sase autonomy¶
Predict and inspect %auto gate decisions
Reference for sase autonomy. Run sase autonomy --help for the exact output on this checkout.
usage: sase autonomy [-h] {explain,list,log,show} ...
Inspect the core-owned %auto autonomy record: predict each gate decision exactly (explain), list the built-in profiles (list), read the host decision log (log), and show one profile's matrix (show). With no subcommand, sase autonomy defaults to sase autonomy list.
Bare sase autonomy defaults to sase autonomy list.
Options:
| Option | Description | Default |
|---|---|---|
-h, --help |
show this help message and exit | — |
Subcommands:
| Subcommand | Summary |
|---|---|
sase autonomy explain |
Predict each %auto decision for an agent, prompt, or gate |
sase autonomy list |
List the built-in autonomy profiles |
sase autonomy log |
Read the host %auto decision log, newest first |
sase autonomy show |
Show one autonomy profile's matrix |
sase autonomy explain¶
usage: sase autonomy explain [-h] [-g ID] [-j] [-p TEXT] [AGENT]
Predict each %auto decision exactly. With an agent name, show its live record's summary, the per-kind cells with rule and source, the decisions so far from the host log, and the coverage line. With --prompt, dry-run a prompt's %auto through the side-effect-free scan: $(...) is never executed and is labeled as unexpanded. With --gate, show the settled gate's deciding policy block, which is the revision that decided it.
Options:
| Option | Description | Default |
|---|---|---|
-g ID, --gate ID |
Gate as KIND/REQUEST_ID, or a gate-turn reference (short id, member name, or owning agent name) | — |
-h, --help |
show this help message and exit | — |
-j, --json |
Emit machine-readable JSON | false |
-p TEXT, --prompt TEXT |
Dry-run this prompt's %auto without executing anything | — |
Arguments:
| Argument | Description |
|---|---|
agent |
Agent name, resolved the way sase agent show resolves names |
sase autonomy list¶
usage: sase autonomy list [-h] [-j]
List the built-in autonomy profiles with their one-liners. standard is the default profile.
Options:
| Option | Description | Default |
|---|---|---|
-h, --help |
show this help message and exit | — |
-j, --json |
Emit machine-readable JSON | false |
sase autonomy log¶
usage: sase autonomy log [-h] [-j] [-k KIND] [-o OUTCOME] [-s DATE] [AGENT]
Read the host %auto decision log, newest first, rendered with the core decision sentence. Only non-manual evaluations are logged: manual agents leave no rows.
Options:
| Option | Description | Default |
|---|---|---|
-h, --help |
show this help message and exit | — |
-j, --json |
Emit machine-readable JSON | false |
-k KIND, --kind KIND |
Only this gate kind (plan, epic_plan, question) (choices: epic_plan, plan, question) |
— |
-o OUTCOME, --outcome OUTCOME |
Only this outcome (auto, ask) (choices: ask, auto) |
— |
-s DATE, --since DATE |
Only decisions at/after DATE | — |
Arguments:
| Argument | Description |
|---|---|
agent |
Only decisions created by this agent |
sase autonomy show¶
usage: sase autonomy show [-h] [-j] PROFILE
Show one built-in profile's matrix: its layer, the selections that pick it, the per-kind cells, and the coverage line.
Options:
| Option | Description | Default |
|---|---|---|
-h, --help |
show this help message and exit | — |
-j, --json |
Emit machine-readable JSON | false |
Arguments:
| Argument | Description |
|---|---|
profile |
Profile to inspect (epic, manual, standard, tale) |
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.