v5
latestOpenAPI 3.1.12026-08-0826601.1 MBCreates a launch run and starts the CloudLaunch workflow against it.
Headers
Request body
The plugin to install and the skill to run. A value without a file: prefix means a registry ref (either a full workspace/plugin[@version] or a bare plugin[@version] name resolved across the workspaces the caller can see); a value with a file: prefix means a local plugin path inside the cloned repo (e.g. file:apps/cli/plugins/agent-enablement). Either form may carry a trailing #skill selector (e.g. workspace/plugin@1.0.0#implement-ticket or file:apps/cli/plugins/agent-enablement#implement-ticket) that installs the whole plugin and launches the one named skill; it is required when the plugin exposes more than one skill. This is a wire convention: the value is stored verbatim and interpreted downstream by the launch recipe.
Commit SHA or tag pinning the repo snapshot for this run. Pins the checked-out repository, not the sandbox runtime image. Use sandboxSnapshot for the latter.
Operational override selecting the sandbox runtime image the launch run is created from. Distinct from snapshot, which pins the checked-out repository. When omitted the run falls back to the configured default.
Id of a workspace environment whose sealed .env payload is opened server-side at launch and delivered to the sandbox. Must belong to the launch workspace. A live reference resolved when each run starts, so environment edits affect subsequently started and resumed runs and a deleted environment fails the launch.
Additional upload keys (context archives, config tarballs) keyed by a caller-defined logical name. Each must be an existing, viewable upload.
Skill-specific inputs forwarded to the launched skill, keyed by the skill's own placeholder names (e.g. ISSUE_IDENTIFIER, ISSUE_TITLE, ISSUE_DESCRIPTION).
Free-text instructions appended to the skill prompt the launch agent runs, mirroring the local --instructions flag. Distinct from the structured inputs channel.
Response
Default Response