Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
238 changes: 119 additions & 119 deletions content/.metadata.json

Large diffs are not rendered by default.

10 changes: 5 additions & 5 deletions content/claude/third-party/claude-desktop/configuration.md
Original file line number Diff line number Diff line change
Expand Up @@ -1235,21 +1235,21 @@ object\[]Since 1.2581.0
>
> **Extended context** (`supports1m`) is a capability assertion you make about your deployment; only set it for models you've confirmed support the 1M-token window:
>
> ```json theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
> ```json theme={null}
> [{"name": "claude-sonnet-5", "supports1m": true}, "claude-opus-4-8"]
> ```
>
> `"claude-sonnet-5[1m]"` is shorthand for the same entry. When an ID is listed both bare and with `[1m]` (as a gateway lists it), the picker shows one model with a 1M variant; put `labelOverride` on the bare entry (a label on the `[1m]` spelling is ignored there); tier-tagged entries are not folded. `prefer1m: true` (no effect without `supports1m`) shows only the 1M variant of the model. Under dynamic discovery (no explicit list), set `modelPrefer1mContext` instead.
>
> **Display label** (`labelOverride`) is for IDs the picker can't derive a friendly name from (Bedrock ARNs, gateway routing aliases). Display-only; `name` is still what the app sends:
>
> ```json theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
> ```json theme={null}
> [{"name": "arn:aws:bedrock:us-east-1:123:application-inference-profile/abc", "labelOverride": "Claude Opus (Prod)"}]
> ```
>
> **Tier mapping** (`anthropicFamilyTier`) tells the app which Claude tier (`haiku`/`sonnet`/`opus`/`fable`/`mythos`) an entry stands in for, so bare tier aliases (e.g. in Code sessions) resolve to your model. `isFamilyDefault: true` picks the winner when several entries share a tier:
>
> ```json theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
> ```json theme={null}
> [{"name": "us.anthropic.claude-opus-4-8", "anthropicFamilyTier": "opus"}]
> ```
>
Expand Down Expand Up @@ -1361,7 +1361,7 @@ object\[]Since 1.37937.0
>
> Each row replaces Anthropic list price for one model in the Usage page's estimate, in USD per million tokens (`inputPerMtok`, `outputPerMtok`, `cacheReadPerMtok`, `cacheWritePerMtok`, all four required; `cacheWritePerMtok` prices both 5-minute and 1-hour cache writes); rows apply only while `inferenceModelPricingEnabled` is `true` and do not turn the estimate on by themselves. Mirrors Claude Code's managed `modelPricing.overrides`, and `name` is matched the same way: a built-in Claude model ID (e.g. `claude-sonnet-4-6`, or its Bedrock, Vertex, or Foundry ID) covers every dated and provider spelling of that model; any other value (a gateway alias, an inference-profile ARN) matches that exact ID only (case-insensitive) and wins over a built-in row. An ID Claude Code cannot map to a Claude model at all gets no estimate until a row here prices it. `inferenceModelPricingMultiplier` still applies on top of a row.
>
> ```json theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
> ```json theme={null}
> {"inferenceModelPricingEnabled": true, "inferenceModelPricingMultiplier": 0.9, "inferenceModelPricing": [{"name": "claude-sonnet-4-6", "inputPerMtok": 2.4, "outputPerMtok": 12, "cacheReadPerMtok": 0.24, "cacheWritePerMtok": 3}]}
> ```
>
Expand Down Expand Up @@ -3577,7 +3577,7 @@ object\[]Since 1.8089.0
>
> Locks per-tool permissions on MCP servers provided by any installed plugin — from the org-plugins directory or a plugin marketplace, remote or run locally — one entry per server name (compared case-insensitively):
>
> ```json theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
> ```json theme={null}
> [{"serverName": "internal-search", "tools": [{"toolName": "delete_document", "permission": "blocked"}]}]
> ```
>
Expand Down
10 changes: 10 additions & 0 deletions content/claude/third-party/claude-desktop/installation.md
Original file line number Diff line number Diff line change
Expand Up @@ -206,6 +206,16 @@ Download the installer from a connected machine and bring it across your boundar

Pair the offline installer with [`disableAutoUpdates`](https://claude.com/docs/third-party/claude-desktop/configuration#disableautoupdates). The app cannot reach the update feed from an air-gapped network, and you update the fleet by distributing each new offline installer through your MDM. Also set [`modelCatalogEnabled`](https://claude.com/docs/third-party/claude-desktop/configuration#modelcatalogenabled) to `false`, or point [`modelCatalogUrl`](https://claude.com/docs/third-party/claude-desktop/configuration#modelcatalogurl) at a mirror inside your network. Otherwise the app tries to fetch the signed model catalog from `downloads.claude.ai` at launch and every 5 to 15 minutes after that, and while those requests fail the model picker keeps the names and effort options that ship with the app. With updates and the catalog fetch handled this way, the only egress an air-gapped deployment needs is your inference provider; see [Telemetry and egress](https://claude.com/docs/third-party/claude-desktop/telemetry.md#required-egress-paths).

### SSH remote sessions with the offline installer

With the offline installer, neither the device nor the host needs to reach `downloads.claude.ai` to set up a Linux host for an [SSH remote session](https://claude.com/docs/third-party/claude-desktop/ssh-remote-sessions.md). The installed Claude Desktop package then includes copies of the two programs that Claude Desktop [puts on a host](https://claude.com/docs/third-party/claude-desktop/ssh-remote-sessions.md#host-requirements), the remote server and the Claude Code engine. Claude Desktop uses those copies without a setting.

* **Linux hosts**: both programs are included for x64 and arm64, with glibc or musl. Claude Desktop uploads them over the SSH connection. Expect an upload for each user account on a host and each Claude Desktop version, of about 3 MB for the remote server and 100 MB for the engine.
* **macOS and Windows hosts**: neither program is included. Where `downloads.claude.ai` is blocked, the session fails with a message that the installer doesn't include the programs, so connect to Linux hosts only.
* **Updates of both programs**: the Claude Desktop version determines the version of both programs. With [`disableAutoUpdates`](https://claude.com/docs/third-party/claude-desktop/configuration#disableautoupdates) set, both programs change on your hosts only when you distribute a new installer. Claude Desktop also starts the engine with [`DISABLE_AUTOUPDATER`](https://code.claude.com/docs/en/env-vars) set to `1`, which turns off the engine's background updates.

The host still has to reach your inference endpoint and, if configured, your OTLP collector. See [Host requirements](https://claude.com/docs/third-party/claude-desktop/ssh-remote-sessions.md#host-requirements).

## Updates

By default, Claude Desktop downloads updates from Anthropic's update server automatically and applies them the next time the app restarts. If the app hasn't restarted within 72 hours of downloading an update, it restarts itself, waiting for 10 minutes of user inactivity before doing so. This enforcement is always on and offers no in-app prompt to defer the restart; the `autoUpdaterEnforcementHours` key tunes the 72-hour window rather than enabling it.
Expand Down
Loading
Loading