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 -2
View File
@@ -19,6 +19,7 @@ from nisse_dev.control import (
PR_OPEN,
Orchestrator,
)
from nisse_dev.execution import SSHHost
from nisse_dev.executor import LLMExecutor
from nisse_dev.llm import LiteLLMClient, RoleMap
from nisse_dev.oplog import OpLog
@@ -59,7 +60,7 @@ def _drive_to_execution(
def test_plan_approve_execute_produces_a_real_file(
tmp_path: Path, litellm: LiteLLMClient, live_model: str
tmp_path: Path, litellm: LiteLLMClient, live_model: str, ssh_host: SSHHost
) -> None:
# Both roles use the capable model here: the point is the whole gated
# loop over a real proxy, not local-model competence (measured separately).
@@ -67,7 +68,7 @@ def test_plan_approve_execute_produces_a_real_file(
roles = RoleMap(executor=model, planner=model, helper=model, expert=model)
client = litellm
store = StateStore(tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO()))
workspace = Workspace(tmp_path / "work", timeout_s=60)
workspace = Workspace(ssh_host, tmp_path / "work", timeout_s=60)
transport = InMemoryTransport()
orchestrator = Orchestrator(
store,