sase chat¶
Discover and inspect prior agent chat transcripts
Reference for sase chat. Run sase chat --help for the exact output on this checkout.
usage: sase chat [-h] {list,show} ...
Bare sase chat defaults to sase chat list.
Options:
| Option | Description | Default |
|---|---|---|
-h, --help |
show this help message and exit | — |
Subcommands:
| Subcommand | Summary |
|---|---|
sase chat list |
List recent chat transcripts (pretty table by default, JSON with -j) |
sase chat show |
Show a chat transcript by agent name, path, or basename |
sase chat list¶
usage: sase chat list [-h] [-j] [-l LIMIT] [-m MACHINE]
[-P {local,shared,remote,unknown}] [-q QUERY]
List recent chat transcripts, newest first, with the sync provenance of each one: 'local' (written here, not published), 'shared' (written here and published to an agents sidecar), 'remote' (imported from another machine), or 'unknown' (provenance could not be determined).
Options:
| Option | Description | Default |
|---|---|---|
-h, --help |
show this help message and exit | — |
-j, --json |
Emit a machine-readable JSON array (stable schema) | false |
-l LIMIT, --limit LIMIT |
Maximum number of transcripts to return (default: 20) | 20 |
-m MACHINE, --machine MACHINE |
Only show transcripts whose source machine matches this name (case-insensitive); remote transcripts report their origin machine, local and shared ones report this machine | — |
-P PROVENANCE, --provenance PROVENANCE |
Only show transcripts with this sync provenance (choices: local, remote, shared, unknown) |
— |
-q QUERY, --query QUERY |
Case-insensitive substring filter over path/basename/content | — |
sase chat show¶
usage: sase chat show [-h] (-n AGENT | -p PATH | -b BASENAME)
[-f {raw,resume,response}]
Options:
| Option | Description | Default |
|---|---|---|
-n AGENT, --agent AGENT |
Resolve transcript by named agent (done.response_path or meta.chat_path) | — |
-b BASENAME, --basename BASENAME |
Chat transcript basename (with or without .md extension) | — |
-f FORMAT, --format FORMAT |
Output format: 'raw' (default) prints transcript markdown, 'resume' prints flattened User/Assistant turns, 'response' prints the latest response only (choices: raw, response, resume) |
raw |
-h, --help |
show this help message and exit | — |
-p PATH, --path PATH |
Path to a chat transcript file (~ is expanded) | — |
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.