Skip to content

Integration configuration behavior

Configuration behavior for chat and mobile integrations.

chat_install

Configuration for chat-driven update workflows. External chat integrations can call sase.integrations.chat_install.start_chat_install_worker() to run the built-in sase update --json engine in a detached worker. The worker uses the same managed-vs-dev routing as the TUI Updates tab and the sase update CLI, so no custom update command is required.

chat_install:
  timeout_seconds: 900
  restart_attempts: 3

Generated reference for chat_install

Only one chat update worker may run at a time; a lock under ~/.sase/chat_install/install.lock rejects concurrent starts. Worker output is written to timestamped logs under ~/.sase/chat_install/logs/. The configuration key and state paths remain named chat_install for compatibility. The old chat_install.command and chat_install.sync_workspace keys have been removed; delete them from user config if schema validation reports them. See Integration API details for the integration-facing Python API.

Source: src/sase/default_config.yml, src/sase/integrations/chat_install.py

telegram

Custom Telegram slash commands are keyed by the bot command name. Define them in user configuration or an overlay; the Telegram integration deliberately ignores project-local configuration so a repository cannot add commands to your bot. Core SASE validates the definitions, and sase doctor checks that each command's executable resolves.

telegram:
  commands:
    projects:
      description: List enabled SASE projects.
      run: sase project list --state enabled
      output: message
      timeout: 60s

Generated reference for telegram

Command names must contain 1–32 lowercase letters, digits, or underscores. The built-in names bead, beads, changes, fork, kill, list, update, and macros are reserved. The integration parses run as an argument vector and never invokes a shell. Text following /name is appended as one final argument, and the process runs from an isolated temporary directory, so use absolute paths or commands available on PATH rather than relying on a project working directory.

Run sase doctor -C integrations.telegram_commands after editing the map; unresolved command heads produce a warning with the affected names.

Source: src/sase/default_config.yml, src/sase/doctor/checks_integrations.py

mobile_gateway

Configuration for sase mobile gateway start, which launches the workstation-hosted Rust gateway for paired mobile clients.

mobile_gateway:
  bind_address: "127.0.0.1"
  port: 7629
  state_dir: ""
  allow_non_loopback: false
  command: ""
  agent_bridge_command: ""
  helper_bridge_command: ""
  push_provider: "disabled"
  fcm_project_id: ""
  fcm_service_account_json: ""
  fcm_credential_env: ""
  fcm_dry_run: false
  push_timeout_seconds: 5
  push_retry_limit: 1
  startup_timeout_seconds: 10

Generated reference for mobile_gateway

Push payloads are hint-only and must not contain bearer tokens, pairing codes, prompt bodies, response text, attachment contents, attachment tokens, or host paths. Only credential paths or environment-variable names are placed on the gateway command line. See docs/reference/integrations/mobile-gateway.md for setup examples and security notes.

Source: src/sase/default_config.yml, src/sase/integrations/mobile_gateway.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.