dongarandClaude Opus 5.5
761ebdb857
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
103 lines
3.4 KiB
Python
103 lines
3.4 KiB
Python
"""A real delegation over the Anthropic passthrough: scoped sub-task in,
|
|
working code and a structured handback out."""
|
|
|
|
import io
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from nisse_dev.delegation import Caps, Delegation
|
|
from nisse_dev.execution import SSHHost
|
|
from nisse_dev.git import GitRepo
|
|
from nisse_dev.llm import AnthropicPassthroughClient
|
|
from nisse_dev.oplog import OpLog
|
|
from nisse_dev.state import StateStore
|
|
from nisse_dev.tools import Workspace
|
|
|
|
pytestmark = pytest.mark.integration
|
|
|
|
BRIEF = """Create `slugify.py` in the workspace root containing a function
|
|
`slugify(text)` that lowercases the text and replaces every run of
|
|
non-alphanumeric characters with a single hyphen, with no leading or trailing
|
|
hyphen. Then create `test_slugify.py` with at least two assertions covering
|
|
it, and run `python -m pytest test_slugify.py -q` until it passes."""
|
|
|
|
|
|
def build(
|
|
ssh_host: SSHHost,
|
|
tmp_path: Path,
|
|
caps: Caps,
|
|
client: AnthropicPassthroughClient,
|
|
model: str,
|
|
) -> tuple[Delegation, GitRepo, StateStore]:
|
|
repo = GitRepo(ssh_host, tmp_path / "work")
|
|
repo.init()
|
|
repo.configure_identity("nisse-dev-testing", "n@t.test")
|
|
(repo.root / "README.md").write_text("sandbox\n")
|
|
repo.commit_all("seed")
|
|
store = StateStore(tmp_path / "state.db", oplog=OpLog("nisse-dev", io.StringIO()))
|
|
delegation = Delegation(
|
|
client,
|
|
store,
|
|
Workspace(ssh_host, repo.root, timeout_s=60),
|
|
repo,
|
|
model=model,
|
|
caps=caps,
|
|
)
|
|
return delegation, repo, store
|
|
|
|
|
|
def test_delegate_completes_a_scoped_subtask(
|
|
tmp_path: Path,
|
|
passthrough: AnthropicPassthroughClient,
|
|
live_model: str,
|
|
ssh_host: SSHHost,
|
|
) -> None:
|
|
delegation, repo, store = build(
|
|
ssh_host, tmp_path, Caps(turns=12, wall_clock_s=300.0), passthrough, live_model
|
|
)
|
|
|
|
result = delegation.run(
|
|
store.transcript("t", "helper"), brief=BRIEF, branch="live/delegation-1"
|
|
)
|
|
|
|
assert result.usable, f"delegation did not hand back: {result.status} {result.note}"
|
|
assert (repo.root / "slugify.py").exists()
|
|
|
|
# The handback is the entire interface back, so it must actually say
|
|
# something in each part rather than be structurally present but empty.
|
|
handback = result.handback
|
|
assert handback is not None
|
|
assert len(handback.changed) > 10
|
|
assert len(handback.now_true) > 10
|
|
assert len(handback.next) > 5
|
|
|
|
# The delegate's own work is on its branch, and it really runs.
|
|
assert repo.current_branch() == "live/delegation-1"
|
|
check = Workspace(ssh_host, repo.root, timeout_s=60).run_command(
|
|
"python -m pytest test_slugify.py -q"
|
|
)
|
|
assert check.success, f"delegate's own tests do not pass: {check.result[:400]}"
|
|
|
|
|
|
def test_a_cap_breach_discards_the_work(
|
|
tmp_path: Path,
|
|
passthrough: AnthropicPassthroughClient,
|
|
live_model: str,
|
|
ssh_host: SSHHost,
|
|
) -> None:
|
|
# One turn cannot finish the brief, so this exercises the abort path
|
|
# against a real model rather than a scripted one.
|
|
delegation, repo, store = build(
|
|
ssh_host, tmp_path, Caps(turns=1, wall_clock_s=120.0), passthrough, live_model
|
|
)
|
|
|
|
result = delegation.run(
|
|
store.transcript("t", "helper"), brief=BRIEF, branch="live/delegation-2"
|
|
)
|
|
|
|
assert not result.usable
|
|
assert result.status == "capped"
|
|
assert repo.current_branch() == "main"
|
|
assert not (repo.root / "slugify.py").exists()
|