Source Intelligence
Sweep 28 Aug 2026 · 00:00Z Build v2.1.250 478 read Stable v2.1.236 Latest v2.1.250 Next v2.1.251 Feeds RSS JSON llms.txt
Reading a new release v2.1.251 Analysing changes · 2/5 Deeper second pass · 0/5 agents 427 findings $12.75 so far

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

One change

Changelog

cowork/changelog

first seen The page's own history The capture it came from

Nearest release: v2.1.234, published 2 hours before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

cowork/changelog Changed · +43 / -0 lines

from line 2
 
 > Release notes for Claude Desktop
 
+<Update label="v1.32352.0" description="2026-08-17">
+  **General**
+
+  * Fixed Windows updates sometimes leaving the app half installed, with later updates failing too.
+  * Fixed the app staying on "Couldn't connect to Claude" when a network proxy blocked its first connection; it now keeps retrying for a few minutes and again when you return to the window.
+  * Fixed the composer staying disabled after a usage-limit notice when your organization has extra usage turned off or not set up; sending works again once your admin turns it on.
+  * Fixed settings and connector links in chat doing nothing, or opening your web browser, when clicked in the app; they now open the app's own settings.
+  * Fixed text typed on the new chat page sometimes disappearing when turning on incognito.
+  * Fixed the chat showing an error screen instead of the conversation when Claude created or linked a file whose name contains a percent sign.
+
+  **Code**
+
+  * Changed auto-continue after the 5-hour usage limit to be on by default: sessions left open resume when the limit resets. Uncheck "Auto-continue when limits reset" in the limit banner to turn it off for your account.
+  * Fixed sessions sometimes hanging after resume, either showing "The session stopped responding" after the first message or never starting when a file system or MCP server stalled.
+  * Fixed undo (Cmd+Z, or Ctrl+Z on Windows and Linux) in the message composer sometimes failing with an error and then no longer working.
+  * Fixed a brand-new cloud session losing its first message when you navigated away within a few seconds of sending it.
+  * Fixed sessions started right after the app opened sometimes running in a more permissive mode than your saved permission mode.
+  * Fixed Remote Control sessions staying stuck at "connecting" after you completed the sign-in or device-check prompt, and file links not opening when the session was viewed from another computer.
+
+  **Cowork**
+
+  * Removed the "Allow all browser actions" option from Claude in Chrome permission cards; allow each website instead. The switch in Settings is unchanged.
+  * Fixed the workspace startup error suggesting a restart or reinstall when the computer was low on disk space; it now asks you to free up space and retry.
+  * Fixed a tool call hanging for a full minute when its local MCP server crashed mid-call; it now fails right away.
+  * Fixed computer use on macOS refusing every click after you had taken a screenshot or while a screen recording was running.
+  * Fixed the approval mode still showing "Skip all approvals" when your organization's policy had blocked it; switching back to "Manually approve" now asks again before Claude fetches web pages it visited while approvals were off.
+  * Fixed the activity panel button doing nothing while a file was open beside the chat; it now closes the file and shows the panel.
+
+  **3P**
+
+  * Added `claudeAiImport.exportEnabled`. With it and `claudeAiImport.enabled` both `true`, users can export this computer's chats, Cowork tasks, and Code sessions from Settings > Import & export as a zip that another install can import. Off by default.
+  * Added a `url` source for `allowedPluginMarketplaces` (beta): a hosted `marketplace.json` that delivers plugins as zip archives over HTTPS, with no git on the device. Set `manifestSha256` to pin the exact manifest; it is required for automatically installed plugins.
+  * Added `inferenceCredential` as a `credentialKind` for `allowedPluginMarketplaces` (beta): a `url` marketplace hosted on your inference gateway is fetched with the same credential the app already uses for inference.
+  * Changed `coworkEgressAllowedHosts`: a `:port` suffix now also applies to shell commands and package installs in Cowork sessions, which previously could not reach a port-scoped host at all.
+  * Changed settings from a locally configured (not device-managed) bootstrap URL that need user approval to apply all or nothing: nothing takes effect until the user chooses Allow; Quit closes the app and asks again next launch.
+  * Changed a served configuration with an invalid connection value to report that field by name and keep the organization's other settings in force; a non-Anthropic model entry is now skipped with a warning instead of invalidating the whole configuration.
+  * Changed admin-configured plugin marketplaces (`allowedPluginMarketplaces`, beta), including automatically installed and required plugins, to apply to Code sessions as well as Cowork.
+  * Changed new Cowork sessions to use much shorter folder names on disk so file paths are less likely to exceed Windows path-length limits; existing sessions keep their folders, and tooling that matches the `local_` prefix should also match the new names.
+  * Fixed Settings > Import & export saying import isn't enabled on deployments that provision the sign-in import without setting `claudeAiImport.enabled`; that key now governs only file and earlier-session import, the import prompt, and session export.
+  * Fixed the Setup window accepting a mis-typed inference region, Azure AI Foundry resource name, blank Vertex AI project ID, or non-Anthropic model ID that was only rejected later on the device; these are now flagged before saving.
+  * Fixed imported project instructions arriving as a loose file instead of the project's editable Instructions; they are now shown for review on the project page and apply once you accept them.
+</Update>
+
 <Update label="v1.30096.5" description="2026-08-14">
   **General**