Files
nisse/nisse-dev/tests/test_agent_build.py
T
dongarandClaude Opus 5 2fb25b8195
CI / checks (push) Skipped
CI / checks (pull_request) Successful in 1m14s
Add the composition root and a runnable entry point
Nothing had ever assembled the agent. main.py was still the hello-world
placeholder from the scaffold, and no code outside the test suite
constructed an Orchestrator — which is how two fully built, fully
tested components came to be reachable from nothing: the delegation
harness, and the Gitea comment poller. Unit tests that construct a
component directly cannot catch that; only assembly can.

- config.py validates every variable before anything is built and
  names all of them at once, rather than failing at first use twenty
  minutes into a milestone on the call that mattered. Whitespace-only
  counts as missing, since a token of spaces passes a truthiness check
  and fails at the first request instead
- agent.py builds the whole graph and owns startup and shutdown order:
  reconcile before accepting commands, and on stop, stop watching,
  then stop talking, then close the store last
- The Gitea account is read via whoami rather than configured: it names
  the identity every permission is evaluated against, and proves the
  token works before anything depends on it
- Poller lifecycle is now a state-machine concern: watch the plan issue
  while a gate stands, the PR while it is open, and stop on leaving.
  The orchestrator owns when to watch; an injected factory owns how to
  build one
- The executor reports each turn, because it runs synchronously inside
  the transport callback: without it the agent is silent for a whole
  milestone and a working run looks exactly like a hung one
- main.py loads .env, builds, and shuts down cleanly on SIGINT/SIGTERM

The entry-point tests changed shape: nisse-dev no longer greets, it
refuses to start unconfigured and says everything that is missing. Both
tests now run with a deliberately empty environment and a .env path
that does not exist, because the working directory's .env holds live
credentials and a test must never be one cwd away from starting a real
agent.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-08 22:26:26 +00:00

180 lines
6.1 KiB
Python

"""The composition root. These tests exist because two components — the
delegation harness and the comment poller — were fully built, fully tested,
and reachable from nothing but their own tests. Unit tests that construct a
component directly cannot catch that; only assembly can."""
import sqlite3
from pathlib import Path
from typing import Any
import httpx
import pytest
from test_config import COMPLETE
from nisse_dev.agent import build_agent, prepare_workspace
from nisse_dev.config import AgentConfig
from nisse_dev.git import GitRepo
def config_for(tmp_path: Path, **overrides: str) -> AgentConfig:
env = {
**COMPLETE,
"NISSE_STATE_DB": str(tmp_path / "state.db"),
"NISSE_WORKSPACE": str(tmp_path / "work"),
**overrides,
}
return AgentConfig.from_env(env)
@pytest.fixture
def origin(tmp_path: Path) -> Path:
"""A bare repo standing in for the project on the forge."""
remote = tmp_path / "origin.git"
GitRepo(tmp_path)._run("init", "-q", "--bare", "-b", "main", str(remote))
seed = GitRepo(tmp_path / "seed")
seed.init()
seed.configure_identity("seed", "seed@test")
(seed.root / "README.md").write_text("project\n")
seed.commit_all("seed")
seed.push(str(remote), "main")
return remote
def test_workspace_is_cloned_when_absent(tmp_path: Path, origin: Path) -> None:
config = config_for(tmp_path, NISSE_GITEA_URL=f"file://{origin}")
# authenticated_url would mangle a file:// remote, so clone directly.
GitRepo(tmp_path).clone(str(origin), config.workspace)
repo = prepare_workspace(config, "nisse-dev-testing")
assert (config.workspace / "README.md").exists()
assert repo.current_branch() == "main"
def test_workspace_is_reused_when_already_cloned(tmp_path: Path, origin: Path) -> None:
config = config_for(tmp_path)
GitRepo(tmp_path).clone(str(origin), config.workspace)
(config.workspace / "local-work.txt").write_text("in progress")
prepare_workspace(config, "nisse-dev-testing")
# Re-cloning would silently destroy uncommitted work.
assert (config.workspace / "local-work.txt").exists()
class FakeTransport:
def __init__(self) -> None:
self.sent: list[str] = []
self.started = False
self.closed = False
def send_message(self, text: str) -> None:
self.sent.append(text)
def send_approval_request(self, text: str) -> None:
self.sent.append(text)
def ask_question(self, text: str) -> None:
self.sent.append(text)
def on_message(self, callback: Any) -> None:
self.callback = callback
def start(self) -> None:
self.started = True
def close(self) -> None:
self.closed = True
def build_offline(tmp_path: Path, origin: Path, monkeypatch: Any) -> Any:
"""Assemble the real graph with only the network boundaries faked."""
config = config_for(tmp_path)
GitRepo(tmp_path).clone(str(origin), config.workspace)
monkeypatch.setattr(
"nisse_dev.agent.GiteaClient.whoami", lambda self: "nisse-dev-testing"
)
monkeypatch.setattr("nisse_dev.agent.MatrixTransport", lambda cfg: FakeTransport())
monkeypatch.setattr(
"nisse_dev.agent.authenticated_url",
lambda base, repo, user, token: str(origin),
)
return build_agent(config)
def test_the_whole_graph_assembles(tmp_path: Path, origin: Path, monkeypatch) -> None:
agent = build_offline(tmp_path, origin, monkeypatch)
orchestrator = agent.orchestrator
# Every component that was previously unreachable is now connected.
assert orchestrator._executor is not None
assert orchestrator._publisher is not None
assert orchestrator._board is not None
assert orchestrator._delegate is not None
assert orchestrator._poller_factory is not None
assert orchestrator._executor._delegate is not None # A12 escalation path
assert orchestrator._executor._expert is not None # A14 consult path
agent.stop()
def test_start_announces_where_it_resumed(
tmp_path: Path, origin: Path, monkeypatch
) -> None:
agent = build_offline(tmp_path, origin, monkeypatch)
agent.start()
assert agent.transport.started
readiness = agent.transport.sent[-1]
assert "nisse-dev up as nisse-dev-testing" in readiness
assert "greet" in readiness # the project
assert "claude-opus-5" in readiness # the pinned planner
agent.stop()
def test_stop_closes_everything_and_releases_the_wait(
tmp_path: Path, origin: Path, monkeypatch
) -> None:
agent = build_offline(tmp_path, origin, monkeypatch)
agent.start()
agent.stop()
assert agent.transport.closed
agent.wait() # returns immediately rather than hanging
with pytest.raises(sqlite3.ProgrammingError):
agent.store.get_state() # the store really is closed
def test_poller_factory_ignores_the_agents_own_comments(
tmp_path: Path, origin: Path, monkeypatch
) -> None:
# Without this the agent answers its own PR replies in a loop.
agent = build_offline(tmp_path, origin, monkeypatch)
poller = agent.orchestrator._poller_factory(lambda c: None)
assert "nisse-dev-testing" in poller._ignore
agent.stop()
def test_delegation_uses_the_passthrough_route(
tmp_path: Path, origin: Path, monkeypatch
) -> None:
# A13: delegations run vendor-native; the normalized route is for the
# places where fidelity is cheap.
from nisse_dev.llm import AnthropicPassthroughClient, LiteLLMClient
agent = build_offline(tmp_path, origin, monkeypatch)
delegation = agent.orchestrator._delegate
assert isinstance(delegation._client, AnthropicPassthroughClient)
assert isinstance(agent.orchestrator._executor._client, LiteLLMClient)
agent.stop()
def test_httpx_clients_are_not_shared_between_routes(
tmp_path: Path, origin: Path, monkeypatch
) -> None:
agent = build_offline(tmp_path, origin, monkeypatch)
normalized = agent.orchestrator._executor._client._http
passthrough = agent.orchestrator._delegate._client._http
assert isinstance(normalized, httpx.Client)
assert normalized is not passthrough # different base URLs and headers
agent.stop()