rein-aharness/tests/test_runner.py
tegwick cfc1b75157 Harness foundation: INTENT, ADR-001, architecture, prototype adoption
- INTENT.md: three-layer model (blueprint/instance/harness), single
  shared runtime, never-become boundaries
- ADR-001 (accepted): DEC-2026-002 resolution — one harness repo for
  all projects; instances are declarative state in consuming repos
- docs/architecture.md: components, contracts (manifest, tool
  profiles, completion events, credential lanes), deployment shape
- agent_harness/: executor-worker prototype adopted and renamed
  (6/6 tests green); HARNESS-WP-0001 initial workplan (7 tasks)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-17 23:35:27 +02:00

88 lines
2.7 KiB
Python

from __future__ import annotations
import subprocess
from pathlib import Path
import pytest
from agent_harness.runner import RunResult, run_task
from agent_harness.taskspec import TaskSpec, TaskSpecError
def _make_repo(tmp_path: Path) -> Path:
repo = tmp_path / "sandbox"
repo.mkdir()
subprocess.run(["git", "init", "-q"], cwd=repo, check=True)
(repo / "README.md").write_text("sandbox\n")
subprocess.run(["git", "add", "."], cwd=repo, check=True)
subprocess.run(
["git", "-c", "user.email=t@t", "-c", "user.name=t", "commit", "-qm", "init"],
cwd=repo,
check=True,
)
return repo
class CommittingAdapter:
"""Fake adapter that simulates a session which commits."""
def __init__(self, repo: Path):
self.repo = repo
self.prompts: list[str] = []
def execute_prompt(self, prompt, config):
self.prompts.append(prompt)
(self.repo / "HELLO.md").write_text("hello\n")
subprocess.run(["git", "add", "."], cwd=self.repo, check=True)
subprocess.run(
["git", "-c", "user.email=t@t", "-c", "user.name=t", "commit", "-qm", "task done"],
cwd=self.repo,
check=True,
)
from llm_connect.models import LLMResponse
return LLMResponse(content="done", model="fake", usage={}, finish_reason="stop")
class IdleAdapter:
def execute_prompt(self, prompt, config):
from llm_connect.models import LLMResponse
return LLMResponse(content="nothing to do", model="fake", usage={}, finish_reason="stop")
def _spec(repo: Path) -> TaskSpec:
return TaskSpec(title="write hello", description="create HELLO.md", target_repo=repo)
def test_run_task_success_when_session_commits(tmp_path) -> None:
repo = _make_repo(tmp_path)
adapter = CommittingAdapter(repo)
result = run_task(_spec(repo), adapter=adapter, report_to_hub=False)
assert isinstance(result, RunResult)
assert result.ok is True
assert result.committed is True
assert result.head_before != result.head_after
assert "write hello" in adapter.prompts[0]
assert "Never push" in adapter.prompts[0]
def test_run_task_fails_without_commit(tmp_path) -> None:
repo = _make_repo(tmp_path)
result = run_task(_spec(repo), adapter=IdleAdapter(), report_to_hub=False)
assert result.ok is False
assert result.committed is False
assert result.reason == "session completed without committing"
def test_taskspec_rejects_non_repo(tmp_path) -> None:
spec_file = tmp_path / "task.json"
spec_file.write_text(
'{"title": "x", "description": "y", "target_repo": "%s"}' % tmp_path
)
with pytest.raises(TaskSpecError, match="not a git repository"):
TaskSpec.from_file(spec_file)