sase launch

Resolve pending LaunchApproval requests

Reference for sase launch. Run sase launch --help for the exact output on this checkout.

usage: sase launch [-h] {approve,reject,request} ...

Resolve pending launch approval requests created before detached agents are spawned.

Options:

Option	Description	Default
-h, --help	show this help message and exit	—

Subcommands:

Subcommand	Summary
sase launch approve	Approve a pending launch request
sase launch reject	Reject a pending launch request
sase launch request	Create a pending launch approval request

sase launch approve

usage: sase launch approve [-h] [-Q PATH] [-R PATH] selector

Approve a pending launch request by request id or notification prefix.

Options:

Option	Description	Default
-h, --help	show this help message and exit	—
-Q PATH, --request-path PATH	Private versioned operation request sidecar. Defaults to $SASE_PROC_REQUEST_PATH when that environment variable is set.	—
-R PATH, --result-path PATH	Private versioned typed result sidecar. Defaults to $SASE_PROC_RESULT_PATH when that environment variable is set.	—

Arguments:

Argument	Description
selector	Launch request id, notification id, or unique notification prefix

sase launch reject

usage: sase launch reject [-h] [-f FEEDBACK] [-Q PATH] [-R PATH] selector

Reject a pending launch request by request id or notification prefix.

Options:

Option	Description	Default
-f FEEDBACK, --feedback FEEDBACK	Optional feedback to return with the launch rejection	—
-h, --help	show this help message and exit	—
-Q PATH, --request-path PATH	Private versioned operation request sidecar. Defaults to $SASE_PROC_REQUEST_PATH when that environment variable is set.	—
-R PATH, --result-path PATH	Private versioned typed result sidecar. Defaults to $SASE_PROC_RESULT_PATH when that environment variable is set.	—

Arguments:

Argument	Description
selector	Launch request id, notification id, or unique notification prefix

sase launch request

usage: sase launch request [-h] [-a APPROVAL] [-f PAYLOAD_FILE] [-m MAX_SLOTS]
                           [-o {text,json}] [-p PROMPT] [-r REASON]
                           [-s SOURCE]
                           [payload]

Create a LaunchApproval request from a structured JSON payload or prompt flags. Agent-side callers wait for the response; no agent is spawned unless host dispatch is approved and succeeds.

Options:

Option	Description	Default
-a APPROVAL, --approval APPROVAL	Approval policy to request (currently: required).	required
-f PAYLOAD_FILE, --file PAYLOAD_FILE	Read the structured launch request JSON from PATH.	—
-h, --help	show this help message and exit	—
-m MAX_SLOTS, --max-slots MAX_SLOTS	Maximum number of launch slots this request may expand to.	1
-o OUTPUT, --output OUTPUT	Output format. (choices: json, text)	text
-p PROMPT, --prompt PROMPT	Prompt to request when not passing a JSON payload.	—
-r REASON, --reason REASON	Short reason shown to the approver.	—
-s SOURCE, --source SOURCE	Source surface label for the launch preview.	—

Arguments:

Argument	Description
payload	Inline JSON payload, or @PATH to read JSON from a file.

Related: CLI command groups.

_[project]: A sase project is a named unit of work registered with SASE. _[workspace]: A sase workspace is a numbered clone of a project's primary repo, managed by the workspace store and tracked in that project's registry.json. _[agent]: A sase agent is an agent session or a single agent that does not belong to a session. _[prompt]: A prompt is the text SASE hands to a provider to start an agent turn. _[macro]: A macro is a reusable prompt triggered with #name in agent prompts. _[Patch]: A Patch is SASE's local unit of change. _[bead]: A bead is one tracked work item in SASE's git-native issue tracker. _[plan]: A plan is a persisted, approved artifact recording the intent behind agent work. _[TUI]: The TUI is SASE's terminal interface for running agents and reviewing results. _[epic]: An epic is an executable multi-phase plan run with sase bead work. _[gate]: A sase gate is a durable, command-backed request for one user decision, created when work must pause for the user. _[monitor]: A sase monitor is a monitor turn that runs one long command under a detached supervisor, so the command outlives the agent that started it. *[stitch]: A stitch is the lightweight ordered change record inside a Patch's STITCHES: section.