Chat in Claude Desktop on 3P

Chat in Claude Desktop on third-party (3P) is a conversational surface for quick questions and drafting. Unlike Cowork and Code, which run agentic sessions with access to folders you grant and a code-execution environment, a Chat conversation runs with a deliberately small tool surface: it can search and fetch the web under your admin configuration, read files attached to the conversation, read and update the project’s memory and read the files in the project’s folders when the conversation is inside a project, write files into a scratch space of its own, and use skills from the plugins you provision, and nothing else on the machine. Chat is off by default and is enabled with a single configuration key. Chat conversations run against your configured inference provider, and their history is stored on the user’s device. See User identity and local data for exactly what is written where and what can leave the device.

​

What a Chat conversation can reach

disabledBuiltinTools and builtinToolPolicy apply in Chat the same way they do in Cowork and Code sessions. For example, adding "WebFetch" removes web fetch from Chat conversations too.

​

Project folders in Chat

For a conversation inside a project, Claude can list and read files in folders added to the project in Claude Desktop, and can’t change them.

• Folders the user adds. To have Claude read a folder, the user adds it to the project in Claude Desktop and starts a new conversation. For a folder that an import put on the project, or that was on the project before Chat could read folders, the user adds it to the project again.
• Folders you allow. If you set allowedWorkspaceFolders, the list also limits which of a project’s folders Claude reads.

​

What a Chat conversation cannot do

Apart from reading the folders added to a project, in a Chat conversation Claude cannot:

• Read or write the filesystem beyond the conversation’s own uploads and scratch directories, its own transcript and saved tool results (read-only), and, inside a project, the project’s memory. The tool for requesting folder access is removed, and the app refuses folder grants to a Chat conversation even when requested through internal interfaces.
• Run code on the host. There is no shell access. With advanced file analysis off (the default), the sandbox VM is never started for Chat; with it on, code runs only inside the sandbox described under Advanced file analysis, never on the host itself.
• Run in auto mode. Chat conversations always run in the default permission mode. Auto mode and other reduced-supervision modes are rejected for Chat regardless of autoModeEnabled.
• Create or run scheduled tasks, or list the ones that exist.
• Escalate into an agentic session. The tools that launch Code sessions or dispatch background agent tasks are removed. When a request needs capabilities Chat doesn’t have, Claude says so and suggests starting the task in Cowork instead.
• Read other conversations. The tools that list sessions or read other sessions’ transcripts are removed, so a Chat conversation cannot search or quote your other chats, Cowork sessions, or Code sessions.

These restrictions are enforced in the app’s main process, not just hidden in the UI.

​

Advanced file analysis

By default, Chat can read attached files only in the formats Claude understands natively. Setting chatAdvancedFileAnalysisEnabled to true lets Claude also run code against attachments and, inside a project, against files in the project’s folders. This is useful for spreadsheets, PowerPoint files, and other formats that need parsing, and for inline data analysis on attached data. The execution environment is intentionally narrower than the Cowork sandbox:

• Code runs in the same isolated local VM that Cowork uses. For Chat, the VM starts only when analysis is coming: on the first analysis call, or at the start of a turn with files attached.
• Commands in the sandbox can reach the hosts in coworkEgressAllowedHosts. See Sandbox network access.
• The only conversation data the sandbox sees is the conversation’s attached files (read-only), its scratch directory (writable), its own transcript and saved tool results, such as connector results (read-only), and, for a conversation inside a project, that project’s memory (read-only), plus read-only reference material bundled by the app. The sandbox sees no user folders except, for a conversation inside a project, the project’s folders (read-only), and no other sessions’ working directories or transcripts.
• The sandbox doesn’t see project folders in a conversation that starts while a rule for "Read", "Grep", or "Glob" is set in disabledBuiltinTools, in builtinToolPolicy with a value other than "allow", or as a deny or ask rule in Claude Code’s own managed settings on the device. See chatAdvancedFileAnalysisEnabled for more cases.
• Each command runs independently; results land in the scratch directory, where Claude can offer them to the user as downloads or artifacts.

The data flow end to end: an attached file is copied into the conversation’s local uploads directory, mounted read-only into the sandbox when analysis runs, and any outputs are written to the conversation’s scratch directory on local disk. File content leaves the device only as conversation context sent to your configured inference provider, in web search queries to your configured search backend, through web fetches your egress allowlist permits, through sandbox network access, in a connector tool call permitted by your toolPolicy configuration and the user’s approvals, or, if you have enabled content capture, in telemetry to your own collector.

​

Sandbox network access

Commands that Claude runs in the advanced file analysis sandbox can reach the hosts in coworkEgressAllowedHosts. A command-line tool that a plugin adds to the sandbox can also reach the hosts that its plugin declares. Those hosts don’t need to be in the list. If the list is unset or empty, no host is allowed for other commands.

• Other hosts. A web request to any other host gets a 403 Forbidden response with the header X-Proxy-Error: blocked-by-allowlist. pip install reports this as Tunnel connection failed: 403 Forbidden.
• Package installs. Package managers contact their default index, so list its hosts. For pip, list pypi.org and files.pythonhosted.org. To install from a private mirror, list its host. The command must name the mirror, for example with pip’s --index-url.

​

Configuration

While the desktopHome key for Unified Claude has a value, Claude Desktop ignores chatTabEnabled, chatAdvancedFileAnalysisEnabled, and coworkTabEnabled. When chatTabEnabled is true, Claude Desktop presents Chat and Cowork together as Home in its sidebar, next to Code. From Home, the user chooses Chat or Cowork in the message box, and the sidebar lists chats and tasks together. When the key is unset or false, the sidebar shows Cowork in place of Home and the message box offers no choice. If coworkTabEnabled is false while Chat is enabled, the message box offers Chat only. Enforcement of chatTabEnabled happens in the app’s main process: when the key is unset or false, Chat does not appear in the app, and the app additionally refuses to start or continue a Chat conversation, including conversations created before an admin turned the key off. The rule that at least one surface must stay enabled counts Chat only when chatTabEnabled is explicitly true: a configuration that disables Cowork and Code without enabling Chat re-enables Cowork with a validation warning, rather than leaving users with an empty app. With chatTabEnabled set to true, a chat-only configuration is valid.

​

Where Chat data lives

Chat conversations are stored on the local device, in the same per-session layout as Cowork sessions: conversation history, attachment copies, scratch outputs, and a tamper-evident audit log, all under the application-data directory. Nothing is synced to a server, and there is no server-side index of past conversations. See Chat conversations on the data-storage page for the breakdown.