Run every command on the build VM over SSH (M1.3)
CI / checks (push) Skipped
CI / checks (pull_request) Failing after 55s

execution.SSHHost.execute is now the only way the agent runs anything
(L13). Commands travel as a script on SSH's stdin, so the secrets handed
to a call are never on a command line, and every value handed out is
redacted from the output. Timeouts kill the remote process group, and
an unreachable host is reported as such, not as a failed command.

Workspace and GitRepo run on the build VM. The clone uses the
repository's SSH URL, so no credential is stored in it (#89); fetches
and pushes get the push key over stdin, in a short-lived ssh-agent,
and PRs are still opened from the agent's host with its API token.
The bench runs on the build host too.

Tests reach "the build VM" through a throwaway local sshd (nisse_dev
.testing); CI installs openssh-server. The live push test now pushes
with the sandbox's deploy key (NISSE_PUSH_KEY).

Fixes #89.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
This commit is contained in:
dongarandClaude Opus 5.5 committed 2026-10-02 21:39:46 +00:00
1 parent b7f1f3371c
commit 761ebdb857
32 files changed
+1098 -280

No files matched your search

+3 -1
View File
@@ -14,7 +14,7 @@ import os
import sys
from pathlib import Path
from nisse_dev.agent import make_llm_clients
from nisse_dev.agent import build_host, make_llm_clients
from nisse_dev.bench.results import append, load, render, results_file, summarise
from nisse_dev.bench.runner import agent_commit, run_task
from nisse_dev.bench.tasks import load_tasks
@@ -46,6 +46,7 @@ def run(args: argparse.Namespace) -> int:
catalog = ModelCatalog.discover(config.llm_base_url, config.llm_token)
catalog.require_limits({m: m for m in models})
normalized, _passthrough = make_llm_clients(config, catalog)
host = build_host(config) # runs happen on the build VM, as the agent's do
commit = agent_commit(REPO)
for model in models:
@@ -60,6 +61,7 @@ def run(args: argparse.Namespace) -> int:
facts,
normalized,
config.tuning,
host=host,
note=args.note,
commit=commit,
)