Unverified bounded-proof profile for rein-aharness metered-once: bwrap-local
with empty egress, no credential routes, 900 s / 60k tokens, 30 turns and a
USD 5.00 native cap matching the accepted spend envelope. 1.0.0 stays
blocked; unpinned selection becomes ambiguous. 134 tests pass.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 272244@bnt-lap001
Assistant-Session: c8962fa7-b290-47df-865f-403ddb6c77e9
- src/glas_harness/contract.py: Rein ABC (start_session/dispatch_tool/
end_session), SandboxHandle/ToolCall/ToolResult, per docs/harness-contract.md.
- reins/rein_aharness.py: adapter around the rein-aharness CLI. Collapses
a whole `agent-harness run` into one dispatch_tool call for now (no
per-tool hooks yet — tracked in rein-aharness HARNESS-WP-0002-T03);
verifies success via new-commit detection, mirroring rein-aharness's
own success signal.
- gateway.py + cli.py: resolves a sand-boxer sandbox, runs one task
through a rein, tears the sandbox down.
- registry/reins/*.yaml (rein-aharness implemented, rein-openweights
planned) and profiles/harness.agent-dev{,-local}.yaml, pairing with
sand-boxer's profile.agent-dev and the new profile.bwrap-local.
Tested against a real local git repo + mocked SandboxManager/CLI
subprocess (10 tests, all passing). A real live run against the actual
Claude Code CLI is deliberately left for a human-triggered follow-up —
not executed autonomously since it spends real API credits/credentials.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
