Skip to content

Monitor configuration

Settings for monitor execution, wrappers, and continuation.

monitor

Controls which monitors run their command inside sase tool run and the amount of command evidence projected into a monitor continuation prompt. The evidence limits do not change the monitor's bounded rotating log or the output available to sase monitor show; they bound only automatically selected prompt content.

monitor:
  tool_wrap: verify
  evidence_limits:
    selected_diagnostics_bytes: 8192
    fallback_tail_bytes: 4096
    total_raw_excerpt_bytes: 12288
    raw_tail_lines: 200

Generated reference for monitor

selected_diagnostics_bytes and fallback_tail_bytes must each be no larger than total_raw_excerpt_bytes. The runtime falls back to all four packaged defaults if that relationship is invalid; schema validation rejects non-positive values. Strict --next-output file and none policies still embed no raw command output.

An unrecognized tool_wrap value falls back to verify at runtime. Wrapping changes only the argv the proc supervisor execs, never the recorded monitor command; see Tool-run wrapping for the per-command rules.

Source: src/sase/default_config.yml, src/sase/config/_settings_display.py, src/sase/config/sase.schema.json, src/sase/monitor/result_projection.py, src/sase/monitor/tool_wrap.py

_[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.