From 198e170ee38782356c0e566f354be67f51240719 Mon Sep 17 00:00:00 2001 From: "warp-agent-staging[bot]" <240773466+warp-agent-staging[bot]@users.noreply.github.com> Date: Wed, 19 Aug 2026 20:29:32 +0000 Subject: [PATCH] docs(factories): document agentDefaults.computerUseModel key --- .../docs/factories/factory-as-code.mdx | 20 +++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/src/content/docs/factories/factory-as-code.mdx b/src/content/docs/factories/factory-as-code.mdx index 0a0b9f339..f9c20210d 100644 --- a/src/content/docs/factories/factory-as-code.mdx +++ b/src/content/docs/factories/factory-as-code.mdx @@ -194,6 +194,22 @@ MCP servers for agents that don't declare their own, in the same form as [`mcpSe Where runs execute: `warp` for Warp-hosted compute, or the ID of a connected [self-hosted worker](/platform/self-hosting/). +### `agentDefaults.computerUseModel` + +Optional. The model the computer use subagent runs with, as a `model_id`. When unset, Warp chooses the computer use model automatically. + +```yaml +agentDefaults: + model: auto + computerUseModel: claude-4-5-sonnet +``` + +Applies only to runs on the Warp Agent harness (`type: oz`); a third-party harness ignores it. It's also ignored when computer use is disabled for the run. Unlike `model`, this key isn't mutually exclusive with `harness` — it selects the model for the computer use subagent, not the model the agent itself runs on. + +Computer use supports a restricted set of models. See [model choice for agents](/agents/inference/model-choice/) for the full catalog Warp supports; not every listed model supports computer use. + +A managed [self-hosted worker](/platform/self-hosting/) needs an up-to-date worker and agent CLI version that supports `computerUseModel`. + ## `agents//agent.md` One file per agent. The YAML frontmatter configures how the agent runs, and the Markdown body is the agent's prompt: the durable instructions for its role. The agent's name comes from its directory. @@ -213,7 +229,7 @@ The frontmatter accepts: * `description` - Optional. What the agent does. * [`agentType`](#agenttype) - Optional. The agent's role. * `credentialStrategy` - Optional. Overrides the factory-level [`credentialStrategy`](#credentialstrategy) for this agent's runs. -* `model` or `harness`, `runner`, `environmentId`, `secrets`, `mcpServers`, `workerHost` - Optional. The same keys as [`agentDefaults`](#agentdefaults); a key declared here overrides the default for this agent. +* `model` or `harness`, `runner`, `environmentId`, `secrets`, `mcpServers`, `workerHost`, `computerUseModel` - Optional. The same keys as [`agentDefaults`](#agentdefaults); a key declared here overrides the default for this agent. ### `agentType` @@ -281,7 +297,7 @@ triggers: ### Execution overrides -An automation may also declare `model` or `harness`, `runner`, `environmentId`, `secrets`, `mcpServers`, and `workerHost` (the same keys as [`agentDefaults`](#agentdefaults)) to override the target agent's settings for the runs it starts. +An automation may also declare `model` or `harness`, `runner`, `environmentId`, `secrets`, `mcpServers`, `workerHost`, and `computerUseModel` (the same keys as [`agentDefaults`](#agentdefaults)) to override the target agent's settings for the runs it starts. ## `runners/.yaml`