Follow Discord
Sweep 03 Nov 2026 · 22:27Z Build v2.1.318 536 read Stable v2.1.311 Latest v2.1.318 Next v2.1.318 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Code CLI 28 Oct 2026
One change · claude-code

Claude apps gateway configuration changedclaude-apps-gateway-config

Upstream edited this page at 28 Oct 2026 19:51 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 28 Oct 2026 20:07 UTC.

Upstream edited
Recorded here
Lines+9added
Lines−2removed
From line 627 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits69to this page, all time

The whole hunk

from line 627, old and new numbered
/
lines
from line 627
627627 
628628The gateway keeps no record of failed upstreams, so while an upstream is down, every request that reaches it still tries it and waits for it to fail before moving on.
629629 
630For an Anthropic API upstream, [`timeouts.upstream_ttfb_ms`](#http-tuning) bounds the wait on a down upstream. That setting doesn't apply to the other providers, where the gateway waits up to one hour for an upstream to start responding.
630The gateway waits this long for a response to start:
631631 
632* **`provider: anthropic` upstreams**: [`timeouts.upstream_ttfb_ms`](#http-tuning), 120 seconds by default
633* **Other providers**: up to one hour. To shorten that wait for streaming requests, set `timeouts.upstream_ttfb_ms` on gateway v2.1.295 or later. Non-streaming model requests wait up to one hour either way
634 
632635`404` is per-upstream model availability, so an upstream that hasn't enabled a model doesn't block a later upstream that serves it. An upstream that can't resolve the requested model is skipped without a network round-trip.
633636 
634637This example routes a provisioned-throughput Amazon Bedrock allotment first, overflows to on-demand and a second account, and falls back to the Anthropic API last:
from line 1149
11461149 
11471150`blockReadsOutsideWorkingDirectories`, `disableBypassPermissionsMode`, `configRecheckIntervalMinutes`, and `sshClientPath` need Claude Code v2.1.281 or later on the gateway server. So do the `required` value of `microsoftAuthBroker` and the `continuousAccessEvaluation` field of a Microsoft 365 `managedMcpServers` entry. Claude Desktop releases that predate the `required` value read it as `disabled`, so set `required` only after every member's Claude Desktop supports it. Claude Desktop's [managed configuration reference](https://claude.com/docs/third-party/claude-desktop/configuration) lists the release that first reads each key.
11481151 
1152> [!NOTE]
1153>
1154> [`sshTransport`](https://claude.com/docs/third-party/claude-desktop/configuration#sshtransport) needs Claude Code v2.1.293 or later on the gateway server.
1155 
11491156If you set `orgPluginSettings` in a policy's `desktop` block, the gateway serves it in the array form that Claude Desktop 1.15200.0 and later reads. Older desktops ignore the array and enforce no plugin tool policy, so update members to 1.15200.0 or later before you rely on it.
11501157 
11511158##### How a role policy inherits the base `desktop` block
from line 1403
13961403| `limits` | `max_request_bytes` | 32 MiB | Max inbound request body; oversize requests get `413` before the body is buffered. Raise for large file or image requests. |
13971404| `limits` | `max_request_header_bytes` | unset | Lowers the gateway's 256 KiB limit on a request's total headers. A request over the limit returns `431`, and a value above 256 KiB has no effect. If developers get `431` after signing in, see [Request headers too large after sign-in](https://code.claude.com/docs/en/claude-apps-gateway-deploy.md#request-headers-too-large-after-sign-in). |
13981405| `limits` | `max_url_length` | unset | When set, an over-long URL returns `414` |
1399| `timeouts` | `upstream_ttfb_ms` | 120000 | Max wait for the upstream's response headers (time to first byte). The response body then streams with no wall-clock cap. Applies to the direct Anthropic upstream path; on every other provider the gateway waits up to one hour for the response to start. |
1406| `timeouts` | `upstream_ttfb_ms` | 120000 | Max wait for the upstream's response headers (time to first byte). The response body then streams with no wall-clock cap. If the key is unset, the default applies to `provider: anthropic` upstreams, and on every other provider the gateway waits up to one hour for the response to start. To shorten that wait, see [Multiple upstreams](#multiple-upstreams). |
14001407| `rate_limits` | `device_authorization.max` / `.window_seconds` | 30 / 600 | Per-IP rate limit on the unauthenticated device-authorization endpoint. Raise for a large org behind a shared egress IP or NAT. [Large rollouts](https://code.claude.com/docs/en/claude-apps-gateway-deploy.md#large-rollouts) shows how to size it. These limits apply only to the device-grant sign-in flow, not to `/v1/messages` inference. See [User-code brute-force resistance](https://code.claude.com/docs/en/claude-apps-gateway-deploy.md#user-code-brute-force-resistance). |
14011408| `rate_limits` | `device_verify.max` / `.window_seconds` | 10 / 600 | Per-IP rate limit on `user_code` submissions at `/device`. It is what stops someone from guessing another developer's code. [Large rollouts](https://code.claude.com/docs/en/claude-apps-gateway-deploy.md#large-rollouts) shows how far to raise it. |
14021409 
Feedback