Implement the harness contract and prove it against rein-aharness (GLAS-WP-0001-T02/T03/T04)
All checks were successful
CI Smoke / host-smoke (push) Successful in 1s
CI Smoke / container-smoke (push) Successful in 3s

- 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>
This commit is contained in:
tegwick 2026-07-26 13:02:59 +02:00
parent 97a50fc780
commit 5681fce787
16 changed files with 556 additions and 4 deletions

View file

@ -0,0 +1,72 @@
"""Minimal gateway proving the harness contract against rein-aharness.
GLAS-WP-0001-T04: resolve a sand-boxer profile, request a sandbox,
dispatch one rein-aharness task through the Rein contract, verify a
commit landed, tear the sandbox down. This is the parity proof gating
any later "retire rein-aharness as a standalone concern" conversation
it is not itself that conversation.
Requires the `sandbox` extra (sand-boxer installed as a sibling
editable dependency).
"""
from __future__ import annotations
from typing import Any
from sandboxer.core.manager import SandboxManager
from sandboxer.models import Consumer, SandboxCreateRequest
from glas_harness.contract import Rein, SandboxHandle, ToolCall
from glas_harness.reins.rein_aharness import ReinAharness
def run_task_through_rein(
*,
sandbox_profile: str,
repo: str,
title: str,
description: str,
rein: Rein | None = None,
actor: str = "agt",
project: str = "glas-harness",
manager: SandboxManager | None = None,
) -> dict[str, Any]:
"""Resolve `sandbox_profile`, run one task inside it via `rein`, verify, tear down.
Defaults to `ReinAharness` when no rein is supplied the only
implemented rein as of GLAS-WP-0001-T04. `rein-openweights` plugs in
the same way once REIN-OW-WP-0001 lands.
"""
manager = manager or SandboxManager()
rein = rein or ReinAharness()
request = SandboxCreateRequest(
profile=sandbox_profile,
inputs={"repo": repo},
consumer=Consumer(actor=actor, project=project),
)
status = manager.create(request)
try:
reachability = status.reachability.model_dump(mode="json") if status.reachability else {}
sandbox = SandboxHandle(
sandbox_id=status.sandbox_id, host=status.host or "", reachability=reachability
)
session = rein.start_session(
profile={"id": sandbox_profile},
inputs={"title": title, "description": description},
sandbox=sandbox,
)
tool_result = rein.dispatch_tool(session, ToolCall(name="run_task", actor=actor))
summary = rein.end_session(session)
return {
"sandbox_id": status.sandbox_id,
"tool_ok": tool_result.ok,
"tool_output": tool_result.output,
"tool_error": tool_result.error,
"summary": summary,
}
finally:
manager.destroy(status.sandbox_id)