The platform's side of D6: git runs on the host, in a gitdir that is never mounted into a container, so repository credentials never reach the model. - adapters/git_workspace.py: LocalGitWorkspaceAdapter implementing RepoWorkspacePort. Bare shared gitdir + a dev work tree mounted at /workspace + one linked worktree per task under work/.worktrees/<id> (excluded via the gitdir's info/exclude, not the project's .gitignore). Explicit --git-dir/--work-tree, core.hooksPath=/dev/null, fsmonitor off, quotePath off, GIT_CONFIG_NOSYSTEM, a private HOME per project, prompts off, one asyncio.Lock per project. Token via GIT_ASKPASS reading a 0600 file; SSH key as a 0600 temp file with a pinned known_hosts. Everything deleted in a finally; only a *path* ever travels through the environment. - The bug this phase existed to find: --git-dir=<shared> does not address a linked worktree, so `git commit` in a task worktree committed straight to `dev`. Operations now address <gitdir>/worktrees/<task_id> explicitly — and never read the worktree's .git file, which a repository can rewrite. - domain/platform/rules.py: is_blocked_address (pure) + assert_remote_host_allowed (resolves, refuses if any address is loopback/private/link-local/metadata). Shared by the git remote test and, later, every deploy target. - ProjectExternalGit domain model + repository; container_delivery wires the real adapter behind GIT_WORKSPACE=local with a resolver that joins the project, its repo and its (decrypted) credentials. Tests: 394 API (+48) against real git and a local bare repo; ruff and mypy clean. Report: docs/plan/reports/agent-3-phase-2.md
694 lines
26 KiB
Python
694 lines
26 KiB
Python
"""§v2-A3.2 — the platform's git adapter, exercised against real git.
|
|
|
|
These tests run a real ``git`` binary against a local bare repository standing in
|
|
for the remote. Nothing is faked except the *remote's location*: the flags, the
|
|
locking, the worktree dance and the credential plumbing are the real thing,
|
|
because those are precisely the parts that cannot be verified by a mock.
|
|
|
|
``protocol.file.allow=user`` is passed explicitly. The production default is
|
|
``never`` — a repository must not be able to make git read a local path through a
|
|
submodule or ``--upload-pack`` — but a local bare repo *is* a local path, so the
|
|
hardening has to be relaxed for the test to be able to run at all. That is why
|
|
the setting exists rather than being hard-coded.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import os
|
|
|
|
import pytest
|
|
|
|
from app.core.errors import NotFoundError
|
|
from app.domain.platform.rules import RuleViolation, assert_remote_host_allowed, is_blocked_address
|
|
from app.infrastructure.adapters.git_workspace import (
|
|
LocalGitWorkspaceAdapter,
|
|
ProjectGitSource,
|
|
)
|
|
from app.infrastructure.adapters.process import ProcessResult, run_process
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# helpers
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
async def _git(args: list[str], *, cwd: str, ok: bool = True) -> ProcessResult:
|
|
result = await run_process(
|
|
["git", *args],
|
|
cwd=cwd,
|
|
timeout_seconds=60,
|
|
env={
|
|
"GIT_CONFIG_NOSYSTEM": "1",
|
|
"GIT_TERMINAL_PROMPT": "0",
|
|
"GIT_AUTHOR_NAME": "t",
|
|
"GIT_AUTHOR_EMAIL": "t@example.com",
|
|
"GIT_COMMITTER_NAME": "t",
|
|
"GIT_COMMITTER_EMAIL": "t@example.com",
|
|
},
|
|
)
|
|
if ok:
|
|
assert result.ok, f"git {' '.join(args)} failed: {result.stderr}"
|
|
return result
|
|
|
|
|
|
async def _make_remote(tmp_path) -> str:
|
|
"""A local bare repository with one commit on ``main``; returns its path."""
|
|
remote = tmp_path / "remote.git"
|
|
seed = tmp_path / "seed"
|
|
await _git(["init", "--quiet", "--bare", str(remote)], cwd=str(tmp_path))
|
|
await _git(["init", "--quiet", str(seed)], cwd=str(tmp_path))
|
|
(seed / "README.md").write_text("hello\n")
|
|
await _git(["add", "-A"], cwd=str(seed))
|
|
await _git(["commit", "--quiet", "-m", "init"], cwd=str(seed))
|
|
await _git(["branch", "-M", "main"], cwd=str(seed))
|
|
await _git(["remote", "add", "origin", str(remote)], cwd=str(seed))
|
|
await _git(["push", "--quiet", "origin", "main"], cwd=str(seed))
|
|
return str(remote)
|
|
|
|
|
|
def _resolver(clone_url: str, *, auth_type: str = "none", secret: str | None = None,
|
|
username: str | None = None):
|
|
async def resolve(project_id: str) -> ProjectGitSource | None:
|
|
if project_id == "missing":
|
|
return None
|
|
return ProjectGitSource(
|
|
project_id=project_id,
|
|
organization_id="org1",
|
|
clone_url=clone_url,
|
|
default_branch="main",
|
|
auth_type=auth_type,
|
|
username=username,
|
|
secret=secret,
|
|
)
|
|
|
|
return resolve
|
|
|
|
|
|
def _adapter(tmp_path, clone_url: str, **kwargs) -> LocalGitWorkspaceAdapter:
|
|
kwargs.setdefault("allow_file_protocol", True)
|
|
kwargs.setdefault("runner", run_process)
|
|
return LocalGitWorkspaceAdapter(
|
|
resolver=_resolver(clone_url, **kwargs.pop("credentials", {})),
|
|
root=str(tmp_path / "root"),
|
|
**kwargs,
|
|
)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# ensure_workspace
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
async def test_ensure_workspace_clones_and_creates_dev(tmp_path):
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
|
|
ref = await adapter.ensure_workspace(project_id="proj1")
|
|
|
|
assert ref.default_branch == "dev"
|
|
assert os.path.isdir(ref.host_path), "the work tree must exist for the sandbox mount"
|
|
assert (tmp_path / "root" / "org1" / "proj1" / "work" / "README.md").is_file()
|
|
assert await adapter.head(project_id="proj1", branch="dev") is not None
|
|
# `dev` was pushed to the platform remote because it did not exist there.
|
|
assert await adapter.head(project_id="proj1", branch="dev") is not None
|
|
|
|
|
|
async def test_ensure_workspace_is_idempotent(tmp_path):
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
|
|
first = await adapter.ensure_workspace(project_id="proj1")
|
|
(tmp_path / "root" / "org1" / "proj1" / "work" / "new.txt").write_text("x")
|
|
second = await adapter.ensure_workspace(project_id="proj1")
|
|
|
|
assert first.host_path == second.host_path
|
|
assert (tmp_path / "root" / "org1" / "proj1" / "work" / "new.txt").is_file()
|
|
|
|
|
|
async def test_ensure_workspace_rejects_an_unknown_project(tmp_path):
|
|
adapter = _adapter(tmp_path, str(tmp_path / "nothing.git"))
|
|
with pytest.raises(NotFoundError):
|
|
await adapter.ensure_workspace(project_id="missing")
|
|
|
|
|
|
async def test_gitdir_is_not_inside_the_work_tree(tmp_path):
|
|
"""The git dir must never be reachable from the sandbox mount (D6)."""
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
ref = await adapter.ensure_workspace(project_id="proj1")
|
|
|
|
gitdir = tmp_path / "root" / "org1" / "proj1" / "git"
|
|
assert gitdir.is_dir()
|
|
assert not os.path.exists(os.path.join(ref.host_path, ".git"))
|
|
assert not str(gitdir).startswith(ref.host_path + os.sep)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# worktrees
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
async def test_task_worktree_is_created_and_removed(tmp_path):
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
|
|
worktree = await adapter.create_task_worktree(project_id="proj1", task_id="t1")
|
|
|
|
assert worktree.branch == "task/t1"
|
|
assert worktree.sandbox_path == "/workspace/.worktrees/t1"
|
|
assert os.path.isdir(worktree.host_path)
|
|
|
|
await adapter.remove_worktree(worktree=worktree)
|
|
assert not os.path.isdir(worktree.host_path)
|
|
|
|
|
|
async def test_task_worktree_is_invisible_in_the_main_work_tree(tmp_path):
|
|
"""`info/exclude` keeps .worktrees out of `status` without touching .gitignore."""
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
ref = await adapter.ensure_workspace(project_id="proj1")
|
|
await adapter.create_task_worktree(project_id="proj1", task_id="t1")
|
|
|
|
result = await _git(
|
|
["--git-dir", str(tmp_path / "root" / "org1" / "proj1" / "git"),
|
|
"--work-tree", ref.host_path,
|
|
"status", "--porcelain=v1", "-uall"],
|
|
cwd=ref.host_path,
|
|
)
|
|
assert result.stdout.strip() == "", "the worktree dir must not show up as untracked"
|
|
assert not os.path.exists(os.path.join(ref.host_path, ".gitignore"))
|
|
|
|
|
|
async def test_create_task_worktree_is_idempotent(tmp_path):
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
|
|
first = await adapter.create_task_worktree(project_id="proj1", task_id="t1")
|
|
second = await adapter.create_task_worktree(project_id="proj1", task_id="t1")
|
|
assert first.host_path == second.host_path
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# diff / commit
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
async def test_diff_reports_a_new_directory_thanks_to_uall(tmp_path):
|
|
"""`git status` without ``-uall`` hides new directories — a real agybot bug."""
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
worktree = await adapter.create_task_worktree(project_id="proj1", task_id="t1")
|
|
|
|
(tmp_path / "root" / "org1" / "proj1" / "work" / ".worktrees" / "t1" / "src").mkdir()
|
|
(
|
|
tmp_path / "root" / "org1" / "proj1" / "work" / ".worktrees" / "t1" / "src" / "a.py"
|
|
).write_text("print('hi')\n")
|
|
|
|
diff = await adapter.diff(worktree=worktree)
|
|
|
|
assert diff.changed_files == ["src/a.py"]
|
|
assert diff.is_empty is False
|
|
|
|
|
|
async def test_diff_detects_an_escaping_symlink(tmp_path):
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
worktree = await adapter.create_task_worktree(project_id="proj1", task_id="t1")
|
|
|
|
outside = tmp_path / "outside.txt"
|
|
outside.write_text("secret")
|
|
os.symlink(outside, os.path.join(worktree.host_path, "escape.txt"))
|
|
|
|
diff = await adapter.diff(worktree=worktree)
|
|
|
|
assert diff.escaping_symlinks == ["escape.txt"]
|
|
|
|
|
|
async def test_commit_returns_none_when_there_is_nothing_to_commit(tmp_path):
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
worktree = await adapter.create_task_worktree(project_id="proj1", task_id="t1")
|
|
|
|
assert await adapter.commit(worktree=worktree, message="empty", author="AI") is None
|
|
|
|
|
|
async def test_commit_records_the_author_and_returns_a_sha(tmp_path):
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
worktree = await adapter.create_task_worktree(project_id="proj1", task_id="t1")
|
|
|
|
target = os.path.join(worktree.host_path, "feature.py")
|
|
with open(target, "w", encoding="utf-8") as handle:
|
|
handle.write("x = 1\n")
|
|
|
|
sha = await adapter.commit(worktree=worktree, message="task/t1: add feature", author="Alice")
|
|
|
|
assert sha and len(sha) == 40
|
|
shared_gitdir = tmp_path / "root" / "org1" / "proj1" / "git"
|
|
log = await _git(
|
|
["--git-dir", str(shared_gitdir), "log", "-1", "--format=%an <%ae>|%s", "task/t1"],
|
|
cwd=str(tmp_path),
|
|
)
|
|
assert log.stdout.strip() == "Alice <alice@smart-org.local>|task/t1: add feature"
|
|
|
|
# ...and specifically to `task/t1`, not to `dev`. A shared gitdir makes this
|
|
# the easiest thing in the world to get wrong.
|
|
task_head = await _git(
|
|
["--git-dir", str(shared_gitdir), "rev-parse", "task/t1"], cwd=str(tmp_path)
|
|
)
|
|
assert task_head.stdout.strip() == sha
|
|
dev_head = await _git(
|
|
["--git-dir", str(shared_gitdir), "rev-parse", "dev"], cwd=str(tmp_path)
|
|
)
|
|
assert dev_head.stdout.strip() != sha, "the commit must not land on dev directly"
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# merge / push / head
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
async def test_merge_into_dev_and_push(tmp_path):
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
worktree = await adapter.create_task_worktree(project_id="proj1", task_id="t1")
|
|
|
|
with open(os.path.join(worktree.host_path, "a.txt"), "w", encoding="utf-8") as handle:
|
|
handle.write("a\n")
|
|
sha = await adapter.commit(worktree=worktree, message="task/t1: a", author="AI")
|
|
|
|
merged = await adapter.merge_into(project_id="proj1", branch="task/t1", target="dev")
|
|
assert merged.ok is True, merged.message
|
|
|
|
# `--no-ff` means dev gets a merge *commit*, not the task commit itself, so
|
|
# the task sha is a parent of dev's new head rather than dev's head.
|
|
dev_head = await adapter.head(project_id="proj1", branch="dev")
|
|
assert dev_head == merged.sha
|
|
assert dev_head != sha
|
|
ancestry = await _git(
|
|
["--git-dir", str(tmp_path / "root" / "org1" / "proj1" / "git"),
|
|
"rev-list", "--parents", "-1", "dev"],
|
|
cwd=str(tmp_path),
|
|
)
|
|
assert sha in ancestry.stdout.split()
|
|
|
|
pushed = await adapter.push(project_id="proj1", branch="dev")
|
|
assert pushed.ok is True, pushed.message
|
|
|
|
# The remote really received it.
|
|
ls = await _git(["--git-dir", remote, "rev-parse", "dev"], cwd=str(tmp_path))
|
|
assert ls.stdout.strip() == dev_head
|
|
|
|
|
|
async def test_merge_conflict_leaves_a_clean_tree(tmp_path):
|
|
"""A half-merge would break every later operation (agybot bug H3).
|
|
|
|
The task branch has to fork *before* ``dev`` moves, otherwise the merge is a
|
|
trivial fast-forward and there is nothing to conflict about.
|
|
"""
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
|
|
# 1. The task branches off dev as it stands.
|
|
worktree = await adapter.create_task_worktree(project_id="proj1", task_id="t1")
|
|
with open(os.path.join(worktree.host_path, "README.md"), "w", encoding="utf-8") as handle:
|
|
handle.write("task version\n")
|
|
await adapter.commit(worktree=worktree, message="task/t1: edit", author="AI")
|
|
|
|
# 2. dev moves on, touching the same file.
|
|
main_work = tmp_path / "root" / "org1" / "proj1" / "work"
|
|
(main_work / "README.md").write_text("dev version\n")
|
|
await _git(
|
|
["--git-dir", str(tmp_path / "root" / "org1" / "proj1" / "git"),
|
|
"--work-tree", str(main_work), "add", "-A"],
|
|
cwd=str(main_work),
|
|
)
|
|
await _git(
|
|
["--git-dir", str(tmp_path / "root" / "org1" / "proj1" / "git"),
|
|
"--work-tree", str(main_work), "commit", "--quiet", "-m", "dev edit"],
|
|
cwd=str(main_work),
|
|
)
|
|
|
|
outcome = await adapter.merge_into(project_id="proj1", branch="task/t1", target="dev")
|
|
|
|
assert outcome.ok is False
|
|
assert outcome.conflict_files == ["README.md"]
|
|
|
|
# No merge in progress: the next status is clean.
|
|
status = await _git(
|
|
["--git-dir", str(tmp_path / "root" / "org1" / "proj1" / "git"),
|
|
"--work-tree", str(main_work), "status", "--porcelain=v1", "-uall"],
|
|
cwd=str(main_work),
|
|
)
|
|
assert status.stdout.strip() == ""
|
|
assert not os.path.exists(
|
|
tmp_path / "root" / "org1" / "proj1" / "git" / "MERGE_HEAD"
|
|
)
|
|
|
|
|
|
async def test_sync_with_base_reports_that_the_base_moved(tmp_path):
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
worktree = await adapter.create_task_worktree(project_id="proj1", task_id="t1")
|
|
|
|
# Nothing moved yet.
|
|
quiet = await adapter.sync_with_base(worktree=worktree)
|
|
assert quiet.ok is True and quiet.base_changed is False
|
|
|
|
# Move dev forward.
|
|
main_work = tmp_path / "root" / "org1" / "proj1" / "work"
|
|
(main_work / "other.txt").write_text("x\n")
|
|
await _git(
|
|
["--git-dir", str(tmp_path / "root" / "org1" / "proj1" / "git"),
|
|
"--work-tree", str(main_work), "add", "-A"],
|
|
cwd=str(main_work),
|
|
)
|
|
await _git(
|
|
["--git-dir", str(tmp_path / "root" / "org1" / "proj1" / "git"),
|
|
"--work-tree", str(main_work), "commit", "--quiet", "-m", "dev moved"],
|
|
cwd=str(main_work),
|
|
)
|
|
|
|
moved = await adapter.sync_with_base(worktree=worktree)
|
|
assert moved.ok is True
|
|
assert moved.base_changed is True
|
|
assert os.path.isfile(os.path.join(worktree.host_path, "other.txt"))
|
|
|
|
|
|
async def test_concurrent_merges_are_serialised(tmp_path):
|
|
"""Without the per-project lock two merges corrupt the index."""
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
|
|
for task in ("t1", "t2"):
|
|
worktree = await adapter.create_task_worktree(project_id="proj1", task_id=task)
|
|
with open(
|
|
os.path.join(worktree.host_path, f"{task}.txt"), "w", encoding="utf-8"
|
|
) as handle:
|
|
handle.write(f"{task}\n")
|
|
await adapter.commit(worktree=worktree, message=f"task/{task}", author="AI")
|
|
|
|
first, second = await asyncio.gather(
|
|
adapter.merge_into(project_id="proj1", branch="task/t1", target="dev"),
|
|
adapter.merge_into(project_id="proj1", branch="task/t2", target="dev"),
|
|
)
|
|
|
|
assert first.ok is True and second.ok is True
|
|
status = await _git(
|
|
["--git-dir", str(tmp_path / "root" / "org1" / "proj1" / "git"),
|
|
"--work-tree", str(tmp_path / "root" / "org1" / "proj1" / "work"),
|
|
"status", "--porcelain=v1", "-uall"],
|
|
cwd=str(tmp_path),
|
|
)
|
|
assert status.stdout.strip() == ""
|
|
|
|
|
|
async def test_push_reports_a_rejection_without_forcing(tmp_path):
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
|
|
# Someone else advances the remote's dev, so our push is no longer a
|
|
# fast-forward. `origin/dev` is what the clone checked out, not a fresh
|
|
# branch off the default one.
|
|
other = tmp_path / "other"
|
|
await _git(["clone", "--quiet", remote, str(other)], cwd=str(tmp_path))
|
|
await _git(["checkout", "--quiet", "-B", "dev", "origin/dev"], cwd=str(other))
|
|
(other / "divergent.txt").write_text("other\n")
|
|
await _git(["add", "-A"], cwd=str(other))
|
|
await _git(["commit", "--quiet", "-m", "divergent"], cwd=str(other))
|
|
await _git(["push", "--quiet", "origin", "dev"], cwd=str(other))
|
|
|
|
# Local dev moves a different way.
|
|
main_work = tmp_path / "root" / "org1" / "proj1" / "work"
|
|
(main_work / "mine.txt").write_text("mine\n")
|
|
await _git(
|
|
["--git-dir", str(tmp_path / "root" / "org1" / "proj1" / "git"),
|
|
"--work-tree", str(main_work), "add", "-A"],
|
|
cwd=str(main_work),
|
|
)
|
|
await _git(
|
|
["--git-dir", str(tmp_path / "root" / "org1" / "proj1" / "git"),
|
|
"--work-tree", str(main_work), "commit", "--quiet", "-m", "mine"],
|
|
cwd=str(main_work),
|
|
)
|
|
|
|
outcome = await adapter.push(project_id="proj1", branch="dev")
|
|
|
|
assert outcome.ok is False
|
|
assert outcome.rejected is True, outcome.message
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# hardening
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
async def test_hooks_are_never_executed(tmp_path):
|
|
"""A repository may ship hooks; a hook is arbitrary host code execution."""
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
|
|
gitdir = tmp_path / "root" / "org1" / "proj1" / "git"
|
|
hooks = gitdir / "hooks"
|
|
hooks.mkdir(parents=True, exist_ok=True)
|
|
marker = tmp_path / "HOOK_RAN"
|
|
hook = hooks / "post-commit"
|
|
hook.write_text(f"#!/bin/sh\ntouch {marker}\n")
|
|
os.chmod(hook, 0o755)
|
|
|
|
worktree = await adapter.create_task_worktree(project_id="proj1", task_id="t1")
|
|
with open(os.path.join(worktree.host_path, "a.txt"), "w", encoding="utf-8") as handle:
|
|
handle.write("a\n")
|
|
await adapter.commit(worktree=worktree, message="task/t1", author="AI")
|
|
|
|
assert not marker.exists(), "a post-commit hook must not run"
|
|
|
|
|
|
async def test_a_tampered_dot_git_file_is_ignored(tmp_path):
|
|
"""The `.git` pointer inside a worktree is attacker-controlled text."""
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
worktree = await adapter.create_task_worktree(project_id="proj1", task_id="t1")
|
|
|
|
decoy = tmp_path / "decoy"
|
|
await _git(["init", "--quiet", str(decoy)], cwd=str(tmp_path))
|
|
with open(os.path.join(worktree.host_path, ".git"), "w", encoding="utf-8") as handle:
|
|
handle.write(f"gitdir: {decoy}\n")
|
|
|
|
with open(os.path.join(worktree.host_path, "a.txt"), "w", encoding="utf-8") as handle:
|
|
handle.write("a\n")
|
|
sha = await adapter.commit(worktree=worktree, message="task/t1", author="AI")
|
|
|
|
assert sha is not None
|
|
# The commit landed on OUR task branch, not in the decoy.
|
|
shared_gitdir = tmp_path / "root" / "org1" / "proj1" / "git"
|
|
real = await _git(
|
|
["--git-dir", str(shared_gitdir), "rev-parse", "task/t1"], cwd=str(tmp_path)
|
|
)
|
|
assert real.stdout.strip() == sha
|
|
decoy_log = await _git(
|
|
["--git-dir", str(decoy), "log", "--oneline"], cwd=str(tmp_path), ok=False
|
|
)
|
|
assert decoy_log.exit_code != 0 or "task/t1" not in decoy_log.stdout
|
|
|
|
|
|
async def test_credentials_never_appear_in_argv(tmp_path):
|
|
"""argv is world-readable via `ps`; a secret must travel another way."""
|
|
secret = "ghp_thisisasecrettokenvalue0123456789"
|
|
seen: list[tuple[str, ...]] = []
|
|
|
|
async def recording_runner(argv, **kwargs): # noqa: ANN001, ANN003
|
|
seen.append(tuple(argv))
|
|
return await run_process(argv, **kwargs)
|
|
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = LocalGitWorkspaceAdapter(
|
|
resolver=_resolver(remote, auth_type="token", secret=secret, username="git"),
|
|
root=str(tmp_path / "root"),
|
|
allow_file_protocol=True,
|
|
runner=recording_runner,
|
|
)
|
|
|
|
# A token against a local path fails, but the *attempt* is what we assert on.
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
|
|
assert seen, "the adapter must have invoked git"
|
|
for argv in seen:
|
|
joined = " ".join(argv)
|
|
assert secret not in joined, f"secret leaked into argv: {argv}"
|
|
|
|
|
|
async def test_the_credential_file_is_removed_after_the_call(tmp_path):
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = LocalGitWorkspaceAdapter(
|
|
resolver=_resolver(remote, auth_type="token", secret="s3cret-token-value", username="git"),
|
|
root=str(tmp_path / "root"),
|
|
allow_file_protocol=True,
|
|
)
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
|
|
private = tmp_path / "root" / "org1" / "proj1" / "private"
|
|
assert private.is_dir()
|
|
assert not (private / "credentials").exists(), "the 0600 secret file must be deleted"
|
|
assert not (private / "id_key").exists()
|
|
|
|
|
|
async def test_the_askpass_helper_is_private_and_holds_no_secret(tmp_path):
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = LocalGitWorkspaceAdapter(
|
|
resolver=_resolver(remote, auth_type="token", secret="s3cret-token-value", username="git"),
|
|
root=str(tmp_path / "root"),
|
|
allow_file_protocol=True,
|
|
)
|
|
await adapter.ensure_workspace(project_id="proj1")
|
|
|
|
helper = tmp_path / "root" / "org1" / "proj1" / "private" / "askpass.sh"
|
|
assert helper.is_file()
|
|
assert oct(helper.stat().st_mode)[-3:] == "700"
|
|
assert "s3cret-token-value" not in helper.read_text()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# SSRF: the shared host check
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"address",
|
|
[
|
|
"127.0.0.1",
|
|
"10.0.0.1",
|
|
"172.16.0.1",
|
|
"192.168.1.1",
|
|
"169.254.169.254",
|
|
"::1",
|
|
"fd00::1",
|
|
"fe80::1",
|
|
"0.0.0.0",
|
|
],
|
|
)
|
|
def test_is_blocked_address_covers_the_dangerous_ranges(address: str):
|
|
assert is_blocked_address(address) is True
|
|
|
|
|
|
@pytest.mark.parametrize("address", ["8.8.8.8", "1.1.1.1", "2606:4700::1111"])
|
|
def test_is_blocked_address_allows_public_addresses(address: str):
|
|
assert is_blocked_address(address) is False
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"url",
|
|
[
|
|
"http://169.254.169.254/latest/meta-data/",
|
|
"http://127.0.0.1:6379/",
|
|
"http://localhost/repo.git",
|
|
"https://10.0.0.5/repo.git",
|
|
"http://[::1]/repo.git",
|
|
"https://user:pass@example.com/repo.git",
|
|
"file:///etc/passwd",
|
|
"https://example.com:6379/repo.git",
|
|
],
|
|
)
|
|
def test_assert_remote_host_allowed_refuses_dangerous_targets(url: str):
|
|
with pytest.raises(RuleViolation):
|
|
assert_remote_host_allowed(url, resolver=lambda *a, **k: [])
|
|
|
|
|
|
def test_assert_remote_host_allowed_accepts_a_public_host():
|
|
def resolver(host, port, **kwargs): # noqa: ANN001, ANN003
|
|
return [(2, 1, 6, "", ("93.184.216.34", port))]
|
|
|
|
host, port = assert_remote_host_allowed(
|
|
"https://git.example.com/team/app.git", resolver=resolver
|
|
)
|
|
assert host == "git.example.com"
|
|
assert port is None
|
|
|
|
|
|
def test_assert_remote_host_allowed_refuses_a_name_that_resolves_private():
|
|
"""A public-looking name can resolve into the private network."""
|
|
|
|
def resolver(host, port, **kwargs): # noqa: ANN001, ANN003
|
|
return [(2, 1, 6, "", ("10.1.2.3", port))]
|
|
|
|
with pytest.raises(RuleViolation):
|
|
assert_remote_host_allowed("https://internal.example.com/repo.git", resolver=resolver)
|
|
|
|
|
|
def test_assert_remote_host_allowed_can_be_told_to_allow_private():
|
|
host, _ = assert_remote_host_allowed(
|
|
"http://127.0.0.1:8080/repo.git", allow_private=True
|
|
)
|
|
assert host == "127.0.0.1"
|
|
|
|
|
|
def test_assert_remote_host_allowed_accepts_scp_style_ssh():
|
|
def resolver(host, port, **kwargs): # noqa: ANN001, ANN003
|
|
return [(2, 1, 6, "", ("93.184.216.34", port))]
|
|
|
|
host, _ = assert_remote_host_allowed("git@git.example.com:team/app.git", resolver=resolver)
|
|
assert host == "git.example.com"
|
|
|
|
|
|
async def test_test_remote_refuses_a_private_host(tmp_path):
|
|
adapter = _adapter(tmp_path, "https://example.com/x.git")
|
|
from app.application.ports.repo_workspace import RemoteCredentials
|
|
|
|
check = await adapter.test_remote(
|
|
url="http://169.254.169.254/repo.git", credentials=RemoteCredentials()
|
|
)
|
|
assert check.ok is False
|
|
assert "داخلی" in check.message
|
|
|
|
|
|
async def test_test_remote_lists_branches_of_a_local_repo(tmp_path, monkeypatch):
|
|
"""The ls-remote path, with the SSRF check stubbed out.
|
|
|
|
The check itself is covered by the tests above; here the subject is the
|
|
parsing of `git ls-remote --heads` and the branch list it produces. A local
|
|
bare repo is used as the remote because the suite must not need a network.
|
|
"""
|
|
import app.infrastructure.adapters.git_workspace as module
|
|
from app.application.ports.repo_workspace import RemoteCredentials
|
|
|
|
monkeypatch.setattr(module, "assert_remote_host_allowed", lambda *a, **k: ("local", None))
|
|
|
|
remote = await _make_remote(tmp_path)
|
|
adapter = _adapter(tmp_path, remote)
|
|
|
|
check = await adapter.test_remote(
|
|
url=f"file://{remote}", credentials=RemoteCredentials()
|
|
)
|
|
|
|
assert check.ok is True, check.message
|
|
assert check.branches == ["main"]
|
|
assert check.default_branch == "main"
|
|
|
|
|
|
async def test_test_remote_reports_a_missing_repository(tmp_path, monkeypatch):
|
|
import app.infrastructure.adapters.git_workspace as module
|
|
from app.application.ports.repo_workspace import RemoteCredentials
|
|
|
|
monkeypatch.setattr(module, "assert_remote_host_allowed", lambda *a, **k: ("local", None))
|
|
|
|
adapter = _adapter(tmp_path, "https://example.com/x.git")
|
|
check = await adapter.test_remote(
|
|
url=f"file://{tmp_path}/does-not-exist.git", credentials=RemoteCredentials()
|
|
)
|
|
|
|
assert check.ok is False
|
|
assert check.message
|