Implement the harness contract and prove it against rein-aharness (GLAS-WP-0001-T02/T03/T04)
- 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:
parent
97a50fc780
commit
5681fce787
16 changed files with 556 additions and 4 deletions
72
src/glas_harness/gateway.py
Normal file
72
src/glas_harness/gateway.py
Normal 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)
|
||||
Loading…
Add table
Add a link
Reference in a new issue