and delivered, and has text for sharing it with an organisation","teaser":null,"tier":"soon","area":"Plugins","section":"What probably matters to you","position":41,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/plugin-authoring-hand-over-telemetry-constant-tengu-woven-p","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/plugin-authoring-hand-over-telemetry-constant-tengu-woven-p.json"},{"anchor":"cloud-memory-tool-call-rendering-flag-and-quiet-words","heading":"Memory saves are counted and can be quieted in the transcript, and cloud memory calls are marked","glance":"Memory saves are now counted in tool-call summaries, can be shown quietly, are recorded in session stats, and cloud memory tool calls are tagged","teaser":null,"tier":"notice","area":"Memory","section":"What probably matters to you","position":43,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/cloud-memory-tool-call-rendering-flag-and-quiet-words","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/cloud-memory-tool-call-rendering-flag-and-quiet-words.json"},{"anchor":"new-settings-key-attributionprojectpolicy-and-a-new-analytic","heading":"Sessions can name a claude.ai Project for organization usage reports","glance":"New `attributionProject` and `attributionProjectPolicy` settings and `CLAUDE_CODE_ATTRIBUTION_PROJECT` name the claude.ai Project a session's usage is reported under","teaser":null,"tier":"notice","area":"Managed Settings","section":"What probably matters to you","position":45,"scope":"org","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/new-settings-key-attributionprojectpolicy-and-a-new-analytic","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/new-settings-key-attributionprojectpolicy-and-a-new-analytic.json"},{"anchor":"test-skill-argument-hint-adds-all","heading":"Claude Test: a safer browser helper and a new <code>all<\/code> argument","glance":"The `\/claude-test` skill's browser helper ignores risky project environment settings and explains missing Node.js, and the skill accepts `all`","teaser":null,"tier":"use","area":"Skills","section":"What probably matters to you","position":46,"scope":"individual","heads_up":true,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/test-skill-argument-hint-adds-all","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/test-skill-argument-hint-adds-all.json"},{"anchor":"tools-typo-warnings-now-also-surface-as-securitywarnings","heading":"Mistyped <code>--tools<\/code> exclusions now also produce short security warnings","glance":"A `--tools` exclusion that matches no built-in tool, or a bare prefix with no tool name, now also produces a short security warning","teaser":null,"tier":"use","area":"Permissions","section":"What probably matters to you","position":47,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/tools-typo-warnings-now-also-surface-as-securitywarnings","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/tools-typo-warnings-now-also-surface-as-securitywarnings.json"},{"anchor":"new-sandbox-setting-allownestedusernamespaces","heading":"Nested user namespace sandbox setting now covers WSL and more tools","glance":"`sandbox.allowNestedUserNamespaces` now also applies on WSL, names more tools that need it, and stays off by default","teaser":null,"tier":"use","area":"Sandbox","section":"What probably matters to you","position":48,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/new-sandbox-setting-allownestedusernamespaces","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/new-sandbox-setting-allownestedusernamespaces.json"},{"anchor":"axscreenreader-setting-ignored-in-projectlocal-settings","heading":"Project settings can no longer turn on screen reader mode","glance":"`axScreenReader` is now ignored in project and local settings, with a message saying how to turn screen reader mode on instead","teaser":null,"tier":"use","area":"Elsewhere","section":"What probably matters to you","position":49,"scope":"individual","heads_up":true,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/axscreenreader-setting-ignored-in-projectlocal-settings","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/axscreenreader-setting-ignored-in-projectlocal-settings.json"},{"anchor":"new-promo-credit-check-background-task-reads-wattle-ember","heading":"Claude Code checks your account for a promotional offer in the background","glance":"A new background task checks your usage for a promotional offer and saves whether it is open and when it ends, without showing you anything yet","teaser":null,"tier":"internal","area":"Usage & Limits","section":"What probably matters to you","position":50,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/new-promo-credit-check-background-task-reads-wattle-ember","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/new-promo-credit-check-background-task-reads-wattle-ember.json"},{"anchor":"plugin-sync-reports-converted-skills-as-plugins","heading":"Switch for syncing skills as plugins renamed to tengu_steady_finch, with server reporting added","glance":"The switch for treating skills as plugins moves from tengu_cached_pebble to tengu_steady_finch, and plugin sync now notes converted skills","teaser":null,"tier":"soon","area":"Plugins","section":"What probably matters to you","position":51,"scope":"both","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/plugin-sync-reports-converted-skills-as-plugins","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/plugin-sync-reports-converted-skills-as-plugins.json"},{"anchor":"teardown-waits-for-session-end-and-get-context-usage","heading":"Headless runs wait for the session to end and for context usage requests before exiting","glance":"Headless Claude Code now waits up to 30 seconds for the session to end and up to 5 minutes for a pending `get_context_usage` request before exiting","teaser":null,"tier":"notice","area":"Headless Mode","section":"Improvements","position":0,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/teardown-waits-for-session-end-and-get-context-usage","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/teardown-waits-for-session-end-and-get-context-usage.json"},{"anchor":"plugin-authoring-nudge-also-fires-on-a-third-content-marker","heading":"The plugin-authoring note after a command appears in one more case","glance":"The note Claude Code can add after you run a command about plugin authoring now triggers on a third kind of content","teaser":null,"tier":"notice","area":"Plugins","section":"Improvements","position":1,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/plugin-authoring-nudge-also-fires-on-a-third-content-marker","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/plugin-authoring-nudge-also-fires-on-a-third-content-marker.json"},{"anchor":"spawn-mode-message-printed-when-saved-choice-is-used","heading":"Claude Code now says when it uses your saved spawn mode for a folder","glance":"When a spawn mode saved for the current folder is used, Claude Code prints which one, and in an interactive terminal says to press w to change it","teaser":null,"tier":"notice","area":"Spawn Mode","section":"Improvements","position":2,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/spawn-mode-message-printed-when-saved-choice-is-used","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/spawn-mode-message-printed-when-saved-choice-is-used.json"},{"anchor":"model-switch-pending-error-gets-an-error-code","heading":"A pending model switch error now carries an error code","glance":"The error returned when a model switch is still pending now includes `error_code: \"verdict_pending\"`","teaser":null,"tier":"notice","area":"SDK","section":"Improvements","position":3,"scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/model-switch-pending-error-gets-an-error-code","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/model-switch-pending-error-gets-an-error-code.json"},{"anchor":"team-memory-sync-backs-off-when-the-server-asks","heading":"Memory sync and uploads now wait when the server asks them to","glance":"Team memory sync and some uploads now honor the server's retry-after signal, skip work while it lasts, and retry once the wait is over","teaser":null,"tier":"notice","area":"Memory","section":"Improvements","position":4,"scope":"both","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/team-memory-sync-backs-off-when-the-server-asks","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/team-memory-sync-backs-off-when-the-server-asks.json"},{"anchor":"teammate-plan-mode-exit-now-requires-leader-approval-based-o","heading":"Teammates need lead approval to leave plan mode based on their task","glance":"In agent teams, a teammate leaving plan mode is sent to the lead for approval based on its task, and no longer changes shared permissions","teaser":null,"tier":"notice","area":"Agent Teams","section":"Improvements","position":5,"scope":"individual","heads_up":true,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/teammate-plan-mode-exit-now-requires-leader-approval-based-o","entry_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/teammate-plan-mode-exit-now-requires-leader-approval-based-o.json"}],"facets":{"sections":[{"value":"What probably matters to you","entries":44},{"value":"Improvements","entries":92},{"value":"Bug Fixes","entries":20},{"value":"In Development","entries":16},{"value":"Internal Changes","entries":79},{"value":"Removed","entries":1}],"tiers":[{"value":"notice","entries":121},{"value":"internal","entries":83},{"value":"soon","entries":30},{"value":"use","entries":18}],"areas":[{"value":"Plugins","entries":25},{"value":"Sessions","entries":22},{"value":"Elsewhere","entries":20},{"value":"MCP","entries":19},{"value":"Internals","entries":16},{"value":"Sandbox","entries":13},{"value":"Permissions","entries":11},{"value":"Cloud Sessions","entries":9},{"value":"Terminal UI","entries":9},{"value":"Auth","entries":8},{"value":"Hooks","entries":8},{"value":"Background Tasks","entries":7},{"value":"Memory","entries":7},{"value":"Auto Mode","entries":5},{"value":"Models","entries":5},{"value":"SDK","entries":5},{"value":"Usage Report","entries":5},{"value":"Chrome & Browser","entries":4},{"value":"Headless Mode","entries":4},{"value":"Subagents","entries":4},{"value":"Telemetry","entries":4},{"value":"Agent Teams","entries":3},{"value":"Artifacts","entries":3},{"value":"Compaction","entries":3},{"value":"Remote Control","entries":3},{"value":"Tool Search","entries":3},{"value":"Tools","entries":3},{"value":"Usage & Limits","entries":3},{"value":"Workflows","entries":3},{"value":"Bash Safety","entries":2},{"value":"Skills","entries":2},{"value":"Unattended Serving","entries":2},{"value":"Autonomous Mode","entries":1},{"value":"Claude API Skill","entries":1},{"value":"Desktop","entries":1},{"value":"Evaluation","entries":1},{"value":"Managed Settings","entries":1},{"value":"Mods","entries":1},{"value":"Output Limits","entries":1},{"value":"Projects","entries":1},{"value":"Settings","entries":1},{"value":"Spawn Mode","entries":1},{"value":"Testing","entries":1},{"value":"Windows","entries":1}]}}