state-hub/tests/test_forge_projection.py
tegwick a32112e5ab
All checks were successful
CI Smoke / host-smoke (push) Successful in 0s
CI Smoke / container-smoke (push) Successful in 1s
Build and Publish Multi-Context Image / build-and-push (push) Successful in 26s
fix: preserve stale task identity history
Assistant: codex
Assistant-Model: gpt-5.6-sol
Assistant-Session: 01a053ff-1d6f-7fe2-ac1c-a6eb40a42a0c
2026-08-31 02:02:35 +02:00

1280 lines
52 KiB
Python

"""Deriving a projection from the forge (STATE-WP-0083-T01).
The properties that matter are identity and determinism: a forge-derived
projection must compute the same record identities as repo-manager, and the same
commit must always yield the same projection. Without both, the reset in T03
cannot be verified against anything.
"""
from __future__ import annotations
from pathlib import Path
import pytest
from api.services import forge_credential as fc
from api.services import forge_projection as fp
def test_identity_matches_the_fleet_derivation():
"""Same namespace as ADR-007, so overlay and forge agree on identity."""
assert fp.derived_record_uuid("CUST-WP-0067") == "16249302-2767-55df-aec0-d92c2751c225"
assert fp.derived_record_uuid("CUST-WP-0067-T01") == "f3608db4-20a5-58fb-a965-885eb14858af"
def _repo(tmp_path: Path) -> Path:
root = tmp_path / "demo"
(root / "workplans" / "archived").mkdir(parents=True)
(root / "workplans" / "DEMO-WP-0001-a.md").write_text(
"---\nid: DEMO-WP-0001\ntype: workplan\ntitle: \"First\"\nstatus: active\n---\n\n"
"## Do the thing\n\n```task\nid: DEMO-WP-0001-T01\nstatus: todo\npriority: high\n```\n\n"
"## Do the other\n\n```task\nid: DEMO-WP-0001-T02\nstatus: done\npriority: low\n```\n",
encoding="utf-8",
)
(root / "workplans" / "archived" / "260101-DEMO-WP-0002-b.md").write_text(
"---\nid: DEMO-WP-0002\ntype: workplan\ntitle: \"Second\"\nstatus: finished\n---\n\n# b\n",
encoding="utf-8",
)
(root / "workplans" / "NOTES.md").write_text(
"---\nid: NOT-A-WORKPLAN\ntype: note\n---\n\n# not a workplan\n", encoding="utf-8"
)
return root
def test_derives_workplans_tasks_and_archived_flag(tmp_path):
p = fp.derive_from_checkout(_repo(tmp_path), "demo", "abc123")
assert [w.record_id for w in p.workplans] == ["DEMO-WP-0001", "DEMO-WP-0002"]
first, second = p.workplans
assert first.status == "active" and first.archived is False
assert second.archived is True
assert p.task_count == 2
assert [t.record_id for t in first.tasks] == ["DEMO-WP-0001-T01", "DEMO-WP-0001-T02"]
def test_ignores_files_that_are_not_workplans(tmp_path):
"""Selection is by `type: workplan`; anything else is not this hub's business."""
p = fp.derive_from_checkout(_repo(tmp_path), "demo", "abc123")
assert all(w.record_id != "NOT-A-WORKPLAN" for w in p.workplans)
def test_task_titles_fall_back_to_the_preceding_heading(tmp_path):
p = fp.derive_from_checkout(_repo(tmp_path), "demo", "abc123")
titles = [t.title for t in p.workplans[0].tasks]
assert titles == ["Do the thing", "Do the other"]
def test_identifiers_are_derived_not_read_from_the_file(tmp_path):
"""A forge projection must not inherit whatever id a file happens to carry."""
root = _repo(tmp_path)
f = root / "workplans" / "DEMO-WP-0001-a.md"
f.write_text(
f.read_text(encoding="utf-8").replace(
"status: active",
'status: active\nstate_hub_workstream_id: "00000000-0000-4000-8000-000000000000"',
),
encoding="utf-8",
)
p = fp.derive_from_checkout(root, "demo", "abc123")
assert p.workplans[0].uuid == fp.derived_record_uuid("DEMO-WP-0001")
assert p.workplans[0].uuid != "00000000-0000-4000-8000-000000000000"
def test_same_input_yields_identical_output(tmp_path):
root = _repo(tmp_path)
assert fp.derive_from_checkout(root, "demo", "abc").to_dict() == \
fp.derive_from_checkout(root, "demo", "abc").to_dict()
def test_missing_workplans_directory_is_empty_not_an_error(tmp_path):
(tmp_path / "bare").mkdir()
p = fp.derive_from_checkout(tmp_path / "bare", "bare", "abc")
assert p.workplans == [] and p.commit == "abc"
def test_clone_failure_is_reported_not_swallowed(monkeypatch):
def boom(*a, **k):
raise fp.ForgeDeriveError("repository not found")
monkeypatch.setattr(fp, "_run_git", boom)
with pytest.raises(fp.ForgeDeriveError, match="not found"):
fp.derive_from_forge("nope")
class TestReset:
"""Applying the reset (STATE-WP-0083-T03).
The properties worth guarding are the refusals, not the happy path. A reset
that quietly retires a record someone still needs is worse than one that
does nothing.
"""
@staticmethod
def _derived(*records):
wps = []
for rid, status, path in records:
wps.append(
fp.DerivedWorkplan(
record_id=rid, uuid=fp.derived_record_uuid(rid), title=rid,
status=status, relative_path=path, archived=False, tasks=[],
)
)
return fp.DerivedProjection(repo_slug="demo", commit="c0ffee", workplans=wps)
@pytest.mark.asyncio
async def test_refuses_retirement_unless_acknowledged(self, monkeypatch):
"""A record that stops deriving may mean a deleted file — or a wrong branch."""
session = _FakeSession(
repo=_Repo(),
rows=[_Row(slug="demo-wp-0001", status="active", path="workplans/a.md")],
)
out = await fp.reset_repository_projection(
session, "demo", derived=self._derived() # forge has nothing
)
assert out.status == "refused"
assert out.refused and out.refused[0]["slug"] == "demo-wp-0001"
assert out.retired == []
assert session.committed is False
@pytest.mark.asyncio
async def test_retires_when_acknowledged(self):
row = _Row(slug="demo-wp-0001", status="active", path="workplans/a.md")
session = _FakeSession(repo=_Repo(), rows=[row])
out = await fp.reset_repository_projection(
session, "demo", derived=self._derived(), acknowledge_retirements=True
)
assert out.status == "applied" and out.retired == ["demo-wp-0001"]
assert row.projection_retired_at is not None
assert row.projection_retired_reason == fp.RETIRE_REASON
@pytest.mark.asyncio
async def test_retirement_is_not_deletion(self):
"""Hub-native records reference workplans with RESTRICT; the row survives."""
row = _Row(slug="demo-wp-0001", status="active", path="workplans/a.md")
session = _FakeSession(repo=_Repo(), rows=[row])
await fp.reset_repository_projection(
session, "demo", derived=self._derived(), acknowledge_retirements=True
)
assert row in session.rows
assert session.deleted == []
@pytest.mark.asyncio
async def test_unretires_a_record_that_derives_again(self):
from datetime import datetime, timezone
row = _Row(slug="demo-wp-0001", status="active", path="workplans/a.md")
row.projection_retired_at = datetime.now(tz=timezone.utc)
row.projection_retired_reason = fp.RETIRE_REASON
session = _FakeSession(repo=_Repo(), rows=[row])
out = await fp.reset_repository_projection(
session, "demo",
derived=self._derived(("DEMO-WP-0001", "active", "workplans/a.md")),
)
assert out.status == "applied"
assert row.projection_retired_at is None
@pytest.mark.asyncio
async def test_unregistered_repository_is_refused_not_created(self):
session = _FakeSession(repo=None, rows=[])
out = await fp.reset_repository_projection(session, "nope", derived=self._derived())
assert out.status == "refused"
assert "not registered" in out.refused[0]["reason"]
@pytest.mark.asyncio
async def test_records_the_commit_it_derived_from(self):
row = _Row(slug="demo-wp-0001", status="proposed", path="workplans/a.md")
session = _FakeSession(repo=_Repo(), rows=[row])
await fp.reset_repository_projection(
session, "demo",
derived=self._derived(("DEMO-WP-0001", "active", "workplans/a.md")),
)
assert row.derived_from_commit == "c0ffee"
assert row.status == "active"
class _Repo:
def __init__(self):
import uuid as _u
self.id = _u.uuid4()
self.topic_id = None
class _Row:
def __init__(self, slug, status, path, title=None):
import uuid as _u
self.id = _u.uuid4()
self.slug = slug
self.status = status
# The title is a derived field the reset syncs; the fixture carried no
# `title` at all, so it could not have caught the drift that left
# cust-wp-0010 describing another workplan's work.
self.title = title
self.backing_relative_path = path
self.backing_filename = path.rsplit("/", 1)[-1]
self.backing_archived = False
self.projection_retired_at = None
self.projection_retired_reason = None
self.derived_from_commit = None
class _FakeSession:
"""Stands in for AsyncSession: enough to prove intent without a database."""
def __init__(
self,
repo,
rows,
foreign=None,
slug_clash=None,
task_rows=None,
task_collision_rows=None,
):
self._repo = repo
self.rows = list(rows)
self._foreign = list(foreign or [])
self._slug_clash = list(slug_clash or [])
self._task_rows = task_rows
self._task_collision_rows = list(task_collision_rows or [])
self.added = []
self.deleted = []
self.committed = False
self._calls = 0
async def execute(self, *_a, **_k):
self._calls += 1
repo, rows = self._repo, self.rows
# 1 resolves the repo, 2 loads its workplans, 3 is the identifier
# lookup, 4 the slug lookup. On the update-only path (no creates)
# the 3rd call is the existing-task load instead.
update_only = (
self._task_rows is not None
and not self._foreign
and not self._slug_clash
)
if self._calls == 2:
payload = rows
elif update_only and self._calls == 3:
payload = self._task_rows
elif update_only and self._calls == 4:
payload = self._task_collision_rows
elif self._calls == 3:
payload = self._foreign
elif self._calls == 4:
payload = self._slug_clash
elif self._calls == 5:
payload = self._task_collision_rows
else:
payload = []
class R:
def scalar_one_or_none(self_inner):
return repo
def scalars(self_inner):
return iter(payload)
return R()
def add(self, obj):
self.added.append(obj)
def delete(self, obj):
self.deleted.append(obj)
async def flush(self):
return None
async def commit(self):
self.committed = True
async def rollback(self):
self.rolled_back = True
class TestCollisionRefusal:
"""A colliding identifier must refuse, not raise (STATE-WP-0083-T03).
net-kingdom's ADHOC-2026-08-23 derives to an identifier another repository
already holds — the case CUST-WP-0066 documents. The reset previously failed
on a database constraint, which tells the caller nothing they can act on.
"""
@staticmethod
def _derived(rid="DEMO-WP-0001"):
return fp.DerivedProjection(
repo_slug="demo", commit="c0ffee",
workplans=[fp.DerivedWorkplan(
record_id=rid, uuid=fp.derived_record_uuid(rid), title=rid,
status="active", relative_path="workplans/a.md",
archived=False, tasks=[])],
)
@pytest.mark.asyncio
async def test_refuses_when_the_identifier_belongs_elsewhere(self):
derived = self._derived()
foreign = _Row(slug="held-by-someone-else", status="finished", path="workplans/x.md")
foreign.id = __import__("uuid").UUID(derived.workplans[0].uuid)
session = _FakeSession(repo=_Repo(), rows=[], foreign=[foreign])
out = await fp.reset_repository_projection(session, "demo", derived=derived)
assert out.status == "refused"
assert out.refused[0]["reason"].startswith("derived identifier already belongs")
assert out.refused[0]["held_by_slug"] == "held-by-someone-else"
assert out.created == [] and session.added == []
@pytest.mark.asyncio
async def test_acknowledging_retirements_does_not_authorise_a_collision(self):
"""Different decision, different authorisation."""
derived = self._derived()
foreign = _Row(slug="held-by-someone-else", status="finished", path="workplans/x.md")
foreign.id = __import__("uuid").UUID(derived.workplans[0].uuid)
session = _FakeSession(repo=_Repo(), rows=[], foreign=[foreign])
out = await fp.reset_repository_projection(
session, "demo", derived=derived, acknowledge_retirements=True
)
assert out.status == "refused"
assert session.added == []
@pytest.mark.asyncio
async def test_no_collision_still_creates(self):
derived = self._derived()
session = _FakeSession(repo=_Repo(), rows=[], foreign=[])
out = await fp.reset_repository_projection(session, "demo", derived=derived)
assert out.status == "applied" and out.created == ["DEMO-WP-0001"]
class TestFleetReset:
"""The fleet form must be a loop over the repository form (T04).
Its value is entirely in what it does with failure: a wide reset that stops
at the first refusal is one nobody can run, because there is always one
unresolved repository somewhere.
"""
class _Factory:
def __init__(self, sessions):
self._sessions = list(sessions)
def __call__(self):
session = self._sessions.pop(0)
class Ctx:
async def __aenter__(self_inner):
return session
async def __aexit__(self_inner, *a):
return False
return Ctx()
@staticmethod
def _derived(rid):
return fp.DerivedProjection(
repo_slug="x", commit="c0ffee",
workplans=[fp.DerivedWorkplan(
record_id=rid, uuid=fp.derived_record_uuid(rid), title=rid,
status="active", relative_path="workplans/a.md", archived=False, tasks=[])])
@pytest.mark.asyncio
async def test_a_refusal_does_not_stop_the_pass(self, monkeypatch):
calls = []
async def fake(session, slug, **kw):
calls.append(slug)
out = fp.ResetOutcome(repo_slug=slug, commit="c0ffee", status="applied")
if slug == "bad":
out.status = "refused"
out.refused.append({"reason": "would be retired", "slug": "x"})
else:
out.updated.append("A-WP-0001")
return out
monkeypatch.setattr(fp, "reset_repository_projection", fake)
s = [_FakeSession(repo=_Repo(), rows=[]) for _ in range(3)]
res = await fp.reset_fleet_projection(self._Factory(s), ["good", "bad", "also-good"])
assert calls == ["good", "bad", "also-good"]
d = res.to_dict()
assert d["by_status"] == {"applied": 2, "refused": 1}
assert d["totals"]["updated"] == 2
@pytest.mark.asyncio
async def test_an_error_does_not_stop_the_pass(self, monkeypatch):
async def fake(session, slug, **kw):
if slug == "boom":
raise RuntimeError("clone failed")
return fp.ResetOutcome(repo_slug=slug, commit="c", status="noop")
monkeypatch.setattr(fp, "reset_repository_projection", fake)
s = [_FakeSession(repo=_Repo(), rows=[]) for _ in range(3)]
res = await fp.reset_fleet_projection(self._Factory(s), ["a", "boom", "b"])
d = res.to_dict()
assert d["errored"] == 1 and "clone failed" in res.errors["boom"]
assert set(res.results) == {"a", "b"}
@pytest.mark.asyncio
async def test_only_applied_repositories_are_committed(self, monkeypatch):
async def fake(session, slug, **kw):
out = fp.ResetOutcome(repo_slug=slug, commit="c", status="applied")
if slug == "refuser":
out.status = "refused"
else:
out.updated.append("A-WP-0001")
return out
monkeypatch.setattr(fp, "reset_repository_projection", fake)
s = [_FakeSession(repo=_Repo(), rows=[]) for _ in range(2)]
await fp.reset_fleet_projection(self._Factory(s), ["applier", "refuser"])
assert s[0].committed is True
assert s[1].committed is False
class TestSlugCollisionRefusal:
"""slug carries its own unique constraint (STATE-WP-0083-T04).
Checking the identifier alone left disaster-control raising IntegrityError:
two repositories can derive different identifiers whose slugs still collide.
"""
@pytest.mark.asyncio
async def test_refuses_when_the_slug_belongs_elsewhere(self):
derived = fp.DerivedProjection(
repo_slug="demo", commit="c0ffee",
workplans=[fp.DerivedWorkplan(
record_id="REPO-WP-0001", uuid=fp.derived_record_uuid("REPO-WP-0001"),
title="x", status="active", relative_path="workplans/a.md",
archived=False, tasks=[])])
clash = _Row(slug="repo-wp-0001", status="finished", path="workplans/other.md")
session = _FakeSession(repo=_Repo(), rows=[], foreign=[], slug_clash=[clash])
out = await fp.reset_repository_projection(session, "demo", derived=derived)
assert out.status == "refused"
assert out.refused[0]["reason"].startswith("slug already belongs")
assert session.added == []
class TestUnreadableIsNotMissing:
"""STATE-WP-0084-T01.
A repository central is not permitted to read and a repository whose
records no longer derive authorise opposite things. Every test here exists
to keep the retirement path unreachable from an answer that cannot support
it — by construction, not by the reset happening to fail first.
"""
@pytest.mark.parametrize(
"stderr",
[
"fatal: could not read Username for 'https://forgejo.coulomb.social'",
"remote: Invalid username or password.\nfatal: Authentication failed",
"fatal: could not read Username for 'https://f': terminal prompts disabled",
"fatal: repository 'https://forgejo.coulomb.social/rapp-openbao.git' not found",
"fatal: unable to access '...': The requested URL returned error: 403",
],
)
def test_permission_shaped_failures_are_classified_unreadable(self, stderr, monkeypatch):
def boom(*a, **k):
raise fp.ForgeDeriveError(stderr)
monkeypatch.setattr(fp, "_run_git", boom)
with pytest.raises(fp.ForgeUnreadableError):
fp.derive_from_forge("rapp-openbao")
def test_a_genuine_fault_stays_a_plain_error(self, monkeypatch):
def boom(*a, **k):
raise fp.ForgeDeriveError("fatal: early EOF\nfatal: index-pack failed")
monkeypatch.setattr(fp, "_run_git", boom)
with pytest.raises(fp.ForgeDeriveError) as exc:
fp.derive_from_forge("demo")
assert not isinstance(exc.value, fp.ForgeUnreadableError)
def test_unreadable_is_a_derive_error_so_old_callers_still_catch_it(self):
assert issubclass(fp.ForgeUnreadableError, fp.ForgeDeriveError)
def test_a_checkout_without_workplans_cannot_evidence_absence(self, tmp_path):
(tmp_path / "bare").mkdir()
p = fp.derive_from_checkout(tmp_path / "bare", "bare", "abc")
assert p.workplans == []
assert p.records_source_present is False
assert p.retirement_eligible is False
def test_a_real_checkout_can(self, tmp_path):
p = fp.derive_from_checkout(_repo(tmp_path), "demo", "abc")
assert p.records_source_present is True
assert p.retirement_eligible is True
def test_the_diff_withholds_stale_rather_than_computing_it(self):
derived = fp.DerivedProjection(
repo_slug="demo", commit="c0ffee", records_source_present=False
)
hub = [{"id": "11111111-1111-1111-1111-111111111111", "slug": "demo-wp-0001",
"status": "active", "backing_relative_path": "workplans/a.md"}]
d = fp.diff_against_hub(derived, hub, {})
assert d.stale == []
assert d.would_remove == 0
assert d.stale_withheld
@pytest.mark.asyncio
async def test_an_empty_source_cannot_retire_even_when_acknowledged(self):
derived = fp.DerivedProjection(
repo_slug="demo", commit="c0ffee", records_source_present=False
)
row = _Row(slug="demo-wp-0001", status="active", path="workplans/a.md")
session = _FakeSession(repo=_Repo(), rows=[row])
out = await fp.reset_repository_projection(
session, "demo", derived=derived, acknowledge_retirements=True
)
assert out.status == "refused"
assert out.retired == []
assert row.projection_retired_at is None
assert out.refused[0]["reason"].startswith("source produced no records")
@pytest.mark.asyncio
async def test_an_unreadable_repository_reports_unreadable_not_error(self, monkeypatch):
def boom(*a, **k):
raise fp.ForgeUnreadableError("rapp-openbao could not be read from the forge")
monkeypatch.setattr(fp, "derive_from_forge", boom)
session = _FakeSession(repo=_Repo(), rows=[])
out = await fp.reset_repository_projection(session, "rapp-openbao")
assert out.status == "unreadable"
assert out.retired == [] and out.created == [] and out.updated == []
@pytest.mark.asyncio
async def test_the_fleet_keeps_unreadable_out_of_the_error_bucket(self, monkeypatch):
async def fake(session, slug, **kw):
if slug == "private":
out = fp.ResetOutcome(repo_slug=slug, commit="", status="unreadable")
out.refused.append({"reason": "repository could not be read from the forge",
"slug": slug, "detail": "could not read Username"})
return out
if slug == "broken":
raise RuntimeError("index-pack failed")
out = fp.ResetOutcome(repo_slug=slug, commit="c0ffee", status="applied")
out.updated.append("A-WP-0001")
return out
monkeypatch.setattr(fp, "reset_repository_projection", fake)
sessions = [_FakeSession(repo=_Repo(), rows=[]) for _ in range(3)]
outcome = await fp.reset_fleet_projection(
TestFleetReset._Factory(sessions), ["ok", "private", "broken"]
)
assert list(outcome.unreadable) == ["private"]
assert list(outcome.errors) == ["broken"]
assert "private" not in outcome.results
d = outcome.to_dict()
assert d["unreadable_count"] == 1 and d["errored"] == 1
assert d["repositories"] == 3
class TestForgeCredential:
"""Optional forge read credential (STATE-WP-0084-T03).
Absent is a valid state: a hub with no credential must still derive every
public repository. The credential must never reach argv, a log, or an
exception — the places a secret leaks without anyone deciding to leak it.
"""
@pytest.fixture(autouse=True)
def _clear_cache(self):
"""The resolved credential is cached for 5 minutes in production.
That cache is deliberate — a fleet reset of 121 repositories must not
authenticate to OpenBao 121 times — so tests clear it rather than
disable it, and exercise the same code path production uses.
"""
fc.reset_cache()
yield
fc.reset_cache()
def test_absent_credential_is_none_not_empty_string(self, monkeypatch):
monkeypatch.delenv(fc.TOKEN_ENV, raising=False)
monkeypatch.delenv(fc.TOKEN_FILE_ENV, raising=False)
assert fc.forge_read_token() is None
def test_a_file_is_preferred_over_the_environment(self, tmp_path, monkeypatch):
"""Kubernetes rotates a mounted file without a redeploy."""
f = tmp_path / "token"
f.write_text("from-file\n", encoding="utf-8")
monkeypatch.setenv(fc.TOKEN_ENV, "from-env")
monkeypatch.setenv(fc.TOKEN_FILE_ENV, str(f))
assert fc.forge_read_token() == "from-file"
def test_an_unreadable_token_file_does_not_fall_back_silently(self, monkeypatch):
"""Falling back to a stale env value would hide a broken mount."""
monkeypatch.setenv(fc.TOKEN_FILE_ENV, "/nonexistent/token")
monkeypatch.setenv(fc.TOKEN_ENV, "from-env")
assert fc.forge_read_token() is None
def test_openbao_is_the_last_resort_not_the_first(self, tmp_path, monkeypatch):
"""A file or env value must not trigger a network call."""
f = tmp_path / "token"
f.write_text("local", encoding="utf-8")
monkeypatch.setenv(fc.TOKEN_FILE_ENV, str(f))
monkeypatch.setattr(
fc, "_from_openbao", lambda: pytest.fail("OpenBao consulted unnecessarily")
)
assert fc.forge_read_token() == "local"
def test_openbao_failure_resolves_to_absent_not_an_exception(self, monkeypatch):
"""A hub that cannot reach OpenBao must still derive public repos.
Raising here would turn "nine repositories are unreadable" into "the
whole derivation pass failed" — the outcome STATE-WP-0084-T01 exists to
prevent.
"""
monkeypatch.delenv(fc.TOKEN_FILE_ENV, raising=False)
monkeypatch.delenv(fc.TOKEN_ENV, raising=False)
monkeypatch.setenv(fc.OPENBAO_ADDR_ENV, "https://openbao.invalid")
monkeypatch.setenv(fc.SECRET_PATH_ENV, "kv/data/forge")
monkeypatch.setenv(fc.OPENBAO_ROLE_ENV, "state-hub-forge-derivation")
monkeypatch.setenv(fc.OPENBAO_JWT_PATH_ENV, "/nonexistent/sa-token")
assert fc.forge_read_token() is None
def test_openbao_unwraps_kv_v2(self, tmp_path, monkeypatch):
jwt = tmp_path / "sa"
jwt.write_text("jwt-value", encoding="utf-8")
monkeypatch.delenv(fc.TOKEN_FILE_ENV, raising=False)
monkeypatch.delenv(fc.TOKEN_ENV, raising=False)
monkeypatch.setenv(fc.OPENBAO_ADDR_ENV, "https://openbao.test")
monkeypatch.setenv(fc.SECRET_PATH_ENV, "kv/data/forge")
monkeypatch.setenv(fc.OPENBAO_ROLE_ENV, "state-hub-forge-derivation")
monkeypatch.setenv(fc.OPENBAO_JWT_PATH_ENV, str(jwt))
class R:
def __init__(self, payload):
self._p = payload
def raise_for_status(self):
return None
def json(self):
return self._p
class C:
def __enter__(self):
return self
def __exit__(self, *a):
return False
def post(self, url, json):
assert json["jwt"] == "jwt-value"
assert json["role"] == "state-hub-forge-derivation"
return R({"auth": {"client_token": "bao-token"}})
def get(self, url, headers):
assert headers["X-Vault-Token"] == "bao-token"
return R({"data": {"data": {"token": "forge-secret"}}})
monkeypatch.setattr(fc.httpx, "Client", lambda **kw: C())
assert fc.forge_read_token() == "forge-secret"
def test_credential_never_appears_in_argv(self, monkeypatch):
"""`-c http.extraHeader=` would put the token in every ps listing."""
seen = {}
class P:
returncode = 0
stdout = ""
stderr = ""
def fake_run(cmd, **kw):
seen["cmd"] = cmd
seen["env"] = kw.get("env") or {}
return P()
monkeypatch.setattr(fp.subprocess, "run", fake_run)
fp._run_git("clone", "url", "dir", token="s3cret")
assert not any("s3cret" in part for part in seen["cmd"])
assert seen["env"]["GIT_CONFIG_COUNT"] == "1"
assert "s3cret" not in seen["env"]["GIT_CONFIG_KEY_0"]
def test_credential_is_redacted_from_failures(self, monkeypatch):
class P:
returncode = 128
stdout = ""
stderr = "fatal: auth failed using s3cret"
monkeypatch.setattr(fp.subprocess, "run", lambda *a, **k: P())
with pytest.raises(fp.ForgeDeriveError) as exc:
fp._run_git("clone", token="s3cret")
assert "s3cret" not in str(exc.value) and "***" in str(exc.value)
def test_no_credential_still_runs(self, monkeypatch):
class P:
returncode = 0
stdout = "ok"
stderr = ""
seen = {}
def fake_run(cmd, **kw):
seen["env"] = kw.get("env") or {}
return P()
monkeypatch.setattr(fp.subprocess, "run", fake_run)
assert fp._run_git("status") == "ok"
assert "GIT_CONFIG_COUNT" not in seen["env"]
class TestRekeyIsNotRename:
"""A changed identifier is a new record, not a moved file.
The ad-hoc requalification (CUST-WP-0066) keeps the filename by design, so
for those records a re-key never changes the path. Matching on path there
cannot distinguish the two cases, and choosing rename updates a row whose
UUID still encodes the old identifier — leaving the file and the hub
disagreeing about what the record is called.
"""
class _Row:
def __init__(self, id, slug, path):
self.id = id
self.slug = slug
self.backing_relative_path = path
self.projection_retired_at = None
self.status = "finished"
def test_a_derived_row_is_not_matched_by_path(self):
"""uuid5 means identity is a function of the identifier."""
import uuid as _u
old = self._Row(
_u.UUID(fp.derived_record_uuid("ADHOC-2026-08-25")),
"adhoc-2026-08-25",
"workplans/ADHOC-2026-08-25.md",
)
assert fp._identity_is_derived(old)
def test_a_legacy_row_keeps_path_matching(self):
"""v4 rows predate derived identity; there the identifier is a label."""
import uuid as _u
legacy = self._Row(_u.uuid4(), "repo-wp-0001", "workplans/REPO-WP-0001.md")
assert not fp._identity_is_derived(legacy)
def test_the_two_uuids_actually_differ(self):
"""Guards the premise: if they were equal the distinction is moot."""
assert fp.derived_record_uuid("ADHOC-2026-08-25") != fp.derived_record_uuid(
"CUST-WP-ADHOC-2026-08-25"
)
@pytest.mark.parametrize(
"slug",
[
"adhoc-2026-07-02", # grandfathered daily ad-hoc
"cust-wp-adhoc-2026-08-25", # qualified daily ad-hoc
"net-kingdom-adhoc-2026-07-02", # repo-name-qualified legacy form
"adhoc-llmc-2026-06-02", # another legacy qualification
"rcluster-wp-0007", # ordinary workplan
"cust-wp-0066-t01", # task
],
)
def test_identifier_slugs_are_recognised(self, slug):
"""A slug that claims to be an identifier is one, whatever its UUID.
25 of 44 ad-hoc rows are legacy v4, so a UUID-version test alone would
leave them path-matched and silently diverged from their files.
"""
assert fp._slug_is_identifier(slug)
@pytest.mark.parametrize(
"slug",
["three-phoenix-ha-cluster", "testdrive-jsui-publication", "state-hub-v0.1", ""],
)
def test_title_slugs_keep_path_matching(self, slug):
"""Hub-first rows never claimed an identifier; the path is their only link."""
assert not fp._slug_is_identifier(slug)
class TestRetirementReleasesTheIdentifier:
"""`slug` is unique table-wide, so retirement must free it.
Retirement that only sets a timestamp leaves the identifier locked to a
record nothing derives, and the repository that owns it can never claim it.
"""
def test_the_identifier_is_released(self):
from datetime import datetime, timezone
when = datetime(2026, 8, 28, tzinfo=timezone.utc)
assert fp._tombstone_slug("repo-wp-0001", when) == "repo-wp-0001@retired-20260828"
def test_re_retiring_does_not_stack_marks(self):
"""Otherwise the 100-char column overflows after a few passes."""
from datetime import datetime, timezone
a = fp._tombstone_slug("repo-wp-0001", datetime(2026, 8, 28, tzinfo=timezone.utc))
b = fp._tombstone_slug(a, datetime(2026, 9, 1, tzinfo=timezone.utc))
assert b == "repo-wp-0001@retired-20260901"
assert b.count(fp.RETIRED_SLUG_MARK) == 1
def test_a_long_slug_stays_within_the_column(self):
from datetime import datetime, timezone
out = fp._tombstone_slug("x" * 140, datetime(2026, 8, 28, tzinfo=timezone.utc))
assert len(out) <= 100
class _Retired:
def __init__(self, slug, when, id=None):
import uuid as _u
self.id = id or _u.uuid4()
self.slug = slug
self.projection_retired_at = when
self.projection_retired_reason = "x"
self.backing_relative_path = None
self.status = "finished"
def test_rows_retired_before_the_stamp_existed_are_repaired(self):
"""`stale` excludes already-retired rows, so nothing else revisits them.
The 32 rows retired earlier today still hold their identifiers; without
this they would block the owning repository forever.
"""
from datetime import datetime, timezone
when = datetime(2026, 8, 28, tzinfo=timezone.utc)
row = self._Retired("repo-wp-0001", when)
assert fp.RETIRED_SLUG_MARK not in row.slug
row.slug = fp._tombstone_slug(row.slug, row.projection_retired_at)
assert row.slug == "repo-wp-0001@retired-20260828"
def test_an_already_stamped_row_is_left_alone(self):
"""Otherwise every reset rewrites the date and churns the row."""
from datetime import datetime, timezone
row = self._Retired(
"repo-wp-0001@retired-20260828", datetime(2026, 8, 28, tzinfo=timezone.utc)
)
assert fp.RETIRED_SLUG_MARK in row.slug
def test_a_release_is_committed_even_when_the_repo_refuses(self):
"""The fleet driver commits only on `applied` and rolls back otherwise.
Moving the release ahead of the refusal returns achieves nothing if the
rollback then discards it — which is the state railiance-cluster and
inter-hub were in.
"""
import inspect
src = inspect.getsource(fp.reset_fleet_projection)
assert 'result.status == "applied" or result.released' in src
class TestUuidMatchWins:
"""A row whose UUID is uuid5 of the identifier IS that record.
`testdrive-jsui-publication` and `three-phoenix-ha-cluster` carry legacy
title slugs while their UUIDs are derived from MARKITECT-WP-0002 and
RCLUSTER-WP-0007. The slug-identifier rule alone reads them as re-keys and
proposes retiring records that were correct all along.
"""
def test_a_title_slugged_row_is_still_its_derived_record(self):
import uuid as _u
rid = "MARKITECT-WP-0002"
row_id = _u.UUID(fp.derived_record_uuid(rid))
# The slug says one thing, the UUID says another; the UUID is identity.
assert not fp._slug_is_identifier("testdrive-jsui-publication")
assert str(row_id) == fp.derived_record_uuid(rid)
def test_uuid_match_is_checked_before_the_rekey_rules(self):
import inspect
src = inspect.getsource(fp.reset_repository_projection)
uuid_at = src.index("want_by_uuid.get(str(row.id))")
rekey_at = src.index("_identity_is_derived(row) or _slug_is_identifier")
assert uuid_at < rekey_at, "UUID match must precede the re-key heuristics"
class TestTaskIdentityIsQualified:
"""A bare `T01` is unique within its workplan, not in the fleet.
Unqualified, `uuid5("T01")` is the same UUID for every workplan that has a
T01 — llm-connect's 91 task blocks derive 49 distinct UUIDs, and creating
its workplans dies on `duplicate key value violates unique constraint
"tasks_pkey"`.
"""
BODY = """
```task
id: T01
status: done
```
```task
id: T02
status: todo
```
"""
def test_short_ids_are_qualified_by_their_workplan(self):
a = fp._parse_tasks(self.BODY, "LLM-WP-0001")
b = fp._parse_tasks(self.BODY, "LLM-WP-0002")
assert [t.record_id for t in a] == ["LLM-WP-0001-T01", "LLM-WP-0001-T02"]
assert {t.uuid for t in a}.isdisjoint({t.uuid for t in b})
def test_an_already_qualified_id_is_left_alone(self):
body = "```task\nid: LLM-WP-0009-T03\nstatus: todo\n```"
assert fp._parse_tasks(body, "LLM-WP-0001")[0].record_id == "LLM-WP-0009-T03"
def test_it_agrees_with_the_backfill(self):
"""Both must apply the same rule or they disagree on a task's name."""
from api.services.task_record_id_backfill import qualify_task_id
got = fp._parse_tasks(self.BODY, "LLM-WP-0001")[0].record_id
assert got == qualify_task_id("T01", "LLM-WP-0001")
def test_uuid_follows_the_qualified_id(self):
t = fp._parse_tasks(self.BODY, "LLM-WP-0001")[0]
assert t.uuid == fp.derived_record_uuid("LLM-WP-0001-T01")
class TestRetirementIsNotUndoneByPath:
"""A retired row is matched by UUID or not at all.
Releasing the identifier removes the evidence that made the row a re-key:
the tombstoned slug is no longer an identifier, and a legacy row is not
UUID-derived, so both guards fall through to path matching — which matches
the very file the row was retired for and resurrects it beside the correct
record created from that same file.
"""
def test_a_tombstoned_slug_is_not_an_identifier(self):
"""This is the signal the tombstone destroys."""
assert fp._slug_is_identifier("adhoc-2026-06-01")
assert not fp._slug_is_identifier("adhoc-2026-06-01@retired-20260827")
def test_retired_rows_are_skipped_before_path_matching(self):
import inspect
src = inspect.getsource(fp.reset_repository_projection)
skip_at = src.index("if row.projection_retired_at is not None:")
path_at = src.index("if bp and _path_key(bp) in want_paths:")
assert skip_at < path_at, "retired rows must be skipped before path matching"
def test_uuid_match_still_precedes_the_skip(self):
"""A record that genuinely returns must still be un-retired."""
import inspect
src = inspect.getsource(fp.reset_repository_projection)
assert src.index("want_by_uuid.get(str(row.id))") < src.index(
"if row.projection_retired_at is not None:"
)
def test_a_row_that_derives_again_is_not_tombstoned(self):
"""Releasing it would change the slug out from under the matching.
The row would then fail to match its own file and never be un-retired —
which is how five rows ended up tombstoned but not retired.
"""
import inspect
src = inspect.getsource(fp.reset_repository_projection)
rel = src.index("outcome.released.append(before)")
guard = src.index('in want or str(r.id) in want_by_uuid')
assert guard < rel, "the release must exempt records the forge still derives"
def test_a_stamped_slug_counts_as_retired_even_if_the_flag_is_clear(self):
"""Otherwise a resurrected row path-matches its file and reports noop forever."""
import inspect
src = inspect.getsource(fp.reset_repository_projection)
assert "projection_retired_at is None and RETIRED_SLUG_MARK in" in src
def test_a_resurrected_row_becomes_stale_rather_than_being_skipped(self):
"""Skipping it outright is what left six rows reporting noop forever.
`stale` is computed from `matched`, so a row that never enters `matched`
is invisible: not retired, so not stale; path-matching its own file, so
never reported.
"""
import inspect
src = inspect.getsource(fp.reset_repository_projection)
zombie = src.index("projection_retired_at is None and RETIRED_SLUG_MARK in")
tail = src[zombie:zombie + 700]
assert "matched[key] = row" in tail, "a resurrected row must enter `matched`"
class TestCompetingClaims:
"""Two rows can claim one record; the weaker must not vanish.
`cust-wp-0010` claimed CUST-WP-0010 by its own identifier while
`workstream-lifecycle-documentation` claimed it by path. Assigning into
`matched` unconditionally let the later one win and dropped the other
silently — never matched, so never stale, so never reported by any pass.
"""
def test_claims_are_ranked_not_overwritten(self):
import inspect
src = inspect.getsource(fp.reset_repository_projection)
assert "def _claim(" in src
assert "displaced.append" in src
def test_a_displaced_row_becomes_stale(self):
import inspect
src = inspect.getsource(fp.reset_repository_projection)
stale_at = src.index("stale = [")
assert "displaced" in src[stale_at:stale_at + 400]
def test_identifier_beats_path(self):
"""A row naming the record outranks one that merely shares its file."""
import inspect
src = inspect.getsource(fp.reset_repository_projection)
assert src.index("UUID_MATCH, SLUG_MATCH, PATH_MATCH, PREFIX_MATCH = 0, 1, 2, 3") > 0
# Strength is ordered strongest-first, so a lower number wins.
assert "if strength < held:" in src
class TestTitleIsDerivedToo:
"""The title is a derived field and must follow the file.
Not syncing it left `cust-wp-0010` correctly identified and correctly backed
while describing a different workplan's work.
"""
def test_title_is_synced(self):
import inspect
src = inspect.getsource(fp.reset_repository_projection)
assert "row.title = w.title.strip()" in src
def test_an_empty_derived_title_does_not_blank_a_real_one(self):
"""Three activity-core files parse to no title; blanking is worse than stale."""
import inspect
src = inspect.getsource(fp.reset_repository_projection)
i = src.index("row.title = w.title.strip()")
guard = src[max(0, i - 200):i]
assert "w.title and w.title.strip()" in guard
class TestTitleSyncBehaviour:
"""Exercised against the fake session rather than asserted on source."""
@pytest.mark.asyncio
async def test_a_drifted_title_is_corrected(self):
row = _Row(slug="demo-wp-0001", status="active",
path="workplans/a.md", title="Some Other Workplan")
session = _FakeSession(repo=_Repo(), rows=[row])
out = await fp.reset_repository_projection(
session, "demo",
derived=TestReset()._derived(("DEMO-WP-0001", "active", "workplans/a.md")),
)
assert out.status == "applied"
assert row.title != "Some Other Workplan"
@pytest.mark.asyncio
async def test_an_empty_derived_title_leaves_the_existing_one(self):
row = _Row(slug="demo-wp-0001", status="active",
path="workplans/a.md", title="Real Title")
d = TestReset()._derived(("DEMO-WP-0001", "active", "workplans/a.md"))
d.workplans[0].title = None
session = _FakeSession(repo=_Repo(), rows=[row])
await fp.reset_repository_projection(session, "demo", derived=d)
assert row.title == "Real Title"
class _TaskRow:
def __init__(self, record_id, status="todo", title="t", workplan_id=None):
import uuid as _u
self.id = _u.uuid4()
self.record_id = record_id
self.status = status
self.title = title
self.priority = "medium"
self.workplan_id = workplan_id
class TestExistingWorkplanTasks:
"""Tasks of an existing workplan are matched by record_id (CUST-WP-0068-T09)."""
def _derived(self, *tasks):
dts = [
fp.DerivedTask(
record_id=tid,
uuid=fp.derived_record_uuid(tid),
title=title,
status=st,
priority="medium",
)
for tid, title, st in tasks
]
return fp.DerivedProjection(
repo_slug="demo",
commit="c0ffee",
workplans=[
fp.DerivedWorkplan(
record_id="DEMO-WP-0001",
uuid=fp.derived_record_uuid("DEMO-WP-0001"),
title="DEMO-WP-0001",
status="active",
relative_path="workplans/a.md",
archived=False,
tasks=dts,
)
],
)
@pytest.mark.asyncio
async def test_creates_a_missing_identified_task(self):
row = _Row(slug="demo-wp-0001", status="active", path="workplans/a.md")
session = _FakeSession(repo=_Repo(), rows=[row], task_rows=[])
out = await fp.reset_repository_projection(
session, "demo",
derived=self._derived(("DEMO-WP-0001-T01", "Do it", "todo")),
)
assert out.created_tasks == ["DEMO-WP-0001-T01"]
assert session.added
assert session.added[0].record_id == "DEMO-WP-0001-T01"
@pytest.mark.asyncio
async def test_cancels_an_open_task_the_file_no_longer_derives(self):
row = _Row(slug="demo-wp-0001", status="active", path="workplans/a.md")
stale = _TaskRow("DEMO-WP-0001-T09", status="todo", workplan_id=row.id)
session = _FakeSession(repo=_Repo(), rows=[row], task_rows=[stale])
out = await fp.reset_repository_projection(
session, "demo",
derived=self._derived(("DEMO-WP-0001-T01", "Do it", "todo")),
)
assert stale.status.value == "cancel" or stale.status == "cancel" or str(stale.status).endswith("cancel")
assert "DEMO-WP-0001-T09" in out.cancelled_tasks
assert session.deleted == []
@pytest.mark.asyncio
async def test_sets_record_id_when_the_derived_uuid_already_exists(self):
row = _Row(slug="demo-wp-0001", status="active", path="workplans/a.md")
existing = _TaskRow(None, status="done", title="Clear the stale hub rows", workplan_id=row.id)
derived = self._derived(("DEMO-WP-0001-T01", "Clear the stale hub rows", "done"))
existing.id = __import__("uuid").UUID(derived.workplans[0].tasks[0].uuid)
session = _FakeSession(repo=_Repo(), rows=[row], task_rows=[existing])
out = await fp.reset_repository_projection(session, "demo", derived=derived)
assert out.created_tasks == []
assert existing.record_id == "DEMO-WP-0001-T01"
assert session.added == []
@pytest.mark.asyncio
async def test_leaves_unidentified_tasks_alone(self):
row = _Row(slug="demo-wp-0001", status="active", path="workplans/a.md")
orphan = _TaskRow(None, status="todo", title="legacy", workplan_id=row.id)
session = _FakeSession(repo=_Repo(), rows=[row], task_rows=[orphan])
await fp.reset_repository_projection(
session, "demo",
derived=self._derived(("DEMO-WP-0001-T01", "Do it", "todo")),
)
assert orphan.status == "todo"
@pytest.mark.asyncio
async def test_duplicate_identity_inside_current_workplan_is_refused(self):
row = _Row(slug="demo-wp-0001", status="active", path="workplans/a.md")
first = _TaskRow("DEMO-WP-0001-T01", workplan_id=row.id)
second = _TaskRow("demo-wp-0001-t01", workplan_id=row.id)
session = _FakeSession(repo=_Repo(), rows=[row], task_rows=[first, second])
out = await fp.reset_repository_projection(
session,
"demo",
derived=self._derived(("DEMO-WP-0001-T01", "Do it", "todo")),
)
assert out.status == "refused"
assert out.refused[0]["reason"].startswith("current workplan contains duplicate")
assert session.added == []
@pytest.mark.asyncio
async def test_duplicate_stale_history_inside_current_workplan_does_not_block(self):
row = _Row(slug="demo-wp-0001", status="active", path="workplans/a.md")
desired = _TaskRow("DEMO-WP-0001-T01", status="todo", workplan_id=row.id)
stale_a = _TaskRow("DEMO-WP-0001-T09", status="done", workplan_id=row.id)
stale_b = _TaskRow("demo-wp-0001-t09", status="done", workplan_id=row.id)
session = _FakeSession(
repo=_Repo(), rows=[row], task_rows=[desired, stale_a, stale_b]
)
out = await fp.reset_repository_projection(
session,
"demo",
derived=self._derived(("DEMO-WP-0001-T01", "Do it", "todo")),
)
assert out.status in {"applied", "noop"}
assert out.refused == []
@pytest.mark.asyncio
async def test_derived_task_uuid_held_elsewhere_is_refused_before_insert(self):
row = _Row(slug="demo-wp-0001", status="active", path="workplans/a.md")
derived = self._derived(("DEMO-WP-0001-T01", "Do it", "todo"))
holder = _TaskRow("DEMO-WP-0001-T01", workplan_id=__import__("uuid").uuid4())
holder.id = __import__("uuid").UUID(derived.workplans[0].tasks[0].uuid)
session = _FakeSession(
repo=_Repo(),
rows=[row],
task_rows=[],
task_collision_rows=[holder],
)
out = await fp.reset_repository_projection(session, "demo", derived=derived)
assert out.status == "refused"
assert out.refused[0]["reason"].startswith("derived task identifier already belongs")
assert session.added == []
@pytest.mark.asyncio
async def test_tasks_on_retired_copy_do_not_block_current_projection(self):
from datetime import datetime, timezone
current = _Row(slug="demo-wp-0001", status="active", path="workplans/a.md")
current.id = __import__("uuid").UUID(fp.derived_record_uuid("DEMO-WP-0001"))
retired = _Row(
slug="demo-wp-0001@retired-20260831",
status="finished",
path="workplans/a.md",
)
retired.projection_retired_at = datetime.now(tz=timezone.utc)
task = _TaskRow("DEMO-WP-0001-T01", status="todo", workplan_id=current.id)
session = _FakeSession(repo=_Repo(), rows=[current, retired], task_rows=[task])
out = await fp.reset_repository_projection(
session,
"demo",
derived=self._derived(("DEMO-WP-0001-T01", "Do it", "todo")),
)
assert out.status in {"applied", "noop"}
assert out.refused == []
def test_diff_reports_duplicate_current_task_identity_as_ambiguous():
derived = TestExistingWorkplanTasks()._derived(
("DEMO-WP-0001-T01", "Do it", "todo")
)
workplan_id = derived.workplans[0].uuid
hub_workplans = [
{
"id": workplan_id,
"slug": "demo-wp-0001",
"status": "active",
"backing_relative_path": "workplans/a.md",
}
]
hub_tasks = {
workplan_id: [
{
"id": "11111111-1111-4111-8111-111111111111",
"record_id": "DEMO-WP-0001-T01",
"title": "a",
"status": "todo",
},
{
"id": "22222222-2222-4222-8222-222222222222",
"record_id": "demo-wp-0001-t01",
"title": "b",
"status": "todo",
},
]
}
diff = fp.diff_against_hub(derived, hub_workplans, hub_tasks)
assert diff.clean is False
assert diff.to_dict()["counts"]["ambiguous"] == 1
assert diff.ambiguous[0]["source"] == "hub"
@pytest.mark.asyncio
async def test_reset_refuses_duplicate_task_identity_in_forge_projection():
first = TestExistingWorkplanTasks()._derived(
("SHARED-WP-0001-T01", "First", "todo")
).workplans[0]
second = fp.DerivedWorkplan(
record_id="DEMO-WP-0002",
uuid=fp.derived_record_uuid("DEMO-WP-0002"),
title="Second",
status="active",
relative_path="workplans/b.md",
archived=False,
tasks=[
fp.DerivedTask(
record_id="SHARED-WP-0001-T01",
uuid=fp.derived_record_uuid("SHARED-WP-0001-T01"),
title="Second claim",
status="todo",
priority="medium",
)
],
)
derived = fp.DerivedProjection(
repo_slug="demo", commit="c0ffee", workplans=[first, second]
)
session = _FakeSession(repo=_Repo(), rows=[])
out = await fp.reset_repository_projection(session, "demo", derived=derived)
assert out.status == "refused"
assert any(item.get("source") == "forge" for item in out.refused)
assert session.added == []