From 69ddc91c35ef04e173cde6f8627773c1116fcd39 Mon Sep 17 00:00:00 2001 From: James Long Date: Tue, 10 Mar 2026 11:12:14 -0400 Subject: fix(core): a chunk timeout when processing llm stream (#16366) --- packages/web/src/content/docs/config.mdx | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'packages/web/src') diff --git a/packages/web/src/content/docs/config.mdx b/packages/web/src/content/docs/config.mdx index 038f25327..d2770ee20 100644 --- a/packages/web/src/content/docs/config.mdx +++ b/packages/web/src/content/docs/config.mdx @@ -244,7 +244,7 @@ You can configure the providers and models you want to use in your OpenCode conf The `small_model` option configures a separate model for lightweight tasks like title generation. By default, OpenCode tries to use a cheaper model if one is available from your provider, otherwise it falls back to your main model. -Provider options can include `timeout` and `setCacheKey`: +Provider options can include `timeout`, `chunkTimeout`, and `setCacheKey`: ```json title="opencode.json" { @@ -253,6 +253,7 @@ Provider options can include `timeout` and `setCacheKey`: "anthropic": { "options": { "timeout": 600000, + "chunkTimeout": 30000, "setCacheKey": true } } @@ -261,6 +262,7 @@ Provider options can include `timeout` and `setCacheKey`: ``` - `timeout` - Request timeout in milliseconds (default: 300000). Set to `false` to disable. +- `chunkTimeout` - Timeout in milliseconds between streamed response chunks. If no chunk arrives in time, the request is aborted. - `setCacheKey` - Ensure a cache key is always set for designated provider. You can also configure [local models](/docs/models#local). [Learn more](/docs/models). -- cgit v1.2.3