# SCOPE

## One-liner

Meta-framework routing between concrete agent-harness backends ("reins"),
consuming sand-boxer for isolation. See `docs/adr/ADR-001-rein-harness-family.md`.

## Core Idea

glas-harness owns the harness contract (`docs/harness-contract.md`:
`start_session`/`dispatch_tool`/`end_session`) and the outer loop — profile
resolution, sandbox request/teardown via sand-boxer, actor attribution. A
rein owns its own inner agentic loop and is invoked through that contract.

## In Scope

- The `Rein` ABC and `SandboxHandle`/`ToolCall`/`ToolResult` types
  (`src/glas_harness/contract.py`)
- The gateway that resolves a harness profile, requests a sand-boxer sandbox,
  runs one task through a rein, verifies, tears down
  (`src/glas_harness/gateway.py`)
- Rein adapters that shell out to each rein's own CLI
  (`src/glas_harness/reins/`) — currently `rein_aharness.py`,
  `rein_openweights.py`
- The rein registry (`registry/reins/`) and harness profile catalog
  (`profiles/`)

## Out of Scope

- Sandbox provisioning, profiles, placement — owned by `sand-boxer`
- A rein's own agentic loop, tool execution, credential acquisition —
  owned by the rein itself (`rein-aharness`, `rein-openweights`, ...)
- Scheduling/task sourcing — stays rein-local
  (`docs/adr/ADR-003-scheduling-and-blueprint-sourcing-stay-rein-local.md`)
- e2e validation, code generation — owned by `wise-validator`,
  `snuggle-inventor`

## Current State

`GLAS-WP-0001` (harness contract + first two reins) is done. Both
`rein-aharness` and `rein-openweights` are live-proven through the gateway
against their real underlying providers (Claude Code CLI, OpenRouter).
Not yet built: channel bridges, memory/skills layer, glas-harness's own
State Hub reporting from the gateway (currently each rein reports its own
events).

## Getting Oriented

- Start with: `INTENT.md`, `docs/adr/ADR-001-rein-harness-family.md`
- Contract: `docs/harness-contract.md`
- Agent instructions: `AGENTS.md`
- Workplans: `workplans/`